Prediction scoring in exergames for Rehabilitation Patients using K-Means Clustering
Nurezayana Zainal1, M Faeid M Zabid1 , Seyed M.M. Kahaki2, Hafez Hussain3, Waidah Ismail1
1Faculty of Science and Technology, University Sains Islam Malaysia, Malaysia
2Center for Interdisciplinary Research on Complex Systems, Northeastern University, Boston, MA, USA
3PERKESO Rehabilitation Centre, Malacca, Malaysia
3Center for Holistic Intelligence, Institut Sains Islam, Universiti Sains Islam Malaysia, Malaysia
Abstract
This paper highlighted prediction of difficulty in exergames in Rehabilitation Patients. The case study uses 19 rehabilitation patients with lower limb disability. The data set that used are from MIRA Application which the games based on Kinect-based Rehabilitation Gaming System (RGS). In the each of MIRA exergames consists of three difficulty modes which are easy, medium and hard. Currently, in exergames to move the difficulty level of games determined by the physiotherapy based on the improvement of the patents. But in this paper, it will suggest the difficulty level of games based on the history of the patients. The methodology that used is a K-Mean Clustering in finding the benchmarks of the individual patients. In producing the weight of the patients in determine difficulty level or exergames.
Keywords: Rehabilitation, Kinect-based rehabilitation game system, machine learning
Topic: Informatic and Information System