Item type |
Symposium(1) |
公開日 |
2020-06-17 |
タイトル |
|
|
タイトル |
ExerSense: Real-time Exercise Segmentation, Classification and Counting using IMU |
タイトル |
|
|
言語 |
en |
|
タイトル |
ExerSense: Real-time Exercise Segmentation, Classification and Counting using IMU |
言語 |
|
|
言語 |
eng |
キーワード |
|
|
主題Scheme |
Other |
|
主題 |
ユビキタスコンピューティングシステム |
資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_5794 |
|
資源タイプ |
conference paper |
著者所属 |
|
|
|
Aoyama Gakuin University |
著者所属 |
|
|
|
Aoyama Gakuin University |
著者所属 |
|
|
|
Turku University of Applied Sciences |
著者所属 |
|
|
|
Aoyama Gakuin University |
著者所属(英) |
|
|
|
en |
|
|
Aoyama Gakuin University |
著者所属(英) |
|
|
|
en |
|
|
Aoyama Gakuin University |
著者所属(英) |
|
|
|
en |
|
|
Turku University of Applied Sciences |
著者所属(英) |
|
|
|
en |
|
|
Aoyama Gakuin University |
著者名 |
Ishii, Shun
Yokokubo, Anna
Luimura, Mika
Lopez, Guillaume
|
著者名(英) |
Ishii, Shun
Yokokubo, Anna
Luimura, Mika
Lopez, Guillaume
|
論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Even though it is well known that physical exercises have numerous emotional and physical health benefits, maintaining a regular exercise routine is quite challenging. Fortunately, there exist technologies that promote us to do physical activities. Nonetheless, almost all of these technologies only target a narrow set of physical exercises (e.g., either running or physical workouts but not both) and are only applicable either in indoor or in outdoor environments, but do not work well in both environments. This paper introduces ExerSense, a real-time segmentation and classification algorithm that recognizes physical exercises, and that works well in both indoor and outdoor environments. The proposed algorithm achieves a 95% classification accuracy for five indoor and outdoor exercises, including segmentation error. This accuracy is similar or better than previous works that handled only indoor workouts, and those use a vision-based approach. Moreover, while comparable machine learning-based approaches need many training data, the proposed correlation-based method needs only one sample of motion data of each target exercise. |
論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Even though it is well known that physical exercises have numerous emotional and physical health benefits, maintaining a regular exercise routine is quite challenging. Fortunately, there exist technologies that promote us to do physical activities. Nonetheless, almost all of these technologies only target a narrow set of physical exercises (e.g., either running or physical workouts but not both) and are only applicable either in indoor or in outdoor environments, but do not work well in both environments. This paper introduces ExerSense, a real-time segmentation and classification algorithm that recognizes physical exercises, and that works well in both indoor and outdoor environments. The proposed algorithm achieves a 95% classification accuracy for five indoor and outdoor exercises, including segmentation error. This accuracy is similar or better than previous works that handled only indoor workouts, and those use a vision-based approach. Moreover, while comparable machine learning-based approaches need many training data, the proposed correlation-based method needs only one sample of motion data of each target exercise. |
書誌情報 |
マルチメディア,分散協調とモバイルシンポジウム2043論文集
巻 2020,
p. 151-154,
発行日 2020-06-17
|
出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |