中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Disagreement-based class incremental random forest for sensor-based activity recognition

文献类型：期刊论文

作者Hu, Chunyu2,3,4; Chen, Yiqiang4,5,6; Hu, Lisha1; Yu, Han7; Lu, Dianjie3,8
刊名KNOWLEDGE-BASED SYSTEMS
出版日期2022-03-05
卷号239页码:15
关键词Class incremental learning Activity recognition Random forest Semi-supervised learning
ISSN号0950-7051
DOI10.1016/j.knosys.2021.108044
英文摘要Activity recognition plays a key role in many fields, such as health monitoring and elderly care. Handling changes in user habits is a significant technical challenge in activity recognition. Ideally, a model should adapt to newly emerging classes and concept drift dynamically. This paper proposes a novel semi-supervised class incremental learning method, namely, disagreement-based class incremental random forest (Di-CIRF). The proposed model can detect newly emerging classes and update a previously established activity recognition model through streaming data. First, it is necessary to identify novel candidates by employing the disagreement-based confidence voting mechanism and minimum bounding box (MBB)-based separation detection to annotate newly emerging data accurately. Then, the coarse coding-based cohesion detection strategy is adopted to filter out the true novelty instances. This paper also proposes the iterative MBB-based splitting strategy and the pseudo-instance generation mechanism in Di-CIRF for updating the activity model without retaining the trained data. According to experimental results on four public activity recognition datasets, Di-CIRF outperforms the state-of-the-art methods.
资助项目Key-Area Research and Development Program of Guangdong Province, China[2019B010109001] ; National Natural Science Foundation of China[62002187] ; National Natural Science Foundation of China[61972237] ; Nat-ural Science Foundation of Hebei Province, China[F2019207061] ; Nanyang Technological University, Singapore, through the Nanyang Assistant Professorship (NAP)
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000806866700004
出版者ELSEVIER
源URL[http://119.78.100.204/handle/2XEOYT63/19602]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Hu, Chunyu; Hu, Lisha
作者单位1.Hebei Univ Econ & Business, Inst Informat Technol, Shijiazhuang, Hebei, Peoples R China
2.Qilu Univ Technol, Sch Comp Sci & Technol, Shandong Acad Sci, Jinan, Peoples R China
3.Shandong Prov Key Lab Distributed Comp Software N, Jinan, Peoples R China
4.Shandong Acad Intelligent Comp Technol, Jinan, Peoples R China
5.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
6.Univ Chinese Acad Sci, Beijing, Peoples R China
7.Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore
8.Shandong Normal Univ, Sch Informat Sci & Engn, Jinan, Peoples R China
推荐引用方式
GB/T 7714		 Hu, Chunyu,Chen, Yiqiang,Hu, Lisha,et al. Disagreement-based class incremental random forest for sensor-based activity recognition[J]. KNOWLEDGE-BASED SYSTEMS,2022,239:15.
APA Hu, Chunyu,Chen, Yiqiang,Hu, Lisha,Yu, Han,&Lu, Dianjie.(2022).Disagreement-based class incremental random forest for sensor-based activity recognition.KNOWLEDGE-BASED SYSTEMS,239,15.
MLA Hu, Chunyu,et al."Disagreement-based class incremental random forest for sensor-based activity recognition".KNOWLEDGE-BASED SYSTEMS 239(2022):15.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。