Publication: Differentiation of motion patterns between Anterior Cruciate Ligament injuries and healthy individuals
Issued Date
2016-07-22
Resource Type
Other identifier(s)
2-s2.0-84991772104
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
Proceedings of the 2016 5th ICT International Student Project Conference, ICT-ISPC 2016. (2016), 109-112
Suggested Citation
Nantawat Prachasri, Duangkamol Yangchaem, Nattaporn Dirakbussarakom, Worapan Kusakunniran Differentiation of motion patterns between Anterior Cruciate Ligament injuries and healthy individuals. Proceedings of the 2016 5th ICT International Student Project Conference, ICT-ISPC 2016. (2016), 109-112. doi:10.1109/ICT-ISPC.2016.7519248 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/43463
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
Differentiation of motion patterns between Anterior Cruciate Ligament injuries and healthy individuals
Other Contributor(s)
Abstract
© 2016 IEEE. Detecting the sign of Anterior Cruciate Ligament (ACL) injury in advance is very important because the injury could be prevented to seriously occur, or a patient would be provided with the proper treatment timely. ACL injury, mostly happen with athletes, is the injury that one pair of cruciate ligament are torn because of the sport or daily life activities. Finding the differences of gait data patterns between an ACL injury patient and a healthy controlled person is proposed in this paper. Linear Discriminant Analysis (LDA) is applied to assist in the discrimination. After that, the k-nearest neighbor algorithm which focuses on the subject average is applied as a classification tool. The leave-one-out cross-validation is used for evaluating the performance of the proposed method. In this paper, the friendly user interface is also developed to facilitate the general users for using this program. In the experiment, there are 10 subjects which consist of 5 healthy control subjects and other 5 ACL injury subjects. The 3 gait variables are used to verify the proposed method. The 3 variables are the top 3 most significant variables which are ankle joint moment, hip joint moment and knee joint moment. In the experiment, it is shown that the proposed method can achieve a promising accuracy with the limited number of training data.