The classification of skateboarding tricks via transfer learning pipelines
This study aims at classifying flat ground tricks, namely Ollie, Kickflip, Shove-it, Nollie and Frontside 180, through the identification of significant input image transformation on different transfer learning models with optimized Support Vector Machine (SVM) classifier. A total of six amateur ska...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Peerj Inc.
2021
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/32628/1/JOURNAL%20%281%29%20-%20The%20classification%20of%20skateboarding%20tricks%20via%20transfer%20learning%20pipelines%20%281%29.pdf |
| _version_ | 1825814074456276992 |
|---|---|
| author | Muhammad Amirul, Abdullah Muhammad Ar Rahim, Ibrahim Muhammad Nur Aiman, Shapiee Muhammad Aizzat, Zakaria Mohd Azraai, Mohd Razman Rabiu Muazu, Musa Noor Azuan, Abu Osman Anwar P.P., Abdul Majeed |
| author_facet | Muhammad Amirul, Abdullah Muhammad Ar Rahim, Ibrahim Muhammad Nur Aiman, Shapiee Muhammad Aizzat, Zakaria Mohd Azraai, Mohd Razman Rabiu Muazu, Musa Noor Azuan, Abu Osman Anwar P.P., Abdul Majeed |
| author_sort | Muhammad Amirul, Abdullah |
| collection | UMP |
| description | This study aims at classifying flat ground tricks, namely Ollie, Kickflip, Shove-it, Nollie and Frontside 180, through the identification of significant input image transformation on different transfer learning models with optimized Support Vector Machine (SVM) classifier. A total of six amateur skateboarders (20 ± 7 years of age with at least 5.0 years of experience) executed five tricks for each type of trick repeatedly on a customized ORY skateboard (IMU sensor fused) on a cemented ground. From the IMU data, a total of six raw signals extracted. A total of two input image type, namely raw data (RAW) and Continous Wavelet Transform (CWT), as well as six transfer learning models from three different families along with gridsearched optimized SVM, were investigated towards its efficacy in classifying the skateboarding tricks. It was shown from the study that RAW and CWT input images on MobileNet, MobileNetV2 and ResNet101 transfer learning models demonstrated the best test accuracy at 100% on the test dataset. Nonetheless, by evaluating the computational time amongst the best models, it was established that the CWTMobileNet-Optimized SVM pipeline was found to be the best. It could be concluded that the proposed method is able to facilitate the judges as well as coaches in identifying skateboarding tricks execution |
| first_indexed | 2024-03-06T12:53:27Z |
| format | Article |
| id | UMPir32628 |
| institution | Universiti Malaysia Pahang |
| language | English |
| last_indexed | 2024-03-06T12:53:27Z |
| publishDate | 2021 |
| publisher | Peerj Inc. |
| record_format | dspace |
| spelling | UMPir326282021-11-19T04:32:46Z http://umpir.ump.edu.my/id/eprint/32628/ The classification of skateboarding tricks via transfer learning pipelines Muhammad Amirul, Abdullah Muhammad Ar Rahim, Ibrahim Muhammad Nur Aiman, Shapiee Muhammad Aizzat, Zakaria Mohd Azraai, Mohd Razman Rabiu Muazu, Musa Noor Azuan, Abu Osman Anwar P.P., Abdul Majeed TJ Mechanical engineering and machinery This study aims at classifying flat ground tricks, namely Ollie, Kickflip, Shove-it, Nollie and Frontside 180, through the identification of significant input image transformation on different transfer learning models with optimized Support Vector Machine (SVM) classifier. A total of six amateur skateboarders (20 ± 7 years of age with at least 5.0 years of experience) executed five tricks for each type of trick repeatedly on a customized ORY skateboard (IMU sensor fused) on a cemented ground. From the IMU data, a total of six raw signals extracted. A total of two input image type, namely raw data (RAW) and Continous Wavelet Transform (CWT), as well as six transfer learning models from three different families along with gridsearched optimized SVM, were investigated towards its efficacy in classifying the skateboarding tricks. It was shown from the study that RAW and CWT input images on MobileNet, MobileNetV2 and ResNet101 transfer learning models demonstrated the best test accuracy at 100% on the test dataset. Nonetheless, by evaluating the computational time amongst the best models, it was established that the CWTMobileNet-Optimized SVM pipeline was found to be the best. It could be concluded that the proposed method is able to facilitate the judges as well as coaches in identifying skateboarding tricks execution Peerj Inc. 2021-08-18 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/32628/1/JOURNAL%20%281%29%20-%20The%20classification%20of%20skateboarding%20tricks%20via%20transfer%20learning%20pipelines%20%281%29.pdf Muhammad Amirul, Abdullah and Muhammad Ar Rahim, Ibrahim and Muhammad Nur Aiman, Shapiee and Muhammad Aizzat, Zakaria and Mohd Azraai, Mohd Razman and Rabiu Muazu, Musa and Noor Azuan, Abu Osman and Anwar P.P., Abdul Majeed (2021) The classification of skateboarding tricks via transfer learning pipelines. PeerJ Computer Science. pp. 1-18. ISSN 2376-5992. (Published) https://peerj.com/articles/cs-680/ http:10.7717/peerj-cs.680 |
| spellingShingle | TJ Mechanical engineering and machinery Muhammad Amirul, Abdullah Muhammad Ar Rahim, Ibrahim Muhammad Nur Aiman, Shapiee Muhammad Aizzat, Zakaria Mohd Azraai, Mohd Razman Rabiu Muazu, Musa Noor Azuan, Abu Osman Anwar P.P., Abdul Majeed The classification of skateboarding tricks via transfer learning pipelines |
| title | The classification of skateboarding tricks via transfer learning pipelines |
| title_full | The classification of skateboarding tricks via transfer learning pipelines |
| title_fullStr | The classification of skateboarding tricks via transfer learning pipelines |
| title_full_unstemmed | The classification of skateboarding tricks via transfer learning pipelines |
| title_short | The classification of skateboarding tricks via transfer learning pipelines |
| title_sort | classification of skateboarding tricks via transfer learning pipelines |
| topic | TJ Mechanical engineering and machinery |
| url | http://umpir.ump.edu.my/id/eprint/32628/1/JOURNAL%20%281%29%20-%20The%20classification%20of%20skateboarding%20tricks%20via%20transfer%20learning%20pipelines%20%281%29.pdf |
| work_keys_str_mv | AT muhammadamirulabdullah theclassificationofskateboardingtricksviatransferlearningpipelines AT muhammadarrahimibrahim theclassificationofskateboardingtricksviatransferlearningpipelines AT muhammadnuraimanshapiee theclassificationofskateboardingtricksviatransferlearningpipelines AT muhammadaizzatzakaria theclassificationofskateboardingtricksviatransferlearningpipelines AT mohdazraaimohdrazman theclassificationofskateboardingtricksviatransferlearningpipelines AT rabiumuazumusa theclassificationofskateboardingtricksviatransferlearningpipelines AT noorazuanabuosman theclassificationofskateboardingtricksviatransferlearningpipelines AT anwarppabdulmajeed theclassificationofskateboardingtricksviatransferlearningpipelines AT muhammadamirulabdullah classificationofskateboardingtricksviatransferlearningpipelines AT muhammadarrahimibrahim classificationofskateboardingtricksviatransferlearningpipelines AT muhammadnuraimanshapiee classificationofskateboardingtricksviatransferlearningpipelines AT muhammadaizzatzakaria classificationofskateboardingtricksviatransferlearningpipelines AT mohdazraaimohdrazman classificationofskateboardingtricksviatransferlearningpipelines AT rabiumuazumusa classificationofskateboardingtricksviatransferlearningpipelines AT noorazuanabuosman classificationofskateboardingtricksviatransferlearningpipelines AT anwarppabdulmajeed classificationofskateboardingtricksviatransferlearningpipelines |