Afifah Ismail (2022) Jogging activity recognition using k-NN algorithm. Universiti Malaysia Sabah. (Unpublished)
![]() |
Text
JOGGING ACTIVITY RECOGNITION USING k-NN ALGORITHM.24pages.pdf Download (341kB) |
![]() |
Text
JOGGING ACTIVITY RECOGNITION USING k-NN ALGORITHM.fulltext.pdf Restricted to Registered users only Download (998kB) |
Abstract
Jogging activity recognition using the k-NN algorithm is a system that can help users collect information data of user speed movement using speed sensor and give the classification of jogging activity to the user. The objective of this project are 1) to investigate human activity recognition (HAR) for jogging activity and k-Nearest Neighbors (k-NN) algorithm for jogging classifier, 2) to apply HAR AND k-NN for jogging recognition and classification and, 3) to test the functionality of the k-NN algorithm of jogging recognition and classification. The prototype contains 10 GPX data that will be used as jogging activity and classify the intensity of jogging activity into running, running easy, jogging, and jogging easy. To recognize and classify the level of jogging intensity, k-Nearest Neighbours (k-NN) algorithms will be considered as a machine learning method. The k-NN algorithm is a simple and easy-to-implement supervised machine learning algorithm that can be used to solve both classification and regression problems. This system will give the user classification of the jogging activity after the information data is processed. Whereas the methodology for this project is using Software Development Life Cycles (SDLC). There are five phases Requirement gathering and analysis, System design, Implementation Integration, testing, and lastly is maintenance. Finally, usability testing will be used for evaluation. The jogging recognition technology is incorporated into a web-based system using PHP and Python after extraction, training, and test of the data complete, to create the working implementation that can classify the user's jogging activity. The output from this project is the system is sometimes unable to predict the jogging activity. The finding in this project is the k-NN algorithm is good feature extraction and classifier. However, to approach the limitation in this project, different feature extraction approaches and the study of additional classifiers, as well as research by training the model with a larger dataset and using more different intensities are needed.
Item Type: | Academic Exercise |
---|---|
Keyword: | Jogging , k-NN algorithm , Information data |
Subjects: | G Geography. Anthropology. Recreation > GV Recreation Leisure > GV1-1860 Recreation. Leisure > GV201-555 Physical education and training Q Science > QA Mathematics > QA1-939 Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science > QA76.75-76.765 Computer software |
Department: | FACULTY > Faculty of Computing and Informatics |
Depositing User: | DG MASNIAH AHMAD - |
Date Deposited: | 18 Jul 2022 08:09 |
Last Modified: | 18 Jul 2022 08:09 |
URI: | https://eprints.ums.edu.my/id/eprint/33187 |
Actions (login required)
![]() |
View Item |