Open AccessUpper Arm Action Recognition for Self Training with a Smartphone
Author(s) -
Jun Wu,
Weixin Song,
Xiaoying Lai,
Xiao Li
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1616/1/012102
Subject(s) - hidden markov model , coaching , computer science , training (meteorology) , action (physics) , usability , rehabilitation , action recognition , artificial intelligence , machine learning , human–computer interaction , psychology , physics , quantum mechanics , meteorology , psychotherapist , class (philosophy) , neuroscience
The action recognition for upper arm training, in low-cost and effective way, has great application in both sport training and rehabilitation training. However,they almost require extra and expensive equipments. This paper proposes an approach for real-time recognition of upper arm actions based on Hidden Markov Model (HMM) only one sensor and one smartphoneare needed. Data collected by a sensor and Action Pattern Sets are established with HMM training. Empirical Results with the smartphone, one for self-coaching for badminton technique improvement and another for arm injuries rehabilitation, validating the effectiveness and usability. Some problems found on site show that the next step is to further optimize the Action Pattern Sets to improve the overall accuracy and users’subjective satisfaction.