Abstract
The position of on-body motion sensors plays an important role in human activity recognition. Most often, mobile phone sensors at the trouser pocket or an equivalent position are used for this purpose. However, this position is not suitable for recognizing activities that involve hand gestures, such as smoking, eating, drinking coffee and giving a talk. To recognize such activities, wrist-worn motion sensors are used. However, these two positions are mainly used in isolation. To use richer context information, we evaluate three motion sensors (accelerometer, gyroscope and linear acceleration sensor) at both wrist and pocket positions. Using three classifiers, we show that the combination of these two positions outperforms the wrist position alone, mainly at smaller segmentation windows. Another problem is that less-repetitive activities, such as smoking, eating, giving a talk and drinking coffee, cannot be recognized easily at smaller segmentation windows unlike repetitive activities, like walking, jogging and biking. For this purpose, we evaluate the effect of seven window sizes (2–30 s) on thirteen activities and show how increasing window size affects these various activities in different ways. We also propose various optimizations to further improve the recognition of these activities. For reproducibility, we make our dataset publicly available.
Highlights
On-body motion sensors are commonly used in recognizing various activities
We use these short notations in the remainder of the paper, where W stands for wrist, P for pocket, WP for both wrist and pocket positions, A for accelerometer, G for gyroscope and L for linear acceleration sensor
Extending our previous work [24], we evaluated the effect of combining motion sensors at the wrist and pocket positions, such as an accelerometer, a gyroscope and a linear acceleration sensor
Summary
On-body motion sensors are commonly used in recognizing various activities. For example, mobile phone motion sensors have been a popular choice for activity recognition at the trouser pocket or equivalent position (referred to as the pocket in the rest of the paper) [1,2]. Wrist-worn motion sensors are being used for human activity recognition [3,4,5]. Some activities, such as smoking, eating, writing, typing, drinking coffee and giving a talk, cannot be recognized reliably at the pocket position, because these mainly involve hand movements. These activities can be recognized with wrist-worn motion sensors. Other activities can be recognized by motion sensors at the pocket position, such as biking, walking upstairs and walking downstairs In such activities, there is a better repetitive pattern of motion data at the pocket position than at the wrist position. To use the richer context information from both wrist and pocket, we evaluated the effect of using motion sensors at both of these positions with respect to the wrist position alone
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
