Deep activity recognition on imaging sensor data

• Published in: Electronics letters Vol. 55; no. 17; pp. 928 - 931
• Main Authors: Setiawan, Feri, Yahya, Bernardo Nugroho, Lee, Seok-Lyong
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 22.08.2019
• Subjects: activity recognition task; authors; computer vision; computer vision domain; deep activity recognition; deep learning; encoding technique; Gramian Angular Field; Image and vision processing and display technology; image motion analysis; image recognition; image representation; image sensors; learning (artificial intelligence); local temporal relationship; popular sensor‐based activity recognition datasets; recent success; sensor data; state‐of‐the‐art approaches; temporal correlation; sensor data; state-of-the-art approaches; activity recognition task; temporal correlation; image motion analysis; image sensors; recent success; deep learning; Gramian Angular Field; popular sensor-based activity recognition datasets; local temporal relationship; computer vision domain; computer vision; image representation; encoding technique; learning (artificial intelligence); deep activity recognition; image recognition; authors
• ISSN: 0013-5194; 1350-911X; 1350-911X
• DOI: 10.1049/el.2019.0906

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.