Improving Efficiency of Self-care Classification Using PCA and Decision Tree Algorithm

Abstract

Self-care classification for children with physical disability remains an important and challenging issue. It needs the support from occupational therapists to make decision. Data-driven decision making have been widely adopted to make decision based on the data with help of expert systems and machine learning algorithms. In this study, we developed an efficient self-care classification model based principal component analysis (PCA) and decision tree (DT). PCA is used to extract the significant features, while the DT is used to build the classification model. We measure several metrics to evaluate the performance of proposed model as compared to other models and previous study results. Based on 10-fold cross-validation results, the proposed model outperformed other models and previous study results by achieving accuracy of 94.29%. Furthermore, PCA-based feature extraction has shown positive result on improving the model's performance with average accuracy improvement as much as 1.7% as compared to classifiers without PCA-based feature extraction method. Finally, it is projected that the outcomes of the study could assist the occupational therapist on enlightening the efficiency of self- care classification and children therapy. © 2020 IEEE.