An Evaluation of Different Input Transformation for the Classification of Skateboarding Tricks by Means of Transfer Learning

Muhamad Amirul Abdullah; Muhammad Ar Rahim Ibrahim; Muhammad Nur Aiman Shapiee; Mohd Azraai Mohd Razman; Rabiu Muazu Musa; Noor Azuan Abu Osman; Muhammad Aizzat Zakaria; Anwar P. P. Abdul Majeed

doi:10.1007/978-981-99-0297-2_22

An Evaluation of Different Input Transformation for the Classification of Skateboarding Tricks by Means of Transfer Learning

Muhamad Amirul Abdullah, Muhammad Ar Rahim Ibrahim, Muhammad Nur Aiman Shapiee, Mohd Azraai Mohd Razman, Rabiu Muazu Musa, Noor Azuan Abu Osman, Muhammad Aizzat Zakaria, Anwar P. P. Abdul Majeed^*

^*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

Abstract

This study aims to investigate the effect of different input images, namely raw data (RAW) and Continuous Wavelet Transform (CWT) towards the discriminating of street skateboarding tricks, i.e., Ollie, Kickflip, Shove-it, Nollie and Frontside 180 through a variety of transfer learning with optimised k-Nearest Neighbors (kNN) pipelines. Six amateur skateboarders participated in the study, executed the aforesaid tricks five times per trick on an instrumented skateboard where six time-domain signals were extracted prior it was transformed to RAW and CWT. It was shown from the study that the CWT-InceptionV3-optimised kNN pipeline could attain an average test and validation accuracy of 90%.

Original language	English
Title of host publication	Innovation and Technology in Sports - Proceedings of the International Conference on Innovation and Technology in Sports, ICITS 2022, Malaysia
Editors	Syed Faris Syed Omar, Mohd Hasnun Hassan, Alexander Casson, Alan Godfrey, Anwar P. P. Abdul Majeed
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	269-275
Number of pages	7
ISBN (Print)	9789819902965
DOIs	https://doi.org/10.1007/978-981-99-0297-2_22
Publication status	Published - 2023
Externally published	Yes
Event	1st International Conference on Innovation and Technology in Sports, ICITS 2022 - Kuala Lumpur, Malaysia Duration: 14 Nov 2022 → 15 Nov 2022

Publication series

Name	Lecture Notes in Bioengineering
ISSN (Print)	2195-271X
ISSN (Electronic)	2195-2728

Conference

Conference	1st International Conference on Innovation and Technology in Sports, ICITS 2022
Country/Territory	Malaysia
City	Kuala Lumpur
Period	14/11/22 → 15/11/22

Keywords

Classification
Machine learning
Skateboarding
Transfer learning
k-Nearest Neighbor

Access to Document

10.1007/978-981-99-0297-2_22

Cite this

Abdullah, M. A., Ibrahim, M. A. R., Shapiee, M. N. A., Mohd Razman, M. A., Musa, R. M., Abu Osman, N. A., Zakaria, M. A., & P. P. Abdul Majeed, A. (2023). An Evaluation of Different Input Transformation for the Classification of Skateboarding Tricks by Means of Transfer Learning. In S. F. Syed Omar, M. H. Hassan, A. Casson, A. Godfrey, & A. P. P. Abdul Majeed (Eds.), Innovation and Technology in Sports - Proceedings of the International Conference on Innovation and Technology in Sports, ICITS 2022, Malaysia (pp. 269-275). (Lecture Notes in Bioengineering). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-0297-2_22

Abdullah, Muhamad Amirul ; Ibrahim, Muhammad Ar Rahim ; Shapiee, Muhammad Nur Aiman et al. / An Evaluation of Different Input Transformation for the Classification of Skateboarding Tricks by Means of Transfer Learning. Innovation and Technology in Sports - Proceedings of the International Conference on Innovation and Technology in Sports, ICITS 2022, Malaysia. editor / Syed Faris Syed Omar ; Mohd Hasnun Hassan ; Alexander Casson ; Alan Godfrey ; Anwar P. P. Abdul Majeed. Springer Science and Business Media Deutschland GmbH, 2023. pp. 269-275 (Lecture Notes in Bioengineering).

@inproceedings{95ad8c2c800d445eafa28e4892112d25,

title = "An Evaluation of Different Input Transformation for the Classification of Skateboarding Tricks by Means of Transfer Learning",

abstract = "This study aims to investigate the effect of different input images, namely raw data (RAW) and Continuous Wavelet Transform (CWT) towards the discriminating of street skateboarding tricks, i.e., Ollie, Kickflip, Shove-it, Nollie and Frontside 180 through a variety of transfer learning with optimised k-Nearest Neighbors (kNN) pipelines. Six amateur skateboarders participated in the study, executed the aforesaid tricks five times per trick on an instrumented skateboard where six time-domain signals were extracted prior it was transformed to RAW and CWT. It was shown from the study that the CWT-InceptionV3-optimised kNN pipeline could attain an average test and validation accuracy of 90%.",

keywords = "Classification, Machine learning, Skateboarding, Transfer learning, k-Nearest Neighbor",

author = "Abdullah, {Muhamad Amirul} and Ibrahim, {Muhammad Ar Rahim} and Shapiee, {Muhammad Nur Aiman} and {Mohd Razman}, {Mohd Azraai} and Musa, {Rabiu Muazu} and {Abu Osman}, {Noor Azuan} and Zakaria, {Muhammad Aizzat} and {P. P. Abdul Majeed}, Anwar",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 1st International Conference on Innovation and Technology in Sports, ICITS 2022 ; Conference date: 14-11-2022 Through 15-11-2022",

year = "2023",

doi = "10.1007/978-981-99-0297-2_22",

language = "English",

isbn = "9789819902965",

series = "Lecture Notes in Bioengineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "269--275",

editor = "{Syed Omar}, {Syed Faris} and Hassan, {Mohd Hasnun} and Alexander Casson and Alan Godfrey and {P. P. Abdul Majeed}, Anwar",

booktitle = "Innovation and Technology in Sports - Proceedings of the International Conference on Innovation and Technology in Sports, ICITS 2022, Malaysia",

}

Abdullah, MA, Ibrahim, MAR, Shapiee, MNA, Mohd Razman, MA, Musa, RM, Abu Osman, NA, Zakaria, MA & P. P. Abdul Majeed, A 2023, An Evaluation of Different Input Transformation for the Classification of Skateboarding Tricks by Means of Transfer Learning. in SF Syed Omar, MH Hassan, A Casson, A Godfrey & A P. P. Abdul Majeed (eds), Innovation and Technology in Sports - Proceedings of the International Conference on Innovation and Technology in Sports, ICITS 2022, Malaysia. Lecture Notes in Bioengineering, Springer Science and Business Media Deutschland GmbH, pp. 269-275, 1st International Conference on Innovation and Technology in Sports, ICITS 2022, Kuala Lumpur, Malaysia, 14/11/22. https://doi.org/10.1007/978-981-99-0297-2_22

An Evaluation of Different Input Transformation for the Classification of Skateboarding Tricks by Means of Transfer Learning. / Abdullah, Muhamad Amirul; Ibrahim, Muhammad Ar Rahim; Shapiee, Muhammad Nur Aiman et al.
Innovation and Technology in Sports - Proceedings of the International Conference on Innovation and Technology in Sports, ICITS 2022, Malaysia. ed. / Syed Faris Syed Omar; Mohd Hasnun Hassan; Alexander Casson; Alan Godfrey; Anwar P. P. Abdul Majeed. Springer Science and Business Media Deutschland GmbH, 2023. p. 269-275 (Lecture Notes in Bioengineering).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - An Evaluation of Different Input Transformation for the Classification of Skateboarding Tricks by Means of Transfer Learning

AU - Abdullah, Muhamad Amirul

AU - Ibrahim, Muhammad Ar Rahim

AU - Shapiee, Muhammad Nur Aiman

AU - Mohd Razman, Mohd Azraai

AU - Musa, Rabiu Muazu

AU - Abu Osman, Noor Azuan

AU - Zakaria, Muhammad Aizzat

AU - P. P. Abdul Majeed, Anwar

PY - 2023

Y1 - 2023

N2 - This study aims to investigate the effect of different input images, namely raw data (RAW) and Continuous Wavelet Transform (CWT) towards the discriminating of street skateboarding tricks, i.e., Ollie, Kickflip, Shove-it, Nollie and Frontside 180 through a variety of transfer learning with optimised k-Nearest Neighbors (kNN) pipelines. Six amateur skateboarders participated in the study, executed the aforesaid tricks five times per trick on an instrumented skateboard where six time-domain signals were extracted prior it was transformed to RAW and CWT. It was shown from the study that the CWT-InceptionV3-optimised kNN pipeline could attain an average test and validation accuracy of 90%.

AB - This study aims to investigate the effect of different input images, namely raw data (RAW) and Continuous Wavelet Transform (CWT) towards the discriminating of street skateboarding tricks, i.e., Ollie, Kickflip, Shove-it, Nollie and Frontside 180 through a variety of transfer learning with optimised k-Nearest Neighbors (kNN) pipelines. Six amateur skateboarders participated in the study, executed the aforesaid tricks five times per trick on an instrumented skateboard where six time-domain signals were extracted prior it was transformed to RAW and CWT. It was shown from the study that the CWT-InceptionV3-optimised kNN pipeline could attain an average test and validation accuracy of 90%.

KW - Classification

KW - Machine learning

KW - Skateboarding

KW - Transfer learning

KW - k-Nearest Neighbor

UR - http://www.scopus.com/inward/record.url?scp=85161422076&partnerID=8YFLogxK

U2 - 10.1007/978-981-99-0297-2_22

DO - 10.1007/978-981-99-0297-2_22

M3 - Conference Proceeding

AN - SCOPUS:85161422076

SN - 9789819902965

T3 - Lecture Notes in Bioengineering

SP - 269

EP - 275

BT - Innovation and Technology in Sports - Proceedings of the International Conference on Innovation and Technology in Sports, ICITS 2022, Malaysia

A2 - Syed Omar, Syed Faris

A2 - Hassan, Mohd Hasnun

A2 - Casson, Alexander

A2 - Godfrey, Alan

A2 - P. P. Abdul Majeed, Anwar

PB - Springer Science and Business Media Deutschland GmbH

T2 - 1st International Conference on Innovation and Technology in Sports, ICITS 2022

Y2 - 14 November 2022 through 15 November 2022

ER -

Abdullah MA, Ibrahim MAR, Shapiee MNA, Mohd Razman MA, Musa RM, Abu Osman NA et al. An Evaluation of Different Input Transformation for the Classification of Skateboarding Tricks by Means of Transfer Learning. In Syed Omar SF, Hassan MH, Casson A, Godfrey A, P. P. Abdul Majeed A, editors, Innovation and Technology in Sports - Proceedings of the International Conference on Innovation and Technology in Sports, ICITS 2022, Malaysia. Springer Science and Business Media Deutschland GmbH. 2023. p. 269-275. (Lecture Notes in Bioengineering). doi: 10.1007/978-981-99-0297-2_22

An Evaluation of Different Input Transformation for the Classification of Skateboarding Tricks by Means of Transfer Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this