Conference PaperPDF Available

Fall Detection System Using Accelerometer and Gyroscope Based on Smartphone

Authors:

Abstract and Figures

Most of people likes living independently at home. Some activity in our daily life is prone to have some accidents, such as falls. Falls can make people in fatal conditions, even death. A prototype of fall detection system using accelerometer and gyroscope based on smartphone is presented in this paper. Accelerometer and gyroscope sensors are embedded in smartphone to get the result of fall detection more accurately. Automatic call as an alert will be sent to family members if someone using this application in fatal condition and need some help. This research also can distinguish condition of people between falls and activity daily living. Several scenarios were used in these experiments. The result showed that the proposed system could successfully record level of accuracy of the fall detection system till 93.3% in activity daily living and error detected of fall was 2%.
Content may be subject to copyright.
      
 
 
  
   


 
 
 

       
           
          
        
         
      
         
           
         
        
        
         
         
         
   


 
        
        
        
     

         
           
       
        
      
   
         
       
         
         
         
       
       
  
        
         
 
  
           
        
         
       

      
        
          
         
         
      
     
 
      
          
       
         
     

       
       

 
         
          
         
       
           
        
      
  
    
   
           
          
           
          
          
          

        
   
     
           
    
   
        
       
       
        
 
         
         
        
       
          
       

       
        
       
    
        
        
          
            
  
 
       
         
      
 
          
      
    
  

        
  
      

          
         

 
 
        
     

   
   
        
           
        
         
  
      
         
           
      
  
     
         
    
  
  
     


    
    




  








     
         
            
        
  

 
         
     
        
       
       
 
      
         
       
        
 
        
          

         
        
   

  
  



 



  



   

  

 
   
        
         
 

     


  


 




 
 
 



 
  


 








   
       

 
 

 
   
        
      
         
         


 
  
 



  

     
  


 

 

   
   
       
  










   
 

 


 
  
        
     
      
 
        
          
         
       
          
        


 
         
           
          
        
      
      
       




 
 
  
        
       
       
      

 
          
     
           
    
 
 
 
    

   
  
       
    

       
    

        

   
 
 
 
 
    
    
   
  
 
        
 
  

  
 
    
    
     
     

        
         

    

  
 
    
    
     
    
    
    
    
        
        
        
           
          
          
          

 
         
         
      
      
       
       
           
  
         
     
       

       
         
       


            
        
       
            
     
            
        
      
          
        
     
     
        
    




          
  
          
       
  
            
       
        

            
    
    
          
        
  
Article
Full-text available
This study explores a model for detecting fall, non-fall and near-fall events as frequent experiences of near-falls are closely associated with a heightened risk of falls. Detecting near-falls can lead to more accurate predictions of falls. However, near-falls exhibit certain movement patterns similar to actual falls, making it challenging to distinguish between the two. We investigate the detection of fall-related activities, including falls, near-falls, and non-falls, by utilizing dynamic motion images derived from video clips. There are two primary approaches for classification: a vanilla convolutional neural network (CNN) model and a transfer learning approach that utilizes InceptionV3 and DenseNet201 models as feature extractors and train conventional machine learning classifiers, such as support vector machine (SVM), K-nearest neighborhood, decision tree, and random forest, and adaptive boosting models. The vanilla CNN model achieved a high accuracy of 97.89% compared to the transfer learning approach, which reached a maximum accuracy of 95.31 for binary classification of fall and non-fall events. On the other hand, the transfer learning approach, which integrated feature from InceptionV3 and DenseNet201 into machine learning classifiers, achieved an accuracy of up to 90.14% for the three-class classification of fall, non-fall, and near-fall events. This underscores the model’s robustness in detecting various fall-related activities, highlighting its potential for improving safety in at-risk populations.
Article
Background The aging global population and the rising prevalence of chronic disease and multimorbidity have strained health care systems, driving the need for expanded health care resources. Transitioning to home-based care (HBC) may offer a sustainable solution, supported by technological innovations such as Internet of Medical Things (IoMT) platforms. However, the full potential of IoMT platforms to streamline health care delivery is often limited by interoperability challenges that hinder communication and pose risks to patient safety. Gaining more knowledge about addressing higher levels of interoperability issues is essential to unlock the full potential of IoMT platforms. Objective This scoping review aims to summarize best practices and technologies to overcome interoperability issues in IoMT platform development for prehospital care and HBC. Methods This review adheres to a protocol published in 2022. Our literature search followed a dual search strategy and was conducted up to August 2023 across 6 electronic databases: IEEE Xplore, PubMed, Scopus, ACM Digital Library, Sage Journals, and ScienceDirect. After the title, abstract, and full-text screening performed by 2 reviewers, 158 articles were selected for inclusion. To answer our 2 research questions, we used 2 models defined in the protocol: a 6-level interoperability model and a 5-level IoMT reference model. Data extraction and synthesis were conducted through thematic analysis using Dedoose. The findings, including commonly used technologies and standards, are presented through narrative descriptions and graphical representations. Results The primary technologies and standards reported for interoperable IoMT platforms in prehospital care and HBC included cloud computing (19/30, 63%), representational state transfer application programming interfaces (REST APIs; 17/30, 57%), Wi-Fi (17/30, 57%), gateways (15/30, 50%), and JSON (14/30, 47%). Message queuing telemetry transport (MQTT; 7/30, 23%) and WebSocket (7/30, 23%) were commonly used for real-time emergency alerts, while fog and edge computing were often combined with cloud computing for enhanced processing power and reduced latencies. By contrast, technologies associated with higher interoperability levels, such as blockchain (2/30, 7%), Kubernetes (3/30, 10%), and openEHR (2/30, 7%), were less frequently reported, indicating a focus on lower level of interoperability in most of the included studies (17/30, 57%). Conclusions IoMT platforms that support higher levels of interoperability have the potential to deliver personalized patient care, enhance overall patient experience, enable early disease detection, and minimize time delays. However, our findings highlight a prevailing emphasis on lower levels of interoperability within the IoMT research community. While blockchain, microservices, Docker, and openEHR are described as suitable solutions in the literature, these technologies seem to be seldom used in IoMT platforms for prehospital care and HBC. Recognizing the evident benefit of cross-domain interoperability, we advocate a stronger focus on collaborative initiatives and technologies to achieve higher levels of interoperability. International Registered Report Identifier (IRRID) RR2-10.2196/40243
Article
Full-text available
The field of physically interactive electronic games is rapidly evolving, driven by the fact that it combines the benefits of physical activities and the attractiveness of electronic games, as well as advancements in sensor technologies. In this paper, a new game was introduced, which is a special version of Bubble Soccer, which we named Q-eBall. It creates a dynamic and engaging experience by combining simulation and physical interactions. Q-eBall is equipped with a fall detection system, which uses an embedded electronic circuit integrated with an accelerometer, a gyroscopic, and a pressure sensor. An evaluation of the performance of the fall detection system in Q-eBall is presented, exploring its technical details and showing its performance. The system captures the data of players’ movement in real-time and transmits it to the game controller, which can accurately identify when a player falls. The automated fall detection process enables the game to take the required actions, such as transferring possession of the visual ball or applying fouls, without the need for manual intervention. Offline experiments were conducted to assess the performance of four machine learning models, which were K-Nearest Neighbors (KNNs), Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM), for falls detection. The results showed that the inclusion of pressure sensor data significantly improved the performance of all models, with the SVM and LSTM models reaching 100% on all metrics (accuracy, precision, recall, and F1-score). To validate the offline results, a real-time experiment was performed using the pre-trained SVM model, which successfully recorded all 150 falls without any false positives or false negatives. These findings prove the reliability and effectiveness of the Q-eBall fall detection system in real time.
Article
Full-text available
This article analyses the movements of young and elderly people using data collected from an accelerometer and a gyroscope. This study proposes Type I fuzzy logic (FL) and several machine learning (ML) algorithms for the detection and classification of daily life movements and falls. The results obtained demonstrate that a fuzzy logic system can efficiently integrate data from an accelerometer and a gyroscope to classify falls and movements in daily life with 97.4% accuracy. When ML classifiers are used, the performance across several algorithms is also very high.
Chapter
Lack of supervision in home quarantine processes and deficiencies, such as limited vital assessment and no Internet of Things (IoT) integrated into existing healthcare monitoring devices, were factors in brought-in-dead (BID) cases during the coronavirus disease endemic (COVID-19) in Malaysia. This research aims to develop an IoMT remote healthcare monitoring system that monitors five physiological parameters and fall accidents. The proposed system generates alert messages with GPS location when an abnormal vital value or fall is detected. The system is equipped with e-health sensors, triaxial accelerometers, and a GPS module. The collected data are transmitted to an IoT platform via Wi-Fi communication using a message queueing telemetry transport (MQTT) protocol for further processing and analysis. Web and mobile applications are developed for visualizing and receiving alert messages. The performance of the proposed system is benchmarked with the medical devices in the market. The average accuracies of measuring oxygen saturation (SpO2), heart rate, body temperature, and respiratory rate are 98.83%, 98.12%, 98.88%, and 97.61%, respectively. The accuracy, sensitivity, and specificity of fall detection are 95%, 94%, and 96%. The system is a viable solution enabling medical professionals to perform in-time treatment during emergencies and mitigate BID cases and fall problems.
Article
Full-text available
This paper presents a system called FallAlarm, which is utilized for fall detecting and positioning using a smart phone. A tri-axial accelerometer sensor and a Wi-Fi module embeded in the phone are employed to provide needed information. Data from the accelerometer is evaluated with a decision tree model to determine a fall. If a fall is suspected, a notification is raised to require the user's response. If the user is injured hardly and cannot respond in time, the system immediately begin to position the occurence of the fall event by detected surrounding Wi-Fi signals, then automatically send a alarm message to his pre-specified guardian with a message via SMS(Short Message System). Consequently, the victim of fall can be monitored and cared in real time. Tested on a real-world data set, the FallAlarm system can achieve an acceptable accuracy for practical application.
Article
Full-text available
Mobile phones or smartphones are rapidly becoming the central computer and communication device in people's lives. Application delivery channels such as the Apple AppStore are transforming mobile phones into App Phones, capable of downloading a myriad of applications in an instant. Importantly, today's smartphones are programmable and come with a growing set of cheap powerful embedded sensors, such as an accelerometer, digital compass, gyroscope, GPS, microphone, and camera, which are enabling the emergence of personal, group, and communityscale sensing applications. We believe that sensor-equipped mobile phones will revolutionize many sectors of our economy, including business, healthcare, social networks, environmental monitoring, and transportation. In this article we survey existing mobile phone sensing algorithms, applications, and systems. We discuss the emerging sensing paradigms, and formulate an architectural framework for discussing a number of the open issues and challenges emerging in the new area of mobile phone sensing research.
Conference Paper
Full-text available
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.
Conference Paper
Full-text available
Falls are a major health risk that diminish the quality of life among elderly people. With the elderly population surging, especially with aging "baby boomers", fall detection becomes increasingly important. However, ex- isting commercial products and academic solutions struggle to achieve pervasive fall detection. In this paper, we propose utilizing mobile phones as a platform for pervasive fall detection system development. To our knowledge, we are the first to do so. We design a detection algorithm based on mobile phone platforms. We propose PerFallD, a pervasive fall detection sys- tem implemented on mobile phones. We implement a prototype system on the Android G1 phone and conduct experiments to evaluate our system. In particular, we compare PerFallD's performance with that of existing work and a commercial product. Experimental results show that PerFallD achieves strong detection performance and power efficiency.
Conference Paper
Fall situations can be risky especially for elderly people with health problems. This fact has highlighted the need of fall detection systems. Various fall detection systems have been proposed. The proposed systems commonly used special devices placed at several position of user's body. On the other hand, smartphones with various sensors including gyroscopes are available in the market nowadays. This has motivated us to propose a prototype system of fall detection application designed for a smart phone. A threshold based fall detection algorithm is adapted for the proposed system since it relatively requires lower computational processes compared to complex reasoning techniques. Hence is more suitable to be implemented in mart phones with limited resource and processing power. The basic idea of the algorithm is to detect dynamic situations of posture, followed by unintentional falls to lying postures. The algorithm monitors sets of linear acceleration data and angular velocity and compares them to set of thresholds obtained from training data from the observed user. The process to detect a fall situation followed by sending notification to colleagues can be done in real-time manners while still maintain high accuracy for certain fall situations.
Conference Paper
The considerable risk of falls and the substantial increase in the elderly population make the automatic fall detection system become very important. Existing fall detection systems using accelerometer as the detector are often designed based on an empirical acceleration threshold to differentiate falls from normal activities. In this paper, we design the detection method under the Neyman-Pearson detection framework. An optimal detection threshold can be obtained which meets the specified false alarm rate while maximizing the detection probability. We use TelosW mote with accelerometer as the detector, which is attached to the waist of the old people to capture the movement data. Extensive experiments are conducted to evaluate the effectiveness of our method and the accuracy of the detection system.
Conference Paper
This article proposes a head detection algorithm for depth video provided by a Kinect camera and its application to fall detection. The proposed algorithm first detects possible head positions and then based on these positions, recognizes people by detecting the head and the shoulders. Searching for head positions is rapid because we only look for the head contour on the human outer contour. The human recognition is a modification of HOG (Histogram of Oriented Gradient) for the head and the shoulders. Compared with the original HOG, our algorithm is more robust to human articulation and back bending. The fall detection algorithm is based on the speed of the head and the body centroid and their distance to the ground. By using both the body centroid and the head, our algorithm is less affected by the centroid fluctuation. Besides, we also present a simple but effective method to verify the distance from the ground to the head and the centroid.
Article
Robust detection of events and activities, such as falling, sitting, and lying down, is a key to a reliable elderly activity monitoring system. While fast and precise detection of falls is critical in providing immediate medical attention, other activities like sitting and lying down can provide valuable information for early diagnosis of potential health problems. In this paper, we present a fall detection and activity classification system using wearable cameras. Since the camera is worn by the subject, monitoring is not limited to confined areas, and extends to wherever the subject may go including indoors and outdoors. Furthermore, since the captured images are not of the subject, privacy concerns are alleviated. We present a fall detection algorithm employing histograms of edge orientations and strengths, and propose an optical flow-based method for activity classification. The first set of experiments has been performed with prerecorded video sequences from eight different subjects wearing a camera on their waist. Each subject performed around 40 trials, which included falling, sitting, and lying down. Moreover, an embedded smart camera implementation of the algorithm was also tested on a CITRIC platform with subjects wearing the CITRIC camera, and each performing 50 falls and 30 non-fall activities. Experimental results show the success of the proposed method.
Article
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.
Conference Paper
Home health care sounds to be a convenient solution for the elderly person not willing to abandon her natural environment for a living in a hospital. But as most of the older subjects leave alone on their own and because of the isolation, it is necessary to guarantee a more precise follow up of the health and security status of the person. The paper deals with the detection of the fall of the elderly. The ultimate goal is to reach a good compromise between real time detection, sensibility, specificity and intrusivity. Different technical approaches are presented. A more precise description of our smart fall sensor principle is presented, with results, and the proposition of the new flexible version which was realised and is being currently integrated in a garment