基于多视图半监督集成学习的人体动作识别算法

doi:10.11959/j.issn.2096-109x.2021061

Abstract

Abstract:

Mass labeled data are hard to get in mobile devices.Inadequate training leads to bad performance of classifiers in human action recognition.To tackle this problem, a multi-view semi-supervised ensemble learning method was proposed.First, data of two different inertial sensors was used to construct two feature views.Two feature views and two base classifiers were combined to construct co-training framework.Then, the confidence degree was redefined in multi-class task and was combined with active learning method to control predict pseudo-label result in each iteration.Finally, extended training data was used as input to train LightGBM.Experiments show that the method has good performance in precision rate, recall rate and F1 value, which can effectively detect different human action.

Key words: human action recognition, semi-supervised learning, few-shot, LightGBM

CLC Number:

TP393

Shengnan CHEN, Xinmin FAN. Human action recognition method based on multi-view semi-supervised ensemble learning[J]. Chinese Journal of Network and Information Security, 2021, 7(3): 141-148.

Figures/Tables 8

References 19

[1]	LIU L J , LEI X L , CHEN B F ,et al. Human action recognition based on inertial sensors and complexity classification[J]. Journal of Information Technology Research, 2019: 18-35.
[2]	周启臻, 邢建春, 杨启亮 ,等. 基于连续图像深度学习的 Wi-Fi人体行为识别方法[J]. 通信学报, 2020,41(8): 43-54.
	ZHOU Q Z , XING J C , HAN Q L ,et al. Sequential image deep learning-based Wi-Fi human activity recognition method[J]. Journal on Communications, 2020,41(8): 43-54.
[3]	钱慧芳, 易剑平, 付云虎 . 基于深度学习的人体动作识别综述[J]. 计算机科学与探索, 2021(1): 1-20.
	QIAN H F , YI J P , FU Y H . Human action recognition based on deep learning：a review[J]. Journal of Frontiers of Computer Science ＆ Technology, 2021(1): 1-20.
[4]	张会珍, 刘云麟, 任伟建 ,等. 人体行为识别特征提取方法综述[J]. 吉林大学学报(信息科学版), 2020,38(3): 360-370.
	ZHANG H J , LIU Y L , REN J W ,et al. Human behavior recognition feature extraction method:a survey[J]. Journal of Jilin University (Information Science Edition), 2020,38(3): 360-370.
[5]	邹建 . 基于BP神经网络的人体行为识别[J]. 网络与信息安全学报, 2017,3(9): 55-60.
	ZOU J . Human action recognition based on back propagation neural network[J]. Chinese Journal of Network and Information Security, 2017,3(9): 55-60.
[6]	WANG Y J , WU K S , LIONEL M N . WiFall:device-free fall detection by wireless networks[J]. IEEE Transactions on Mobile Computing, 2017,16(2): 581-594
[7]	肖玲, 潘浩 . 基于Wi-Fi信号的人体动作识别系统[J]. 北京邮电大学学报, 2018,41(3): 119-124.
	XIAO L , PAN H . Human activity recognition system based on Wi-Fi signal[J]. Journal of Beijing University of Posts and Telecommunications, 2018,41(3): 119-124.
[8]	CAO S M , YANG P L , LI X Y ,et al. iPand:accurate gesture input with smart acoustic sensing on hand[C]// 15th Annual IEEE International Conference on Sensing,Communication,and Networking(SECON). 2018.
[9]	LIU Y T , ZHANG Y A , ZENG M . Novel algorithm for hand gesture recognition utilizing a wrist-worn inertial sensor[J]. IEEE Sensors Journal, 2018,18(24): 10085-10095.
[10]	殷晓玲, 陈晓江, 夏启寿 ,等. 基于智能手机内置传感器的人体运动状态识别[J]. 通信学报, 2019,40(3): 161-173.
	YING X L , CHEN X J , XIA Q S ,et al. Human motion state recognition based on smart phone built-in sensor[J]. Journal on Communications, 2019,40(3): 161-173.
[11]	WANG Y , CANG H N , YU H N . A survey on wearable sensor modality centred human activity recognition in health care[J]. Expert Systems with Applications, 2019,137: 167-190.
[12]	ALEJANDRO B , YAGO S , PEDRO I . Evolutionary design of convolutional neural networks for human activity recognition in sensor-rich environments[J]. Sensors, 2018,18(4): 1288-1312
[13]	张儒鹏, 于亚新, 张康 ,等. 基于 OI-LSTM 神经网络结构的人类动作识别模型研究[J]. 计算机科学与探索, 2018,12(12): 1926-1939.
	ZHANG R P , YU Y X , ZHANG K ,et al. Research on human action recognition model based on OI-LSTM neural network structure[J]. Journal of Frontiers of Computer Science ＆ Technology, 2018,12(12): 1926-1939.
[14]	韩嵩, 韩秋弘 . 半监督学习研究的述评[J]. 计算机工程与应用, 2020(6): 19-27.
	HAN S , HAN Q H . Review of semi-supervised learning research[J]. Computer Engineering and Applications, 2020(6): 19-27.
[15]	尹玉, 詹永照, 姜震 . 伪标签置信选择的半监督集成学习视频语义检测[J]. 计算机应用, 2019,39(8): 2204-2209.
	YIN Y , ZHAN Y Z , JIANG Z ,et al. Semi-supervised ensemble learning for video semantic detection based on pseudo-label confidence selection[J]. Journal of Computer Applications, 2019,39(8): 2204-2209.
[16]	GUO L K , QI M , FINLEY T ,et al. LightGBM:a highly efficient gradient boosting decision tree[C]// Advances in Neural Information Processing Systems(NIPS). 2017: 3146-3154.
[17]	ANGUITA D , GHIO A , ONETO L ,et al. A public domain dataset for human activity recognition using smartphones[C]// European Symposium on Artificial Neural Networks,Computational Intelligence and Machine Learning (ESANN). 2013.
[18]	ROSENBERG C , HEBERT M , SCHNEIDERMAN H . Semi-supervised self-training of object detection models[C]// IEEE Workshops on Applications of Computer Vision (WACV). 2005: 29-36.
[19]	ZHOU Z H , LI M . Semisupervised regression with co-trainingstyle algorithms[J]. IEEE Transactions on Knowledge and Data Engineering, 2007: 1479-1493.

Metrics

Recommended 0

No Suggested Reading articles found!

分类器组合	M_Precision	M_Recall	M_F1
(SVM,SVM)(KNN,KNN)(SVM,KNN)(KNN,SVM)	0.868 00.784 30.888 40.693 2	0.824 60.732 10.879 40.656 6	0.819 60.757 30.880 30.674 4

方法	运行时间/s	M_Precision	M_Recall	M_F1
模型1	0.15	0.840 3	0.811 0	0.810 3
模型2	0.11	0.695 5	0.731 7	0.705 7
模型3	0.65	0.875 1	0.874 3	0.873 9
模型4	0.54	0.893 2	0.8854	0.889 6
模型5	0.95	0.967 0	0.9650	0.965 5
模型6	0.77	0.951 3	0.948 6	0.949 5

Human action recognition method based on multi-view semi-supervised ensemble learning

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 19

Related Articles 2

Metrics

Recommended 0

[1]	Renfeng CHEN, Hongbin ZHU. Research on credit card transaction security supervision based on PU learning [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 73-78.
[2]	Jian ZOU. Human action recognition based on back propagation neural network [J]. Chinese Journal of Network and Information Security, 2017, 3(9): 55-60.