Visual analysis of action using machine learning and distributed expectation-maximization algorithm. (October 2022)

• Record Type: Journal Article
• Authors: Mao, Feng; Han, ShiHao
• Is Part Of: Computers & electrical engineering. Volume 103(2022)
• Publication Date: 2022-10
• Subjects: Distributed EM algorithm -- Machine learning -- Technical analysis effect -- Video of things -- visualization; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108293
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: We propose the novel visual analysis system Video of Things (VoT) using machine learning and a distributed Expectation-Maximization (EM) method. The VoT-enabled approach is proposed to perform a visual analysis of action in the context of wireless sensor systems. For the technical impact analysis of VoT, we used the EM algorithm. Furthermore, we investigate the notion of merging the clustered grid with the uniform filter in the target tracking of the distributed EM of particle filtering. We grid the network monitoring region with the technical impact analysis of VoT, then clusters the whole sensor nodes, build the system structure using a real scenario of visual actions in the VoT, and thoroughly analyze the system implementation process. Finally, we present investigations to validate the performance of the proposed research approach with a technical impact analysis of VoT. According to the study findings, the proposed VoT-based system can play an essential role in the recognition and technical impact analysis of table tennis activity.