| 470 | 14 | 242 |
| 下载次数 | 被引频次 | 阅读次数 |
针对传统的识别方法不能满足人类活动识别(Human Activity Recognition, HAR)技术研究需求的现状，提出了一种基于小波变换和卷积神经网络(Convolutional Neural Networks, CNN)相结合的深度学习模型。将多通道传感器的波形数据通过小波变换分解并重组作为输入。利用不同卷积核的CNN高效提取多维特征，使用最大池化层对人体无意识抖动引起的干扰噪声进行滤波操作。经过全连接层输出分类，实现对人体活动状态的准确识别。实验分别从模型收敛速度、损耗和精度三方面评估了模型性能，并在OPPORTUNITY公共数据集上与较先进的识别模型进行了对比。实验结果表明，提出的小波变化卷积网络Wavelet-CNN实现了91.65%的F1分数，具有更高的活动识别能力。
Abstract：As traditional recognition methods cannot meet the research needs of Human Activity Recognition(HAR),a deep learning model based on a combination of Wavelet Transform(WT) and convolutional neural network is proposed.The waveform data of the multi-channel sensor is decomposed and reorganized through wavelet transform as input.Then, the convolutional neural network with different convolution kernels is used to efficiently extract the multi-dimensional features, and the max-pooling layers are used to filter the interference noise caused by the unconscious jitter of human body.Finally, accurate recognition of human body activity state is realized through the output classification of the fully connected layer.The model performance is evaluated by experiment in three aspects including model convergence speed, loss and accuracy, and it is compared with that of the state-of-the-art recognition models on the OPPORTUNITY public dataset.Experimental results show that the proposed Wavelet-CNN architecture achieves 91.65% F1 score and is of higher activity recognition capability.
[1] DAI J,BAI X,YANG Z,et al.PerFallD:A Pervasive Fall Detection System Using Mobile Phones[C]//2010 8th IEEE International Conference on Pervasive Computing and Communications Workshops.Mannheim:IEEE,2010:292-297.
[2] FONTECHA J,NAVARRO F J,HERVAS R,et al.Elderly Frailty Detection by Using Accelerometer-enabled Smartphones and Clinical Information Records[J].Personal and Ubiquitous Computing,2013,17(6):1073-1083.
[3] PREUVENEERS D,BERBERS Y.Mobile Phones Assisting with Health Self-care:A Diabetes Case Study[C]//10th International Conference on Human Computer Interaction with Mobile Devices and Services.Amsterdam:ACM Press,2008:177-186.
[4] TAPIA E M,INTILLE S S,LARSON K.Activity Recognition in the Home Using Simple and Ubiquitous Sensors[C]//International Conference on Pervasive Computing.Linz/Vienna:Springer,2004:158-175.
[5] LIMA W S,SOUTO E,ROCHA T,et al.User Activity Recognition for Energy Saving in Smart Home Environment[C]//2015 IEEE Symposium on Computers and Communication (ISCC).Larnaca:IEEE,2015:751-757.
[6] 梁山清，李恩宁，葛红志，等.基于大数据平台的货车位置服务应用研究[J].无线电工程，2020,50(5):368-372.
[7] 黄璐，甘兴利，李雅宁.基于智能终端的室内定位系统研究与实现[J].无线电工程，2017,47(9):44-50.
[8] WU B,MA C,POSLAD S,et al.An Adaptive Human Activity-aided Hand-held Smartphone-based Pedestrian Dead Reckoning Positioning System[J].Remote Sensing,2021,13(11):2137.
[9] ZHOU B,YANG J,LI Q.Smartphone-based Activity Recognition for Indoor Localization Using a Convolutional Neural Network[J].Sensors,2019,19(3):621.
[10] YANG J,NGUYEN M N,SAN P P,et al.Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition[C]//IJCAI 2015.Buenos Aires:AAAI Press,2015:3995-4001.
[11] GU F,KHOSHELHAM K,YU C,et al.Accurate Step Length Estimation for Pedestrian Dead Reckoning Localization Using Stacked Autoencoders[J].IEEE Transactions on Instrumentation and Measurement,2019,68(8):2705-2713.
[12] XU C,CHAI D,HE J,et al.InnoHAR:A Deep Neural Network for Complex Human Activity Recognition[J].IEEE Access,2019,7:9893-9902.
[13] RANIERI C M,VARGAS P A,ROMERO R A F.Uncovering Human Multimodal Activity Recognition with a Deep Learning Approach[C]//2020 International Joint Conference on Neural Networks (IJCNN).Glasgow:IEEE,2020:1-8.
[14] CHAVARRIAGA R,SAGHA H,CALATRONI A,et al.The Opportunity Challenge:A Benchmark Database for on-Body Sensor-based Activity Recognition[J].Pattern Recognition Letters,2013,34(15):2033-2042.
[15] 蒋强卫，甘兴利，李雅宁.基于CNN双目特征点匹配目标识别与定位研究[J].无线电工程，2018,48(8):643-649.
[16] 李彦东，郝宗波，雷航.卷积神经网络研究综述[J].计算机应用，2016,36(9):2508-2515.
[17] RONAO C A,CHO S B.Human Activity Recognition with Smartphone Sensors Using Deep Learning Neural Networks[J].Expert Systems with Applications,2016,59:235-244.
[18] ORDó?EZ F J,ROGGEN D.Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition[J].Sensors,2016,16(1):115.
[19] HAMMERLA N Y,HALLORAN S,PLOETZ T.Deep,Convolutional,and Recurrent Models for Human Activity Recognition Using Wearables[C]//25th International Joint Conference on Artificial Intelligence.New York:AAAI Press,2016:1533-1540.
基本信息:
中图分类号:TP183;TP274
引用信息:
[1]张琳,易卿武,黄璐,等.基于Wavelet-CNN网络的人类活动识别技术[J].无线电工程,2022,52(04):590-597.
基金信息:
河北省重点研发计划项目(19210906D)~~
2021-10-12
2021
2021-12-01
2021
1
2021-12-21
2021-12-21
2021-12-21