计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230700044-8.doi: 10.11896/jsjkx.230700044

• 网络&通信 • 上一篇    下一篇

WiCare:一种非接触式的老人如厕跌倒监测模型

段鹏松1, 刁宪广1, 张大龙1, 曹仰杰1, 刘广怡2, 孔金生1   

  1. 1 郑州大学网络空间安全学院 郑州 450002
    2 解放军战略支援部队信息大学 郑州 450001
  • 发布日期:2024-06-06
  • 通讯作者: 张大龙(ttengzhang@163.com)
  • 作者简介:(duanps@zzu.edu.cn)
  • 基金资助:
    郑州市协同创新重大专项(20XTZX06013);中国工程科技发展战略河南研究院战略咨询研究项目(2022HENYB03);河南省科技攻关项目(232102210050)

WiCare:Non-contact Fall Monitoring Model for Elderly in Toilet

DUAN Pengsong1, DIAO Xianguang1, ZHANG Dalong1, CAO Yangjie1, LIU Guangyi2, KONG Jinsheng1   

  1. 1 School of Cyber Science and Engineering,Zhengzhou University,Zhengzhou 450002,China
    2 People’s Liberation Army Strategic Support Force Information Engineering University,Zhengzhou 450001,China
  • Published:2024-06-06
  • About author:DUAN Pengsong,born in 1983,Ph.D,is a member of CCF(No.43410M).His main research interests include wireless sensing Internet of things and machine learning.
    ZHANG Dalong,born in 1976,professor,Ph.Dsupervisor,is a member of CCF(No.T98T4M).His main research interests include wireless communication network,satellite positioning and network information.
  • Supported by:
    Collaborative Innovation Major Projectof Zhengzhou(20XTZX06013),China Engineering Science and Technology Development Strategy Henan Research Institute Strategic Consulting Research Project(2022HENYB03)and Key Science and Technology Project of Henan Province(232102210050).

PDF (PC)

262

摘要： 老人在卫生间内的跌倒行为存在因救助及时性差而导致严重危害的风险,因此高效快捷的如厕跌倒监测研究具有重要意义。针对当前基于Wi-Fi感知的跌倒监测方法中存在的受噪声影响大而特征提取不充分、监测精度有限的问题,提出了一种基于多级离散小波变换和软阈值处理的信号降噪算法,及一种融合卷积神经网络、双向长短期记忆网络及自注意力机制的非接触式如厕跌倒监测模型WiCare。首先,从原始CSI数据中提取振幅作为基础数据;其次,使用多级离散小波变换和软阈值处理进行感知数据降噪;然后,将感知数据进行多维重构,以更准确地表征跌倒行为特征;最后,利用WiCare提取感知数据中的有效特征,进而实现卫生间如厕跌倒行为监测功能。实验结果表明,WiCare在居家卫生间环境下对跌倒行为监测的准确率为99.41%,与其他同类模型相比,WiCare的识别准确率高,模型复杂度低,且泛化能力更强。

关键词: :Wi-Fi感知, 如厕跌倒监测, 离散小波变换, 软阈值处理, 深度学习

Abstract: The fall down behavior of elderly people in the bathroom poses a risk of serious harm due to poor timely rescue.Therefore,efficient and rapid monitoring of fall down in toilet is of great significance.A non-contact fall down in toiletmonitoring model WiCare,which integrates convolutional neural network(CNN),Bi-directional long short-term memory(BiLSTM),and self-attention mechanism,is proposed to address the issues of insufficient feature extraction and limited monitoring accuracy in current fall monitoring methods based on Wi-Fi perception,which are greatly affected by noise.Firstly,the amplitude is extracted from the original CSI data as the basic data.Secondly,multi-level discrete wavelet transform and soft threshold processing are used to reduce perceived data noise.Then,the perceptual data is reconstructed in multiple dimensions to more accurately characterize the characteristics of fall behavior.Finally,WiCare is used to extract effective features in the perception data,and then realize the function of monitoring toilet fall behavior in the toilet.Experimental results show that the accuracy of WiCare in monitoring fall behavior in the home bathroom environment is 99.41%.Compared with other similar models,WiCare has high recognition accuracy,low model complexity,and stronger generalization ability.

Key words: Wi-Fi sensing, Fall down in toilet detection, Multilevel discrete wavelet transform, Soft threshold processing, Deep learning

中图分类号: 

  • TP391
[1]YUX P,LU B Y.Active Measures for Current Situation of Po-pulation Aging in China[J].China Economist,2023(2):21-22.
[2]ZHANG T T,FENG Z Q,WANG W C,et al.A study on the status quo and influencing factors of falls among the elderly in China[J].Chinese Journal of Disease Control and Prevention,2022,26(5):502-507.
[3]ZHANG H,QI S G,CUI L,et al.Prevalence of falls and fall-related injuries among Chinese community-dwelling older adults:a one-year retrospective follow-up data analysis[J].Chinese Journal of Public Health,2022,26(5):502-507.
[4]LIU J,TAN R,HAN G,et al.Privacy-preserving in-home falldetection using visual shielding sensing and private information-embedding[J].IEEE Transactions on Multimedia,2020,23:3684-3699.
[5]LOTFI A,ALBAWENDI S,POWELLH,et al.Supporting independent living for older adults;employing a visual based fall detection through analysing the motion and shape of the human body[J].IEEE Access,2018,6:70272-70282.
[6]CHONG C J,TAN W H,CHANG Y C,et al.Visual based falldetection with reduced complexity horprasert segmentation using superpixel[C]//2015 IEEE 12th International Conference on Networking,Sensing and Control.IEEE,2015:462-467.
[7]ISLAM M S,SHAHRIAR H,SNEHA S,et al.Mobile sensor-based fall detection framework[C]//2020 IEEE 44th Annual Computers,Software,and Applications Conference(COMPSAC).IEEE,2020:693-698.
[8]HNOOHOM N,JITPATTANAKUL A,INLUERGSRIP,et al.Multi-sensor-based fall detection and activity daily living classification by using ensemble learning[C]//2018 International ECTI Northern Section Conference on Electrical,Electronics,Compu-ter and Telecommunications Engineering(ECTI-NCON).IEEE,2018:111-115.
[9]XU J D,CHEN Q,XUY X,et al.Design of real time fall detection system based on MEMS sensor[J].Transducer and Micro-system Technologies,2022,41(7):77-80.
[10]HU D M,WANG S H,SUN X Y,et al.Improved Grey Model Prediction Algorithm for Falling Down[J].Science Technology and Engineering,2019,19(20):31-36.
[11]HE J,ZHANG Z J,WANGW D,et al.Low-Power Fall Detection Technology Based on ZigBee and CNN Algorithm[J].Journal of Tianjin University(Science and Technology),2019,52(10):1045-1054.
[12]HALPERIRR D,HU W,SHETHA,et al.Tool release:gathe-ring 802.11n traces with channel state information[J].Acm Sigcomm Computer Communication Review,2011,41(1):53-53.
[13]ZHANG T,SONG T,CHEN D,et al.WiGrus:A WiFi-based gesture recognition system using software-defined radio[J].IEEE Access,2019,7:131102-131113.
[14]ABDELNASSER H,YOUSSEF M,HARRASK A.Wigest:Aubiquitous wifi-based gesture recognition system[C]//2015 IEEE Conference on Computer Communications(INFOCOM).IEEE,2015:1472-1480.
[15]LI C,LIU M,CAO Z.WiHF:Gesture and user recognition withWiFi[J].IEEE Transactions on Mobile Computing,2020,21(2):757-768.
[16]WANG W,LIU A X,SHAHZAD M.Gait recognition using wifi signals[C]//Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing.2016:363-373.
[17]ZENG Y,PATHAK P H,MOHAPATRA P.WiWho:WiFi-based person identification in smart spaces[C]//2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks(IPSN).IEEE,2016:1-12.
[18]DENG L,YANG J,YUAN S,et al.Gaitfi:Robust device-freehuman identification via wifi and vision multimodal learning[J].IEEE Internet of Things Journal,2022,10(1):625-636.
[19]HU Y,ZHANG F,WU C,et al.DeFall:Environment-indepen-dent passive fall detection using WiFi[J].IEEE Internet of Things Journal,2021,9(11):8515-8530.
[20]HU Y,ZHANG F,WUC,et al.A WiFi-based passive fall detection system[C]//ICASSP 2020－2020 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).IEEE,2020:1723-1727.
[21]LI X W,YU J,CHANGJ P,et al.Non-cooperative Human Behavior Recognition Method Based on CSI[J].Computer Science,2019,46(12):266-271.
[22]YANG C,SHAO H R.WiFi-based indoor positioning[J].IEEE Communications Magazine,2015,53(3):150-157.
[23]LUKITO Y,CHRISMANTO A R.Recurrent neural networksmodel for WiFi-based indoor positioning system[C]//2017 International Conference on Smart Cities,Automation & Intelligent Computing Systems(ICON-SONICS).IEEE,2017:121-125.
[24]DANG X C,ZHANG T,HAO Z J,et al.Indoor Key Area Monitoring Method Based on WiFi[J].Journal of Chinese Computer Systems,2020,41(2):344-349.
[25]WANG Y,WU K,NIL M.Wifall:Device-free fall detection by wireless networks[J].IEEE Transactions on Mobile Computing,2016,16(2):581-594.
[26]ZHANG D,WANG H,WANG Y,et al.Anti-fall:A non-intrusive and real-time fall detector leveraging CSI from commodity WiFi devices[C]//13th International Conference on Smart Homes and Health Telematics(ICOST 2015).Geneva,Switzerland,Springer International Publishing,2015:181-193.
[27]WANG H,ZHANG D,WANG Y,et al.RT-Fall:A real-timeand contactless fall detection system with commodity WiFi devices[J].IEEE Transactions on Mobile Computing,2016,16(2):511-526.
[28]RAN Y X,YU J,CHANG J,et al.A CSI-based fall detectionmethod[J].Journal of Yunnan University(Natural Sciences Edition),2020,42(2):220-227.
[29]LECUN Y,BOTTOU L,BENGIOY,et al.Gradient-based lear-ning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[30]WU K,XIAO J,YI Y,et al.FILA:Fine-grained indoor localization[C]//2012 Proceedings IEEE INFOCOM.IEEE,2012:2210-2218.
[31]GU Y,ZHANG X,LIU Z,et al.BeSense:leveraging WiFi channel data and computational intelligence for behavior analysis[J].IEEE Computational Intelligence Magazine,2019,14(4):31-41.
[32]HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[33]SRIVASTAVA N,HINTON G,KRIZHEVSKY A,et al.Dropout:a simple way to prevent neural networks from overfitting[J].The journal of Machine Learning Research,2014,15(1):1929-1958.
[34]DUAN P S,LI J X,WANG C,et al.WiSFall:a Device-free Fall Detection Model for Shower Room[J].Journal of Chinese Computer Systems,2023,44(2):232-238.
[35]YANG J,CHEN X,ZOU H,et al.SenseFi:A library and benchmark on deep-learning-empowered WiFi human sensing[J].Patterns,2023,4(3).
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发