Abstract
Recognizing human activity plays a significant role in theadvancements of human-interaction applications in healthcare, personalfitness, and smart devices. Many papers presented various techniques forhuman activity representation that resulted in distinguishable this http URL this study, we conduct an extensive literature review on recent, top-performing techniques in human activity recognition based on wearablesensors. Due to the lack of standardized evaluation and to assess andensure a fair comparison between the state-of-the-art techniques, we ap-plied a standardized evaluation benchmark on the state-of-the-art tech-niques using six publicly available data-sets: MHealth, USCHAD, UTD-MHAD, WISDM, WHARF, and OPPORTUNITY. Also, we propose anexperimental, improved approach that is a hybrid of enhanced hand-crafted features and a neural network architecture which outperformedtop-performing techniques with the same standardized evaluation bench-mark applied concerning MHealth, USCHAD, UTD-MHAD data-sets.
Abstract (translated)
URL
https://arxiv.org/abs/2101.01665