F-norm based low-power motion recognition on wearable devices in the presence of outlier motions^☆,☆☆

Abstract

Motion recognition refers to the intelligent recognition of human motion using data collected from wearable sensors, which exceedingly has gained significant interest from both academic and industrial fields. However, temporary-sudden activities caused by accidental behavior pose a major challenge to motion recognition and have been largely overlooked in existing works. To address this problem, the multi-dimensional time series of motion data is modeled as a Time-Frequency (TF) tensor, and the original challenge is transformed into a problem of outlier-corrupted tensor pattern recognition, where transient sudden activity data are considered as outliers. Since the TF tensor can capture the latent spatio-temporal correlations of the motion data, the tensor MPCA is used to derive the principal spatio-temporal pattern of the motion data. However, traditional MPCA uses the squared F-norm as the projection distance measure, which makes it sensitive to the presence of outlier motion data. Therefore, in the proposed outlier-robust MPCA scheme, the F-norm with the desirable geometric properties is used as the distance measure to simultaneously mitigate the interference of outlier motion data while preserving rotational invariance. Moreover, to reduce the complexity of outlier-robust motion recognition, we impose the proposed outlier-robust MPCA scheme on the traditional MPCANet which is a low-complexity deep learning network. The experimental results show that our proposed outlier-robust MPCANet can simultaneously improve motion recognition performance and reduce the complexity, especially in practical scenarios where the real-time data is corrupted by temporary-sudden activities.

Keywords

Motion recognition / F-norm / Time-frequency tensor / MPCANet / Low-power consumption

References

[1] S. Beniczky, P. Karoly, E. Nurse, P. Ryvlin, M. Cook, Machine learning and wearable devices of the future, Epilepsia 62 (2021) S116-S124.

[2] S. Majumder, T. Mondal, M.J. Deen, Wearable sensors for remote health monitoring, Sensors 17 (1) (2017) 130.

[3] M. Elhoushi, J. Georgy, M. Korenberg, A. Noureldin, Broad motion mode recognition for portable navigation, in: Proceedings of the 27th International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS+ 2014), 2014, pp. 1768-1773.

[4] M. Susi, D. Borio, G. Lachapelle,Accelerometer signal features and classification algorithms for positioning applications, in:Proceedings of the 2011 International Technical Meeting of the Institute of Navigation, 2011, pp. 158-169.

[5] L. Pei, R. Chen, J. Liu, W. Chen, H. Kuusniemi, T. Tenhunen, T. Kröger, Y. Chen, H. Leppäkoski, J. Takala, Motion recognition assisted indoor wireless navigation on a mobile phone, in: Proceedings of the 23rd International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS 2010), 2010, pp. 3366-3375.

[6] H.-G. Kim, G.Y. Kim, J.Y. Kim, Music recommendation system using human activity recognition from accelerometer data, IEEE Trans. Consum. Electron. 65 (3) (2019) 349-358.

[7] G. Ding, J. Tian, J. Wu, Q. Zhao, L. Xie, Energy efficient human activity recognition using wearable sensors, in: 2018 IEEE Wireless Communications and Networking Conference Workshops (WCNCW), IEEE, 2018, pp. 379-383.

[8] T. Ahmad, J. Wu, SDIGRU: spatial and deep features integration using multilayer gated recurrent unit for human activity recognition, IEEE Trans. Comput. Soc. Syst. 11 (1) (2024) 973-985.

[9] T.D. Nguyen, J.H. Park, M.I. Hossain, M.D. Hossain, S.-J. Lee, J.W. Jang, S.H. Jo, L.N. Huynh, T.K. Tran, E.-N. Huh, Performance analysis of data parallelism technique in machine learning for human activity recognition using LSTM, in: 2019 IEEE Interna-tional Conference on Cloud Computing Technology and Science (CloudCom), IEEE, 2019, pp. 387-391.

[10] J. He, Z. Zhang, X. Wang, S. Yang, A low power fall sensing technology based on FD-CNN, IEEE Sens. J. 19 (13) (2019) 5110-5118.

[11] F. Moya Rueda, R. Grzeszick, G.A. Fink, S. Feldhorst, M. Ten Hompel, Convolutional neural networks for human activity recognition using body-worn sensors, in: Infor-matics, vol. 5, MDPI, 2018, p. 26.

[12] W. Qi, H. Su, C. Yang, G. Ferrigno, E. De Momi, A. Aliverti, A fast and robust deep convolutional neural networks for complex human activity recognition using smart-phone, Sensors 19 (17) (2019) 3731.

[13] T. Ahmad, J. Wu, H.S. Alwageed, F. Khan, J. Khan, Y. Lee, Human activity recog-nition based on deep-temporal learning using convolution neural networks features and bidirectional gated recurrent unit with features selection, IEEE Access 11 (2023) 33148-33159.

[14] Q. Ding, X. Zhao, J. Han, C. Bu, C. Wu, Adaptive hybrid classifier for myoelectric pattern recognition against the interferences of outlier motion, muscle fatigue, and electrode doffing, IEEE Trans. Neural Syst. Rehabil. Eng. 27 (5) (2019) 1071-1080.

[15] Q. Ding, X. Zhao, Z. Li, J. Han, An incremental emg classification model to detect and recognize randomly-occurred outlier motion, in: 2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), IEEE, 2017, pp. 1050-1055.

[16] N.A. Choudhury, B. Soni, In-depth analysis of design & development for sensor-based human activity recognition system, Multimed. Tools Appl. 83 (29) (2024) 73233-73272.

[17] M. Munoz-Organero, Outlier detection in wearable sensor data for human activity recognition (HAR) based on DRNNs, IEEE Access 7 (2019) 74422-74436.

[18] T.-H. Chan, K. Jia, S. Gao, J. Lu, Z. Zeng, Y. Ma, PCANet: a simple deep learning base-line for image classification?, IEEE Trans. Image Process. 24 (12) (2015) 5017-5032.

[19] D. Wang, Y. Si, W. Yang, G. Zhang, T. Liu, A novel heart rate robust method for short-term electrocardiogram biometric identification, Appl. Sci. 9(1) (2019) 201-220.

[20] S. Gan, Q. Zhuang, B. Gong, Human-computer interaction based interface design of intelligent health detection using PCANet and multi-sensor information fusion, Comput. Methods Programs Biomed. 216 (2022) 106637.

[21] B. Pan, C. Li, H. Che, M.-F. Leung, K. Yu, Low-rank tensor regularized graph fuzzy learning for multi-view data processing, IEEE Trans. Consum. Electron. 70 (1) (2024) 2925-2938.

[22] H. Che, B. Pan, M.-F. Leung, Y. Cao, Z. Yan, Tensor factorization with sparse and graph regularization for fake news detection on social networks, IEEE Trans. Comput. Soc. Syst. (2023) 1-11.

[23] X. Peng, C. Lu, Z. Yi, H. Tang, Connections between nuclear-norm and Frobenius-norm-based representations, IEEE Trans. Neural Netw. Learn. Syst. 29 (1) (2016) 218-224.

[24] X. Peng, Z. Yu, Z. Yi, H. Tang, Constructing the 𝑙2-graph for robust subspace learning and subspace clustering, IEEE Trans. Cybern. 47 (4) (2016) 1053-1066.

[25] H. Lu, K.N. Plataniotis, A.N. Venetsanopoulos, MPCA: multilinear principal compo-nent analysis of tensor objects, IEEE Trans. Neural Netw. 19 (1) (2008) 18-39.

[26] Y. Guo, Y. Zhou, Z. Zhang, Fault diagnosis of multi-channel data by the CNN with the multilinear principal component analysis, Measurement 171 (2021) 108513.

[27] Y. Zhang, K. Xing, R. Bai, D. Sun, Z. Meng, An enhanced convolutional neural net-work for bearing fault diagnosis based on time-frequency image, Measurement 157 (2020) 107667.

[28] F. Hlawatsch, G.F. Boudreaux-Bartels, Linear and quadratic time-frequency signal representations, IEEE Signal Process. Mag. 9(2) (1992) 21-67.

[29] G.L. Santos, P.T. Endo, K.H.d.C. Monteiro, E. d, S. Rocha, I. Silva, T. Lynn, Accelerometer-based human fall detection using convolutional neural networks, Sen-sors 19 (7) (2019) 1644.

[30] L. Tong, H. Ma, Q. Lin, J. He, L. Peng, A novel deep learning Bi-GRU-I model for real-time human activity recognition using inertial sensors, IEEE Sens. J. 22 (6) (2022) 6164-6174.

[31] G. Wang, Q. Li, L. Wang, Y. Zhang, Z. Liu, CMFALL: a cascade and parallel multi-state fall detection algorithm using waist-mounted tri-axial accelerometer signals, IEEE Trans. Consum. Electron. 66 (3) (2020) 261-270.