Low-Cost Method for Recognizing Table Tennis Activity

Se-Min LIM  Jooyoung PARK  Hyeong-Cheol OH  

IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.10   pp.2051-2054
Publication Date: 2019/10/01
Publicized: 2019/06/18
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2019EDL8017
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
activity recognition,  sports skill assessment,  wearable technology,  cosine similarity,  recurrent neural network,  

Full Text: PDF>>
Buy this Article

This study designs a low-cost portable device that functions as a coaching assistant system which can support table tennis practice. Although deep learning technology is a promising solution to realizing human activity recognition, we propose using cosine similarity in making inferences. Our experiments show that the cosine similarity based inference can be a good alternative to the deep learning based inference for the assistant system when resources are limited.