No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Unobtrusive Monitoring to Detect Depression for Elderly With Chronic Illnesses
Abstract
Mental health related disorders are common diseases, especially among the elderly. Among the various mental health diseases, one potential threat to ageing-in-place is the risk of depression. In this paper, we propose a simple unobtrusive sensing system using Passive Infra-Red (PIR) motion sensors to monitor the Activities of Daily Living (ADLs) of elderly who are living alone. A feature extraction module comprising of three layers - states, events and activities - and the corresponding algorithms are proposed to extract features. Four popular classification models - neural network, C4.5 decision tree, Bayesian network, and Support Vector Machine (SVM) - are then applied to detect the severity of depression. We implement and test the algorithms on sensor data collected over three months from 20 elderly, each in different daily living conditions. Our evaluation shows that the proposed algorithms are effective in detecting both normal condition and mild depression with up to 96% accuracy, using neural network as the classification algorithm. The sensing system is non-intrusive and cost-effective, with the potential of use for long-term depression monitoring and detection of early symptoms of mental related disorders. This enables caregivers to provide timely interventions to elderly who are at risk of depression.
... (Taysi et al., 2010;Englert et al., 2013;Pathak et al., 2015;Pandya & Ghayvat, 2021) Energy consumption monitoring Passive infrared sensor (PIR) sensors Nonwearable (Luo et al., 2012;Popescu et al., 2012;Guan et al., 2017) Fall detection monitoring PIR sensors, which can estimate presence and movements of users, were used to detect falls, monitor ADLs based on indoor locations of users, and analyse occupancy patterns to understand energy demands of users. (Crandall & Cook, 2013;Fanti et al., 2016;Kim et al., 2017;Luo et al., 2017;Jiménez & Seco, 2018) ADL monitoring (Byun et al., 2012;Machorro-Cano et al., 2020;Paredes-Valverde et al., 2020) Energy consumption monitoring ...
... Other types of nonwearable devices, such as PIR and floor sensors, do not highly intrude privacy. Several studies (Crandall & Cook, 2013;Fanti et al., 2016;Kim et al., 2017;Luo et al., 2017) used PIR sensors, which can detect the presence of users for ADL monitoring, because they are inexpensive and not highly privacy invasive. Kim et al. (2017) used PIR sensors with door-switch sensors to estimate the indoor locations of users in a residential environment for the detection of mental disorders based on the changes in ADLs. ...
... Several studies (Crandall & Cook, 2013;Fanti et al., 2016;Kim et al., 2017;Luo et al., 2017) used PIR sensors, which can detect the presence of users for ADL monitoring, because they are inexpensive and not highly privacy invasive. Kim et al. (2017) used PIR sensors with door-switch sensors to estimate the indoor locations of users in a residential environment for the detection of mental disorders based on the changes in ADLs. Crandall and Cook (2013) deployed multiple PIR sensors on a ceiling to track the indoor locations of users based on the sequence detected by each PIR sensor. ...
In recent decades, smart home technology has advanced, improving the well-being and quality of life of its users. Thus, its applications have expanded, particularly in health and environmental monitoring. Numerous devices have been developed to accommodate user requirements of monitoring; however, the adoption of monitoring devices is closely related to user perception. User perception can be considered from different perspectives. One method of understanding different user perceptions is comparing wearable and nonwearable devices, owing to the differences in their obtrusiveness. The aim of this study was to systematically review the applications and user perceptions of health and environmental monitoring devices, emphasizing on the wearable and nonwearable distinction. We conducted a focused search of articles related to smart home technology and its user perceptions based on its applications. The inclusion criteria were original and peer-reviewed articles centered on health and environmental monitoring devices. We identified and analysed 159 of the 4476 relevant articles and divided the articles into two categories. The first category comprised health and environmental monitoring and their applications by the type of device. The second category comprised user perceptions of monitoring devices. The devices were grouped into wearable and nonwearable devices for our analysis. We identified user perceptions based on usefulness, ease of use, and privacy. Because wearable and nonwearable devices complement their limitations, we recommend their integration for improving user perception.
... According to the World Health Organization (WHO), in 2021, 3.8% of the world's population suffered from depression, and the rate in the elderly over the age of 60 was 5.7%, 1.5 times the overall level [3]. It should pay particular attention to depression of the elderly because it is difficult for the elderly to recognize that they are depressed on their own, so they often complain of physical symptoms rather than complaining of changes in their emotions [4,5]. ...
... Researchers in this field detect depression by recognizing changes in body shape such as a patient's gait [13,14], head position [15], and thoracic kyphosis [16]. The method of detecting depression using the sensors is again divided into obtrusive and unobtrusive; the former has the problem of inconvenience and the latter suffers from low accuracy [5,17]. The other one detects depression early by analyzing behavior in cyberspace using various AI techniques [18]. ...
... She recently went to the hospital for insomnia and loss of appetite, but her symptoms did not improve because she did not recognize by herself that there were symptoms of depression. Generally, the elderly have difficulty recognizing signs that they are depressed, so they often complain of physical symptoms such as insomnia and loss of appetite rather than complaining of emotional changes [5]. As a result, it is hard to detect depression in the elderly in the early stages, so treatment time is often missed, leading to serious social problems such as suicide in the elderly. ...
Although the diagnosis and treatment of depression is a medical field, ICTs and AI technologies are used widely to detect depression earlier in the elderly. These technologies are used to identify behavioral changes in the physical world or sentiment changes in cyberspace, known as symptoms of depression. However, although sentiment and physical changes, which are signs of depression in the elderly, are usually revealed simultaneously, there is no research on them at the same time. To solve the problem, this paper proposes knowledge graph-based cyber–physical view (CPV)-based activity pattern recognition for the early detection of depression, also known as KARE. In the KARE framework, the knowledge graph (KG) plays key roles in providing cross-domain knowledge as well as resolving issues of grammatical and semantic heterogeneity required in order to integrate cyberspace and the physical world. In addition, it can flexibly express the patterns of different activities for each elderly. To achieve this, the KARE framework implements a set of new machine learning techniques. The first is 1D-CNN for attribute representation in relation to learning to connect the attributes of physical and cyber worlds and the KG. The second is the entity alignment with embedding vectors extracted by the CNN and GNN. The third is a graph extraction method to construct the CPV from KG with the graph representation learning and wrapper-based feature selection in the unsupervised manner. The last one is a method of activity-pattern graph representation based on a Gaussian Mixture Model and KL divergence for training the GAT model to detect depression early. To demonstrate the superiority of the KARE framework, we performed the experiments using real-world datasets with five state-of-the-art models in knowledge graph entity alignment.
... In previous studies, Internet-of-Things (IoT) or multiple sensors have been used to collect data on daily activities or risk of deterioration [1][2][3][4][5][6][7][8]. In these studies, various kinds of sensors were used and the usefulness of the collected data for monitoring changes of daily activities or detecting risk for elderly peoples were demonstrated [7]. ...
... Therefore, we decided to use a single sensor placed in the bed, which does not require wearing or video data. In addition, several models constructed in previous studies tried to detect whether subjects have illness by comparing the values collected in two periods [5,10]. However, for facility use, a daily anomaly detection system that alerts abnormal condition for each day and for each subject is needed. ...
... Further, to analyze the relation between the amount of training data and accuracy, we constructed several simulation models with training data of different numbers of days (1,3,5,7,14,30, and 60 days), and the accuracy was calculated. ...
Currently, the shortage of care workers for the elderly has become a big problem, and more streamlined care operations are needed. In care facilities, care workers are required to use their subjective experience to detect anomalies in physical condition of care receivers, including serious or insignificant deterioration or behavioral and psychological symptoms of dementia, which can decrease the work efficiency. Therefore, we aim to create a model using objective data for detecting anomalies in physical condition. In this study, data from 13 subjects in a care facility were collected, and isolation forest models were constructed for each subject. The subject's anomalies in physical condition were documented in a care record by a nurse and used as reference for model evaluation. Recall and specificity were used to evaluate the model, expressed as the percentage of detection success for abnormal or normal conditions. Data collected for 1 to 60 days were used to train the isolation models, and the relationship between the amount of training data and model performance was simulated. Heart rate, respiratory rate, and time of getting out of bed were collected from a sensor placed on the subject's bed and used as the model features. In addition, dietary intake information was collected from the care record. Analysis of the evaluation results showed recall and specificity of 45.6 ± 46.7% and 83.88 ± 6.06%, respectively, for the model constructed using training data of 60 days. For future studies, we will continue to collect data and increase the number of participants to improve the robustness and accuracy of the proposed anomaly detection system.
... Eleven studies [43,44,47,49,51,55,[58][59][60]65,67] have been more focused in developing smart homes with protection of user privacy being the utmost priority. ...
... Eight [43,44,58,60,63,66] of the 31 studies included in this review, the systems deployed were aimed at providing some sort of medical support by health monitoring and taking appropriate action. Fourteen [43,45,[47][48][49][51][52][53]55,60,64,65,69,72] of the 31 studies were aimed at monitoring the environment for any abnormalities and detecting falls, which allowed the elderly to stay alone in their homes. ...
... Eight [43,44,58,60,63,66] of the 31 studies included in this review, the systems deployed were aimed at providing some sort of medical support by health monitoring and taking appropriate action. Fourteen [43,45,[47][48][49][51][52][53]55,60,64,65,69,72] of the 31 studies were aimed at monitoring the environment for any abnormalities and detecting falls, which allowed the elderly to stay alone in their homes. Figure 2 shows the numbers of studies with different features of smart home. ...
Owing to progressive population aging, elderly people (aged 65 and above) face challenges in carrying out activities of daily living, while placement of the elderly in a care facility is expensive and mentally taxing for them. Thus, there is a need to develop their own homes into smart homes using new technologies. However, this raises concerns of privacy and data security for users since it can be handled remotely. Hence, with advancing technologies it is important to overcome this challenge using privacy-preserving and non-intrusive models. For this review, 235 articles were scanned from databases, out of which 31 articles pertaining to in-home technologies that assist the elderly in living independently were shortlisted for inclusion. They described the adoption of various methodologies like different sensor-based mechanisms, wearables, camera-based techniques, robots, and machine learning strategies to provide a safe and comfortable environment to the elderly. Recent innovations have rendered these technologies more unobtrusive and privacy-preserving with increasing use of environmental sensors and less use of cameras and other devices that may compromise the privacy of individuals. There is a need to develop a comprehensive system for smart homes which ensures patient safety, privacy, and data security; in addition, robots should be integrated with the existing sensor-based platforms to assist in carrying out daily activities and therapies as required.
... Awais et al. [76] used accelerometers to recognize the ADL of the elderly, such as sitting, walking, and standing. To estimate the indoor location of the elderly, Morita et al. [77] employed Bluetooth low energy (BLE) beacons in a nursing home. Kim et al. [78] developed a framework to detect depression in the elderly by analyzing activity patterns based on indoor location, estimated using PIR sensors. ...
... Thus, with the approval of elderly users, the sensor data can also be accessed by other entities through a web-based platform on any device. Subsequently, through this sensor-set's wearable BLE beacons [77], BLE receivers and its integrated accelerometers [76], the elderly user's ADL recognition can be acquired by analysis of the sensor's collected user's indoor location information [71][72][73][74] and activity recognition [69,70] (which are significantly closely associated to each other). The daily activities which can be recognized through sensor data include sitting, walking, sleeping, watching TV, cooking, bathroom usage, and etc. [77]. ...
... Subsequently, through this sensor-set's wearable BLE beacons [77], BLE receivers and its integrated accelerometers [76], the elderly user's ADL recognition can be acquired by analysis of the sensor's collected user's indoor location information [71][72][73][74] and activity recognition [69,70] (which are significantly closely associated to each other). The daily activities which can be recognized through sensor data include sitting, walking, sleeping, watching TV, cooking, bathroom usage, and etc. [77]. The purpose of the recognition of these daily activity provides an automatically generated report of the elderly's daily profile, which can potentially be used to effectively improve their QoL. ...
An integrated smart home system (ISHS) is an effective way to improve the quality of life of the elderly. The elderly’s willingness is essential to adopt an ISHS; to the best of our knowledge, no study has investigated the elderly’s perception of ISHS. Consequently, this study aims to investigate the elderly’s perception of the ISHS by comprehensively evaluating its possible benefits and negative responses. A set of sensors required for an ISHS was determined, and interviews were designed based on four factors: perceived comfort, perceived usability, perceived privacy, and perceived benefit. Subsequently, technological trials of the sensor-set followed by two focus group interviews were conducted on nine independently living elderly participants at a senior welfare center in South Korea. Consistent with previous studies, the results of this investigation indicate that elderly participants elicited negative responses regarding usability complexity, and discomfort to daily activities. Despite such negative responses, after acquiring enough awareness about the ISHS’s benefits, the elderly acknowledged its necessity and showed a high level of willingness. Furthermore, these results indicate that for a better adoption of an ISHS, sufficient awareness regarding its benefits and development of elderly-friendly smart home sensors that minimize negative responses are required.
... The third privacy concern was (C) risk and regulation of privacy, which included discussions surrounding dissemination of data or active data theft [44][45][46][47], as well as change in behavior or relationships due to interaction with technology [48,49]. Researchers were aware of both legal and design-contextual measures that must be observed in order to ensure that these risks were minimized [45,50,51]. ...
... This trust in technology was increased when a physical robot instead of an only virtual agent was involved [60,65]. Studies in the realm of embodiment of virtual agents and robots suggest that the presence of a body or face promotes human-like interactions with said agents [51]. Furthermore, our systematic review discovered other characteristics which promote trust in SHHTs, such as perceived usefulness [94] or time spent with the technology [59]. ...
Background
The worldwide increase in older persons demands technological solutions to combat the shortage of caregiving and to enable aging in place. Smart home health technologies (SHHTs) are promoted and implemented as a possible solution from an economic and practical perspective. However, ethical considerations are equally important and need to be investigated.
Methods
We conducted a systematic review according to the PRISMA guidelines to investigate if and how ethical questions are discussed in the field of SHHTs in caregiving for older persons.
Results
156 peer-reviewed articles published in English, German and French were retrieved and analyzed across 10 electronic databases. Using narrative analysis, 7 ethical categories were mapped: privacy, autonomy, responsibility, human vs. artificial interactions, trust, ageism and stigma, and other concerns.
Conclusion
The findings of our systematic review show the (lack of) ethical consideration when it comes to the development and implementation of SHHTs for older persons. Our analysis is useful to promote careful ethical consideration when carrying out technology development, research and deployment to care for older persons.
Registration
We registered our systematic review in the PROSPERO network under CRD42021248543.
... Clustering [1,28,30,34,53], (n=5) and Hidden Markov Model [23,30,34,39] (n=4) were the most commonly used in data analysis to identify a regular pattern and predict future patterns. Other algorithms used in the studies are: decision tree emerging pattern [11,25,27], clustering conditional random field [37,51], context-aware reasoning [28,42], fuzzy logic [41,49], K-Nearest Neighbors (KNN) [10,51], logistic regression classifier [51,55], AdaBoost [10], Bayes network [27], boosting model using ensemble [42], Circadian Activity Rhythms (CAR) [47], multi-HMM [34], , Multiple Regression Model [42], multivariate habits cluster [44], ontological modelling [41], Software for Automatic Measurement of Circadian Activity Deviation (SAMCAD) [47], and Support Vector Machines (SVM) [52]. ...
... Clustering [1,28,30,34,53], (n=5) and Hidden Markov Model [23,30,34,39] (n=4) were the most commonly used in data analysis to identify a regular pattern and predict future patterns. Other algorithms used in the studies are: decision tree emerging pattern [11,25,27], clustering conditional random field [37,51], context-aware reasoning [28,42], fuzzy logic [41,49], K-Nearest Neighbors (KNN) [10,51], logistic regression classifier [51,55], AdaBoost [10], Bayes network [27], boosting model using ensemble [42], Circadian Activity Rhythms (CAR) [47], multi-HMM [34], , Multiple Regression Model [42], multivariate habits cluster [44], ontological modelling [41], Software for Automatic Measurement of Circadian Activity Deviation (SAMCAD) [47], and Support Vector Machines (SVM) [52]. ...
... The third privacy concern was C) risk and regulation of privacy, which included discussions surrounding dissemination of data or active data theft (44)(45)(46)(47), as well as change in behavior or relationships due to interaction with technology (48,49). Researchers were aware of both legal and design-contextual measures that must be observed in order to ensure that these risks were minimized (45,50,51). ...
... This trust in technology was increased when a physical robot instead of an only virtual agent was involved (60,65). Studies in the realm of embodiment of virtual agents and robots suggest that the presence of a body or face promotes human-like interactions with said agents (51). Furthermore, our systematic review discovered other characteristics which promote trust in SHHTs, such as perceived usefulness (94) or time spent with the technology (59). ...
Background
The worldwide increase in older persons demands technological solutions to combat the shortage of caregiving and to enable aging in place. Smart home health technologies (SHHTs) are promoted and implemented as a possible solution from an economic and practical perspective. However, ethical considerations are equally important and need to be investigated.
Methods
we conducted a systematic review according to the PRISMA guidelines to investigate if and how ethical questions are discussed in the field of SHHTs in caregiving for older persons.
Results
156 peer-reviewed articles published in English, German and French were retrieved and analyzed across 10 electronic databases. Using narrative analysis, 7 ethical categories were mapped: privacy, autonomy, responsibility, human vs. artificial interactions, trust, ageism and stigma, and other concerns.
Conclusions
The findings of our systematic review show the (lack of) ethical consideration when it comes to the development and implementation of SHHTs for older persons. Our analysis is useful to promote careful ethical consideration when carrying out technology development, research and deployment to care for older persons.
Registration
We registered our systematic review in the PROSPERO network under CRD42021248543
... Seven studies were included that identified older adults' functional, psychological, and social abnormal activities such as unexpected and irregular behaviors using in-home monitoring technologies and machine-learning algorithms [16][17][18][19][20][21][22]. For example, movement at 3 AM in a living room can be considered abnormal behavior if monitoring data showed that older residents usually wake up at 6 AM every morning. ...
... The investigators found a significant relationship between predicted loneliness and observed loneliness, demonstrating that it is possible to estimate older adults' loneliness by analyzing sensor data. Other studies [18] have estimated older adults' depression levels by analyzing daily activities, demonstrating that proposed algorithms can effectively detect depression with up to 96% accuracy. ...
Background
For successful aging-in-place strategy development, in-home monitoring technology is necessary as a new home modification strategy. Monitoring an older adult’s daily physical activity at home can positively impact their health and well-being by providing valuable information about functional, cognitive, and social health status. However, it is questionable how these in-home monitoring technologies have changed the traditional residential environment. A comprehensive review of existing research findings should be utilized to characterize recent relative technologies and to inform design considerations.
Objective
The main purpose of this study was to classify recent smart home technologies that monitor older adults’ health and to architecturally describe these technologies as they are used in older adults’ homes.
Methods
The scoping review method was employed to identify key characteristics of in-home monitoring technologies for older adults. In June 2021, four databases, including Web of Science, IEEE Xplore, ACM Digital Library, and Scopus, were searched for peer-reviewed articles pertaining to smart home technologies used to monitor older adults’ health in their homes. We used two search strings to retrieve articles: types of technology and types of users. For the title, abstract, and full-text screening, the inclusion criteria were original and peer-reviewed research written in English, and research on monitoring, detecting, recognizing, analyzing, or tracking human physical, emotional, and social behavior. The exclusion criteria included theoretical, conceptual, or review papers; studies on wearable systems; and qualitative research.
Results
This scoping review identified 30 studies published between June 2016 and 2021 providing overviews of in-home monitoring technologies, including (1) features of smart home technologies and (2) sensor locations and sensor data. First, we found six functions of in-home monitoring technology among the reviewed papers: daily activities, abnormal behaviors, cognitive impairment, falls, indoor person positioning, and sleep quality. Most of the research (n=27 articles) focused on functional monitoring and analysis, such as activities of daily living, instrumental activities of daily living, or falls among older adults; a few studies (n=3) covered social interaction monitoring. Second, this scoping review also found 16 types of sensor technologies. The most common data types encountered were passive infrared motion sensors (n=21) and contact sensors (n=19), which were used to monitor human behaviors such as bodily presence and time spent on activities. Specific locations for each sensor were also identified.
Conclusions
This wide-ranging synthesis demonstrates that in-home monitoring technologies within older adults’ homes play an essential role in aging in place, in that the technology monitors older adults’ daily activities and identifies various health-related issues. This research provides a key summarization of in-home monitoring technologies that can be applied in senior housing for successful aging in place. These findings will be significant when developing home modification strategies or new senior housing.
... The D2D communications in this paper is different from the above in the sense of not requiring existing networks. We notice the fact that data gathering for elderly care is not necessarily conducted in real-time, because collected ADL sensor data are generally analyzed and compared on daily base in long-term elderly care monitoring [19]. For example, let the ADL sensor data be collected and saved consecutively at the targeted elderly houses, then gathering the saved ADL data from the targeted houses to a local community center from time to time can provide useful observation. ...
Elderly care becomes more and more important as elderly populations increase. Many solutions are proposed for monitoring elderly activities of daily living (ADL) or healthcare related data. There are two aspects to be tackled to enable monitoring for elderly care. On the one hand, the up-to-date ADL sensors and biosensors greatly facilitate collection of various ADL and healthcare related data. On the other hand, data captured by sensors need to be gathered from residences of elderly people to local community center for monitoring and analysis. Therefore, gathering sensor data plays a significant role for building elderly care systems or architectures. Most current elderly care systems or architectures are developed based on reliable network infrastructures. However, such presumption is less practical in network deficient environments such as geographically depopulated rural and remote areas. In this paper, we propose a data gathering system model for elderly care based on autonomous device-to-device (D2D) communications, which is self-contained and independent from other network infrastructures. The proposed system model doesn’t need central control; thus, it can be simply deployed in network deficient environments or for users without access to existing networks. The idea behind is to use ad hoc D2D links by introducing moving devices. Procedures of data gathering using D2D are proposed and configured by modifying the two-way untargeted discovery protocols of IEEE Std 802.15.8. To examine the feasibility of the proposed system model, a prototype D2D system is developed using off-the-shelf radio modules and ADL sensors. We examine the efficacy of the prototype system through field trials in a mountainous village. Our obtained results confirm the usefulness of the proposed D2D solution for gathering ADL sensor data for elderly care in network deficient environments. Examples of using the gathered ADL data to detect anomalous events are presented.
... A study that tracked smartphone geographic position information, acceleration, and call patterns on depressive individuals' physical activity found a connection between changes in mental condition and movements, including sleeping, walking, and running [35]. Other research presents a sensor-based monitoring technique for identifying the severity of depression in older adults based on their daily movement in their homes [37]. A few studies have also used smartphone GPS to track people's daily activities and tasks to determine depression severity [28,38,39]. ...
Mental health issues are becoming more common, and they are often experienced by people who would rather live alone, spend a lot of time on social media or playing video games, have trouble sleeping, struggle to maintain a work-life balance and avoid social situations. People experience depression as a result, which is one of these serious and common mental illnesses. This study introduces a method for measuring a person’s level of sadness by monitoring their regular sleeping habits and a few other aspects. The proposal aimed to use a decision integration strategy model to identify sleeping patterns by using the sleeping-behavioural attributes obtained from a wearable sensor. An imbalance in sleep patterns causes the body to experience several issues, such as an increase in body temperature and a decrease in energy. A wearable sensor was used to categorize the data to simplify sleeping habits better. Using the “Montgomery-Asberg Depression Rating Scale” score, which produced 12 characteristics, people’s sleeping habits and other characteristics were analyzed together with their weekly depression levels. Using the wrapper feature selection strategy, a subset of features was selected and employed in a linear regression model to estimate the depression score. Next, the decision integration strategy algorithm was employed to classify each person’s level of depression into four categories: normal, mild, moderate, and severe. In instances of general regular, mild, moderate, and severe depression severity, it outperformed other classification models, such as the support vector machine, decision trees, random forest, and gradient boosting machine, with an accuracy of 96.1%. The Pearson correlation test shows deep sleep, light sleep, number of awakings, total sleep, average body temperature, heart-beat-rate, absolute energy, age, and ssuh/gaming were shown to be significantly related (r = 0.22; p < 0.001, r = − 0.21; p < 0.001, r = − 0.21; p < 0.001, r = 0.17; p < 0.001, r = 0.35; p < 0.001, r = 0.33; p < 0.001, r = 0.33; p < 0.001, r = − 0.32; p < 0.001, r = − 0.25; p < 0.001, respectively). In our proposed model, the tenfold validation precision, recall, f1-Score, and accuracy are 93.4, 94.8, 95.2, and 95.1, respectively. This approach to diagnosing depression can monitor people for depression without compromising their privacy or causing other daily disruptions, making it an affordable long-term option.
... In fact, PIR sensing is a potential unobtrusive technology that has been widely used to monitor activities of daily living [25,26]. In our experiment, the camera was only used for dataset collection purposes. ...
Passive Infrared (PIR) Sensors have been used widely in human detection indoors nowadays due to their low cost and range. However, traditional PIR sensors may get fault detection, especially when the human is in a static pose. To overcome this limitation, a Machine Learning (ML)-based PIR sensor is proposed in this work for detection accuracy enhancement. The Learning Vector Quantization (LVQ) approach is used to be easily implemented in the embedded device (which requires a low computational complexity) to provide a real-time response. The experimental scenarios to create the datasets are conducted in two distinct locations for training and testing purposes. In each location, participants performed a series of different activities and left the room unoccupied. Data is collected via a PIR sensor and then wireless transmitted to a computer for training and testing. In the test set, the presence of humans with an accuracy of 89.25% is obtained using the proposed LVQ algorithm prediction. Finally, the LVQ is implemented on an embedded device based on Xtensa Dual-Core 32-bit LX6 CPU to form an intelligent PIR (iPIR)-based LVQ sensor, this novel iPIR sensor then is evaluated and tested with a remarkable result.
... They gain a deeper understanding in the field of the treatment and prevention of mental health problems, and in the continuous research, the methods and models of mental health prediction have been also continuously developed. However, the research on mental health still cannot keep up with the pace of social development, and there is a problem of asynchronous development [4]. So far, domestic experts' research on mental health mainly in facing psychological problems, coping strategies, challenges, reasons and how to predict and deal with them in time. ...
Psychological health is an important issue faced by college students, therefore conducting relevant research is meaningful. The use of Adaboost algorithm for ensemble learning, combined with the application of decision tree algorithm, can fully utilize the information in mental health test data and improve the prediction accuracy of the classifier. The C4.5 decision tree algorithm is a commonly used classification algorithm that can classify and distinguish samples based on feature attributes, so it has been selected as the basic algorithm for this study. In order to verify the effectiveness of this method, we selected the mental health test data of 2780 students from a certain university in 2020 for the experiment. Through analyzing experimental results, we found that the method can accurately identify sensitive psychological problems among students. In practical applications, this method can serve as an auxiliary tool to help schools accurately understand the distribution of students’ mental health problems, and thus develop corresponding educational measures and intervention plans. In summary, the mental health prediction method based on Adaboost algorithm proposed in the article, combined with the application of decision tree algorithm, can effectively identify psychological problems among college students. In the experiment, this method demonstrated high accuracy and robustness.
... 6 AI algorithms may be used with an array of unobtrusive sensors installed in the target's environment to detect and analyse motion and behavioral patterns associated with depression and with difficulties in activities of daily living. 45 The combined measures of autonomic functioning with measures of physical activity can provide context to improve the clinical relevance of these measures. 34 Another study used multiple input streams to represent changes in pain states over time, with sensors recording both actigraphy and speech, then combining these data with questionnaires on sleep quality, mood, alertness, pain intensity, activities of daily living (ADLs), and medication use. ...
Technology offers possibilities for quantification of behaviors and physiological changes of relevance to chronic pain, using wearable sensors and devices suitable for data collection in daily life contexts. We conducted a scoping review of wearable and passive sensor technologies that sample data of psychological interest in chronic pain, including in social situations. Sixty articles met our criteria from the 2783 citations retrieved from searching. Three-quarters of recruited people were with chronic pain, mostly musculoskeletal, and the remainder with acute or episodic pain; those with chronic pain had a mean age of 43 (few studies sampled adolescents or children) and 60% were women. Thirty-seven studies were performed in laboratory or clinical settings and the remainder in daily life settings. Most used only 1 type of technology, with 76 sensor types overall. The commonest was accelerometry (mainly used in daily life contexts), followed by motion capture (mainly in laboratory settings), with a smaller number collecting autonomic activity, vocal signals, or brain activity. Subjective self-report provided “ground truth” for pain, mood, and other variables, but often at a different timescale from the automatically collected data, and many studies reported weak relationships between technological data and relevant psychological constructs, for instance, between fear of movement and muscle activity. There was relatively little discussion of practical issues: frequency of sampling, missing data for human or technological reasons, and the users' experience, particularly when users did not receive data in any form. We conclude the review with some suggestions for content and process of future studies in this field.
... The works on monitoring ADL of older adults focus mainly on long-term behavioral analysis [6] in the contexts of daily activities [7][8][9][10][11][12] , abnormal behaviors [13][14][15][16][17][18][19] , cognitive impairment [20][21][22][23] , falls [24][25][26][27][28] , indoor person positioning [29][30][31] , and sleep quality [32] . Techniques can be broadly divided into video monitoring systems [33] , Wi-Fi fingerprinting-based technologies [34] , and on BLE fingerprinting-based technologies [35] . ...
p> Background: Assisted ambient living interfaces are technologies designed to improve the quality of life for people who require assistance with daily activities. They are crucial for individuals to maintain their independence for as long as possible. To this end, these interfaces have to be user-friendly, intuitive, and accessible, even for those who are not tech-savvy. Research in recent years indicates that people find it uncomfortable to wear invasive or large intrusive devices to monitor health status, and poor user interface design implies a lack of user engagement. Methods: This paper presents the design and implementation of non-intrusive mobile and smartwatch applications for detecting older adults when executing their routines. The solution uses an intuitive mobile application to set up beacons and incorporates biometric data acquired from the smartwatch to measure bio-signals correlated to the user’s location. User testing and interface evaluation are carried out using the User Experience Questionnaire (UEQ). Results: Six older adults participated in the evaluation of the interfaces. Results show that users found the interaction to be excellent in all the parameters of the UEQ in the evaluation of the mobile interface. For the smartwatch application, results vary from above average to excellent. Conclusions: The applications are intuitive and easy to use, and data obtained from integrating systems is essential to link information and provide feedback to the user.</p
... In [12], the author present sensor based depression detection algorithm with the chronic disorder patients. In [13], the author present schizophrenia prediction algorithm which analyses the problem using decision tree. ...
The problem of bipolar disorder has been well studied and analyzed. To perform the detection of presence of BD, there are number of approaches available and the result of detection has been used in several ways. In order to improve the performance in BD detection and utilize the result in gauging the performance of students, a behavioral pattern base psychotic analysis model has been presented in this paper. The method maintains the behaviors, habits and interests of different students in different period of time. The student behaviors includes mood change, depression, sudden laughs, uninterested, short temper, lack of concentration, adamant, frustration, energy, sleep and so on. Such behaviors has been tracked for number of students for prolong period and stored in the behavior set. By reading the behavior set and with the identified samples of BD, the method generates set of behavioral patterns. The behavioral pattern has been generated for three different classes like lower, medium and high. For each class of behavioral pattern, the method generates set of fuzzy rules. Using the fuzzy rule, each student has been analyzed for their behavioral pattern in different time window. Based on the patterns, the method estimates BDCW (Bipolar Disorder Class Weight). Based on the weight measure, the presence of BD has been identified and classified under different class. Identified results have been used to generate academic pattern and helps to generate analysis result to improve the student performance. The proposed approach improve the performance of student development, monitoring and health development.
... In the same way, [15] In their research, [16] researched people living alone to monitor their daily living activities. ...
In recent years, social media platforms have proved to be a vast repository of real-time information. People have expressed their inner feelings on the internet through social networking. Through reviewing their writings and postings on social media, it could help us to recognize various mental health problems early on. Tweets were retrieved using various keywords for mental health disorders from Twitter, Pre-processed using sentiment analysis and natural language processing techniques. Classification Models to analyze the tweets were developed using different data mining algorithms.The developed models analyze tweets relating to the area of mental health and then predict people having signs of mental health conditions. The accuracy of the predictions shows that Decision Tree and Random Forest classifiers performed better than other classifiers which suggests that multiple covariates and multiple decisions work better than other classifiers. This could help track mental health conditions such as depression, schizophrenia, anxiety disorders, drug abuse, and seasonal emotional disorders through the social media activities of users andsubsequently in real-time to monitor mental health.
... Several studies have demonstrated the utility of using wearable-based digital measures in assessing general depression [54][55][56] . Furthermore, one instance reported on the assessment of late-life depression using PIR-derived information on activities of daily living (ADL) 57 . However, it is unclear whether their methodology prevented data leakage, judging by the unusually high ROC AUC values ≥ 0.95. ...
Using connected sensing devices to remotely monitor health is a promising way to help transition healthcare from a rather reactive to a more precision medicine oriented proactive approach, which could be particularly relevant in the face of rapid population ageing and the challenges it poses to healthcare systems. Sensor derived digital measures of health, such as digital biomarkers or digital clinical outcome assessments, may be used to monitor health status or the risk of adverse events like falls. Current research around such digital measures has largely focused on exploring the use of few individual measures obtained through mobile devices. However, especially for long-term applications in older adults, this choice of technology may not be ideal and could further add to the digital divide. Moreover, large-scale systems biology approaches, like genomics, have already proven beneficial in precision medicine, making it plausible that the same could also hold for remote-health monitoring. In this context, we introduce and describe a zero-interaction digital exhaust: a set of 1268 digital measures that cover large parts of a person’s activity, behavior and physiology. Making this approach more inclusive of older adults, we base this set entirely on contactless, zero-interaction sensing technologies. Applying the resulting digital exhaust to real-world data, we then demonstrate the possibility to create multiple ageing relevant digital clinical outcome assessments. Paired with modern machine learning, we find these assessments to be surprisingly powerful and often on-par with mobile approaches. Lastly, we highlight the possibility to discover novel digital biomarkers based on this large-scale approach.
... Many studies have been conducted to predict depression using sleep time with a wearable band [10,11] because of the convenience. Studies using passive infrared (PIR) motion sensors in residential spaces to collect data from real living spaces are reported [12]. Individual depression can be predicted from daily life activities of spatial characteristics such as bedroom, bathroom, and kitchen. ...
Depression in the elderly is an important social issue considering the population aging of the world. In particular, elderly living alone who has narrowed social relationship due to bereavement and retirement are more prone to be depressed. Long-term depressed mood can be a precursor to eventual depression as a disease. Our goal is how to predict the depressed mood of single household elderly from unobtrusive monitoring of their daily life. We have selected a wearable band with multiple sensors for monitoring elderly people. Depression questionnaire has been surveyed periodically to be used as the labels. Instead of working with depression patients, we recruited 14 single household elderly people from a nearby community. The wearable band provided daily activity and biometric data for 71 days. From the data, we generate a depressed mood prediction model. Multiple features from the collected sensor data are exploited for model generation. One general model is generated to be used as the baseline for the initial model deployment. Personal models are also generated for model refinement. The general model has a high recall of 80% in an MLP model. Individual models achieved an average recall of 82.7%. In this study, we have demonstrated that we can generate depressed mood prediction models with data collected from real daily living. Our work has shown the feasibility of using a wearable band as an unobtrusive depression monitoring sensor even for elderly people.
... Researchers have used smart home sensors combined with computing and machine learning algorithms to detect changes in individuals' behaviors that are indicative of changes in health (Sprint et al., 2021;Bakar et al., 2015;Robben et al., 2017;Dahmen and Cook, 2021;Forbes et al., 2020;Forbes et al., 2021). In one study, researchers monitored residents' socialization patterns using ambient sensors and found that decreased socialization was predictive of depression (Kim et al., 2017). In other studies, machine learning techniques identifying behavior markers such as sleep/wake behaviors and activity level were used to predict pain (Fritz et al., 2020), clinical scores (Dawadi et al., 2013), and mobility, cognition, and depression symptoms in older adults (Alberdi Aramendi et al., 2018). ...
Background
: Telehealth and home-based care options significantly expanded during the SARS-CoV2 pandemic. Sophisticated, remote monitoring technologies now exist that support at-home care. Advances in the research of smart homes for health monitoring have shown these technologies are capable of recognizing and predicting health changes in near-real time. However, few nurses are familiar enough with this technology to use smart homes for optimizing patient care or expanding their reach into the home between healthcare touch points.
Objective
: The objective of this work is to explore a partnership between nurses and smart homes for automated remote monitoring and assessing of patient health. A series of health event cases is presented to demonstrate how this partnership may be harnessed to effectively detect and report on clinically relevant health events that can be automatically detected by smart homes.
Participants
: 25 participants with multiple chronic health conditions
Methods
: Ambient sensors were installed in the homes of 25 participants with multiple chronic health conditions. Motion, light, temperature, and door usage data were continuously collected from participants’ homes. Descriptions of health events and participants’ associated behaviors were captured via weekly nursing telehealth visits with study participants and used to analyze sensor data representing health events. Two cases of participants with congestive heart failure exacerbations, one case of urinary tract infection, two cases of bowel inflammation flares, and four cases of participants with sleep interruption were explored.
Results
: For each case, clinically relevant health events aligned with changes from baseline in behavior data patterns derived from sensors installed in the participant's home. In some cases, the detected event was precipitated by additional behavior patterns that could be used to predict the event.
Conclusions
: This case series provides evidence that continuous sensor-based monitoring of patient behavior in home settings may be used to provide automated detection of health events. Nursing insights into smart home sensor data could be used to initiate preventive strategies and provide timely intervention.
Tweetable abstract
: Smart home partnered with nurses could detect exacerbations of health conditions at home leading to early intervention
... Coupled with the relevant analytical capabilities, such as those provided by AI and big data applications, use cases of biosensors and wearables serve to detect and monitor mental disorders and provide complementary insights into self-report instruments (UC7). For example, the unobtrusive measurement of activities of daily living and social rhythm, and even voice signals detected through sensors, can inform health care providers about the state of patients' chronic diseases, including depressive symptoms or bipolar disorders [e.g., [25][26][27]. Further studies suggest accurate monitoring opportunities for stress and anxiety, schizophrenia, and PTSD [10]. ...
Digital technology trends for mental health, instantiated with only emerging use cases or already established applications, offer significant potential to improve clinical therapy and care. In this paper, we identify five major trends, mHealth/eHealth, telehealth, artificial intelligence (AI), big data, and biosensors/wearables; describe seven specific technology use cases for mental health care and psychotherapy; and provide an overview of their maturity in practice.
... 12, [30][31][32]36,39 However, studies to screen for and diagnose depression based on differences in levels of depression are lacking. 39,40 Therefore, a study targeting different patient groups is necessary for the diagnosis of depression. ...
Purpose
Depression is a symptom commonly encountered in primary care; however, it is often not detected by doctors. Recently, disease diagnosis and treatment approaches have been attempted using smart devices. In this study, instrumental effectiveness was confirmed with the diagnostic meta-analysis of studies that demonstrated the diagnostic effectiveness of PHQ-9 for depression using mobile devices.
Patients and Methods
We found all published and unpublished studies through EMBASE, MEDLINE, MEDLINE In-Process, and PsychINFO up to March 26, 2021. We performed a meta-analysis by including 1099 subjects in four studies. We performed a diagnostic meta-analysis according to the PHQ-9 cut-off score and machine learning algorithm techniques. Quality assessment was conducted using the QUADAS-2 tool. Data on the sensitivity and specificity of the studies included in the meta-analysis were extracted in a standardized format. Bivariate and summary receiver operating characteristic (SROC) curve were constructed using the metandi, midas, metabias, and metareg functions of the Stata algorithm meta-analysis words.
Results
Using four studies out of the 5476 papers searched, a diagnostic meta-analysis of the PHQ-9 scores of 1099 people diagnosed with depression was performed. The pooled sensitivity and specificity were 0.797 (95% CI = 0.642–0.895) and 0.85 (95% CI = 0.780–0.900), respectively. The diagnostic odds ratio was 22.16 (95% CI = 7.273–67.499). Overall, a good balance was maintained, and no heterogeneity or publication bias was presented.
Conclusion
Through various machine learning algorithm techniques, it was possible to confirm that PHQ-9 depression screening in mobiles is an effective diagnostic tool when integrated into a diagnostic meta-analysis.
... However, despite various technological convergences, the scope of SHS provision for the elderly focuses on supporting energy efficiency and physical functions, such as indoor environment control, automation [46][47][48][49], and remote response in case of emergency [42,43]. On the other hand, in the case of SHS related to mental health, studies dealing with practical support services at the level of detecting or predicting dementia and depressive states are insufficient [52,58,59]. Therefore, this study emphasized the need for psychological satisfaction and positive emotional management of the elderly in their house and sought an SHS plan that considers the requirements of the elderly from a bio-friendly perspective. ...
Smart home services (SHS) should support the positive experiences of the elderly in homes with a focus on getting closer to nature. The study identified the services preferred by the elderly through a survey on the biophilic experience-based SHS, and to discuss the configuration of the sensors and devices required to provide the service. We reorganized the biophilic experience-based SHS and related sensors and devices, focusing on our previous study, and developed a survey instrument. A preference survey was conducted on 250 adults aged 20 and older, and the SPSS program was used for a factor analysis and independent two-sample T-test. We derived six factors for biophilic experience-based SHS. Compared to other age groups, the elderly preferred services that were mainly attributed to factors such as 'Immersion and interaction with nature' (A), 'Management of well-being and indoor environmental quality (IEQ)' (B), and 'Natural process and systems' (F). We proposed 15 prioritized services, along with their sensor and device configurations, in consideration of service provision regarding the elderly's preferences and universality. This study contributes to new developments in elderly-friendly smart home research by converting bio-friendly ideas into the market in the development of medical services and SHS for the elderly.
... A data collection of 510 geriatric patients was used to assess and check 10 classifiers using 10 crossvalidation approaches (Tables 5.1À5.4). Chen et al. [14] Not involvement of grey literature Robotics Pino et al. [15] Smaller number of participants Robotics Kim et al. [16] Smaller number of participants Machine learning Abdollahi et al. [17] Smaller number of participants Robotics Zhongzhi et al. [18] Not enough data on patient's hospitalization. ...
Depression is a common disease occurring in every human at least once in his or her lifetime. Patients were analyzed based upon their text information, audio, video and image (IOT-based data) recording. The most effective techniques available in the deep learning models are being obtained and combined together to form the hybrid fusion model that how various types of fusion techniques. The fusion-based deep learning (FBDL) model was found to have a more accurate result along with the early fusion techniques, which also provided a good result. This technique is also being used in various IoT-based data applications to detect the depression of a person based upon their messages. The prevention of depression can be done using robotics which contains FBDL models. Several robots were used in the form of social animals or humanoids to minimize the effect of depression in elderly people. Thus deep learning models and robotics domain can be used to detect and cure the symptoms of depression in elderly people.
... Depressive state was reflected in low energy, slow movement and expanded limbs and torso [19,20]. Normally human activity like walking, researches keep a attention on arm swing and vertical head movements reducing, reduced walking speed, abnormal hand movements and head position in walking comparing to neutral, larger lateral swaying movements of the upper body and a more slumped posture and depressed patients showed larger reaction time variability [21,22]. ...
Background
Depression, a common worldwide mental disorder, which brings huge challenges to family and social burden around the world is different from fluctuant emotion and psychological pressure in their daily life. Although body signs have been shown to present manifestations of depression in general, few researches focus on whole body kinematic cues with the help of machine learning methods to aid depression recognition. Using the Kinect V2 device to record participants’ simple kinematic skeleton data of the participant’s body joints, the presented spatial features and low-level features is directly extracted from the record original Kinect-3D coordinates. This research aimed to constructed machine learning model with the preprocessed data importing, which could be used for depression automatic classification.
Methods
Considering some patients’ conditions and current status and refer to psychiatrists’ advices, simple and significant designed stimulus task will lead human skeleton data collection job. With original Kinect skeleton data extracting and preprocessing, the proposed experiment demonstrated four strong machine learning tools: Support Vector Machine, Logistic Regression, Random Forest and Gradient Boosting. Using the precision, recall, sensitivity, specificity, roc-curve, confusion matrix et.al, indicators were calculated as the measurement of methods, which were commonly used to evaluate classification methodologies.
Results
Across screened 64 pairs with age and gender totally matching in depression and control group, and Gradient Boosting achieved the best performance with the prediction accuracy of 76.92%. Sorted by female (54.69%) and male for the gender-based depression recognition, we applied best performance classifier Gradient Boosting got prediction accuracy of 66.67% in the male group, and 71.73% in the female group. Utilizing the best model Gradient Boosting for age-based classification, prediction accuracy got 76.92% in the older group (age >40, 50% of total) and 53.85% accuracy in the younger group (age <= 40).
Conclusion
The depression and non-depression individuals can be well classified by computational models using Kinect captured skeletal data. The Gradient Boosting, an excellent machine learning tool, get the performance in the four methods we demonstrated. Meanwhile, in the gender-based depression classification also gets reasonable accuracy. In particular, the recognition results of the old group are significantly better than that of the young group. All these findings suggest that kinematic skeletal data based depression recognition can be applied as an effective tool for assisting in depression analysis.
... Early detection of cognitive impairment has also been investigated in (50), by installing an unobtrusive activity assessment system containing motion sensors and contact sensors to monitor the activity of older adults in their homes. Moreover, passive infrared motion sensors have been employed to monitor the daily activities of elderly persons and achieve long-term depression monitoring by creating smart homes (Figure 6) (47). Last, a smart home test bed was designed at Washington State University represented by an apartment that was instrumented with motion sensors on the ceiling and sensors on cabinets and doors as well as sensors on selected kitchen items. ...
Collecting and analyzing data from sensors embedded in the context of daily life has been widely employed for the monitoring of mental health. Variations in parameters such as movement, sleep duration, heart rate, electrocardiogram, skin temperature, etc., are often associated with psychiatric disorders. Namely, accelerometer data, microphone, and call logs can be utilized to identify voice features and social activities indicative of depressive symptoms, and physiological factors such as heart rate and skin conductance can be used to detect stress and anxiety disorders. Therefore, a wide range of devices comprising a variety of sensors have been developed to capture these physiological and behavioral data and translate them into phenotypes and states related to mental health. Such systems aim to identify behaviors that are the consequence of an underlying physiological alteration, and hence, the raw sensor data are captured and converted into features that are used to define behavioral markers, often through machine learning. However, due to the complexity of passive data, these relationships are not simple and need to be well-established. Furthermore, parameters such as intrapersonal and interpersonal differences need to be considered when interpreting the data. Altogether, combining practical mobile and wearable systems with the right data analysis algorithms can provide a useful tool for the monitoring and management of mental disorders. The current review aims to comprehensively present and critically discuss all available smartphone-based, wearable, and environmental sensors for detecting such parameters in relation to the treatment and/or management of the most common mental health conditions.
... ANNs are extremely dynamic and find applications in domains related to pattern recognition. Kim et al. [49] used an inconspicuous method of IR sensors placed throughout the house to monitor movement, bathroom time, sleep, and excursions to detect signs of depression among elderly people through processing information received over telecom data using ANN. Bhatia and Sood [50] proposed using back propagation ANN to predict probabilistic health state vulnerabilities during exercising. ...
The Internet of Things (IoT) is playing a vital role in the rapid automation of the healthcare sector. The branch of IoT dedicated towards medical science is at times termed as Healthcare Internet of Things (H-IoT). The key elements of all H-IoT applications are data gathering and processing. Due to the large amount of data involved in healthcare, and the enormous value that accurate predictions hold, the integration of machine learning (ML) algorithms into H-IoT is imperative. This paper aims to serve both as a compilation as well as a review of the various state of the art applications of ML algorithms currently being integrated with H-IoT. Some of the most widely used ML algorithms have been briefly introduced and their use in various H-IoT applications has been analyzed in terms of their advantages, scope, and possible improvements. Applications have been divided into the domains of diagnosis, prognosis and spread control, assistive systems, monitoring, and logistics. In healthcare, practical use of a model requires it to be highly accurate and to have ample measures against security attacks. The applications of ML algorithms in H-IoT discussed in this paper have shown experimental evidence of accuracy and practical usability. The constraints and drawbacks of each of these applications have also been described.
... It is highly extensible. R can be use as programming, transforming, discovering, modelling and communicate the results [50]. The collection of library and package helps in transforming data, modelling and produce output visualization [49]. ...
... Kim et al. proposed a simple unobtrusive sensing system to monitor the activities of elderly people living alone. The results showed that the neural network effectively detected normal and mild depression [11]. Gao et al. focused on machine learning to predict major depression disorder utilizing features derived from magnetic resonance imaging (MRI) data [12]. ...
In this work, we propose a combined sampling technique to improve the performance of imbalanced classification of university student depression data. In experimental results, we found that combined random oversampling with the Tomek links under sampling methods allowed generating a relatively balanced depression dataset without losing significant information. In this case, the random oversampling technique was used for sampling the minority class to balance the number of samples between the datasets. Then, the Tomek links technique was used for undersampling the samples by removing the depression data considered less relevant and noisy. The relatively balanced dataset was classified by random forest. The results show that the overall accuracy in the prediction of adolescent depression data was 94.17%, outperforming the individual sampling technique. Moreover, our proposed method was tested with another dataset for its external validity. This dataset’s predictive accuracy was found to be 93.33%.
... (1) Biosensor-based real-time monitoring and remote management of geriatric physical activities and vital signs [28][29][30][31] (2) Medication safety and management with smart technologies including RFID, sensor, electronic tag, twodimension code, and global positioning system (GPS) [32][33][34][35][36] (3) Smart assessment of geriatric cognitive function with online and offline methods [37][38][39][40], e.g., estimating the influence of healthy lifestyle on episodic memory among adults who have subjective memory complaints [40] (4) Smart nursing methods for geriatric common and chronic diseases [41][42][43] In this section, we construct the framework of smart geriatric nursing in physical health by demonstrating two scenarios. The first scenario is biosensor-based real-time remote monitoring and management of geriatric physical activities and vital signs. ...
The National Bureau of Statistics of China shows that the population over 65 years old in China exceeds 166 million accounting for 11.93% of the total population by the end of 2018. The importance and severity of taking care of the elderly are becoming increasingly prominent. High-quality and meticulous care for the daily life of the elderly needs helpful and advanced sciences and technologies. Smart geriatric nursing is a must. Basing on the professional knowledge of geriatric nursing, this paper proposes a framework of smart geriatric nursing which consists of three aspects of smart nursing: smart geriatric nursing in physical health using biosensor and advanced devices, smart geriatric nursing in mental health based on user profile, and smart geriatric nursing for daily life based on big data in health. The deployment of the proposed method relies on the technologies of the Internet of Things (IoT), user profile system, big data, and many other advanced information technologies. The framework of methods can provide a useful reference for the systematic technical scheme of smart geriatric nursing in an aging society.
Depression, characterized by prolonged periods of low mood and a lack of pleasure or interest, poses significant threats to patients, necessitating effective monitoring to prevent suicides and reduce healthcare costs. Emerging wearable sensing technologies , known for real-time data collection and minimal intrusiveness, have revolutionized information systems (IS) studies on depression monitoring. However, existing sensing IS studies fall short in our context due to two technical challenges: the high individual heterogeneity among depressed patients, which undermines the effectiveness of population-level models, and the scarcity of data for individual patients, which limits the performance of individual-level models. To this end, we develop a novel Multi-stage Adaptive Robust Transfer (MART) learning algorithm that harnesses data from diverse source patients to help learn an individual-level model for a target patient with limited data. MART includes a new performance-based measurement to infer the similarity between source patients and the target patient, a similarity-aware distributionally robust optimization (DRO) to generate an adaptive and robust pre-trained model for the target patient, and a novel multi-stage transfer learning mechanism to iteratively improve the reliability of similarity measurement and the performance of the target model. We evaluate MART against alternative learning algorithms and state-of-the-art depression monitoring models on a real-world dataset comprising daily depression self-assessments and passive mobile phone-based behavioral data. Extensive experimental results demonstrate the superiority of MART, highlighting its generalizability across various classifiers. This study facilitates precision depression monitoring and benefits patients, caregivers, and doctors. Additionally, it contributes methodologically to the IS knowledge base, holding significant generalizability for domains where individual heterogeneity and data scarcity are salient.
Sustainable Development Goals (SDGs) give the UN a road map for development with Agenda 2030 as a target. SDG3 "Good Health and Well-Being" ensures healthy lives and promotes well-being for all ages. Digital technologies can support SDG3. Burnout and even depression could be reduced by encouraging better preventive health. Due to the lack of patient knowledge and focus to take care of their health, it is necessary to help patients before it is too late. New trends such as positive psychology and mindfulness are highly encouraged in the USA. Digital Twin (DT) can help with the continuous monitoring of emotion using physiological signals (e.g., collected via wearables). Digital twins facilitate monitoring and provide constant health insight to improve quality of life and well-being with better personalization. Healthcare DT challenges are standardizing data formats, communication protocols, and data exchange mechanisms. To achieve those data integration and knowledge challenges, we designed the Mental Health Knowledge Graph (ontology and dataset) to boost mental health. The Knowledge Graph (KG) acquires knowledge from ontology-based mental health projects classified within the LOV4IoT ontology catalog (Emotion, Depression, and Mental Health). Furthermore, the KG is mapped to standards (e.g., ontologies) when possible. Standards from ETSI SmartM2M, ITU/WHO, ISO, W3C, NIST, and IEEE are relevant to mental health.
Purpose of review
Environmental factors such as climate, urbanicity, and exposure to nature are becoming increasingly important influencers of mental health. Incorporating data gathered from real-life contexts holds promise to substantially enhance laboratory experiments by providing a more comprehensive understanding of everyday behaviors in natural environments. We provide an up-to-date review of current technological and methodological developments in mental health assessments, neuroimaging and environmental sensing.
Recent findings
Mental health research progressed in recent years towards integrating tools, such as smartphone based mental health assessments or mobile neuroimaging, allowing just-in-time daily assessments. Moreover, they are increasingly enriched by dynamic measurements of the environment, which are already being integrated with mental health assessments. To ensure ecological validity and accuracy it is crucial to capture environmental data with a high spatio-temporal granularity. Simultaneously, as a supplement to experimentally controlled conditions, there is a need for a better understanding of cognition in daily life, particularly regarding our brain's responses in natural settings.
Summary
The presented overview on the developments and feasibility of “real-life” approaches for mental health and brain research and their potential to identify relationships along the mental health-environment-brain axis informs strategies for real-life individual and dynamic assessments.
Background
Smart home health technologies (SHHTs) have been discussed in the frame of caregiving to enable aging-in-place and independence. A systematic review was conducted in accordance with the PRISMA guidelines to gather the up-to-date knowledge on the benefits and barriers of using SHHTs in the care of older persons from the perspective of older persons and their caregivers.
Methods
Ten electronic databases were reviewed for empirical peer-reviewed literature published from 01.01.2000 to 31.12.2021 in English, German, and French reporting on experimental, qualitative, quantitative, and other empirical study designs were included. Included studies contained user-feedback from older persons over 65 years of age or their caregivers (formal and informal). We used an extraction document to collect relevant data from all included studies and applied narrative synthesis to analyze data related to benefits and barriers of SHHTs.
Results
163 empirical peer-reviewed articles were included, the majority of those published between 2014 and 2021. Five first-order categories of benefits and five of barriers were found with individual sub-themes. SHHTs could be useful in the care context where continuous monitoring is needed. They improve self-management and independent living of older persons. Barriers currently exist with respect to ease of usability, social acceptance, and cost.
Conclusions
SHHTs could be useful in the care context but are not without concerns. Researchers and policy makers can use the information as a starting point to better understand how the roles and outcomes of SHHTs could be improved for the care of older persons, while caregivers of older adults could use our findings to comprehend the scope of SHHTs and to decide when and where such technology could best address their individual family needs. Limitations lie in the possible exclusion of relevant articles published outside the inclusion criteria as well as the fact that due to digital divide, our review represents opinions of those who could and wanted to participate in the included 163 studies.
Trial registration
This review has been registered as PROSPERO CRD42021248543. A protocol was completed in March 2021 with the PRISMA-P guidance. We have extended the review period from 2000 to 2020 since the registration of the protocol to 2000–2021.
Depression, as a common mental illness, has become a significant public health issue, and the recurrence rate for patients with depression who have been treated is relatively high. In this study, a mental health monitoring system based on wearable sensing wristbands with sensors for voice, activity, and heart rate has been developed. Using this system, we perform a therapeutic monitoring study for hospitalized patients with depression and healthy controls to investigate multimodal changes before, during, and after a course of treatment. The obtained results demonstrate there are significant changes in multimodal features such as audio short-time energy and angular velocity shape skewness with the remission of depressive symptoms. According to Mikels’ emotion wheel, a day’s data for subjects is defined as three types of emotional units and the emotional state of each emotional unit is recognized as positive or negative emotions. With this, emotion-sensing-graphs guided by Mikels’ emotion wheel theory are constructed. The analysis of emotion-sensing-graphs reveals that the same emotions are more closely linked to each other and the average degree and proportion of positive emotion nodes after a course of treatment have increased significantly. Finally, an emotion-sensing-graph graph convolutional network model fused three types of emotion-sensing-graphs with emotion labels has been developed to assess the levels of depression, thereby monitoring the changes in depressive symptoms. Compared with classical machine learning models, the accuracy, F1 score, and recall rate of the model perform best and the model achieves a verification accuracy of 0.83.
In this paper, machine learning techniques are used to detect and predict the mental health status of individuals based on the concept of Perceived Control using a mobile app. Perceived control has long been established to have a strong link with an individual’s mental health. Individuals with a high level of perceived control seem to have good mental health while those with low levels of perceived control usually suffer from depression, anxiety and stress.
In the proposed method, an individual’s measure of perceived control is solicited by allowing them to download and install an android app called the Judgement App. The users then participate in an experiment, where they perform a number of trials and make a judgement after 8 trials. The data generated is then analysed and used to train supervised machine learning models to predict whether an individual is suffering from depression or not. Data generated for internal and external perceived control were of both tabular and time-series types. The data is labelled by the subject's Beck Depressive Inventory (BDI-II) score, which is performed by the individual answering the 21-questions before the experiment begins. Due to the imbalanced nature of the data available, Synthetic Minority Oversampling Technique (SMOTE) and some of its variants were used to process the training data before being used to train ML algorithms. Simple evaluation criteria consisting of Precision, Recall, F1-score and overall model efficiency were used.
The evaluation was completed by analyzing 274 samples from 140 participants. Out of the 274 samples, 53 were labelled as mildly depressed and 221 as non-depressed.
As aging problem gets severe, more elderly people require better residences to support their later lives. Considering complicated safety and health risks the elderly would encounter indoors, such as falls and sudden diseases, researchers have tried to implement smart buildings to reduce indoor risks for the elderly. Fortunately, residential buildings have benefited from rapid development of smart techniques. It is meaningful to look back on how smart buildings deal with indoor risks of the elderly. This article adopts approaches of systematic literature review to identify 92 eligible articles which proposed smart buildings for the elderly. Then the time trend, publication journals, co-authorship and co-occurrence of these eligible articles are revealed by the bibliometric analysis. Five critical targets of these smart building solutions are summarized, including fall detection, activity recognition, disease prediction, health monitoring, and emotional care. Previous smart buildings mostly adopted Support Vector Machine (SVM), classifier comparison, neural network, Hidden Markov Model (HMM) and robotics as main smart techniques. Furthermore, these different smart building techniques are generally developed for different sub-targets or integrated for one main target, that are regarded as two correlation modes between techniques and targets. Current challenges and future direction of the development of smart buildings are pointed out. This review helps to know what kinds of indoor risks of the elderly were focused by smart buildings and which smart techniques were widely applied to develop smart buildings, then provides suggestions for future research to promote smart buildings to be more safe and healthy for the elderly.
Many people in our busy society are subjected to circumstances where mental stress is inevitable. As a result, people encounter a variety of mental health issues, some of which may develop into chronic mental diseases. As mental health issues are stereotyped, people with these conditions usually wish to hide their health difficulties. Majority of them are in a state of denial, which might lead to extremely significant societal issues since, people who have mental health issues will often acquire mental dis- eases and may be dangerous to both themselves and those around them. It’s critical to give those with mental health difficulties the appropriate care and drugs. It is extremely possible that if a person’s mental state is monitored and evaluated, their mental health disorders may be dis- covered very early on and are thus treatable and curable. This project’s contribution is a web-based system for mental health consulting. The system is designed to be able to dynamically generate user interfaces from the initial state to reach a decision during the consultation process.KeywordsCounsellingPsychologistPsychiatristMental health problemsMental health consultation
Purpose
This study aims to reduce data bias during human activity and increase the accuracy of activity recognition.
Design/methodology/approach
A convolutional neural network and a bidirectional long short-term memory model are used to automatically capture feature information of time series from raw sensor data and use a self-attention mechanism to learn select potential relationships of essential time points. The proposed model has been evaluated on six publicly available data sets and verified that the performance is significantly improved by combining the self-attentive mechanism with deep convolutional networks and recursive layers.
Findings
The proposed method significantly improves accuracy over the state-of-the-art method between different data sets, demonstrating the superiority of the proposed method in intelligent sensor systems.
Originality/value
Using deep learning frameworks, especially activity recognition using self-attention mechanisms, greatly improves recognition accuracy.
The upward trend in the percentage of the population older than 65 has made smart aging more relevant than ever before. Growing old in a traditional assisted living facility can take a toll on the mental well-being of the elderly individual, on top of other factors like extravagant costs, potential negligence from caregivers, and a ceaseless demand for healthcare personnel. Aging in one’s own space instead of a senior residence is the desirable alternative thanks to enabling technologies like the Internet of Things (IoT). The IoT facilitates connected healthcare, safety, entertainment, and social well-being of the older population. However, it suffers from a multitude of security vulnerabilities. Although researchers have investigated the security challenges of several IoT ecosystems, IoT systems in the context of smart aging care have not been well studied from a security perspective. In this paper, we present an in-depth analysis of smart aging care system security issues. A smart aging care system is essentially a superset of smart homes and healthcare monitoring systems. The sheer variety of technologies at play and the amount of data generated, combined with physical vulnerabilities and a lack of technological exposure of the intended occupant group put smart aging care systems at great risk. Attacks against relatively benign smart home devices can bring serious consequences because of the context in which these devices are employed. Thus, the purpose of our study is four-fold: (i) defining the components and functionalities of a smart aging care system, (ii) identifying security vulnerabilities and outlining suitable countermeasures for them, (iii) analyzing how the attacks uniquely impact senior users’ Quality of Life (QoL), (iv) highlighting avenues for future research and how the threat landscape in smart aging care systems differ from general smart homes.
Background:
The Internet of Things (IoT) has become integrated into everyday life, with devices becoming permanent fixtures in many homes. As countries face increasing pressure on their health care systems, smart home technologies have the potential to support population health through continuous behavioral monitoring.
Objective:
This scoping review aims to provide insight into this evolving field of research by surveying the current technologies and applications for in-home health monitoring.
Methods:
Peer-reviewed papers from 2008 to 2021 related to smart home technologies for health care were extracted from 4 databases (PubMed, Scopus, ScienceDirect, and CINAHL); 49 papers met the inclusion criteria and were analyzed.
Results:
Most of the studies were from Europe and North America. The largest proportion of the studies were proof of concept or pilot studies. Approximately 78% (38/49) of the studies used real human participants, most of whom were older females. Demographic data were often missing. Nearly 60% (29/49) of the studies reported on the health status of the participants. Results were primarily reported in engineering and technology journals. Almost 62% (30/49) of the studies used passive infrared sensors to report on motion detection where data were primarily binary. There were numerous data analysis, management, and machine learning techniques employed. The primary challenges reported by authors were differentiating between multiple participants in a single space, technology interoperability, and data security and privacy.
Conclusions:
This scoping review synthesizes the current state of research on smart home technologies for health care. We were able to identify multiple trends and knowledge gaps-in particular, the lack of collaboration across disciplines. Technological development dominates over the human-centric part of the equation. During the preparation of this scoping review, we noted that the health care research papers lacked a concrete definition of a smart home, and based on the available evidence and the identified gaps, we propose a new definition for a smart home for health care. Smart home technology is growing rapidly, and interdisciplinary approaches will be needed to ensure integration into the health sector.
Today, many changes have been seen in the life of people in society with the development of new technologies. For example, developing various new communication platforms and applications such as social networks has been able to affect the lifestyle and communication of people in different age groups. The elderly are one of the most important sections of society, and other age groups have been affected by new applications and social networks in recent years. One of the important issues that should be considered for the elderly people is to provide a suitable environment to improve their quality of life because they are one of the most vulnerable groups in society who, due to old age and various diseases, don't have this power to do their daily routine, and this affects their moods. So, designing new intelligence applications for improving their emotional intelligence can play an important role to facilitate their work and communications. In this chapter, the authors discuss new artificial intelligence applications that can control the emotional intelligence of the elderly.
Information and communication technologies (ICT) such as smart devices, the Internet of Things and wireless sensor networks are gradually being introduced into the health system for early diagnosis and management of certain diseases. The state of the art of the use of these technologies in mental health identified 37 articles published in indexed high impact journals in the period 2003-2021. The snowball sampling method was used to select these papers. From this literature review, it appears that several of these technologies are used to support the early detection of mental disorders. Various systems based on wearable sensor networks, the Internet of Things and pervasive and ubiquitous computing have been designed and implemented in this sense. However, most of the applications are designed for academic purposes. 29% of the papers deal with the use of mobile technology in the detection of mental illness, while 67% have studied other technologies such as wearable sensor networks. 4% of the papers concern the use of web platforms in the detection and assessment of mental health disorders.
The Internet of Medical Things is promising for monitoring depression symptoms. Therefore, it is necessary to develop multimodal monitoring systems tailored for elderly individuals with high feasibility and usability for further research and practice. This study comprised two phases: (1) methodological development of the system; and (2) system validation to evaluate its feasibility. We developed a system that includes a smartphone for facial and verbal expressions, a smartwatch for activity and heart rate monitoring, and an ecological momentary assessment application. A sample of 21 older Koreans aged 65 years and more was recruited from a community center. The 4-week data were collected for each participant (n = 19) using self-report questionnaires, wearable devices, and interviews and were analyzed using mixed methods. The depressive group (n = 6) indicated lower user acceptance relative to the nondepressive group (n = 13). Both groups experienced positive emotions, had regular life patterns, increased their self-interest, and stated that a system could disturb their daily activities. However, they were interested in learning new technologies and actively monitored their mental health status. Our multimodal monitoring system shows potential as a feasible and useful measure for acquiring mental health information about geriatric depression.
Background: The Internet of Things (IoT) has become more integrated into everyday life, with devices becoming permanent fixtures in many homes. As countries face increasingly older populations, the use of IoT devices to support independent living for elderly individuals and others who need support is now possible. These groups may require assistance or varying levels of monitoring within the home. Smart home technologies that are unobtrusive, continuous, and reliably monitor healthy behaviour can fill this gap. The rationale of this scoping review is to provide insight into this evolving field of research by surveying the technologies available for in-home monitoring.
Objective: This scoping review evaluated smart home technology approaches to identify behavioural patterns and health indicators that could support caregivers and healthcare providers with standardized guidelines.
Methods: The study used the methodological framework proposed by Arksey and O'Malley. We analyzed articles published between 2008 and 2021 to understand better the scope of smart home data used to monitor vulnerable populations. Interest in smart home research increased rapidly after 2008, as technologies became more widely available. Only journal articles in English were included from PubMed, Scopus, ScienceDirect, and CINAHL databases. Search terms included smart home, ambient assisted living, health, and monitor.
Results: Forty-nine of the most recent and relevant articles were included in this scoping review. Most of the studies were from Europe and North America. The largest proportion of the studies were proof of concept, pilot studies, and related to the development of infrastructure architecture and testing of algorithms. Findings from these studies have been summarised by human-centric and techno-centric features. Nearly 78% of the studies have data from humans, 63 % mentioned age, and only 33 % mentioned the sex of the participants. Most of the studies had data from the elderly population (primarily female subjects) in the home setting. Nearly 60 % of the studies reported on the health status of the participants. Technocentric features included the type of data collected, the type of sensors used and analysis methods, respectively. A wide range of sensors were used across the studies, as were the variety of outcomes measured by each representing different health indicators. PIR sensors were the frequently used sensors, while activity or motion detection and recognition were the commonly used health parameters. There were many technical challenges and barriers, including a lack of collaboration and the use of interdisciplinary approaches. There is no standardized definition of a smart home in the literature, and, thus, the authors proposed a new definition.
Conclusions: In conclusion, smart home technology has the potential to improve the monitoring of vulnerable populations, especially those ageing in the community, but it has not been fully explored. The use of Big Data, artificial intelligence algorithms, including machine and deep learning, with near-real-time dissemination of the results, will be the future of in-home health monitoring.
Modern advancements have allowed society to be at the most innovative stages of technology which involves the possibility of multimodal data collection. Dartmouth dataset is a rich dataset collected over 10 weeks from 60 participants. The dataset includes different types of data but this paper focuses on 10 different smartphone sensor data and a Patient Health Questionnaire (PHQ) 9 survey that monitors the severity of depression. This paper extracts key features from smartphone data to identify depression. A multi-view bi-clustering (MVBC) algorithm is applied to categorize homogeneous behaviour subgroups. MVBC takes multiple views of sensing data as input. The algorithm inputs three views: average, trend, and location views. MVBC categorizes the subjects to low, medium and high PHQ-9 scores. Real-world data collection may have fewer sensors, allowing for less features to be extracted. This creates a focus on prioritization of features. In this body of work, minimum redundancy maximum relevance (mRMR) is applied to the sensing features to prioritize the features that better distinguish the different groups. The resulting MVBC are compared to literature to support the categorized clusters. Decision Tree (DT) 10-fold cross validation shows that our method can classify individuals into the correct subgroups using a reduced number of features to achieve an overall accuracy of 94.7±1.62%. Achieving high accuracies with reduced features allows for focus on low power analysis and edge computing applications for long-term mental health monitoring using a smartphone.
Social companion robots are getting more attention to assist elderly people to stay independent at home and to decrease their social isolation. When developing solutions, one remaining challenge is to design the right applications that are usable by elderly people. For this purpose, co-creation methodologies involving multiple stakeholders and a multidisciplinary researcher team (e.g., elderly people, medical professionals, and computer scientists such as roboticists or IoT engineers) are designed within the ACCRA (Agile Co-Creation of Robots for Ageing) project. This paper will address this research question: How can Internet of Robotic Things (IoRT) technology and co-creation methodologies help to design emotional-based robotic applications? This is supported by the ACCRA project that develops advanced social robots to support active and healthy ageing, co-created by various stakeholders such as ageing people and physicians. We demonstra this with three robots, Buddy, ASTRO, and RoboHon, used for daily life, mobility, and conversation. The three robots understand and convey emotions in real-time using the Internet of Things and Artificial Intelligence technologies (e.g., knowledge-based reasoning).
The area of Data mining is expanding day by day since it provides interesting insights covering many sectors under it, one of it being the Medical Science area. Under the Medical sciences specifically when it comes to the mental health, it helps to understand and classify the type of disease whose symptoms might be predominant in the human body. The chief aim of this article is to review the most lately literature belonging to the intercessions for Data Mining in Mental Health covering many techniques and algorithms linked with Data Mining in the most occurring diseases such as Alzheimer, Dementia, Depression, Schizophrenia and Bipolar Disorder. Some of the academic databases used for this literature review are Google Scholar, IEEE Xplore, Research Gate which include a handful of e-journals for study and research-based materials.
The ageing of the population, and their increasing wish of living independently, are motivating the development of welfare and healthcare models. Existing approaches based on the direct heath-monitoring using body sensor networks (BSN) are precise and accurate. Nonetheless, their intrusiveness causes non-acceptance. New approaches seek the indirect monitoring through monitoring activities of daily living (ADLs), which proves to be a suitable solution. ADL monitoring systems use many heterogeneous sensors, are less intrusive, and are less expensive than BSN, however, the deployment and maintenance of wireless sensor networks (WSN) prevent them from a widespread acceptance. In this work, a novel technique to monitor the human activity, based on non-intrusive load monitoring (NILM), is presented. The proposal uses only smart meter data, which leads to minimum intrusiveness and a potential massive deployment at minimal cost. This could be the key to develop sustainable healthcare models for smart homes, capable of complying with the elderly people’ demands. This study also uses the Dempster-Shafer theory to provide a daily score of normality with regard to the regular behavior. This approach has been evaluated using real datasets and, additionally, a benchmarking against a Gaussian mixture model approach is presented.
Wireless-sensor-network-based home monitoring system for elderly activity behavior involves functional assessment of daily activities. In this paper, we reported a mechanism for estimation of elderly well-being condition based on usage of house-hold appliances connected through various sensing units. We defined two new wellness functions to determine the status of the elderly on performing essential daily activities. The developed system for monitoring and evaluation of essential daily activities was tested at the homes of four different elderly persons living alone and the results are encouraging in determining wellness of the elderly.
The age span of elderly people is increasing and this trend may continue for another two decades. The independent living of elderly people are keen on fulfilling lives, but the self-regulating way of life involve with risks, such as weakening, memory loss or impaired judgment and falls that limit mobility. In particular, the daily home activity involving basic functions like preparing breakfast or food, showering, walking, sleeping, watching television, reading books etc., is a key indicator in determining the performance of elder home activity. An intelligent, robust, less cost, flexible and real time home monitoring unit has been developed to record the basic home activities and respond immediately when there is a change in the regular daily activity of the elder person. This paper will report our recent works on the development of intelligent algorithm to determine the behavior.
The tutorial starts with an overview of the concepts of VC dimension and structural risk minimization. We then describe linear Support Vector Machines (SVMs) for separable and non-separable data, working through a non-trivial example in detail. We describe a mechanical analogy, and discuss when SVM solutions are unique and when they are global. We describe how support vector training can be practically implemented, and discuss in detail the kernel mapping technique which is used to construct SVM solutions which are nonlinear in the data. We show how Support Vector machines can have very large (even infinite) VC dimension by computing the VC dimension for homogeneous polynomial and Gaussian radial basis function kernels. While very high VC dimension would normally bode ill for generalization performance, and while at present there exists no theory which shows that good generalization performance is guaranteed for SVMs, there are several arguments which support the observed high accuracy of SVMs, which we review. Results of some experiments which were inspired by these arguments are also presented. We give numerous examples and proofs of most of the key theorems. There is new material, and I hope that the reader will find that even old material is cast in a fresh light.
By 2050, about one third of the French population will be over 65. Our laboratory's current research focuses on the monitoring of elderly people at home, to detect a loss of autonomy as early as possible. Our aim is to quantify criteria such as the international activities of daily living (ADL) or the French Autonomie Gerontologie Groupes Iso-Ressources (AGGIR) scales, by automatically classifying the different ADL performed by the subject during the day. A Health Smart Home is used for this. Our Health Smart Home includes, in a real flat, infrared presence sensors (location), door contacts (to control the use of some facilities), temperature and hygrometry sensor in the bathroom, and microphones (sound classification and speech recognition). A wearable kinematic sensor also informs postural transitions (using pattern recognition) and walk periods (frequency analysis). This data collected from the various sensors are then used to classify each temporal frame into one of the ADL that was previously acquired (seven activities: hygiene, toilet use, eating, resting, sleeping, communication, and dressing/undressing). This is done using support vector machines. We performed a 1-h experimentation with 13 young and healthy subjects to determine the models of the different activities, and then we tested the classification algorithm (cross validation) with real data.
Current methods of assessing psychopathology depend almost entirely on verbal report (clinical interview or questionnaire) of patients, their family, or caregivers. They lack systematic and efficient ways of incorporating behavioral observations that are strong indicators of psychological disorder, much of which may occur outside the awareness of either individual. We compared clinical diagnosis of major depression with automatically measured facial actions and vocal prosody in patients undergoing treatment for depression. Manual FACS coding, active appearance modeling (AAM) and pitch extraction were used to measure facial and vocal expression. Classifiers using leave-one-out validation were SVM for FACS and for AAM and logistic regression for voice. Both face and voice demonstrated moderate concurrent validity with depression. Accuracy in detecting depression was 88% for manual FACS and 79% for AAM. Accuracy for vocal prosody was 79%. These findings suggest the feasibility of automatic detection of depression, raise new issues in automated facial image analysis and machine learning, and have exciting implications for clinical theory and practice.
Classifier learning with data-sets that suffer from imbalanced class distributions is a challenging problem in data mining community. This issue occurs when the number of examples that represent one class is much lower than the ones of the other classes. Its presence in many real-world applications has brought along a growth of attention from researchers. In machine learning, the ensemble of classifiers are known to increase the accuracy of single classifiers by combining several of them, but neither of these learning techniques alone solve the class imbalance problem, to deal with this issue the ensemble learning algorithms have to be designed specifically. In this paper, our aim is to review the state of the art on ensemble techniques in the framework of imbalanced data-sets, with focus on two-class problems. We propose a taxonomy for ensemble-based methods to address the class imbalance where each proposal can be categorized depending on the inner ensemble methodology in which it is based. In addition, we develop a thorough empirical comparison by the consideration of the most significant published approaches, within the families of the taxonomy proposed, to show whether any of them makes a difference. This comparison has shown the good behavior of the simplest approaches which combine random undersampling techniques with bagging or boosting ensembles. In addition, the positive synergy between sampling techniques and bagging has stood out. Furthermore, our results show empirically that ensemble-based algorithms are worthwhile since they outperform the mere use of preprocessing techniques before learning the classifier, therefore justifying the increase of complexity by means of a significant enhancement of the results.
We study activity recognition using 104 hours of annotated data collected from a person living in an instrumented home. The home contained over 900 sensor inputs, including wired reed switches, current and water flow inputs, object and person motion detectors, and RFID tags. Our aim was to compare dierent sensor modalities on data that approached "real world" conditions, where the subject and annotator were unaliated with the authors. We found that 10 infra-red motion detectors outperformed the other sensors on many of the activities stud- ied, especially those that were typically performed in the same location. However, several activities, in particular "eating" and "reading" were dicult to detect, and we lacked data to study many fine-grained activi- ties. We characterize a number of issues important for designing activity detection systems that may not have been as evident in prior work when data was collected under more controlled conditions.
The aim of this prospective study was to investigate the reciprocal nature of the physical activity-depressive symptoms relationship in 17,593 older adults from 11 European countries older adults (M age = 64.07, SD = 9.58) across two-year follow-up. Also, gender and age were examined as potential moderators of this relation.
A two-wave cross-lagged panel design and latent change score models with structural equation modeling was used to analyze data. Depressive symptoms were measured at baseline (T1) and follow-up (T2) using the EURO-D scale, capturing the two factors of affective suffering and motivation. Physical activity was measured at T1 and T2 as frequency of moderate physical activity and vigorous physical activity.
Cross-sectional latent variable analyses revealed that higher levels of physical activity at T1 and T2 were associated with lower levels of affective suffering and motivation at T1 and T2. Physical activity at T1 was significantly associated with affective suffering and motivation at T2. The relations of depressive symptoms at T1 with physical activity at T2 were not significant. However, a cross-lagged model showed best model fit, supporting a reciprocal prospective relationship between physical activity and depressive symptoms in older adults. Latent change in depressive symptoms factors was related to latent change in physical activity indicating complex and dynamic associations across time.
Regular physical activity may be a valuable tool in the prevention of future depressive symptoms in older adults, and depressive symptoms may also prevent older adults from engaging in regular physical activity.
The purpose of this study was to examine scale dimensionality, reliability, invariance, targeting, continuity, cutoff scores, and diagnostic use of the Geriatric Depression Scale-Short Form (GDS-SF) over time with a sample of 177 English-speaking U.S. elders.
An item response theory, Rasch analysis, was conducted with data from a larger study that implemented 3 interventions and collected data at 3 time points (prior to intervention, after intervention, and a year following the end of intervention).
A unidimensional structure was found in this study to adequately fit the data. There appears to be significant differential item functioning, with up to one third of the items indicating that the items have different meanings for different groups of participants. As a screening tool, the GDS-SF is more likely to discriminate between older adults who have a "moderate" level of depression than between those with mild depression and no diagnosed depression.
We would recommend that the GDS-SF not be used as the sole method of screening for depression but incorporated into other clinical knowledge related to the geriatric patient in question, given that not all items are equally functional. The GDS-SF may be less effective as a screening tool but could be better used to detect a change in moderate levels of depression. Clinicians may also benefit by identifying person responses that misfit. If an individual provides responses that are atypical, the person might be referred to provide a more in-depth assessment of mental health status.
One-hundred and ninety-eight elderly subjects attending their general practitioners (GPs) were asked to complete the 15 item Geriatric Depression Scale (GDS15). Analysable results were obtained from 194 (98%). Of these, 67 (34%) scored above the GDS15 cut-off (4/5) for significant depressive symptomatology. 87.6% found the questionnaire to be acceptable and only 3.6% found it very difficult or very stressful. The GDS15 had a high level of internal consistency (Cronbach's alpha = 0.80). All the individual items of the GDS15 associated significantly (P < 0.01) with total score and 'caseness'. A single question "do you feel that your life is empty?" identified 84% of 'cases'. In an attempt to devise short scales to screen elderly primary care patients for depression, the data were subjected to logistic regression analysis. Ten (GDS10), four (GDS4) and on (GDS1) item versions were generated. Agreement between these short scales and the GDS15 in the original sample was 95, 91 and 79% respectively. Cronbach's alpha was 0.72 for the GDS10 and 0.55 for the GDS4. The short scales were then validated in an independent sample of 120 patients in whom both GDS data and the results of a detailed psychiatric interview (the Geriatric Mental Status Schedule, GMS) were available. The sensitivity and specificity of the GDS10 against GMS caseness were 87 and 77% (cut-off 3/4); those of the GDS4 were 89 and 65% (cut-off 0/1) and 61 and 81% (cut-off 1/2). Sensitivity and specificity for the GDS1 were 59 and 75%. It is concluded that these short scales may be useful in helping GPs and practice staff to identify elderly patients with significant depressive symptoms.
The growing percentage of elderly people in society calls for novel healthcare support services to enhance elders' daily life independence in indoor and outdoor environments. Ubiquitous technologies create significant opportunities not only for indoor, but also for outdoor anytime and anywhere assistance. However, outdoor emergency assistance requires that we address several challenging aspects, from elder location tracking and health condition monitoring to the formation of ad hoc assistance groups capable of assisting elders in need of help. This article focuses on the creation and management of outdoor assistance teams and proposes a group management system, AGAPE, that exploits visibility of location and group/user/device profile information as a key principle to trigger and control the team formation and team member interactions required to coordinate emergency activities.
Managing Depression, Growing Older: A Guide for Professionals and Carers By Kerrie Eyers, Gordon Parker, Henry Brodaty Allen & Unwin. 2012. AUD $27.99 (pb), 300pp. ISBN: 9781742378800
Old age psychiatry has experienced a change in its culture. With the ageing population predicted to rise
Objective: This study aimed at determining the relationship between daily living activities, sleep and depression among individuals 60 years or older living at home. Methodology: This descriptive and cross-sectional study was conducted with 166 patients of a family health center between December 2010 and March 2011. Data were collected via Questionnaire Form, Katz Index of Activities of Daily Living (ADL), Geriatric Depression Scaleshort form (GDS_SF), and the Pittsburgh Sleep Quality Index (PSQI). Results: The participants' mean age was 67.34±6.5, 78.9% had chronic diseases and 29.5% had walking problems. In words 56.8% had poor sleep, 26.5% had depressive symptoms and the majority were independent in ADL. A negative relationship was observed between ADL score and PSQI and GDS but a positive one between PSQI and GDS (p<0.05). Conclusions: Although individuals' elderly people living at home are independent in basic ADL, they are displaying considerable depressive symptoms and having sleep problems.
We examine a graphical representation of uncertain knowledge called a Bayesian network. The representation is easy to construct and interpret, yet has formal probabilistic semantics making it suitable for statistical manipulation. We show how we can use the representation to learn new knowledge by combining domain knowledge with statistical data. 1 Introduction Many techniques for learning rely heavily on data. In contrast, the knowledge encoded in expert systems usually comes solely from an expert. In this paper, we examine a knowledge representation, called a Bayesian network, that lets us have the best of both worlds. Namely, the representation allows us to learn new knowledge by combining expert domain knowledge and statistical data. A Bayesian network is a graphical representation of uncertain knowledge that most people find easy to construct and interpret. In addition, the representation has formal probabilistic semantics, making it suitable for statistical manipulation (Howard,...
It has been identified that performance of Activities of Daily living (ADL) and chronic disease are predictors of depression for older Asian immigrants. This study examined the independent and interactive effects of ADL performance and chronic disease on depressive symptoms among older Korean immigrants. Data from 210 older Korean immigrants in Los Angeles County were analyzed. Self-reported measures included sociodemographic characteristics, ADL performance, chronic disease, and depressive symptoms. A hierarchical regression model indicated that performance of activities of daily living were negatively associated with depressive symptoms. Also, older Korean immigrants with more chronic diseases were more likely to have depressive symptoms. The interaction between ADL performance and chronic diseases was significantly associated with lower levels of depressive symptoms (β = .46, p Document Type: Research Article DOI: http://dx.doi.org/10.1080/03601277.2014.982006 Affiliations: 1: School of Social Work, University of Hawaii at Manoa, Honolulu, Hawaii, USA 2: School of Social Welfare, Chung-Ang University, Seoul, South Korea Publication date: June 3, 2015 More about this publication? Information for Authors Subscribe to this Title ingentaconnect is not responsible for the content or availability of external websites (document).ready(function() { var shortdescription = (".originaldescription").text().replace(/\\&/g, '&').replace(/\\, '<').replace(/\\>/g, '>').replace(/\\t/g, ' ').replace(/\\n/g, ''); if (shortdescription.length > 350){ shortdescription = "" + shortdescription.substring(0,250) + "... more"; } (".shortdescription a").click(function() { (".originaldescription").slideDown(); return false; }); }); Related content In this: publication By this: publisher In this Subject: Education By this author: Kim, Bum Jung ; Choi, Young GA_googleFillSlot("Horizontal_banner_bottom");
In this paper, the ability to determine the wellness of an elderly living alone in a smart home using a low-cost, robust, flexible and data driven intelligent system is presented. A framework integrating temporal and spatial contextual information for determining the wellness of an elderly has been modeled. A novel behavior detection process based on the observed sensor data in performing essential daily activities has been designed and developed. The developed prototype is used to forecast the behavior and wellness of the elderly by monitoring the daily usages of appliances in a smart home. Wellness models are tested at various elderly houses, and the experimental results are encouraging. The wellness models are updated based on the time series analysis.
Principal component analysis (PCA) is a mainstay of modern data analysis - a
black box that is widely used but (sometimes) poorly understood. The goal of
this paper is to dispel the magic behind this black box. This manuscript
focuses on building a solid intuition for how and why principal component
analysis works. This manuscript crystallizes this knowledge by deriving from
simple intuitions, the mathematics behind PCA. This tutorial does not shy away
from explaining the ideas informally, nor does it shy away from the
mathematics. The hope is that by addressing both aspects, readers of all levels
will be able to gain a better understanding of PCA as well as the when, the how
and the why of applying this technique.
The present review on depression in older people is occurring at a time when depression is fast becoming a major public health problem throughout the world with a very high prevalence rate in the 65 and over age group. Particular groups at risk will need to be identified so that early detection and interventions can be implemented. The concept of late-onset depression with a possible vascular cause, poor treatment response to antidepressants and a specific disability of executive dysfunction has developed further and has opened the field to the possibility of primary prevention and the opportunity of development of new treatments for this debilitating condition. Much confusion exists about the nature of the association between disability and depression and there is an urgent need for research in this area if we are to understand depression, its disabilities and mortality further.
This paper presents an automated methodology for extracting the spatiotemporal activity model of a person using a wireless
sensor network deployed inside a home. The sensor network is modeled as a source of spatiotemporal symbols whose output is
triggered by the monitored person’s motion over space and time. Using this stream of symbols, the problem of human activity
modeling is formulated as a spatiotemporal pattern-matching problem on top of the sequence of symbolic information the sensor
network produces, and is solved using an exhaustive search algorithm. The effectiveness of the proposed methodology is demonstrated
on a real 30-day dataset extracted from an ongoing deployment of a sensor network inside a home monitoring an elder. The developed
algorithm examines the person’s data over these 30days and automatically extracts the person’s daily pattern.
KeywordsHuman activity model–Spatiotemporal activity patterns–Sensor networks
Research studies focusing on the psychometric properties of the Beck Depression Inventory (BDI) with psychiatric and nonpsychiatric samples were reviewed for the years 1961 through June, 1986. A meta-analysis of the BDI's internal consistency estimates yielded a mean coefficient alpha of 0.86 for psychiatric patients and 0.81 for nonpsychiatric subjects. The concurrent validitus of the BDI with respect to clinical ratings and the Hamilton Psychiatric Rating Scale for Depression (HRSD) were also high. The mean correlations of the BDI samples with clinical ratings and the HRSD were 0. 72 and 0.73, respectively, for psychiatric patients. With nonpsychiatric subjects, the mean correlations of the BDI with clinical ratings and the HRSD were 0.60 and 0.74, respectively. Recent evidence indicates that the BDI discriminates subtypes of depression and differentiates depression from anxiety.
We conducted a feasibility study of a system for non-invasive monitoring of subjects at home. Electrical activity was recorded from room lights and from electrical domestic appliances; this was translated into the probability of physical activity or a particular Activity of Daily Living (ADL). Thirteen volunteer subjects were monitored for a period of 6.4 months (range 3-8). The mean age of the subjects was 80 years and they all lived alone at home; one had moderate Alzheimer's disease. A one-week validation was carried out to ascertain whether the recorded activity actually occurred. The results showed that daily and nocturnal activity could be well differentiated. The probability of having eaten, taken a bath and going to the toilet could be calculated each day. Eating was the most accurately measured ADL; toileting and bathing results were less accurate. The system appears to be a promising component of home telecare.
There is a general belief that physical activity and exercise have positive effects on mood and anxiety and a great number of studies describe an association of physical activity and general well-being, mood and anxiety. In line, intervention studies describe an anxiolytic and antidepressive activity of exercise in healthy subjects and patients. However, the majority of published studies have substantial methodological shortcomings. The aim of this paper is to critically review the currently available literature with respect to (1) the association of physical activity, exercise and the prevalence and incidence of depression and anxiety disorders and (2) the potential therapeutic activity of exercise training in patients with depression or anxiety disorders. Although the association of physical activity and the prevalence of mental disorders, including depression and anxiety disorders have been repeatedly described, only few studies examined the association of physical activity and mental disorders prospectively. Reduced incidence rates of depression and (some) anxiety disorders in exercising subjects raise the question whether exercise may be used in the prevention of some mental disorders. Besides case series and small uncontrolled studies, recent well controlled studies suggest that exercise training may be clinically effective, at least in major depression and panic disorder. Although, the evidence for positive effects of exercise and exercise training on depression and anxiety is growing, the clinical use, at least as an adjunct to established treatment approaches like psychotherapy or pharmacotherapy, is still at the beginning. Further studies on the clinical effects of exercise, interaction with standard treatment approaches and details on the optimal type, intensity, frequency and duration may further support the clinical administration in patients. Furthermore, there is a lack of knowledge on how to best deal with depression and anxiety related symptoms which hinder patients to participate and benefit from exercise training.
Chronic forms of depression are more common and impairing than is generally recognized. This article introduces an In Session issue devoted to dysthymic disorder and chronic depression, and it reviews current knowledge about these disorders. First, we discuss nosological issues, followed by a summary of potential risk factors. Finally, the naturalistic course of chronic depression is described and implications for clinical practice are discussed. © 2003 Wiley Periodicals, Inc. J Clin Psychol/In Session.
Depression is underrecognized in older adults, especially those with chronic conditions such as heart disease and arthritis. Left untreated, depression may progress and have dramatic effects on overall health. The Geriatric Depression Scale: Short Form is a 15-question screening tool for depression in older adults that takes five to seven minutes to complete and can be filled out by the patient or administered by a provider with minimal training in its use. The questions focus on mood; the score can help clinicians decide whether further assessment is needed. (This screening tool is included in a series, Try This: Best Practices in Nursing Care to Older Adults, from the Hartford Institute for Geriatric Nursing at New York University's College of Nursing.) For a free online video demonstrating the use of this tool, go to http://links.lww.com/A101.
Numerous advances have been made in developing intelligent programs, some inspired by biological neural networks. Researchers from many scientific disciplines are designing artificial neural networks (ANNs) to solve a variety of problems in pattern recognition, prediction, optimization, associative memory; and control. Although successful conventional applications can be found in certain well-constrained environments, none is flexible enough to perform well outside its domain. ANNs provide exciting alternatives, and many applications could benefit from using them. This article is for those readers with little or no knowledge of ANNs to help them understand the other articles in this issue of Computer. It discusses the motivation behind the development of ANNs; describes the basic biological neuron and the artificial computation model; outlines network architectures and learning processes; and presents multilayer feed-forward networks, Kohonen's self-organizing maps, Carpenter and Grossberg's Adaptive Resonance Theory models, and the Hopfield network. It concludes with character recognition, a successful ANN application.
United Nations Department of Economic and Social Affairs
World Population Ageing 2015, United Nations Department of Economic
and Social Affairs, New York, NY, USA, 2015.