作者: Tae-Seong Kim , Jin-Ho Cho , Jeong Tai Kim
DOI: 10.1007/978-3-642-36645-1_87
关键词:
摘要: This paper presents a work on human activity recognition (HAR) using motion sensors embedded in smart phone building environments. Our HAR system recognizes general activities including walking, going-upstairs, going-downstairs, running, and motionless, statistical orientation features from signals of hierarchical Support Vector Machine classifier. Upon recognition, our also generates energy expenditures the recognized physical activities: are computed based Metabolic Equivalents (METS) values, step count, distance, speed, duration activities. By testing environments, we have obtained an average rate 98.26% with physically consumed information. With presented system, different designs environments can be evaluated terms consumptions residents for their