Swimming style classification based on ensemble learning and adaptive feature value by using inertial measurement unit

Yuto Omae, Yoshihisa Kon, Masahiro Kobayashi, Kazuki Sakai, Akira Shionoya, Hirotaka Takahashi, Takuma Akiduki, Kazufumi Nakai, Nobuo Ezaki, Yoshihisa Sakurai, Chikara Miyaji

Research output: Contribution to journalArticlepeer-review

15 Citations (Scopus)

Abstract

We have been constructing a swimming ability improvement support system. One of the issues to be addressed is the automatic classification of swimming styles (backstroke, breaststroke, butterfly, and front crawl). The mainstream swimming style classification technique of conventional researches is based on non-ensemble learning; in their classification, breaststroke and butterfly are mixed up with each other. To improve its generalization performance, we need to use better classifiers and more adaptive feature values than previously considered. Therefore, this research has introduced (1) random forest technique, one of ensemble learning techniques, and (2) feature values specific to breaststroke and butterfly to construct a four-swimming-style classifier that has resolved this issue. From subjects with 7 to 20 years history of swimming races, we have obtained their sensor data during swimming and have divided the data into learning data and test data. We have also converted them into feature values that represent their body motions. We have selected from those body-motion-representing feature values the important data to classify four swimming styles and feature values specific to breaststroke and butterfly. We have used the learning data to construct a swimming style classifier, and the test data to evaluate its classification accuracy. The evaluation results show that (1') the introduction of ensemble learning has improved the mean value of F-measure for breaststroke and butterfly by 0.053, and (2') the introduction of feature values specific to breaststroke and butterfly has improved the mean value of F-measure for breaststroke and butterfly by 0.121 as compared with (1'). The proposed swimming style classifier has performed a mean F-measure of 0.981 for the four swimming styles as well as good classification accuracies for front crawl and backstroke. Therefore, we have concluded that the swimming style classifier we have constructed has resolved the problem of mixing up breaststroke and butterfly, as well as can properly classify all different swimming styles.

Original languageEnglish
Pages (from-to)616-631
Number of pages16
JournalJournal of Advanced Computational Intelligence and Intelligent Informatics
Volume21
Issue number4
DOIs
Publication statusPublished - Jul 2017
Externally publishedYes

Keywords

  • Ensemble learning
  • Inertial measurement unit
  • Machine learning
  • Random forest
  • Swimming style classification

Fingerprint

Dive into the research topics of 'Swimming style classification based on ensemble learning and adaptive feature value by using inertial measurement unit'. Together they form a unique fingerprint.

Cite this