Abstract
Pedestrian motion recognition algorithms using the accelerometer on a smartphone are implemented, and performance evaluation results are presented. The features for classifying the decision tree and design parameters of a CNN (Convolutional Neural Network) for recognizing pedestrian motion are listed. The accelerometer outputs of a smartphone that was used to monitor six adults who performed six motion types were collected. The decision tree thresholds were determined, and the CNN weights were learned from the collected data. With the derived thresholds and weights, the real-time pedestrian motion recognition algorithms were implemented on a smartphone, and their performance was evaluated. The performance evaluation results show that the CNN-based motion recognition algorithm has better accuracy than the decision tree-based motion recognition algorithm.
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 callMore From: Journal of Institute of Control, Robotics and Systems
Disclaimer: 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.
