Human Fall Detection Based on Machine Learning Using a THz Radar System

A terahertz (THz) frequency modulated continuous wave radar system was used for human fall detection in this paper. Five features were extracted from the range-time spectrograms and time-frequency spectrograms for further classification. Eight machine learning classifiers have been implemented including the logistic regression, the support vector machine, the k-nearest neighbor, the decision tree, the Naive Bayes, the quadratic discriminant analysis, the adaptive boosting and the back propagation neural network. Different kinds of combinations of five features were tested to obtain the optimum combination when 10 cross-validation and 100 repeated time tests were considered. In the experiment, total 600 motions including 300 falls and 300 non-falls from 10 different subjects were acquired by the THz radar system in a normal room. Eight machine learning classifiers all showed a good performance with AUC values larger than 0.921 when detecting falls.

[1]  Paul Leroux,et al.  Analysis of an Indoor Biomedical Radar-Based System for Health Monitoring , 2013, IEEE Transactions on Microwave Theory and Techniques.

[2]  Paul Leroux,et al.  Optimized SFCW radar sensor aiming at fall detection in a real room environment , 2013, 2013 IEEE Topical Conference on Biomedical Wireless Technologies, Networks, and Sensing Systems.

[3]  Moeness Amin,et al.  Fall Detection Using Deep Learning in Range-Doppler Radars , 2018, IEEE Transactions on Aerospace and Electronic Systems.

[4]  Marjorie Skubic,et al.  Doppler Radar Fall Activity Detection Using the Wavelet Transform , 2015, IEEE Transactions on Biomedical Engineering.

[5]  Jianxin Wu,et al.  Linear Regression-Based Efficient SVM Learning for Large-Scale Classification , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[6]  Wei Sun,et al.  A Survey of Fall Detection Algorithm for Elderly Health Monitoring , 2015, 2015 IEEE Fifth International Conference on Big Data and Cloud Computing.

[7]  Liang Liu,et al.  Automatic fall detection based on Doppler radar motion signature , 2011, 2011 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops.

[8]  Hehua Zhang,et al.  Combining Amplitude Spectrum Area with Previous Shock Information Using Neural Networks Improves Prediction Performance of Defibrillation Outcome for Subsequent Shocks in Out-Of-Hospital Cardiac Arrest Patients , 2016, PloS one.

[9]  Yongzhen Li,et al.  Suppression of Cross-Channel Interference Based on the Fractional Fourier Transform in Polarimetric Radar , 2013, IEEE Geoscience and Remote Sensing Letters.

[10]  Hong Rong,et al.  Efficient k-Nearest Neighbor Classification Over Semantically Secure Hybrid Encrypted Cloud Database , 2018, IEEE Access.

[11]  Wenbing Tao,et al.  Radar-based fall detection based on Doppler time-frequency signatures for assisted living , 2015 .

[12]  Eun Yi Kim.  Vision-based wheelchair navigation using geometric AdaBoost learning , 2017 .

[13]  Laura Montanini,et al.  A Footwear-Based Methodology for Fall Detection , 2018, IEEE Sensors Journal.

[14]  Antoni Broquetas,et al.  Modeling Fast Boat Motion Impact on Satellite SAR MTI Systems , 2015, IEEE Geoscience and Remote Sensing Letters.

[15]  Jacques Demongeot,et al.  A Novel Monitoring System for Fall Detection in Older People , 2018, IEEE Access.

[16]  R. Herrmann,et al.  M-sequence-based ultra-wideband sensor network for vitality monitoring of elders at home , 2015 .

[17]  Mi He,et al.  Combining multiple ECG features does not improve prediction of defibrillation outcome compared to single features in a large population of out-of-hospital cardiac arrests , 2015, Critical Care.

[18]  Yimin Zhang,et al.  Radar Signal Processing for Elderly Fall Detection: The future for in-home monitoring , 2016, IEEE Signal Processing Magazine.

[19]  Bin Deng,et al.  Micro-Doppler Ambiguity Resolution for Wideband Terahertz Radar Using Intra-Pulse Interference , 2017, Sensors.