A Transfer Learning Algorithm Applied to Human Activity Recognition

被引：0

作者：

Zhao H. ^{[1
]}

Chen J.-W. ^{[1
]}

Shi H. ^{[1
]}

Wang X. ^{[1
]}

机构：

[1] School of Computer Science & Engineering, Northeastern University, Shenyang

来源：

Dongbei Daxue Xuebao/Journal of Northeastern University | 2022年 / 43卷 / 06期

关键词：

body area network; human activity recognition; machine learning; physiological signal; transfer learning;

D O I：

10.12068/j.issn.1005-3026.2022.06.003

中图分类号：

学科分类号：

摘要：

Collecting wearable motion sensor signals and using transfer learning to overcome the inconsistency of data distribution to identify the daily behavior of the human body are very popular technologies. Using wearable sensors to collect signals will result in generating noise samples that affect the transfer effect. Traditional algorithms lack the processing of these samples. To solve this problem, the traditional algorithm was improved by introducing a sample screening algorithm based on Mahalanobis distance, and a transfer learning algorithm T-WMD was proposed that can be used for human activity recognition. And compared with other five algorithms on two public human activity recognition data sets, the results show that the algorithm proposed in this paper can effectively improve the effect of transfer learning. © 2022 Northeastern University. All rights reserved.

引用

页码：776 / 782

页数：6

共 20 条

[1]

Wang Cheng-liang, Wang Xiao-jun, Daily activity recognition based on triaxial accelerometer of elderly people [J], Acta Electronica Sinica, 45, 3, pp. 570-576, (2017)

[2]

Ramirez H, Velastin S, Fabregas E, Et al., Fall detection using human skeleton features[J], IEEE Access, 4, pp. 73-78, (2021)

[3]

Fan Chang-jun, Gao Fei, Online human activity recognition based on wireless body area network, Journal of Chinese Computer Systems, 41, 1, pp. 72-77, (2020)

[4]

Yin Xiao-ling, Chen Xiao-jiang, Xia Qi-shou, Et al., Human motion state recognition based on smart phone built-in sensor [J], Journal on Communications, 40, 3, pp. 157-169, (2019)

[5]

Fu Z, He X, Wang E, Et al., Personalized human activity recognition based on integrated wearable sensor and transfer learning[J], Sensors, 21, 3, (2021)

[6]

Zheng Zeng-wei, Du Jun-jie, Huo Mei-mei, Et al., Review of human activity recognition based on wearable sensors [ J], Journal of Computer Applications, 38, 5, pp. 1223-1229, (2018)

[7]

Hou W X, Wang J D, Tan X, Et al., Cross-domain speech recognition with unsupervised character-level distribution matching[C], Interspeech 2021, pp. 1-5, (2021)

[8]

Peng Yu-he, Chen Xiang, Chen Shuang-wu, Et al., Cross-domain abnormal traffic detection based on transfer learning [ J ], Journal of Beijing University of Posts and Telecommunications, 44, 2, pp. 33-39, (2021)

[9]

Soleimani E, Nazerfard E., Cross-subject transfer learning in human activity recognition systems using generative adversarial networks [ J ], Neurocomputing, 426, pp. 26-34, (2021)

[10]

Niu H, Nguyen D, Yonekawa K, Et al., Multi-source transfer learning for human activity recognition in smart homes[C], 2020 IEEE International Conference on Smart Computing (SMARTCOMP), pp. 274-277, (2020)

← 1 2 →