Recent advances in wearable electromechanical sensors—Moving towards machine learning-assisted wearable sensing systems. (January 2023)

• Record Type: Journal Article
• Authors: Dai, Nian; Lei, Iek Man; Li, Zhaoyang; Li, Yi; Fang, Peng; Zhong, Junwen
• Is Part Of: Nano energy. Volume 105(2023)
• Publication Date: 2023-01
• Subjects: Wearable electronics -- Electromechanical -- Sensors -- Machine learning -- Human-machine interface; Nanoscience -- Periodicals; Nanotechnology -- Periodicals; Nanostructured materials -- Periodicals; Power resources -- Technological innovations -- Periodicals; Nanoscience; Nanostructured materials; Nanotechnology; Power resources -- Technological innovations; Periodicals; 621.042
• DOI: 10.1016/j.nanoen.2022.108041
• Languages: English
• ISSNs: 2211-2855

Abstract

Abstract: With the assistance of powerful machine learning algorithms, data collecting and processing efficiency of wearable electromechanical sensors are highly improved. Meanwhile, the functions and applications of these intelligent sensing systems are widely enhanced and expanded. In this review, wearable electromechanical sensors with various working mechanisms and their typical usage for monitoring human physiological signals are outlined. The recent advances of machine learning-assisted wearable electromechanical sensing systems in specific applications of tactile perception, gesture/gait recognition, and health care are then summarized and discussed. Finally, current existing limitations and future perspectives are discussed. The progress of intelligent wearable electromechanical sensing systems will promote the development in the domains of human-machine interface (HMI), soft robotics, metaverse, etc . Graphical Abstract: In this review, the recent advances of machine learning-assisted wearable electromechanical sensing systems with different working mechanisms and in specific applications of tactile perception, gesture/gait recognition, and health care are summarized and discussed. ga1 Highlights: Progress in wearable electromechanical sensors based on different working mechanisms is reviewed. The recent applications of machine learning assisted-wearable electromechanical sensing systems are summarized. The existing limitations and future perspectives in this field are discussed.