No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Beyond position-awareness—Extending a self-adaptive fall detection system
... Smartphones were utilized in [1,5,7,17], the authors of these articles suggested HAR systems using deep learning and data from smartphone sensors to detect human body motion. In these studies, machine learning was used to train over data from smartphone inertial sensors to distinguish a range of behaviors, including standing, running, walking, leaping, and sleeping, as well as actions that take place in between distinct activities. ...
... Here, each smartphone has an accelerometer, which generates three values (x, y, and z) as illustrated in Figure 1. Smartphone's orientation will make accelerometer produce different values when the body is moving [1,6]. ...
... Extra Trees can be slower when dealing with high-dimensional data, as it generates more trees than Light GBM. Random Forest uses a combination of bagging and random feature subsets, which needs more time [1,10,27]. Table 8 compares prediction time using the three algorithms, Light GBM was the fastest among the three, it took less than 3 milliseconds using nine features on Raspberry PI 4, Extra Trees came next with 3.6 milliseconds, and Random Forest with more than 27 milliseconds. Using Raspberry PI 3, predictions took longer; it consumed about 6.1 milliseconds using Light GBM, 15.681 milliseconds using Extra Tress, and more than 166 milliseconds using Random Forest algorithm. ...
... The sensor placement highly affects the detection performance. Previous studies [14,33,34] demonstrated that better results are achieved when sensors are placed along the longitudinal axis of the body (e.g. head, chest, waist) when compared to other placements (e.g. ...
... Wearable technologies have several advantages. They are relatively inexpensive and can operate anywhere all of it with minimal intrusion compared to other approaches, such as environmental monitoring [33,34]. In addition, their somewhat limited computational power can be easily overcome with the use of their telecommunication capabilities, which allow the transfer of data for processing outside the device. ...
... However, the model is more complex to create and as a result the training phase is much longer than in other algorithms. Despite this shortcoming, GB is commonly used in the literature [33,34]. ...
Falls are dangerous for the elderly, often causing serious injuries especially when the fallen person stays on the ground for a long time without assistance. This paper extends our previous work on the development of a Fall Detection System (FDS) using an inertial measurement unit worn at the waist. Data come from SisFall, a publicly available dataset containing records of Activities of Daily Living and falls. We first applied a preprocessing and a feature extraction stage before using five Machine Learning algorithms, allowing us to compare them. Ensemble learning algorithms such as Random Forest and Gradient Boosting have the best performance, with a Sensitivity and Specificity both close to 99%. Our contribution is: a multi-class classification approach for fall detection combined with a study of the effect of the sensors’ sampling rate on the performance of the FDS. Our multi-class classification approach splits the fall into three phases: pre-fall, impact, post-fall. The extension to a multi-class problem is not trivial and we present a well-performing solution. We experimented sampling rates between 1 and 200 Hz. The results show that, while high sampling rates tend to improve performance, a sampling rate of 50 Hz is generally sufficient for an accurate detection.
... Research has indicated that the performance of detection systems can be impacted when methods are developed with a singular sensor location in mind [97], as each individual has a unique preferred sensor location [98]. Furthermore, during recording mode, the hardware specifications of various devices (like sampling rate and resolution) vary, which renders trained models unusable on other devices. ...
Fall detection systems are crucial for identifying falls and ensuring timely assistance, thus reducing the risk of serious injuries. With the development of society and increasing attention to health issues, researchers have conducted extensive studies on falls to reduce the severe sequelae of falls. Integrating fall detection systems with the Internet of Things (IoT), particularly the Internet of Medical Things (IoMT), has significantly advanced healthcare and personal safety. This dynamic relationship between fall detection technology and IoT has opened up new vistas for monitoring and assisting individuals, particularly the elderly and those with health conditions that make them prone to falls. This paper presents a review of wearable sensor-based fall detection techniques. We classify the detection methods into their categories from an algorithmic perspective: threshold-based, conventional machine learning-based, and deep learning-based methods. In addition, we identify and summarize the available datasets that can be used to evaluate the performance of the introduced methods. This review aims to provide researchers with a better comprehension of the fall detection problem, intending to foster further advancements in the field.
... In the early era of emerging FDS, two leading types of FDS algorithms were threshold-based and ML, researchers used simple threshold-based algorithms where such algorithms vary from Quaternion, using sum acceleration and angle information [53] to Kalman filter with preprocessing stage [32]. These threshold-based algorithms have shown an acceptable high performance in terms of detection effectiveness and low computational complexity. ...
Over the past years, Fall Detection System (FDS) has undergone extensive research to improve living risk, especially for the elderly who are vulnerable to these fall events. Devices employing sensors are crucial components of FDS in achieving high accuracy and sensitivity. This article overviews different sensor modalities, such as ambient-based and vision-based systems, as well as commonly used wearable devices for fall detection, along with the associated data processing algorithms. The critical elements of fall detection, such as architectures and algorithms for processing sensor data, machine learning and deep learning methodologies, and validation of FDS performance, are considered. The article also delves into safety aspects and presents technical challenges and concerns in FDS for researchers in the field to identify areas requiring further improvement. Finally, future research opportunities to improve fall detection for widespread use are outlined.
... The orientation of these sensors should be considered according to the place of their installation, the nature of movements, and the dataset being used for training [17,33,34]. In this study, an MPU6050 module connected to an ESP32 microcontroller was vertically installed on the shin; another module connected to Raspberry Pi version 3 was installed horizontally on the waist, and a smartphone was vertically placed inside the pocket on the thigh. ...
A wide range of applications, including sports and healthcare, use human activity recognition (HAR). The Internet of Things (IoT), using cloud systems, offers enormous resources but produces high delays and huge amounts of traffic. This study proposes a distributed intelligence and dynamic HAR architecture using smart IoT devices, edge devices, and cloud computing. These systems were used to train models, store results, and process real-time predictions. Wearable sensors and smartphones were deployed on the human body to detect activities from three positions; accelerometer and gyroscope parameters were utilized to recognize activities. A dynamic selection of models was used, depending on the availability of the data and the mobility of the users. The results showed that this system could handle different scenarios dynamically according to the available features; its prediction accuracy was 99.23% using the LightGBM algorithm during the training stage, when 18 features were used. The prediction time was around 6.4 milliseconds per prediction on the smart end device and 1.6 milliseconds on the Raspberry Pi edge, which can serve more than 30 end devices simultaneously and reduce the need for the cloud. The cloud was used for storing users’ profiles and can be used for real-time prediction in 391 milliseconds per request.
... Because of its ability to handle big datasets, the XGBoost algorithm will be a good fit. According to the literature [30][31][32][33][34][35], the XGBoost algorithm is a candidate which can operate with huge and sparse datasets, has strong numerical feature performance, has various hyperparameters that can be adjusted for best performance, and, finally, has a rapid processing speed and accurate prediction performance. The XGBoost algorithm is a decision tree-based algorithm that is developed on the Gradient Boost (GB) framework. ...
Monitoring systems for electrical appliances have gained massive popularity nowadays. These frameworks can
provide consumers with helpful information for energy consumption. Non-intrusive load monitoring (NILM) is the most
common method for monitoring a household’s energy profile. This research presents an optimized approach for identifying
load needs and improving the identification of NILM occupancy surveillance. Our study suggested implementing a
dimensionality reduction algorithm, popularly known as genetic algorithm (GA) along with XGBoost, for optimized
occupancy monitoring. This exclusive model can masterly anticipate the usage of appliances with a significantly reduced
number of voltage-current characteristics. The proposed NILM approach pre-processed the collected data and validated the
anticipation performance by comparing the outcomes with the raw dataset’s performance metrics. While reducing
dimensionality from 480 to 238 features, our GA-based NILM approach accomplished the same performance score in terms
of accuracy (73%), recall (81%), ROC-AUC Score (0.81), and PR-AUC Score (0.81) like the original dataset. This study
demonstrates that introducing GA in NILM techniques can contribute remarkably to reduce computational complexity
without compromising performance.
... We are working on solutions that automate the construction of digital twins as well as the analysis of the modeled food similar to solutions from the area of machine learning, e.g., AutoML [44] or based on our previous works [8,9]. Additionally, we already have several previous works for systems that can adapt the process and support adaptability [3,8,9,47]. We are currently working on integrating and adjusting them for food processing. ...
The production of food is highly complex due to the various chemo-physical and biological processes that must be controlled for transforming ingredients into final products. Further, production processes must be adapted to the variability of the ingredients, e.g., due to seasonal fluctuations of raw material quality. Digital twins are known from Industry 4.0 as a method to model, simulate, and optimize processes. In this vision paper, we describe the concept of a digital food twin. Due to the variability of the raw materials, such a digital twin has to take into account not only the processing steps but also the chemical, physical, or microbiological properties that change the food independently from the processing. We propose a hybrid modeling approach, which integrates the traditional approach of food process modeling and simulation of the bio-chemical and physical properties with a data-driven approach based on the application of machine learning. This work presents a conceptual framework for our digital twin concept based on explainable artificial intelligence and wearable technology. We discuss the potential in four case studies and derive open research challenges.
... As shown in Fig. 1, the present work aims to tackle two potential cross-domain circumstances when designing FD systems for real-world applications: (i) Cross-position: The previous study has shown that people have their preferable sensor positions according to individual preferences [23]. The detection algorithms designed for the single sensor position may limit the usability of the applications [24]. Therefore, the FD systems have to work well in multiple positions. ...
Fall detection (FD) systems are important assistive technologies for healthcare that can detect emergency fall events and alert caregivers. However, it is not easy to obtain large-scale annotated fall events with various specifications of sensors or sensor positions during the implementation of accurate FD systems. Moreover, the knowledge obtained through machine learning has been restricted to tasks in the same domain. The mismatch between different domains might hinder the performance of FD systems. Cross-domain knowledge transfer is very beneficial for machine-learning based FD systems to train a reliable FD model with well-labeled data in new environments. In this study, we propose domain-adaptive fall detection (DAFD) using deep adversarial training (DAT) to tackle cross-domain problems, such as cross-position and cross-configuration. The proposed DAFD can transfer knowledge from the source domain to the target domain by minimizing the domain discrepancy to avoid mismatch problems. The experimental results show that the average F1-score improvement when using DAFD ranges from 1.5% to 7% in the cross-position scenario, and from 3.5% to 12% in the cross-configuration scenario, compared to using the conventional FD model without domain adaptation training. The results demonstrate that the proposed DAFD successfully helps to deal with cross-domain problems and to achieve better detection performance.
... Thus, machine-learning algorithms have shown impressive practical results when placed in steady body location (near gravity point of the body) such as waist and chestworn. Otherwise, they are less efficient especially when placed in extremities such as wrist, requiring further investigations to improve the performance in those cases, mainly because wrist-based solutions are the most comfortable from a user point of view and less associated to the stigma of using a medical device [12,18,19]. ...
Wrist-based fall detection system provides a very comfortable and multi-modal healthcare solution, especially for elderly risking falls. However, the wrist location presents a very challenging and unstable spot to distinguish falls among other daily activities. In this paper, we propose a Supervised Dictionary Learning approach for wrist-based fall detection. Three Dictionary learning algorithms for classification are invoked in this study, namely SRC, FDDL, and LRSDL. To extract the best descriptive representation of the signal data we followed different preprocessing scenarios based on accelerometer, gyroscope, and magnetometer. A considerable overall performance was obtained by the SRC algorithms reaching respectively 99.8%, 100%, and 96.6% of accuracy, sensitivity, and specificity using raw data provided by a triaxial accelerometer, accordingly overthrowing previously proposed methods for wrist placement.
... Dogru et al. [34] adopted Random Forests and simulated data obtained from vehicular ad-hoc networks to determine the occurrence or non-occurrence of traffic incidents. As a powerful algorithm proposed by Microsoft, LightGBM has been used in detection problems in many areas, such as fall systems [35] and static PE malware [36], although its application in traffic incident detection is observed to be lacking. Fig. 3 depicts the total proposed framework, which comprises consists of three parts, i.e., A. data processing, B. conversion of the speed time series into images, and C. classification model. ...
The timely and accurate detection of traffic incidents is beneficial to reduce associated economic losses and avoid secondary crashes. Inspired by the impressive success of the image classification algorithms, especially convolutional neural networks (CNNs), this study proposes a novel framework to detect highway traffic incidents by learning the traffic state as images. In such a framework, the probe vehicles equipped with the global positioning system equipment are used to obtain data. The Gramian Angular Difference Fields and Piecewise Aggregation Approximation algorithms are used to convert the link speed time series data into images. CNNs can extract the traffic features based on these images and consider an incident detection problem as a binary classification task. Further, the effectiveness of the proposed framework is evaluated by applying it to detect the traffic in a real-world environment, i.e., the Guangzhou Airport Expressway. The results illustrate that the proposed model outperforms several other algorithms with respect to almost all the performance indexes, including the detection rate with different false alarm rates and the area under the receiver operating characteristic curve.
Falls are exceptional activities that put one’s health in danger. To limit the effect of falls, it is necessary to build fall detection and prevention systems. The goal of emerging technology is to create such systems that will improve people’s quality of life, especially for the elderly. To limit the danger of injury, a fall detection system detects the fall and generates an assistance signal. The suggested system detects falls by classifying various behaviors as fall or non-fall activities and alerting those who are affected in the event of an emergency. To calculate characteristics, the dataset SisFall is used, which contains a variety of actions performed by numerous people. The machine learning methods XGBoost and LightGBM are used to identify falls based on calculated characteristics. Using the XGBoost algorithm, the system achieves ROC-AUC scores of up to 97.64%. Our proposed solution is based on a transformer model, which is then tailored to produce the best outcomes, with an accuracy of approximately 95.7%.KeywordsFall detectionSisFallDaily living activitiesXGBoostLightGBMTransformer modelPositional encodingMulti-head attention
Elderly persons often require aid to recover after having fallen, and the consequences of falling may be quite dangerous if such aid is delayed. The development of non-invasive systems for automatic fall detection—both reliable and acceptable for the persons to be monitored—remains challenging despite the considerable amount of research related to this topic, carried out during the last several years. This chapter is devoted to an overview of the trends and problems in the area of fall detection based on depth sensors. The results of a series of experiments, aimed at comparing the performance of selected methods of denoising and numerical differentiation—when applied for the detection of human falls on the basis of data from depth sensors—are also reported.
Telemonitoring of human physiological data helps detect emergency occurrences for subsequent medical diagnosis in daily living environments. One of the fatal emergencies in falling incidents. The goal of this paper is to detect significant incidents such as falls. The fall detection system is essential for human body movement investigation for medical practitioners, researchers, and healthcare businesses. Accelerometers have been presented as a practical, low-cost, and dependable approach for detecting and predicting outpatient movements in the user. The accurate detection of body movements based on accelerometer data enables the creation of more dependable systems for incorporating long-term development in physiological remarks. This research describes an accelerometer-based platform for detecting users' body movement when they fall. The ADXL345, MMA8451q, and ITG3200 body sensors capture activity data, subsequently classified into 15 fall incident classes based on SisFall dataset. Falling incidents classification is performed using Long Short-Term Memory results in best AUC-ROC value of 97.7% and best calculation time of 6.16 seconds. Meanwhile, Support Vector Machines results in the best AUC-ROC value of 98.5% and best calculation times of 17.05 seconds.
Fall detector systems are one of the highly researched areas of Ambient Assisted Living (AAL) applications ensuring safety and autonomous living for the elderly. Today, despite the diversity of methods proposed for fall detectors, there is still a need to develop accurate and robust architectures, methods, and protocols for the detection of the occurrence of falls for a special-class of wheelchair-bound people. To address this issue, this paper proposes a wheelchair fall detector system based on a low-cost, light-weight inertial sensing method utilizing a hybrid scheme and unsupervised One-Class SVM (OCSVM) for detection of cases leading to a ‘fall’ anomaly during wheelchair maneuver and for the case of unassisted transfers. To make the system robust against noise, a novel hybrid multi-sensor fusion strategy combining Zero Angular Rate Update (ZART) and Complementary Filter (CF) to compensate sensor integral errors is utilized. A heterogeneous dataset is constructed using the publicly available Sis-Fall dataset to include possible fall cases due to unassisted transfers from wheelchairs and secondly, a prototype is developed to emulate the wheelchair system with the embedded inertial sensors to capture trends in the sensor measurements due to wheelchair tips and falls. The OCSVM anomaly detection technique is utilized to overcome the major disadvantage of supervised learning methods requiring huge datasets from activities performed by human subjects needed to guarantee higher accuracy rates from these detectors. In this regard, to capture the best features from the generated accelerometer and gyroscope feature set, the ReliefF algorithm is used. The proposed method is compared with the widely reported approaches in the literature for fall-detectors, i.e., threshold-based methods and other one-class learning approaches. It is demonstrated that the fall-detection accuracy (i.e., the g-mean score) was achieved up to 96% with the proposed method.
Fall is a major threat to the health and life of the elders. A Fall Detection System (FDS) assist the elders by identifying the fall and save their life. Machine Learning‐ (ML) based FDS has turned into a major research area due to its capability to assist the elders automatically. The efficiency of a FDS depends on its strength to identify the fall from nonfall accurately. The initial fall detection scheme depends on the threshold‐based classification to classify the fall from the Activity of Daily Living (ADL) but this classification method has failed to reduce the false alarm rate, which raises a question on the efficiency of the technique. This review work identifies the problems in threshold‐based classification from existing works and finds the need for an efficient ML‐based classification technique to accurately identify the fall. Then, presents a comprehensive literature review on various ML‐based classification in fall detection. Moreover, the scrutiny investigates the shortcomings associated with the ML‐based techniques for future research. This study finds that present ML‐based FDS has not addressed problems like data preprocessing and data dimensionality reduction techniques even though ML‐based techniques are far superior to threshold‐based techniques. The study concludes that Self‐Adaptive‐based FDS, as well as the complexity reduction of ML‐based models, should be concentrated in future research.
Gradient Boosting Decision Tree (GBDT) is a popular machine learning algorithm , and has quite a few effective implementations such as XGBoost and pGBRT. Although many engineering optimizations have been adopted in these implementations , the efficiency and scalability are still unsatisfactory when the feature dimension is high and data size is large. A major reason is that for each feature, they need to scan all the data instances to estimate the information gain of all possible split points, which is very time consuming. To tackle this problem, we propose two novel techniques: Gradient-based One-Side Sampling (GOSS) and Exclusive Feature Bundling (EFB). With GOSS, we exclude a significant proportion of data instances with small gradients, and only use the rest to estimate the information gain. We prove that, since the data instances with larger gradients play a more important role in the computation of information gain, GOSS can obtain quite accurate estimation of the information gain with a much smaller data size. With EFB, we bundle mutually exclusive features (i.e., they rarely take nonzero values simultaneously), to reduce the number of features. We prove that finding the optimal bundling of exclusive features is NP-hard, but a greedy algorithm can achieve quite good approximation ratio (and thus can effectively reduce the number of features without hurting the accuracy of split point determination by much). We call our new GBDT implementation with GOSS and EFB LightGBM. Our experiments on multiple public datasets show that, LightGBM speeds up the training process of conventional GBDT by up to over 20 times while achieving almost the same accuracy.
Smartphones, smartwatches, fitness trackers, and ad-hoc wearable devices are being increasingly used to monitor human activities. Data acquired by the hosted sensors are usually processed by machine-learning-based algorithms to classify human activities. The success of those algorithms mostly depends on the availability of training (labeled) data that, if made publicly available, would allow researchers to make objective comparisons between techniques. Nowadays, publicly available data sets are few, often contain samples from subjects with too similar characteristics, and very often lack of specific information so that is not possible to select subsets of samples according to specific criteria. In this article, we present a new smartphone accelerometer dataset designed for activity recognition. The dataset includes 11,771 activities performed by 30 subjects of ages ranging from 18 to 60 years. Activities are divided in 17 fine grained classes grouped in two coarse grained classes: 9 types of activities of daily living (ADL) and 8 types of falls. The dataset has been stored to include all the information useful to select samples according to different criteria, such as the type of ADL performed, the age, the gender, and so on. Finally, the dataset has been benchmarked with two different classifiers and with different configurations. The best results are achieved with k-NN classifying ADLs only, considering personalization, and with both windows of 51 and 151 samples.
Research on fall and movement detection with wearable devices has witnessed promising growth. However, there are few publicly available datasets, all recorded with smartphones, which are insufficient for testing new proposals due to their absence of objective population, lack of performed activities, and limited information. Here, we present a dataset of falls and activities of daily living (ADLs) acquired with a self-developed device composed of two types of accelerometer and one gyroscope. It consists of 19 ADLs and 15 fall types performed by 23 young adults, 15 ADL types performed by 14 healthy and independent participants over 62 years old, and data from one participant of 60 years old that performed all ADLs and falls. These activities were selected based on a survey and a literature analysis. We test the dataset with widely used feature extraction and a simple to implement threshold based classification, achieving up to 96% of accuracy in fall detection. An individual activity analysis demonstrates that most errors coincide in a few number of activities where new approaches could be focused. Finally, validation tests with elderly people significantly reduced the fall detection performance of the tested features. This validates findings of other authors and encourages developing new strategies with this new dataset as the benchmark.
During the last years, many research efforts have been devoted to the definition of Fall Detection Systems (FDSs) that benefit from the inherent computing, communication and sensing capabilities of smartphones. However, employing a smartphone as the unique sensor in a FDS application entails several disadvantages as long as an accurate characterization of the patient’s mobility may force to transport this personal device on an unnatural position. This paper presents a smartphone-based architecture for the automatic detection of falls. The system incorporates a set of small sensing motes that can communicate with the smartphone to help in the fall detection decision. The deployed architecture is systematically evaluated in a testbed with experimental users in order to determine the number and positions of the sensors that optimize the effectiveness of the FDS, as well as to assess the most convenient role of the smartphone in the architecture.
Smartphones, smartwatches, fitness trackers, and ad-hoc wearable devices are being
increasingly used to monitor human activities. Data acquired by the hosted sensors are usually
processed by machine-learning-based algorithms to classify human activities. The success of those
algorithms mostly depends on the availability of training (labeled) data that, if made publicly
available, would allow researchers to make objective comparisons between techniques. Nowadays,
there are only a few publicly available data sets, which often contain samples from subjects with too
similar characteristics, and very often lack specific information so that is not possible to select subsets
of samples according to specific criteria. In this article, we present a new dataset of acceleration
samples acquired with an Android smartphone designed for human activity recognition and fall
detection. The dataset includes 11,771 samples of both human activities and falls performed by
30 subjects of ages ranging from 18 to 60 years. Samples are divided in 17 fine grained classes grouped
in two coarse grained classes: one containing samples of 9 types of activities of daily living (ADL)
and the other containing samples of 8 types of falls. The dataset has been stored to include all the
information useful to select samples according to different criteria, such as the type of ADL performed,
the age, the gender, and so on. Finally, the dataset has been benchmarked with four different classifiers
and with two different feature vectors. We evaluated four different classification tasks: fall vs. no
fall, 9 activities, 8 falls, 17 activities and falls. For each classification task, we performed a 5-fold
cross-validation (i.e., including samples from all the subjects in both the training and the test dataset)
and a leave-one-subject-out cross-validation (i.e., the test data include the samples of a subject only,
and the training data, the samples of all the other subjects). Regarding the classification tasks,
the major findings can be summarized as follows: (i) it is quite easy to distinguish between falls and
ADLs, regardless of the classifier and the feature vector selected. Indeed, these classes of activities
present quite different acceleration shapes that simplify the recognition task; (ii) on average, it is
more difficult to distinguish between types of falls than between types of activities, regardless of the
classifier and the feature vector selected. This is due to the similarity between the acceleration shapes
of different kinds of falls. On the contrary, ADLs acceleration shapes present differences except
for a small group. Finally, the evaluation shows that the presence of samples of the same subject
both in the training and in the test datasets, increases the performance of the classifiers regardless
of the feature vector used. This happens because each human subject differs from other subjects in
performing activities even if she shares with them the same physical characteristics.
A fall is an abnormal activity that occurs rarely; however, missing to identify falls can have serious health and safety implications on an individual. Due to the rarity of occurrence of falls, there may be insufficient or no training data available for them. Therefore, standard supervised machine learning methods may not be directly applied to handle this problem. In this paper, we present a taxonomy for the study of fall detection from the perspective of availability of fall data. The proposed taxonomy is independent of the type of sensors used and specific feature extraction/selection methods. The taxonomy identifies different categories of classification methods for the study of fall detection based on the availability of their data during training the classifiers. Then, we present a comprehensive literature review within those categories and identify the approach of treating a fall as an abnormal activity to be a plausible research direction. We conclude our paper by discussing several open research problems in the field and pointers for future research.
It is of little surprise that falling is often accepted as a natural part of the aging process. In fact, it is the impact rather than the occurrence of falls in the elderly, which is of most concern. Aging people are typically frailer, more unsteady, and have slower reactions, thus are more likely to fall and be injured than younger individuals. Typically, research and industry presented various practical solutions for assisting the elderly and their caregivers against falls via detecting falls and triggering notification alarms calling for help as soon as falls occur in order to diminish fall consequences. Furthermore, fall likelihood prediction systems have been emerged lately based on the manipulation of the medical and behavioral history of elderly patients in order to predict the possibility of falls occurrence. Accordingly, response from caregivers may be triggered prior to most fall occurrences and accordingly prevent falls from taking place. This paper presents an extensive review for the state-of-the-art trends and technologies of fall detection and prevention systems assisting the elderly people and their caregivers. Furthermore, this paper discusses the main challenges, facing elderly fall prevention, along with suggestions for future research directions.
Emergency situations associated with falls are a serious concern for an aging society. Yet following the recent development within ICT, a significant number of solutions have been proposed to track body movement and detect falls using various sensor technologies, thereby facilitating fall detection and in some cases prevention. A number of recent reviews on fall detection methods using ICT technologies have emerged in the literature and an increasingly popular approach considers combining information from several sensor sources to assess falls. The aim of this paper is to review in detail the subfield of fall detection techniques that explicitly considers the use of multisensor fusion based methods to assess and determine falls. The paper highlights key differences between the single sensor-based approach and a multifusion one. The paper also describes and categorizes the various systems used, provides information on the challenges of a multifusion approach, and finally discusses trends for future work.
Falls are a major cause of health and psychological problems as well as hospitalization costs among older adults. Thus, the investigation on automatic Fall Detection Systems (FDSs) has received special attention from the research community during the last decade. In this area, the widespread popularity, decreasing price, computing capabilities, built-in sensors and multiplicity of wireless interfaces of Android-based devices (especially smartphones) have fostered the adoption of this technology to deploy wearable and inexpensive architectures for fall detection. This paper presents a critical and thorough analysis of those existing fall detection systems that are based on Android devices. The review systematically classifies and compares the proposals of the literature taking into account different criteria such as the system architecture, the employed sensors, the detection algorithm or the response in case of a fall alarms. The study emphasizes the analysis of the evaluation methods that are employed to assess the effectiveness of the detection process. The review reveals the complete lack of a reference framework to validate and compare the proposals. In addition, the study also shows that most research works do not evaluate the actual applicability of the Android devices (with limited battery and computing resources) to fall detection solutions.
Life expectancy keeps growing and, among elderly people, accidental falls
occur frequently. A system able to promptly detect falls would help in reducing
the injuries that a fall could cause. Such a system should meet the needs of
the people to which is designed, so that it is actually used. In particular,
the system should be minimally invasive and inexpensive. Thanks to the fact
that most of the smartphones embed accelerometers and powerful processing unit,
they are good candidates both as data acquisition devices and as platforms to
host fall detection systems. For this reason, in the last years several fall
detection methods have been experimented on smartphone accelerometer data. Most
of them have been tuned with simulated falls because, to date, datasets of
real-world falls are not available. This article evaluates the goodness of
methods that detect falls as anomalies, thus not requiring to be tuned with
fall patterns. To this end, we compared traditional approaches with anomaly
detectors by experimenting on three different collections of accelerometer
data, and four different data representations. Results demonstrated that in
most of the cases, understanding fall patterns is not necessary to design a
good and effective fall detection method.
Wearable sensors are becoming popular for remote health monitoring as technology improves and cost reduces. One area in which wearable sensors are increasingly being used is falls monitoring. The elderly, in particular are vulnerable to falls and require continuous monitoring. Indeed, many attempts, with insufficient success have been made towards accurate, robust and generic falls and Activities of Daily Living (ADL) classification. A major challenge in developing solutions for fall detection is access to sufficiently large data sets.
This paper presents a description of the data set and the experimental protocols designed by the authors for the simulation of falls, near-falls and ADL. Forty-two volunteers were recruited to participate in an experiment that involved a set of scripted protocols. Four types of falls (forward, backward, lateral left and right) and several ADL were simulated. This data set is intended for the evaluation of fall detection algorithms by combining daily activities and transitions from one posture to another with falls. In our prior work, machine learning based fall detection algorithms were developed and evaluated. Results showed that our algorithm was able to discriminate between falls and ADL with an F-measure of 94%.
Elderly people are prone to fall due to the high rate of risk factors associated with ageing. Existing fall detection sys-tems are mostly designed for a constrained environment, where various assumptions are applied. To overcome these drawbacks, we opt to use mobile phones with standard built-in sensors. Fall detection is performed on motion data col-lected by sensors in the phone alone. We use Genetic Pro-gramming (GP) to learn a classifier directly from raw sensor data. We compare the performance of GP with the popu-lar approach of using threshold-based algorithm. The result shows that GP-evolved classifiers perform consistently well across different fall types and overall more reliable than the threshold-based.
Falls and fall-related injuries are major incidents, especially for elderly people, which often mark the onset of major deterioration of health. More than one-third of home-dwelling people aged 65 or above and two-thirds of those in residential care fall once or more each year. Reliable fall detection, as well as prevention, is an important research topic for monitoring elderly living alone in residential or hospital units. The aim of this study is to review the existing fall detection systems and some of the key research challenges faced by the research community in this field. We categorize the existing platforms into two groups: wearable and ambient devices; the classification methods are divided into rule-based and machine learning techniques. The relative merit and potential drawbacks are discussed, and we also outline some of the outstanding research challenges that emerging new platforms need to address.
For physical activity recognition, smartphone sensors, such as an accelerometer and a gyroscope, are being utilized in many research studies. So far, particularly, the accelerometer has been extensively studied. In a few recent studies, a combination of a gyroscope, a magnetometer (in a supporting role) and an accelerometer (in a lead role) has been used with the aim to improve the recognition performance. How and when are various motion sensors, which are available on a smartphone, best used for better recognition performance, either individually or in combination? This is yet to be explored. In order to investigate this question, in this paper, we explore how these various motion sensors behave in different situations in the activity recognition process. For this purpose, we designed a data collection experiment where ten participants performed seven different activities carrying smart phones at different positions. Based on the analysis of this data set, we show that these sensors, except the magnetometer, are each capable of taking the lead roles individually, depending on the type of activity being recognized, the body position, the used data features and the classification method employed (personalized or generalized). We also show that their combination only improves the overall recognition performance when their individual performances are not very high, so that there is room for performance improvement. We have made our data set and our data collection application publicly available, thereby making our experiments reproducible.
Despite being a major public health problem, falls in the elderly cannot be detected efficiently yet. Many studies have used acceleration as the main input to discriminate between falls and activities of daily living (ADL). In recent years, there has been an increasing interest in using smartphones for fall detection. The most promising results have been obtained by supervised Machine Learning algorithms. However, a drawback of these approaches is that they rely on falls simulated by young or mature people, which might not represent every possible fall situation and might be different from older people's falls. Thus, we propose to tackle the problem of fall detection by applying a kind of novelty detection methods which rely only on true ADL. In this way, a fall is any abnormal movement with respect to ADL. A system based on these methods could easily adapt itself to new situations since new ADL could be recorded continuously and the system could be re-trained on the fly. The goal of this work is to explore the use of such novelty detectors by selecting one of them and by comparing it with a state-of-the-art traditional supervised method under different conditions. The data sets we have collected were recorded with smartphones. Ten volunteers simulated eight type of falls, whereas ADL were recorded while they carried the phone in their real life. Even though we have not collected data from the elderly, the data sets were suitable to check the adaptability of novelty detectors. They have been made publicly available to improve the reproducibility of our results. We have studied several novelty detection methods, selecting the nearest neighbour-based technique (NN) as the most suitable. Then, we have compared NN with the Support Vector Machine (SVM). In most situations a generic SVM outperformed an adapted NN.
Since falls are a major public health problem among older people, the number of systems aimed at detecting them has increased dramatically over recent years. This work presents an extensive literature review of fall detection systems, including comparisons among various kinds of studies. It aims to serve as a reference for both clinicians and biomedical engineers planning or conducting field investigations. Challenges, issues and trends in fall detection have been identified after the reviewing work. The number of studies using context-aware techniques is still increasing but there is a new trend towards the integration of fall detection into smartphones as well as the use of machine learning methods in the detection algorithm. We have also identified challenges regarding performance under real-life conditions, usability, and user acceptance as well as issues related to power consumption, real-time operations, sensing limitations, privacy and record of real-life falls.
Despite extensive preventive efforts, falls continue to be a major source of morbidity and mortality among elderly. Real-time detection of falls and their urgent communication to a telecare center may enable rapid medical assistance, thus increasing the sense of security of the elderly and reducing some of the negative consequences of falls. Many different approaches have been explored to automatically detect a fall using inertial sensors. Although previously published algorithms report high sensitivity (SE) and high specificity (SP), they have usually been tested on simulated falls performed by healthy volunteers. We recently collected acceleration data during a number of real-world falls among a patient population with a high-fall-risk as part of the SensAction-AAL European project. The aim of the present study is to benchmark the performance of thirteen published fall-detection algorithms when they are applied to the database of 29 real-world falls. To the best of our knowledge, this is the first systematic comparison of fall detection algorithms tested on real-world falls. We found that the SP average of the thirteen algorithms, was (mean ± std) 83.0% ± 30.3% (maximum value = 98%). The SE was considerably lower (SE = 57.0% ± 27.3%, maximum value = 82.8%), much lower than the values obtained on simulated falls. The number of false alarms generated by the algorithms during 1-day monitoring of three representative fallers ranged from 3 to 85. The factors that affect the performance of the published algorithms, when they are applied to the real-world falls, are also discussed. These findings indicate the importance of testing fall-detection algorithms in real-life conditions in order to produce more effective automated alarm systems with higher acceptance. Further, the present results support the idea that a large, shared real-world fall database could, potentially, provide an enhanced understanding of the fall process and the information needed to design and evaluate a high-performance fall detector.
The high rate of falls incidence among the elderly calls for the development of reliable and robust fall detection systems. A number of such systems have been proposed, with claims of fall detection accuracy of over 90% based on accelerometers and gyroscopes. However, most such fall detection algorithms have been developed based on observational analysis of the data gathered, leading to thresholds setting for fall/non-fall situations. Whilst the fall detection accuracies reported appear to be high, there is little evidence that the threshold based methods proposed generalise well with different subjects and different data gathering strategies or experimental scenarios. Moreover, few attempts appear to have been made to validate the proposed methods in real-life scenarios or to deliver robust fall decisions in real-time. The research here uses machine learning and particularly decision trees to detect 4 types of falls (forward, backward, right and left). When applied to experimental data from 8 male subjects, the accelerometers and gyroscopes based system discriminates between activities of daily living (ADLs) and falls with a precision of 81% and recall of 92%. The performance and robustness of the method proposed has been further analysed in terms its sensitivity to subject physical profile and training set size.
This paper presents an approach to fall detection with accelerometers that exploits posture recognition to identify postures that may be the result of a fall. Posture recognition as a standalone task was also studied. Nine placements of up to four sensors were considered: on the waist, chest, thigh and ankle. The results are compared to the results of a system using ultra wide band location sensors on a scenario consisting of events difficult to recognize as falls or non-falls. Three accelerometers proved sufficient to correctly recognize all the events except one(a slow fall). The location-based system was comparable to two accelerometers, except that it was able to recognize the slow fall because it resulted in lying outside the bed, whose location was known to the system. One accelerometer was able to recognize only the most clear-cut fall. Two accelerometers achieved over 90% accuracy of posture recognition, which was better than the location-based system. Chest and waist accelerometers proved best at both tasks, with the chest accelerometer having a slight advantage in posture recognition.
Falls are dangerous for the aged population as they can adversely affect health. Therefore, many fall detection systems have been developed. However, prevalent methods only use accelerometers to isolate falls from activities of daily living (ADL). This makes it difficult to distinguish real falls from certain fall-like activities such as sitting down quickly and jumping, resulting in many false positives. Body orientation is also used as a means of detecting falls, but it is not very useful when the ending position is not horizontal, e.g. falls happen on stairs. In this paper we present a novel fall detection system using both accelerometers and gyroscopes. We divide human activities into two categories: static postures and dynamic transitions. By using two tri-axial accelerometers at separate body locations, our system can recognize four kinds of static postures: standing, bending, sitting, and lying. Motions between these static postures are considered as dynamic transitions. Linear acceleration and angular velocity are measured to determine whether motion transitions are intentional. If the transition before a lying posture is not intentional, a fall event is detected. Our algorithm, coupled with accelerometers and gyroscopes, reduces both false positives and false negatives, while improving fall detection accuracy. In addition, our solution features low computational cost and real- time response.
Falls are one of the greatest obstacles to independent living for frail and elderly people. Their early detection is an important step in providing people with the reassurance and confidence necessary to maintain an active lifestyle. We have investigated a worn fall detector linked to a community alarm system. A worn device is the only one which is satisfactory, provided that it generates few false alarms. The fall detector we have developed is the size of a small radio pager. It uses a two-stage detection process which senses shock and the orientation of the wearer. A fall is detected within 20 s and triggers a radio signal to a community alarm system. Tests were devised using a jointed mannequin to simulate five modes of falling to understand the effects of impact at different parts of the body. This allowed us to select the appropriate trigger threshold and wearing positions for the sensor. Prototypes were evaluated with 20 people to observe false alarms. The final design allowed reliable detection in 180 different falling scenarios.
We have designed an intelligent emergency response system to detect falls in the home. It uses image-based sensors. A pilot study was conducted using 21 subjects to evaluate the efficacy and performance of the fall-detection component of the system. Trials were conducted in a mock-up bedroom setting, with a bed, a chair and other typical bedroom furnishings. A small digital videocamera was installed in the ceiling at a height of approximately 2.6 m. The digital camera covered an area of approximately 5.0 m x 3.8 m. The subjects were asked to assume a series of postures, namely walking/standing, sitting/lying down in an inactive zone, stooping, lying down in a 'stretched' position, and lying down in a 'tucked' position. These five scenarios were repeated three times by each subject in a random order. These test positions totalled 315 tasks with 126 fall-simulated tasks and 189 non-fall-simulated tasks. The system detected a fall on 77% of occasions and missed a fall on 23%. False alarms occurred on only 5% of occasions. The results encourage the potential use of a vision-based system to provide safety and security in the homes of the elderly.
This article examines how best to identify the leading causes of mortality in England an Wales, by using different way of grouping causes of death, based on a list developed by the World Health Organization (WHO). Four different versions of this list are compared. The leading cause of death across all age groups depends on the ways in which common diseases and external causes are aggregated or disaggregated into groups. Areas of particular debate, examined in this article, are the grouping or splitting of accidents by mechanism and cancers by site within leading cause lists. These affect which causes appear in the top ten, and their order in different age groups.
Fall detection for elderly and patient has been an active research topic due to that the healthcare industry has a big demand for products and technology of fall detection. This paper gives a survey of fall detection for elderly and patient, focusing on identifying approaches and principles of the existing fall detection methods. To properly build the classification tree of the methods of fall detection we first study the characteristics of fall. Then according to what sensors and how sensors are used we first divide the methods of fall detection into three approaches: wearable device, ambience device, and camera-based. Further we divide each approach into two to three classes according to the used principles. For each class of algorithm we analyze their merits and demerits. We also give comments on how we can improve some algorithms.
Advances in technology have made possible new and innovative methods of health care delivery. Home telecare, in which the patient's health is monitored remotely at home, is one such method. This paper discusses the use of a triaxial accelerometer within a home telecare system for monitoring physiological and functional parameters for daily living. A novel system is described for objectively and continuously monitoring movement, suitable for patients with chronic diseases including congestive heart failure and chronic obstructive pulmonary disease. The key design criteria were ease of use by, and comfort for, the patient together with the provision of clinically relevant information. The patient's posture, energy expenditure and movement are clinically important parameters that can be measured by accelerometry. A data processing scheme in which these parameters are extracted is described.
A 2001 IBM manifesto observed that a looming software complexity crisis -caused by applications and environments that number into the tens of millions of lines of code - threatened to halt progress in computing. The manifesto noted the almost impossible difficulty of managing current and planned computing systems, which require integrating several heterogeneous environments into corporate-wide computing systems that extend into the Internet. Autonomic computing, perhaps the most attractive approach to solving this problem, creates systems that can manage themselves when given high-level objectives from administrators. Systems manage themselves according to an administrator's goals. New components integrate as effortlessly as a new cell establishes itself in the human body. These ideas are not science fiction, but elements of the grand challenge to create self-managing computing systems.
Detection of falls is very important from a health and safety perspective. However, falls occur rarely and infrequently, which leads to either limited or no training data and thus can severely impair the performance of supervised activity recognition algorithms. In this paper, we address the problem of identification of falls in the absence of training data for falls, but with abundant training data for normal activities. We propose two ‘X-Factor’ Hidden Markov Model (XHMMs) approaches that are like normal HMMs, but have “inflated” output covariances (observation models), which can be estimated using cross-validation on the set of ‘outliers’ in the normal data that serve as proxies for the (unseen) fall data. This allows the XHMMs to be learned from only normal activity data. We tested the proposed XHMM approaches on two real activity recognition datasets that show high detection rates for falls in the absence of training data.
Falls are the primary cause of accidents for the elderly in living environment. Falls frequently cause fatal and non-fatal injuries that are associated with a large amount of medical costs. Reduction hazards in living environment and doing exercise for training balance and muscle are the common strategies for fall prevention. But falls cannot be avoided completely; fall detection provides the alarm in time that can decrease the injuries or death caused by no rescue. We propose machine learning-based fall detection algorithm using multi-SVM with linear, quadratic or polynomial kernel function, and k-NN classifier. Eight kinds of falling postures and seven types of daily activities arranged in the experiment are used to explore the performance of the machine learning-based fall detection algorithm. The emulated falls were performed on a soft mat by ten healthy young subjects wearing protectors. The k-nearest neighbor method with 0.1 second window size has the highest accuracy, which is 96.26%. The results show that the proposed machine learning fall detection algorithm can fulfill the requirements of adaptability and flexibility for the individual differences.
Reliable human activity recognition with wearable devices enables the development of human-centric pervasive applications. We aim to develop a robust wearable-based activity recognition system for real life situations where the device position is up to the user or where a user is unable to collect initial training data. Consequently, in this work we focus on the problem of recognizing the on-body position of the wearable device ensued by comprehensive experiments concerning subject-specific and cross-subjects activity recognition approaches that rely on acceleration data. We introduce a device localization method that predicts the on-body position with an F-measure of 89% and a cross-subjects activity recognition approach that considers common physical characteristics. In this context, we present a real world data set that has been collected from 15 participants for 8 common activities where they carried 7 wearable devices in different on-body positions. Our results show that the detection of the device position consistently improves the result of activity recognition for common activities. Regarding cross-subjects models, we identified the waist as the most suitable device location at which the acceleration patterns for the same activity across several people are most similar. In this context, our results provide evidence for the reliability of physical characteristics based cross-subjects models.
Tree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges. We propose a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning. More importantly, we provide insights on cache access patterns, data compression and sharding to build a scalable tree boosting system. By combining these insights, XGBoost scales beyond billions of examples using far fewer resources than existing systems.
Tree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges. We propose a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning. More importantly, we provide insights on cache access patterns, data compression and sharding to build a scalable tree boosting system. By combining these insights, XGBoost scales beyond billions of examples using far fewer resources than existing systems.
Fall detection is a hot research issue in the field of pervasive computing and human-computer interaction. Its key difficulty is to build a fall detection model which obtains high detection accuracy and low false alarm rate simultaneously. In this paper, we propose a fall detection model based on activity transition. Firstly, our method segments continuous activity data based on activity recognition sequence, then extracts features from transition data between adjacent activities to build a fall detection model. Employing this model, we can detect the fall through recognizing abnormal activity transition. Tested on the real-world activity data set, our algorithm outperforms traditional methods.
Falls are one of the leading causes of mortality among the older population, being the rapid detection of a fall a key factor to mitigate its main adverse health consequences. In this context, several authors have conducted studies on acceleration-based fall detection using external accelerometers or smartphones. The published detection rates are diverse, sometimes close to a perfect detector. This divergence may be explained by the difficulties in comparing different fall detection studies in a fair play since each study uses its own dataset obtained under different conditions. In this regard, several datasets have been made publicly available recently. This paper presents a comparison, to the best of our knowledge for the first time, of these public fall detection datasets in order to determine whether they have an influence on the declared performances. Using two different detection algorithms, the study shows that the performances of the fall detection techniques are affected, to a greater or lesser extent, by the specific datasets used to validate them. We have also found large differences in the generalization capability of a fall detector depending on the dataset used for training. In fact, the performance decreases dramatically when the algorithms are tested on a dataset different from the one used for training. Other characteristics of the datasets like the number of training samples also have an influence on the performance while algorithms seem less sensitive to the sampling frequency or the acceleration range.
Copyright © 2015 IPEM. Published by Elsevier Ltd. All rights reserved.
Falls are considered the main cause of fear and loss of independence among the elderly population and are also a major cause of morbidity, disability and health care utilization. In the majority of fall events external support is imperative in order to avoid major consequences. Therefore, the ability to automatically detect these fall events could help reducing the response time and significantly improve the prognosis of fall victims. This paper presents a unobtrusive smartphone based fall detection system that uses a combination of information derived from machine learning classification applied in a state machine algorithm. The data from the smartphone built-in accelerometer is continuously screened when the phone is in the user's belt or pocket. Upon the detection of a fall event, the user location is tracked and SMS and email notifications are sent to a set of contacts. The accuracy of the fall detection algorithm here proposed is near 97.5% for both the pocket and belt usage. In conclusion, the proposed solution can reliably detect fall events without disturbing the users with excessive false alarms, presenting also the advantage of not changing the user's routines, since no additional external sensors are required.
Fall detection is a major challenge in the public health care domain, especially for the elderly, and reliable surveillance is a necessity to mitigate the effects of falls. The technology and products related to fall detection have always been in high demand within the security and the health-care industries. An effective fall detection system is required to provide urgent support and to significantly reduce the medical care costs associated with falls. In this paper, we give a comprehensive survey of different systems for fall detection and their underlying algorithms. Fall detection approaches are divided into three main categories: wearable device based, ambience device based and vision based. These approaches are summarised and compared with each other and a conclusion is derived with some discussions on possible future work.
Summary The fall is a risky event in the elderly people's daily living, especially the independent living, it often cause serious injury both in physiology and psychology. Wearable sensor based fall detection system had been proved in many experiments for its feasibility and effectiveness, but there remain some crucial problems, include: the people maybe forget to wear the clothes with micro sensors, which device standard should be selected between medical device standard and mass market standard, and how to control the false alarm probability to fit the individualized requirements. To deal with these problems, we think it is a reasonable design to combine micro sensors with an ambulatory daily using device which has a common network interface, and adjust the classification parameters via a remote server. In this paper, we embed a tri-axial accelerometer in a cellphone, connect to Internet via the wireless channel, and using 1-Class SVM (Support Vector Machine) algorithm for the pre- processing, KFD (Kernel Fisher Discriminant) and k-NN (Nearest Neighbour) algorithm for the precise classification. And there were 32 volunteers, 12 elders (age 60-80) and 20 younger (age 20-39), attended our experiments, the results show that this method can detect the falls effectively and make less disturbance to people's daily living than the general wearable sensor based fall detection systems.
Falls affect, each year, tens of million of elderly people throughout the world. It can have immediate lethal consequences but also causes many disabling fractures and dramatic psychological consequences which reduce the independence of the person. Falls in the elderly is thus a major public health problem. The “early” detection of fall consequently raises the interest of searchers, as most of elderly fallers cannot return to a standing position on their own following a fall. It is also an interesting scientific problem because it is an ill-defined process. The goals of this study were to classify various approaches used to detect the fall and to point out the difficulty to compare the results of these studies, as there is currently no common evaluation benchmark.
The elderly population is growing rapidly. Fall related injuries are a central problem for this population. Elderly people desire to live at home, and thus, new technologies, such as automated fall detectors, are needed to support their independence and security. The aim of this study was to evaluate different low-complexity fall detection algorithms, using triaxial accelerometers attached at the waist, wrist, and head. The fall data were obtained from standardized types of intentional falls (forward, backward, and lateral) in three middle-aged subjects. Data from activities of daily living were used as reference. Three different detection algorithms with increasing complexity were investigated using two or more of the following phases of a fall event: beginning of the fall, falling velocity, fall impact, and posture after the fall. The results indicated that fall detection using a triaxial accelerometer worn at the waist or head is efficient, even with quite simple threshold-based algorithms, with a sensitivity of 97-98% and specificity of 100%. The most sensitive acceleration parameters in these algorithms appeared to be the resultant signal with no high-pass filtering, and the calculated vertical acceleration. In this study, the wrist did not appear to be an applicable site for fall detection. Since a head worn device includes limitations concerning usability and acceptance, a waist worn accelerometer, using an algorithm that recognizes the impact and the posture after the fall, might be optimal for fall detection.
Lightgbm: A highly efficient gradient boosting decision tree
- Ke