The classification of skateboarding tricks by means of support vector machine: An evaluation of significant time-domain features

This study aims to improve classification accuracy of different Support Vector Machine (SVM) models in classifying flat ground tricks namely Ollie, Kick-flip, Shove-it, Nollie and Frontside 180 through the identification of significant time-domain features. An amateur skateboarder (23 years of age ±...

Full description

Bibliographic Details
Main Authors: Muhammad Amirul, Abdullah, Muhammad Ar Rahim, Ibrahim, Muhammad Nur Aiman, Shapiee, Anwar P. P, Abdul Majeed, Mohd Azraai, Mohd Razman, Rabiu Muazu, Musa, Muhammad Aizzat, Zakaria
Format: Book Chapter
Language:English
Published: Springer 2020
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/32613/
http://umpir.ump.edu.my/id/eprint/32613/1/CONFERENCE%20%282%29%20-%20The%20classification%20of%20skateboarding%20tricks%20by%20means%20of%20support%20vector%20machine%20an%20evaluation%20of%20significant%20time-domain%20features.pdf
_version_ 1848824065731592192
author Muhammad Amirul, Abdullah
Muhammad Ar Rahim, Ibrahim
Muhammad Nur Aiman, Shapiee
Anwar P. P, Abdul Majeed
Mohd Azraai, Mohd Razman,
Rabiu Muazu, Musa
Muhammad Aizzat, Zakaria
author_facet Muhammad Amirul, Abdullah
Muhammad Ar Rahim, Ibrahim
Muhammad Nur Aiman, Shapiee
Anwar P. P, Abdul Majeed
Mohd Azraai, Mohd Razman,
Rabiu Muazu, Musa
Muhammad Aizzat, Zakaria
author_sort Muhammad Amirul, Abdullah
building UMP Institutional Repository
collection Online Access
description This study aims to improve classification accuracy of different Support Vector Machine (SVM) models in classifying flat ground tricks namely Ollie, Kick-flip, Shove-it, Nollie and Frontside 180 through the identification of significant time-domain features. An amateur skateboarder (23 years of age ±5.0 years’ 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 36 features were extracted through statistical measures. The significant features were identified through two feature selection methods, namely Pearson and Chi-Squared. The variation of the SVM models (kernel-based) was evaluated both on all features and selected features in classifying the skateboarding tricks. It was shown from the study that all classifiers improved significantly in terms of training accuracy, prediction speed, training time and test accuracy. The Cubic-based SVM and Quadratic-based SVM demonstrated a 100% accuracy on both the test and train dataset, however, the Cubic-based SVM model provided the fastest training time and prediction speed between the two models. It could be concluded that the proposed method is able to improve the classification of the skateboarding tricks well.
first_indexed 2025-11-15T03:07:06Z
format Book Chapter
id ump-32613
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:07:06Z
publishDate 2020
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling ump-326132021-11-17T08:19:51Z http://umpir.ump.edu.my/id/eprint/32613/ The classification of skateboarding tricks by means of support vector machine: An evaluation of significant time-domain features Muhammad Amirul, Abdullah Muhammad Ar Rahim, Ibrahim Muhammad Nur Aiman, Shapiee Anwar P. P, Abdul Majeed Mohd Azraai, Mohd Razman, Rabiu Muazu, Musa Muhammad Aizzat, Zakaria T Technology (General) This study aims to improve classification accuracy of different Support Vector Machine (SVM) models in classifying flat ground tricks namely Ollie, Kick-flip, Shove-it, Nollie and Frontside 180 through the identification of significant time-domain features. An amateur skateboarder (23 years of age ±5.0 years’ 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 36 features were extracted through statistical measures. The significant features were identified through two feature selection methods, namely Pearson and Chi-Squared. The variation of the SVM models (kernel-based) was evaluated both on all features and selected features in classifying the skateboarding tricks. It was shown from the study that all classifiers improved significantly in terms of training accuracy, prediction speed, training time and test accuracy. The Cubic-based SVM and Quadratic-based SVM demonstrated a 100% accuracy on both the test and train dataset, however, the Cubic-based SVM model provided the fastest training time and prediction speed between the two models. It could be concluded that the proposed method is able to improve the classification of the skateboarding tricks well. Springer 2020-07-09 Book Chapter PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/32613/1/CONFERENCE%20%282%29%20-%20The%20classification%20of%20skateboarding%20tricks%20by%20means%20of%20support%20vector%20machine%20an%20evaluation%20of%20significant%20time-domain%20features.pdf Muhammad Amirul, Abdullah and Muhammad Ar Rahim, Ibrahim and Muhammad Nur Aiman, Shapiee and Anwar P. P, Abdul Majeed and Mohd Azraai, Mohd Razman, and Rabiu Muazu, Musa and Muhammad Aizzat, Zakaria (2020) The classification of skateboarding tricks by means of support vector machine: An evaluation of significant time-domain features. In: Embracing Industry 4.0. Lecture Notes in Electrical Engineering, 678 (11). Springer, Malaysia, pp. 125-132. ISBN 978-981-15-6025-5 https://doi.org/10.1007/978-981-15-6025-5_12 https://doi.org/10.1007/978-981-15-6025-5_12
spellingShingle T Technology (General)
Muhammad Amirul, Abdullah
Muhammad Ar Rahim, Ibrahim
Muhammad Nur Aiman, Shapiee
Anwar P. P, Abdul Majeed
Mohd Azraai, Mohd Razman,
Rabiu Muazu, Musa
Muhammad Aizzat, Zakaria
The classification of skateboarding tricks by means of support vector machine: An evaluation of significant time-domain features
title The classification of skateboarding tricks by means of support vector machine: An evaluation of significant time-domain features
title_full The classification of skateboarding tricks by means of support vector machine: An evaluation of significant time-domain features
title_fullStr The classification of skateboarding tricks by means of support vector machine: An evaluation of significant time-domain features
title_full_unstemmed The classification of skateboarding tricks by means of support vector machine: An evaluation of significant time-domain features
title_short The classification of skateboarding tricks by means of support vector machine: An evaluation of significant time-domain features
title_sort classification of skateboarding tricks by means of support vector machine: an evaluation of significant time-domain features
topic T Technology (General)
url http://umpir.ump.edu.my/id/eprint/32613/
http://umpir.ump.edu.my/id/eprint/32613/
http://umpir.ump.edu.my/id/eprint/32613/
http://umpir.ump.edu.my/id/eprint/32613/1/CONFERENCE%20%282%29%20-%20The%20classification%20of%20skateboarding%20tricks%20by%20means%20of%20support%20vector%20machine%20an%20evaluation%20of%20significant%20time-domain%20features.pdf