Learning to judge like a human: Convolutional networks for classification of ski jumping errors

Heike Brock, Yuji Ohgi, James Lee

研究成果: Conference contribution

11 被引用数 (Scopus)

抄録

Advanced machine learning technologies are seldom applied to wearable motion sensor data obtained from sport movements. In this work, we therefore investigated neural networks for motion performance evaluation utilizing a set of inertial sensor-based ski jump measurements. A multidimensional convolutional network model that related the motion data under aspects of time, placement and sensor type was implemented. Additionally, its applicability as a measure for automatic motion style judging was evaluated. Results indicate that one multi-dimensional convolutional layer is sufficient to recognize relevant performance error representations. Furthermore, comparisons against a Support Vector Machine and a Hidden Markov Model show that the new model outperforms feature-based methods under noisy and biased data environments. Architectures such as the proposed evaluation system can hence become essential for automatic performance analysis and style judging systems in future.

本文言語English
ホスト出版物のタイトルISWC 2017 - Proceedings of the 2017 ACM International Symposium on Wearable Computers
出版社Association for Computing Machinery
ページ106-113
ページ数8
ISBN(電子版)9781450351881
DOI
出版ステータスPublished - 2017 9 11
イベント29th ACM International Symposium on Wearable Computers, ISWC 2017 - Maui, United States
継続期間: 2017 9 112017 9 15

出版物シリーズ

名前Proceedings - International Symposium on Wearable Computers, ISWC
Part F130534
ISSN(印刷版)1550-4816

Other

Other29th ACM International Symposium on Wearable Computers, ISWC 2017
国/地域United States
CityMaui
Period17/9/1117/9/15

ASJC Scopus subject areas

  • ソフトウェア
  • ハードウェアとアーキテクチャ
  • コンピュータ ネットワークおよび通信

フィンガープリント

「Learning to judge like a human: Convolutional networks for classification of ski jumping errors」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル