DiamondNet: A Neural-Network-Based Heterogeneous Sensor Attentive Fusion for Human Activity Recognition

doi:10.1109/TNNLS.2023.3285547

	DiamondNet: A Neural-Network-Based Heterogeneous Sensor Attentive Fusion for Human Activity Recognition
	Zhu, Yida 1; Luo, Haiyong 2; Chen, Runze 1; Zhao, Fang 1
	2023-07-04
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
页码	11
摘要	With the proliferation of intelligent sensors integrated into mobile devices, fine-grained human activity recognition (HAR) based on lightweight sensors has emerged as a useful tool for personalized applications. Although shallow and deep learning algorithms have been proposed for HAR problems in the past decades, these methods have limited capability to exploit semantic features from multiple sensor types. To address this limitation, we propose a novel HAR framework, DiamondNet, which can create heterogeneous multisensor modalities, denoise, extract, and fuse features from a fresh perspective. In DiamondNet, we leverage multiple 1-D convolutional denoising autoencoders (1-D-CDAEs) to extract robust encoder features. We further introduce an attention-based graph convolutional network to construct new heterogeneous multisensor modalities, which adaptively exploit the potential relationship between different sensors. Moreover, the proposed attentive fusion subnet, which jointly employs a global-attention mechanism and shallow features, effectively calibrates different-level features of multiple sensor modalities. This approach amplifies informative features and provides a comprehensive and robust perception for HAR. The efficacy of the DiamondNet framework is validated on three public datasets. The experimental results demonstrate that our proposed DiamondNet outperforms other state-of-the-art baselines, achieving remarkable and consistent accuracy improvements. Overall, our work introduces a new perspective on HAR, leveraging the power of multiple sensor modalities and attention mechanisms to significantly improve the performance.
关键词	Convolutional denoising autoencoders (CDAEs) global-attention mechanism graph convolutional networks human activity recognition (HAR) multisensor modality self-attention mechanism
DOI	10.1109/TNNLS.2023.3285547
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program[2022YFB3904700] ; National Natural Science Foundation of China[62261042] ; National Natural Science Foundation of China[62002026] ; Key Research Projects of the Joint Research Fund for Beijing Natural Science Foundation ; Fengtai Rail Transit Frontier Research Joint Fund[L221003] ; Beijing Natural Science Foundation[4232035] ; Beijing Natural Science Foundation[4212024] ; Beijing Natural Science Foundation[4222034] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDA28040500] ; Fundamental Research Funds for the Central Universities[2022RC13] ; BUPT Excellent Ph.D. Students Foundation[CX2020220] ; Open Project of the Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:001025578500001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21250
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Luo, Haiyong; Zhao, Fang
作者单位	1.Beijing Univ Posts & Telecommun, Sch Software Engn, Beijing 100876, Peoples R China 2.Chinese Acad Sci, Res Ctr Ubiquitous Comp Syst, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Yida,Luo, Haiyong,Chen, Runze,et al. DiamondNet: A Neural-Network-Based Heterogeneous Sensor Attentive Fusion for Human Activity Recognition[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:11.
APA	Zhu, Yida,Luo, Haiyong,Chen, Runze,&Zhao, Fang.(2023).DiamondNet: A Neural-Network-Based Heterogeneous Sensor Attentive Fusion for Human Activity Recognition.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,11.
MLA	Zhu, Yida,et al."DiamondNet: A Neural-Network-Based Heterogeneous Sensor Attentive Fusion for Human Activity Recognition".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):11.