부산대학교 도서관

Gait analysis is essential for diagnosis, assessment, monitoring purpose, and prediction of gait disorder. However, the objective analysis method is less feasible in hospital environments for treatment purposes due to limited coverage of sources. Thus, this study aims to develop a classification algorithm that can effectively classify subjects with relatively simplified temporal spatial gait data. This study employed several datasets acquired from PhysioNet containing subjects’ gait data of three classes. The training dataset contains a total of 48,318 instances of three target classes (young healthy adults, old healthy adults, and Parkinson’s disease patients). Two classification algorithms were developed: Support Vector Machine (SVM) classification algorithm and Artificial Neural Network (ANN). Preprocessing was performed to the original dataset which includes data cleaning, data normalization and new features generation. Next, fine-tuning on the manipulating hyperparameters was performed, and 10-fold cross validation was applied. The optimum configuration of SVM model can generate an accuracy of 93.01% and F1 score of 0.92 with 43 minutes of computational time. On the contrary, the optimum configuration ANN classifier generates an accuracy of 90.56% and F1 score of 0.89 with 112 minutes computational time. Conclusion: In conclusion, comparing both of the proposed classification algorithms, the SVM classifier is more effectively than ANN classifier as overall for the gait dataset used in this study. In addition, after compared with other state-of-the-arts of gait classification algorithms, our proposed classification algorithm produced comparable results with other state-of-arts using a smaller dataset with fewer training features. Clinical Relevance– This establishes the potential of apply machine learning algorithm on basic gait data obtained from the objective gait analysis method in classification of healthy adults, older adults, and Parkinson’s patient.