Unobtrusive Human Fall Detection System Using mmWave Radar and Data Driven Methods

被引:12
|
作者
Rezaei, Ariyamehr [1 ,2 ]
Mascheroni, Alessandro [3 ]
Stevens, Michael C. [1 ,2 ]
Argha, Reza [1 ,2 ]
Papandrea, Michela [3 ]
Puiatti, Alessandro [3 ]
Lovell, Nigel H. [1 ,2 ]
机构
[1] Univ New South Wales UNSW, Grad Sch Biomed Engn, Sydney, NSW 2052, Australia
[2] Univ New South Wales UNSW, Tyree Inst Hlth Engn, Sydney, NSW 2052, Australia
[3] Univ Appl Sci & Arts Southern Switzerland SUPSI, Dept Innovat Technol DTI, CH-6962 Viganello, Switzerland
关键词
Deep learning (DL); fall detection; machine learning (ML); millimeter-wave (mmWave) radar; nonwearable devices;
D O I
10.1109/JSEN.2023.3245063
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
As the population ages, health issues like injurious falls demand more attention. One solution is to use wearable devices to detect falls. Nevertheless, most of these devices raise obtrusiveness, and older people generally resist or might forget to wear them. The millimeter-wave (mmWave) radar technology was used in this study to unobtrusively detect human falls. Data were collected from healthy young volunteers with the radar mounted on the side wall (trial 1) or overhead (trial 2) of an experimental room. A set of features were manually extracted from the data point clouds; then, multilayer perceptron (MLP), random forest (RF), k-nearest neighbor (KNN), and support vector machine (SVM) classifiers were applied on the features. Additionally, we devised a convolutional neural network (CNN)-based deep learning model for the underlying fall detection problem that receives a 3-D representation of the point cloud data, known as occupancy grid, as the input. The optimal installation position of the radar sensor was unknown. Therefore, the sensor was mounted on side wall and on the ceiling of the room to allow the performance comparison between these sensor placements. RF classifier achieved the best results in trial 2 (an accuracy of 92.2%, a recall of 0.881, a precision of 0.805, and an F1-score of 0.841), and the proposed CNN model achieved slightly better results comparing to the RF method in trial 2 (an accuracy of 92.3%, a recall of 0.891, a precision of 0.801, and an F1-score of 0.844). These results suggest that the development of an unobtrusive monitoring system for fall detection using mmWave radar is feasible.
引用
收藏
页码:7968 / 7976
页数:9
相关论文
共 50 条
  • [1] An Unobtrusive Fall Detection System Using Ceiling-mounted Ultra-wideband Radar
    Lu, Wei
    Kumar, Saurav
    Sandhu, Moid
    Zhang, Qing
    [J]. 2023 45TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY, EMBC, 2023,
  • [2] REAL-TIME FALL DETECTION USING MMWAVE RADAR
    Li, Wenxuan
    Zhang, Dongheng
    Li, Yadong
    Wu, Zhi
    Chen, Jinbo
    Zhang, Dong
    Hu, Yang
    Sun, Qibin
    Chen, Yan
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 16 - 20
  • [3] Unsupervised-Learning-Based Unobtrusive Fall Detection Using FMCW Radar
    Yao, Yicheng
    Zhang, Hao
    Liu, Changyu
    Geng, Fanglin
    Wang, Peng
    Du, Lidong
    Chen, Xianxiang
    Han, Baoshi
    Yang, Ting
    Fang, Zhen
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (03) : 5078 - 5089
  • [4] SCL-Fall: Reliable Fall Detection Using mmWave Radar With Supervised Contrastive Learning
    Li, Wenxuan
    Zhang, Dongheng
    Li, Yadong
    Song, Ruiyuan
    Hu, Yang
    Sun, Qibin
    Chen, Yan
    [J]. IEEE Journal of Selected Areas in Sensors, 2024, 1 : 237 - 248
  • [5] Human Fall Detection Based on Machine Learning Using a THz Radar System
    He, Mi
    Nian, Yongjian
    Zhang, Zhu
    Liu, Xiao
    He, Houyuan
    [J]. 2019 IEEE RADAR CONFERENCE (RADARCONF), 2019,
  • [6] A low-cost and unobtrusive system for fall detection
    Fernandez-Bermejo Ruiz, Jesus
    Dorado Chaparro, Javier
    Bolanos Peno, Cristina
    Llumiguano Solano, Henry A.
    del Toro Garcia, Xavier
    Lopez Lopez, Juan C.
    [J]. KNOWLEDGE-BASED AND INTELLIGENT INFORMATION & ENGINEERING SYSTEMS (KSE 2021), 2021, 192 : 2160 - 2169
  • [7] Unobtrusive Fall Detection at Home Using Kinect Sensor
    Kepski, Michal
    Kwolek, Bogdan
    [J]. COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PT I, 2013, 8047 : 457 - 464
  • [8] Design of an Unobtrusive System for Fall Detection in Multiple Occupancy Residences
    Ariani, Arni
    Redmond, Stephen J.
    Zhang, Zhaonan
    Narayanan, Michael R.
    Lovell, Nigel H.
    [J]. 2013 35TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2013, : 4690 - 4693
  • [9] mmFall: Fall Detection Using 4-D mmWave Radar and a Hybrid Variational RNN AutoEncoder
    Jin, Feng
    Sengupta, Arindam
    Cao, Siyang
    [J]. IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2022, 19 (02) : 1245 - 1257
  • [10] Robust Unobtrusive Fall Detection using Infrared Array Sensors
    Fan, Xiuyi
    Zhang, Huiguo
    Leung, Cyril
    Shen, Zhiqi
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON MULTISENSOR FUSION AND INTEGRATION FOR INTELLIGENT SYSTEMS (MFI), 2017, : 194 - 199