Conference PaperPDF Available

Evaluation of Human Activity Recognition and Fall Detection Using Android Phone

Conference Paper

Evaluation of Human Activity Recognition and Fall Detection Using Android Phone

Abstract

Human Activity Recognition (AR) using kinematic sensors is one of the widely used researched area based on smartphone. Development in sensor networks technology pro-vided birth to the applications that can give intelligent and amicable services based on the AR of people. Although, this technology supports analyzing different activities pattern, em-powering applications to identify the activities performed user independently is still a fundamental concern. For improvement quality of life and personal safety, caregiving process can be enhanced by introducing the AR, automatic fall detection, and prevention systems. Modern smartphones have different built in sensors like accelerometer, magnetometer, proximity, and gyroscope which can be used for AR as well as fall detection. In this paper, we present an AR and fall detection system which used built in sensors with alarm notification service. We use Signal Magnitude Vector (SMV) algorithm to analyze the fall like events. To overcome the false alarm activation problem, system uses different threshold values to determine the daily life activities like walking, standing, and siting, that could be wrongly detected as a fall. For assessment, a trial setup is done to acquire sensor's information of diverse positions.
    
     
  1  1,   2
 3  4   5    1
1      
2          
3   
4    
5       
  
$EVWUDFW     
          
      
         
        ! 
  "   ! 
       
      # 
$     !    
    !   ! 
  %    
   ! ! &! 
           
'  !         
      (  ) 
* % + *%+   "   
 ,      ! 
         
 ! !  !     
   # !       $ -
   
 
       
        
         
       
           
      
        
      
        
         
          
          
         
           
        
       
        
            
            
        
        
        
         
         
           
         
          
        
         
   
       
     
       
          
       
        
         
     
        
        
         
          
       
        
      
        
         
       
        
      
       
        
       
   
          
          
2015 IEEE 29th International Conference on Advanced Information Networking and Applications
1550-445X/15 $31.00 © 2015 IEEE
DOI 10.1109/AINA.2015.181
163
          
         
         
        
          
       
      
          
          
       
        
        
       
          

  
         
           
        
        
        
        
       
         
      
       
        
       
       
          
       
         
 
        
        
       
          
      
         
        
       
 80.29%      
           
 
        
          
         
      
         
       
       
        
        
       
        
        
        
       
        
       
        
        

       
         
        
         
        
       
 
       
          
          
         
        
           
       
         
        
       
        
       
    
    
          
       
          
          
          
       
         
         
      
          
          
       
       
         
      
     
        
        
   
       
       
      
      
    
164
        
       
      
        
        

         
        
        
         
           
         
         
        
          
          
   
       
       
     
        
       
          
         
       
        
           
         
      
       
      
  
        
           
          
        
        
     
        
         
        
        
        
      
          
         
       
        
         
           
       
          
         
   
    
     
        
         
      
         
        
        
         
        
        
      
       
     
SMV =A2
x+A2
y+A2
z
 AxAyAz   
          
          
         
    
  
        
         
         
          
           
       
          
        
        
       
          
        
  
         
        
         
        
          
         
165
Ambulance
Medical Server
Bluetooth
GPRS/GPS
Internet
Accelerometer
Ax, Ay, Az
Gyroscope
Ax, Ay, Az
Orientation
Ax, Ay, Az
Data Collection
Features
Extraction/
Selection
Feature
Classification
Decision
Notifications
Alerts
Phase 1 Phase 2 Phase 3
      
       
        
        
         
      
         
       
         
          
          
      
       
         
         
           
         
        
        
       
         
       
        
   
   
        
        
       
        
        
         
        
       
      
   
           
          
          
       
         
         
        
      
        
         
         
   
        
          
       
         
        
 m/s2      
         
         
         
           
        
         
       
          
          
166
     






     






     






    
     








     


 !"


#
$%!
&
''
         
167
     


(
(!


     


(
(!


     


(
(!


    
     



(
(!




     




(
(!


' '
$%!
&
         
168
       ) * +
*




*

 !"


 !"
,-$%
    
*     *
.
.
.
.)
.)
.*
.*
.+
.+
/ !"
/!

/ !"
,
    
     
*
*.
+
+.

.



 !"
'' 
    

)
*
+







 !"
'' 
    
      
     ms      
        
          
         
        
         
  
  
       
       
           
      
          
        
         
           
            
 
  
          
          
         
          
          
169
         
         
        
         
           
           
        
   
  !! "
        
        
          
           
         
          
         
        
        
            
       

    
         
         
       
          
       
        
       
         
        
          
        
      
       
        
       
       
         
        
        
       
          
        
       
         
        
       
       
        
    

        
 
             
          
       
    
           
         
  # $      
  
             
       #
$         
              
% &# $       
             
       
    %!   
    
            
         
            
        
      '(# )*+, ,-!
 $ . . ! $   

          
       
    
           
  / . & $.0
        
            
      $
/ . 1  2   
             
       
$ / . 1  2   
              
      
       
              
       
   % . ! )3!   &
 && &    
                 
         
      
 $ / .  4 . %
    
170
... Each pixel of cell provides gradient weights to its respective angular bin. We can take blocks as spatial regions, which are the neighboring cell group [13]. The base for classification and normalization of histograms is assembling of cells as blocks. ...
Chapter
Full-text available
The activities of human can be classified into human actions, interactions, object–human interactions and group actions. The recognition of actions in the input video is very much useful in computer vision technology. This system gives application to develop a model that can detect and recognize the actions. The variety of HAR applications are surveillance environment systems, healthcare systems, military, patient monitoring system (PMS), etc., that involve interactions between electronic devices such as human–computer interfaces with persons. Initially, collecting the videos containing actions or interactionswas performed by the humans. The given input videos were converted into number of frames, and then these frames were undergone preprocessing stage using by applying median filter. The noise of the given input frame is reduced by applying the median filter of the neighboring pixels. Through frames, desired features were extracted. The actions of the personwhich is recognised from the system is going to extract further. There are three spatial–temporal interest point (STIP) techniques such as Harris SPIT, Gabor SPIT and HOG SPIT used for feature extraction from video frames. SVM algorithm is applied for classifying the extracted feature. The action recognition is based on the colored label identified by classifier. The system performance is measured by calculating the classifier performance which is the accuracy, sensitivity and specificity. The accuracy represents the classifier reliability. The specificity and sensitivity represent how exactly the classifier categorizes its features to each correct category and how the classifier rejects the features that are not belonging to the particular correct category.
... Among the reasons for this is that common activity sets are not used to assess the performance of the developed systems. There exist publicly available datasets as well as studies that acquire and use their own datasets (ADLs and falls) [38,39]. ...
Article
With sensor-based wearable technologies, high precision monitoring and recognition of human physical activities in real time is becoming more critical to support the daily living requirements of the elderly. The use of sensor technologies, including accelerometers (A), gyroscopes (G), and magnetometers (M) is mostly encountered in work focused on assistive technology, ambient intelligence, context-aware systems, gait and motion analysis, sports science, and fall detection. The classification performance of four sensor type combinations is investigated through the use of four machine learning algorithms: support vector machines (SVMs), Manhattan k-nearest neighbor classifier (M.k-NN), subspace linear discriminant analysis (SLDA), and ensemble bagged decision tree (EBDT). In this context, a large dataset containing 2520 tests performed by 14volunteers containing 16 activities of daily living (ADLs) and 20 falls was employed. In binary (fall vs. ADL) and multi-class activity (36 activities) recognition, the highest classification accuracy rate was obtained by the SVM (99.96%) and M.k-NN (95.27%) classifiers, respectively, with the AM sensor type combination in both cases. We also made our dataset publicly available to lay the groundwork for new research.
Article
Full-text available
Weather in Malaysia are hot and humid throughout the year thus having a sudden rain can disrupt the drying of laundries and make them wet. In this study, an automated retractable roof system was developed to overcome this problem. The development and implementation of this study enables user to monitor the parameters at the laundry suspension area by using their smartphone and prevent the laundries getting wet from rain. This study uses humidity sensors, Ultraviolet (UV) sensor, rain sensor, and temperature sensor to detect parameter such as humidity, UV intensity, presence of water and temperature respectively. Data from the sensors were collected and analysed to determine the values of parameters when rains occurred. These parameters were indicated as part of weather prediction study. From experiment, the retractable roof will open and close depended on condition met by the system. In addition, the system can communicate with the user’s phone through using Internet connection. The Blynk application in the smartphone allows the user to monitor and control the system through internet connection between the application and microcontroller. This study will be helpful for non-commercial use and can be expanded to commercial use as with further improvement.
Article
Full-text available
Aromatherapy candles with essential oils which can provides a therapeutic treatments have been made to maintain and improve our wellbeing. In this paper, a mini prototype of automated aromatherapy candle process plant using IoT and WSN has been proposed and developed. The main process of producing aromatherapy candle are heating and mixing. To produce the right quality of the aromatherapy candle, the quantity of the raw material is important. Heating process will be control by using ESP8266 based PID controller and monitored by using Open Source Programmable Logic Controller called OpenPLC that run on Raspberry Pi. The software is efficient because can support users over the entire plant and process. Mixing process will mix the raw material evenly using agitator motor with specific temperature. The whole process in this work can be monitored and control through PC via this implementation of software. To obtain the best quality of this work, the set point of temperature need to be control and the plant able to be achieved after second test of the study. As the result, this study able to produces aromatherapy candle with better quality in minimal time. This study also able to control the candle from releasing too many Volatile Organic Compound that can effect human life. Armed with the wealth of relevant information presented in this article, it is hoped that readers will have greatly benefited and gained a thorough understanding on how to develop an automated aroma therapy candle process planting using IoT and WSN. With further research put forth into this study, it is also hope it could be an advantage in innovation development and can be implemented in real life manufacturing industry.
Article
Full-text available
ARTICLE INFO ABSTRACT The major goal of this research is to use a voice dataset and a video dataset to depict real-time face emotional analysis. The detection technique makes advantage of multi-modal fusion as well as numerous timescale features of speech. Finding the amplitude and also detecting the maximum peaks of the signals are two methods for analyzing audio signals. In our paper, we use audio and video datasets to find human emotions such as happy, sad, clam, angry, fear, disgust, and surprise using a machine learning algorithm and HAR emotion detection. Emotions may be examined and recognized in both pre-recorded and real-time situations. The suggested study uses the most popular machine learning method, random forest, and multi scale wavelet transform techniques to develop a unique data fusion technique for real-time heterogeneous backdrop face emotional signal analysis with voice signal. For better results, this concept was realized using MATLAB 2020 simulation software.
Article
Revolutionary advances in machine and deep learning techniques within the field of computer field have dramatically expanded our opportunities to decipher the merits of digital imagery in the business world. Although extant literature on computer vision has yielded a myriad of approaches for extracting core attributes from images, the esotericism of the advocated techniques hinders scholars from delving into the role of visual rhetoric in driving business performance. Consequently, this tutorial aims to consolidate resources for extracting visual features via conventional machine and/or deep learning techniques. We describe resources and techniques based on three visual feature extraction methods, namely calculation-, recognition-, and simulation-based. Additionally, we offer practical examples to illustrate how image features can be accessed via open-sourced python packages such as OpenCV and TensorFlow.
Chapter
The activities of human can be classified into human actions, interactions, object–human interactions and group actions. The recognition of actions in the input video is very much useful in computer vision technology. This system gives application to develop a model that can detect and recognize the actions. The variety of HAR applications are surveillance environment systems, healthcare systems, military, patient monitoring system (PMS), etc., that involve interactions between electronic devices such as human–computer interfaces with persons. Initially, collecting the videos containing actions or interactions was performed by the humans. The given input videos were converted into number of frames, and then these frames were undergone preprocessing stage using by applying median filter. The noise of the given input frame is reduced by applying the median filter of the neighboring pixels. Through frames, desired features were extracted. The actions of the person which is recognised from the system is going to extract further. There are three spatial–temporal interest point (STIP) techniques such as Harris SPIT, Gabor SPIT and HOG SPIT used for feature extraction from video frames. SVM algorithm is applied for classifying the extracted feature. The action recognition is based on the colored label identified by classifier. The system performance is measured by calculating the classifier performance which is the accuracy, sensitivity and specificity. The accuracy represents the classifier reliability. The specificity and sensitivity represent how exactly the classifier categorizes its features to each correct category and how the classifier rejects the features that are not belonging to the particular correct category.
Article
Full-text available
Advancement in wireless sensor networks gave birth to applications that can provide friendly and intelligent services based on the recognition of human activities. Although the technology supports monitoring activity patterns, enabling applications to recognize activities user-independently is still a main concern. Achieving this goal is tough for two reasons: firstly, different people exhibit different physical patterns for the same activity due to their different behavior. Secondly, different activities performed by the same person could have different underlying models. Therefore, it is unwise to recognize different activities using the same features. This work presents a solution to this problem. The proposed system uses simple time domain features with a single neural network and a three-stage genetic algorithm-based feature selection method for accurate user-independent activity recognition. System evaluation is carried out for six activities in a user-independent setting using 27 subjects. Recognition performance is also compared with well-known existing methods. Average accuracy of 93% in these experiments shows the feasibility of using our method for subject-independent human activity recognition.
Article
Full-text available
Although human activity recognition (HAR) has been studied extensively in the past decade, HAR on smartphones is a relatively new area. Smartphones are equipped with a variety of sensors. Fusing the data of these sensors could enable applications to recognize a large number of activities. Realizing this goal is challenging, however. Firstly, these devices are low on resources, which limits the number of sensors that can be utilized. Secondly, to achieve optimum performance efficient feature extraction, feature selection and classification methods are required. This work implements a smartphone-based HAR scheme in accordance with these requirements. Time domain features are extracted from only three smartphone sensors, and a nonlinear discriminatory approach is employed to recognize 15 activities with a high accuracy. This approach not only selects the most relevant features from each sensor for each activity but it also takes into account the differences resulting from carrying a phone at different positions. Evaluations are performed in both offline and online settings. Our comparison results show that the proposed system outperforms some previous mobile phone-based HAR systems.
Article
Full-text available
Activity recognition for the purposes of recognizing a user's intentions using multimodal sensors is becoming a widely researched topic largely based on the prevalence of the smartphone. Previous studies have reported the difficulty in recognizing life-logs by only using a smartphone due to the challenges with activity modeling and real-time recognition. In addition, recognizing life-logs is difficult due to the absence of an established framework which enables the use of different sources of sensor data. In this paper, we propose a smartphone-based Hierarchical Activity Recognition Framework which extends the Naïve Bayes approach for the processing of activity modeling and real-time activity recognition. The proposed algorithm demonstrates higher accuracy than the Naïve Bayes approach and also enables the recognition of a user's activities within a mobile environment. The proposed algorithm has the ability to classify fifteen activities with an average classification accuracy of 92.96%.
Conference Paper
Full-text available
Aging population is considered to be major problem in modern healthcare. At the same time, fall incidents often occur among elderly and cause serious injuries affecting their independent living. This paper proposes a framework which uses mobile phone technology together with physiological data monitoring in order to detect falls. The system carries out collecting, storing and processing of acceleration data with further alarm generating and transferring all the measurements to remote caregiver. To perform evaluation, an experimental setup involving novice ice-skaters were carried out to obtain realistic fall data and examine the effects of falling on physiological parameters. A fall detection algorithm has been designed therefore to cope with large variations of movement in the torso. The online algorithm operating showed performance results of 90% specificity, 100% sensitivity and 94% accuracy.
Article
Full-text available
In this paper we present a framework that allows for the automatic identification of sporting activities using commonly available smartphones. We extract discriminative informational features from smartphone accelerometers using the Discrete Wavelet Transform (DWT). Despite the poor quality of their accelerometers, smartphones were used as capture devices due to their prevalence in today's society. Successful classification on this basis potentially makes the technology accessible to both elite and non-elite athletes. Extracted features are used to train different categories of classifiers. No one classifier family has a reportable direct advantage in activity classification problems to date; thus we examine classifiers from each of the most widely used classifier families. We investigate three classification approaches; a commonly used SVM-based approach, an optimized classification model and a fusion of classifiers. We also investigate the effect of changing several of the DWT input parameters, including mother wavelets, window lengths and DWT decomposition levels. During the course of this work we created a challenging sports activity analysis dataset, comprised of soccer and field-hockey activities. The average maximum F-measure accuracy of 87% was achieved using a fusion of classifiers, which was 6% better than a single classifier model and 23% better than a standard SVM approach.
Article
Full-text available
With the continuous improvements in video-analysis techniques, automatic low-cost video surveillance gradually emerges for consumer applications. Video surveillance can contribute to the safety of people in the home and ease control of home-entrance and equipment-usage functions. In this paper, we study a flexible framework for semantic analysis of human behavior from a monocular surveillance video, captured by a consumer camera. Successful trajectory estimation and human-body modeling facilitate the semantic analysis of human activities and events in video sequences. An additional contribution is the introduction of a 3-D reconstruction scheme for scene understanding, so that the actions of persons can be analyzed from different views. The total framework consists of four processing levels: (1) a preprocessing level including background modeling and multiple-person detection, (2) an object-based level performing trajectory estimation and posture classification, (3) an event-based level for semantic analysis, and (4) a visualization level including camera calibration and 3-D scene reconstruction. Our proposed framework was evaluated and has shown its good quality (86% accuracy of posture classification and 90% for events) and effectiveness, as it achieves a near real-time performance (6-8 frames/second).
Article
While the quality of life is improving, people care about healthy more than they ever do in the past. Healthcare system and sports management system is useful to everyone. But wearing special instrument is really hard to insist. People carry smartphones everywhere. Accelerometer in smartphones can do activity recognition to support sports management. We use accelerometer embedded in the smartphones to classify five activities: staying still, walking, running, going upstairs and downstairs. People carry smartphones in different positions, such as the pocket of trousers, hands or bags. This work analysis data gathered by accelerometer, extract various features, choose features highly correlated to human behavior, and construct an activity recognition model based on location-independent smartphone. We construct three models: the (behavior, position) vector model, the position-activity model, the activity model. compare all these models, the activity model gain the highest accuracy and lest time-consuming, which can effectively identify human behavior.
Article
Falling remains one of the leading causes of hospitalization and death for the elderly all around the world. The considerable risk of falls and the substantial increase of the elderly population have stimulated scientific research on smartphone-based fall detection systems recently. Even though these systems are helpful for fall detection, the best way to reduce the number of falls and their consequences is to prevent them from happening in the first place. Therefore, our focus is on fall prevention rather than fall detection. To address the issue of fall prevention, in this paper, we propose a smartphone-based fall prevention system that can alert the user about their abnormal walking pattern. Most current systems merely detect a fall whereas our approach attempts to identify high-risk gait patterns and alert the user to save them from an imminent fall. Our system uses a gait analysis approach that couples cycle detection with feature extraction to detect gait abnormality. We validated our approach using a decision tree with 10-fold cross validation and found 99.8% accuracy in gait abnormality detection. To the best of our knowledge, we are the first to use the built-in accelerometer and gyroscope of the smartphone to identify abnormal gaits in users for fall prevention.
Article
Video sensor based human activity recognition systems have potential applications in life care and health care areas. The paper presents a system for elderly care by recognizing six abnormal activities; forward fall, backward fall, chest pain, faint, vomit, and headache, selected from the daily life activities of elderly people. Privacy of elderly people is ensured by automatically extracting the binary silhouettes from video activities. Two problems are addressed in this research, which decrease recognition accuracy during the process of abnormal human activity recognition (HAR) system development. First, the problem of continuous changing distance of a moving person from two viewpoints is resolved by using the R-transform. R-transform extracts periodic, scale and translation invariant features from the sequences of activities. Second, the high similarities in postures of different activities is significantly improved by using the kernel discriminant analysis (KDA). KDA increases discrimination between different classes of activities by using non-linear technique. Hidden markov model (HMM) is used for training and recognition of activities. The system is evaluated against linear discriminant analysis (LDA) on the original silhouette features and LDA on the R-transform features. Average recognition rate of 95.8% proves the feasibility of the system for elderly care at home 1.
Article
to study the sensitivity and specificity of fall detection using mobile phone technology. an experimental investigation using motion signals detected by the mobile phone. the research was conducted in a laboratory setting, and 18 healthy adults (12 males and 6 females; age = 29 ± 8.7 years) were recruited. each participant was requested to perform three trials of four different types of simulated falls (forwards, backwards, lateral left and lateral right) and eight other everyday activities (sit-to-stand, stand-to-sit, level walking, walking up- and downstairs, answering the phone, picking up an object and getting up from supine). Acceleration was measured using two devices, a mobile phone and an independent accelerometer attached to the waist of the participants. Bland-Altman analysis shows a higher degree of agreement between the data recorded by the two devices. Using individual upper and lower detection thresholds, the specificity and sensitivity for mobile phone were 0.81 and 0.77, respectively, and for external accelerometer they were 0.82 and 0.96, respectively. fall detection using a mobile phone is a feasible and highly attractive technology for older adults, especially those living alone. It may be best achieved with an accelerometer attached to the waist, which transmits signals wirelessly to a phone.