Baseball Player Behavior Classification System Using Long Short-Term Memory with Multimodal Features
In this paper, a preliminary baseball player behavior classification system is proposed. By using multiple IoT sensors and cameras, the proposed method accurately recognizes many of baseball players’ behaviors by analyzing signals from heterogeneous sensors. The contribution of this paper...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/6/1425 |
| _version_ | 1811277936591896576 |
|---|---|
| author | Shih-Wei Sun Ting-Chen Mou Chih-Chieh Fang Pao-Chi Chang Kai-Lung Hua Huang-Chia Shih |
| author_facet | Shih-Wei Sun Ting-Chen Mou Chih-Chieh Fang Pao-Chi Chang Kai-Lung Hua Huang-Chia Shih |
| author_sort | Shih-Wei Sun |
| collection | DOAJ |
| description | In this paper, a preliminary baseball player behavior classification system is proposed. By using multiple IoT sensors and cameras, the proposed method accurately recognizes many of baseball players’ behaviors by analyzing signals from heterogeneous sensors. The contribution of this paper is threefold: (i) signals from a depth camera and from multiple inertial sensors are obtained and segmented, (ii) the time-variant skeleton vector projection from the depth camera and the statistical features extracted from the inertial sensors are used as features, and (iii) a deep learning-based scheme is proposed for training behavior classifiers. The experimental results demonstrate that the proposed deep learning behavior system achieves an accuracy of greater than 95% compared to the proposed dataset. |
| first_indexed | 2024-04-13T00:25:45Z |
| format | Article |
| id | doaj.art-7fa2ab8519d24fd6a81ca1663f9801dc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T00:25:45Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7fa2ab8519d24fd6a81ca1663f9801dc2022-12-22T03:10:37ZengMDPI AGSensors1424-82202019-03-01196142510.3390/s19061425s19061425Baseball Player Behavior Classification System Using Long Short-Term Memory with Multimodal FeaturesShih-Wei Sun0Ting-Chen Mou1Chih-Chieh Fang2Pao-Chi Chang3Kai-Lung Hua4Huang-Chia Shih5Department of New Media Art, Taipei National University of the Arts, Taipei 112, TaiwanDepartment of Communication Engineering, National Central University, Taoyuan 320, TaiwanGraduate Institute of Dance Theory, Taipei National University of the Arts, Taipei 112, TaiwanDepartment of Communication Engineering, National Central University, Taoyuan 320, TaiwanDepartment of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei 106, TaiwanDepartment of Electrical Engineering, Yuan Ze University, Taoyuan 320, TaiwanIn this paper, a preliminary baseball player behavior classification system is proposed. By using multiple IoT sensors and cameras, the proposed method accurately recognizes many of baseball players’ behaviors by analyzing signals from heterogeneous sensors. The contribution of this paper is threefold: (i) signals from a depth camera and from multiple inertial sensors are obtained and segmented, (ii) the time-variant skeleton vector projection from the depth camera and the statistical features extracted from the inertial sensors are used as features, and (iii) a deep learning-based scheme is proposed for training behavior classifiers. The experimental results demonstrate that the proposed deep learning behavior system achieves an accuracy of greater than 95% compared to the proposed dataset.https://www.mdpi.com/1424-8220/19/6/1425behavior recognitionmultimodalmachine learningdeep learningLSTM networkdepth camerainertial sensor |
| spellingShingle | Shih-Wei Sun Ting-Chen Mou Chih-Chieh Fang Pao-Chi Chang Kai-Lung Hua Huang-Chia Shih Baseball Player Behavior Classification System Using Long Short-Term Memory with Multimodal Features Sensors behavior recognition multimodal machine learning deep learning LSTM network depth camera inertial sensor |
| title | Baseball Player Behavior Classification System Using Long Short-Term Memory with Multimodal Features |
| title_full | Baseball Player Behavior Classification System Using Long Short-Term Memory with Multimodal Features |
| title_fullStr | Baseball Player Behavior Classification System Using Long Short-Term Memory with Multimodal Features |
| title_full_unstemmed | Baseball Player Behavior Classification System Using Long Short-Term Memory with Multimodal Features |
| title_short | Baseball Player Behavior Classification System Using Long Short-Term Memory with Multimodal Features |
| title_sort | baseball player behavior classification system using long short term memory with multimodal features |
| topic | behavior recognition multimodal machine learning deep learning LSTM network depth camera inertial sensor |
| url | https://www.mdpi.com/1424-8220/19/6/1425 |
| work_keys_str_mv | AT shihweisun baseballplayerbehaviorclassificationsystemusinglongshorttermmemorywithmultimodalfeatures AT tingchenmou baseballplayerbehaviorclassificationsystemusinglongshorttermmemorywithmultimodalfeatures AT chihchiehfang baseballplayerbehaviorclassificationsystemusinglongshorttermmemorywithmultimodalfeatures AT paochichang baseballplayerbehaviorclassificationsystemusinglongshorttermmemorywithmultimodalfeatures AT kailunghua baseballplayerbehaviorclassificationsystemusinglongshorttermmemorywithmultimodalfeatures AT huangchiashih baseballplayerbehaviorclassificationsystemusinglongshorttermmemorywithmultimodalfeatures |