Deep activity recognition on imaging sensor data. Issue 17 (1st August 2019)

• Record Type: Journal Article
• Authors: Setiawan, Feri; Yahya, Bernardo Nugroho; Lee, Seok‐Lyong
• Is Part Of: Electronics letters. Volume 55:Issue 17(2019)
• Page Start: 928
• Page End: 931
• Publication Date: 2019-08-01
• Subjects: computer vision -- image representation -- image motion analysis -- image recognition -- image sensors -- learning (artificial intelligence); sensor data -- image representation -- activity recognition task -- Gramian Angular Field -- encoding technique -- local temporal relationship -- temporal correlation -- popular sensor‐based activity recognition datasets -- authors -- state‐of‐the‐art approaches -- deep activity recognition -- recent success -- deep learning -- computer vision domain; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2019.0906
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : Inspired by the recent success of deep learning (DL) approaches in computer vision domain, this Letter proposes a framework to encode the sensor data into an image representation for the activity recognition task. The signal from sensors is encoded based on the Gramian Angular Field. The encoding technique increases the dimension of the data, captures a local temporal relationship in terms of temporal correlation between time intervals on the geometric interpretation, and can be easily applied to the pre‐trained DL architecture. The proposed framework is examined with respect to six popular sensor‐based activity recognition datasets. Using the authors' framework, the results show that their approach outperforms most of the state‐of‐the‐art approaches.