Unsupervised Doppler Radar Based Activity Recognition for e-Healthcare

Passive radio frequency (RF) sensing and monitoring of human daily activities in elderly care homes is an emerging topic. Micro-Doppler radars are an appealing solution considering their non-intrusiveness, deep penetration, and high-distance range. Unsupervised activity recognition using Doppler radar data has not received attention, in spite of its importance in case of unlabelled or poorly labelled activities in real scenarios. This study proposes two unsupervised feature extraction methods for the purpose of human activity monitoring using Doppler-streams. These include a local Discrete Cosine Transform (DCT)-based feature extraction method and a local entropy-based feature extraction method. In addition, a novel application of Convolutional Variational Autoencoder (CVAE) feature extraction is employed for the first time for Doppler radar data. The three feature extraction architectures are compared with the previously used Convolutional Autoencoder (CAE) and linear feature extraction based on Principal Component Analysis (PCA) and 2DPCA. Unsupervised clustering is performed using K-Means and K-Medoids. The results show the superiority of DCT-based method, entropy-based method, and CVAE features compared to CAE, PCA, and 2DPCA, with more than 5%-20% average accuracy. In regards to computation time, the two proposed methods are noticeably much faster than the existing CVAE. Furthermore, for high-dimensional data visualisation, three manifold learning techniques are considered. The methods are compared for the projection of raw data as well as the encoded CVAE features. All three methods show an improved visualisation ability when applied to the encoded CVAE features.

[1]  Moeness G. Amin,et al.  Radar Data Cube Processing for Human Activity Recognition Using Multisubspace Learning , 2019, IEEE Transactions on Aerospace and Electronic Systems.

[2]  Panos P. Markopoulos,et al.  Indoor human motion classification by L1-norm subspaces of micro-Doppler signatures , 2017, 2017 IEEE Radar Conference (RadarConf).

[3]  Chunhui Yuan,et al.  Research on K-Value Selection Method of K-Means Clustering Algorithm , 2019, J.

[4]  Yangdi Xu,et al.  Log-Likelihood Clustering-Enabled Passive RF Sensing for Residential Activity Recognition , 2018, IEEE Sensors Journal.

[5]  Carlo Tomasi,et al.  Singular Value Decomposition , 2021, Encyclopedia of Social Network Analysis and Mining.

[6]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[7]  Bo Tan,et al.  Use of Low-Resolution Infrared Pixel Array for Passive Human Motion Movement and Recognition , 2018 .

[8]  Yann LeCun,et al.  Convolutional Learning of Spatio-temporal Features , 2010, ECCV.

[9]  Ali Cafer Gürbüz,et al.  Knowledge Exploitation for Human Micro-Doppler Classification , 2015, IEEE Geoscience and Remote Sensing Letters.

[10]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[11]  Francesco Fioranelli,et al.  Feature Diversity for Optimized Human Micro-Doppler Classification Using Multistatic Radar , 2017, IEEE Transactions on Aerospace and Electronic Systems.

[12]  Boualem Boashash,et al.  Wideband radar based fall motion detection for a generic elderly , 2016, 2016 50th Asilomar Conference on Signals, Systems and Computers.

[13]  Daijin Kim,et al.  A Depth Video-based Human Detection and Activity Recognition using Multi-features and Embedded Hidden Markov Models for Health Care Monitoring Systems , 2017, Int. J. Interact. Multim. Artif. Intell..

[14]  Thar Baker,et al.  Remote health monitoring of elderly through wearable sensors , 2019, Multimedia Tools and Applications.

[15]  B. Ainsworth,et al.  Feasibility of three wearable sensors for 24 hour monitoring in middle-aged women , 2015, BMC Women's Health.

[16]  J. Kruskal.  Nonmetric multidimensional scaling: A numerical method , 1964 .

[17]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[18]  Youngwook Kim,et al.  Human Detection and Activity Classification Based on Micro-Doppler Signatures Using Deep Convolutional Neural Networks , 2016, IEEE Geoscience and Remote Sensing Letters.

[19]  Sony George,et al.  Dimensionality reduction and visualisation of hyperspectral ink data using t-SNE. , 2020, Forensic science international.

[20]  Pietro Siciliano,et al.  A Radar-Based Smart Sensor for Unobtrusive Elderly Monitoring in Ambient Assisted Living Applications , 2017, Biosensors.

[21]  Carl Doersch,et al.  Tutorial on Variational Autoencoders , 2016, ArXiv.

[22]  Shyamal Patel,et al.  A review of wearable sensors and systems with application in rehabilitation , 2012, Journal of NeuroEngineering and Rehabilitation.

[23]  S. Z. Gürbüz,et al.  Deep convolutional autoencoder for radar-based classification of similar aided and unaided human activities , 2018, IEEE Transactions on Aerospace and Electronic Systems.

[24]  Md. Zia Uddin,et al.  A Depth Camera-based Human Activity Recognition via Deep Learning Recurrent Neural Network for Health and Social Care Services , 2016, CENTERIS/ProjMAN/HCist.

[25]  Cong Wang,et al.  The Feature Representation Ability of Variational AutoEncoder , 2018, 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC).

[26]  Fadel Adib,et al.  Emotion recognition using wireless signals , 2016, MobiCom.

[27]  Meng Li,et al.  A Three-Dimensional Deep Learning Framework for Human Behavior Analysis Using Range-Doppler Time Points , 2020, IEEE Geoscience and Remote Sensing Letters.

[28]  Bo Tan,et al.  Passive Radar for Opportunistic Monitoring in E-Health Applications , 2018, IEEE Journal of Translational Engineering in Health and Medicine.

[29]  R. L. Thorndike.  Who belongs in the family? , 1953 .

[30]  Xiaojun Jing,et al.  Deep Learning based Human Activity Classification in Radar Micro-Doppler Image , 2018, 2018 15th European Radar Conference (EuRAD).

[31]  Ling Shao,et al.  From handcrafted to learned representations for human action recognition: A survey , 2016, Image Vis. Comput..

[32]  Iztok Fister,et al.  Sensors and Functionalities of Non-Invasive Wrist-Wearable Devices: A Review , 2018, Sensors.

[33]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[34]  Abdelhak M. Zoubir,et al.  Subspace Classification of Human Gait Using Radar Micro-Doppler Signatures , 2018, 2018 26th European Signal Processing Conference (EUSIPCO).

[35]  Taneli Riihonen,et al.  Shallow Neural Networks for mmWave Radar Based Recognition of Vulnerable Road Users , 2020, 2020 12th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP).

[36]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[37]  Marjorie Skubic,et al.  Quantitative Gait Measurement With Pulse-Doppler Radar for Passive In-Home Gait Assessment , 2014, IEEE Transactions on Biomedical Engineering.

[38]  Diederik P. Kingma,et al.  An Introduction to Variational Autoencoders , 2019, Found. Trends Mach. Learn..

[39]  Yu Han Liu,et al.  Feature Extraction and Image Recognition with Convolutional Neural Networks , 2018, Journal of Physics: Conference Series.

[40]  Tomoaki Ohtsuki,et al.  Activity recognition using low resolution infrared array sensor , 2015, 2015 IEEE International Conference on Communications (ICC).

[41]  Guanghui Wang,et al.  Adversarially Approximated Autoencoder for Image Generation and Manipulation , 2019, IEEE Transactions on Multimedia.

[42]  Ole-Christoffer Granmo,et al.  The Dreaming Variational Autoencoder for Reinforcement Learning Environments , 2018, SGAI Conf..

[43]  J. Dunn.  Well-Separated Clusters and Optimal Fuzzy Partitions , 1974 .

[44]  Youngwook Kim,et al.  Human Activity Classification Based on Micro-Doppler Signatures Using a Support Vector Machine , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[45]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[46]  Luca Benini,et al.  Anomaly Detection using Autoencoders in High Performance Computing Systems , 2018, DDC@AI*IA.

[47]  Jian Yang,et al.  Two-dimensional PCA: a new approach to appearance-based face representation and recognition , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[48]  Yangdi Xu,et al.  Passive wireless sensing for unsupervised human activity recognition in healthcare , 2017, 2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC).

[49]  Pablo Tamayo,et al.  Visualizing and interpreting single-cell gene expression datasets with Similarity Weighted Nonnegative Embedding , 2018, bioRxiv.

[50]  J. Kruskal.  Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis , 1964 .

[51]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[52]  Jihoon Hong,et al.  A fall detection system using low resolution infrared array sensor , 2014, 2014 IEEE 25th Annual International Symposium on Personal, Indoor, and Mobile Radio Communication (PIMRC).

[53]  Karl Woodbridge,et al.  Doppler Based Detection of Multiple Targets in Passive Wi-Fi Radar Using Underdetermined Blind Source Separation , 2018, 2018 International Conference on Radar (RADAR).

[54]  L Tian,et al.  Wearable sensors: modalities, challenges, and prospects. , 2018, Lab on a chip.

[55]  Hiromitsu Nishizaki,et al.  Data augmentation and feature extraction using variational autoencoder for acoustic modeling , 2017, 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

[56]  Haiquan Chen,et al.  Classification of Human Activity Based on Radar Signal Using 1-D Convolutional Neural Network , 2020, IEEE Geoscience and Remote Sensing Letters.

[57]  Kai-Tai Song,et al.  Human activity recognition using a mobile camera , 2011, 2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).

[58]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[59]  Jian Liu,et al.  Classification of Daily Activities for the Elderly Using Wearable Sensors , 2017, Journal of healthcare engineering.

[60]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[61]  Tao Dong,et al.  A Review of Wearable Technologies for Elderly Care that Can Accurately Track Indoor Position, Recognize Physical Activities and Monitor Vital Signs in Real Time , 2017, Sensors.

[62]  Dr.T. Velmurugan,et al.  Efficiency of k-Means and K-Medoids Algorithms for Clustering Arbitrary Data Points , 2012 .

[63]  Pierre Baldi,et al.  Autoencoders, Unsupervised Learning, and Deep Architectures , 2011, ICML Unsupervised and Transfer Learning.

[64]  Moeness G. Amin,et al.  Motion Classification Using Kinematically Sifted ACGAN-Synthesized Radar Micro-Doppler Signatures , 2020, IEEE Transactions on Aerospace and Electronic Systems.

[65]  Jaakko Astola,et al.  Ground moving target classification by using DCT coefficients extracted from micro-Doppler radar signatures and artificial neuron network , 2011, 2011 MICROWAVES, RADAR AND REMOTE SENSING SYMPOSIUM.