Visible to the public Machine Learning Based Human Activity Detection in a Privacy-Aware Compliance Tracking System

TitleMachine Learning Based Human Activity Detection in a Privacy-Aware Compliance Tracking System
Publication TypeConference Paper
Year of Publication2018
AuthorsWu, Q., Zhao, W.
Conference Name2018 IEEE International Conference on Electro/Information Technology (EIT)
KeywordsBack, back-bending activities detection, body mechanics, data acquisition, data privacy, expert rules, expert systems, field data acquisition, high-level bending activities, human activity detection, Human activity prediction, human factors, human skeleton data, Injuries, learning (artificial intelligence), lifting-pulling tasks, local nursing home, machine learning, machine learning techniques, Microsoft Kinect, Neural Network, nursing staffs baseline, object detection, PACTS, patient care, privacy, privacy-aware compliance tracking system, pubcrawl, Real-time Systems, Scalability, Skeleton, Support vector machines
AbstractIn this paper, we report our work on using machine learning techniques to predict back bending activity based on field data acquired in a local nursing home. The data are recorded by a privacy-aware compliance tracking system (PACTS). The objective of PACTS is to detect back-bending activities and issue real-time alerts to the participant when she bends her back excessively, which we hope could help the participant form good habits of using proper body mechanics when performing lifting/pulling tasks. We show that our algorithms can differentiate nursing staffs baseline and high-level bending activities by using human skeleton data without any expert rules.
Citation Keywu_machine_2018