근전도 기반의 Spider Chart와 딥러닝을 활용한 일상생활 잡기 손동작 분류 (Classification of Gripping Movement in Daily Life Using EMG-based Spider Chart and Deep Learning)

서지정보

· 발행기관 : 대한의용생체공학회
· 수록지 정보 : 의공학회지 / 43권 / 5호 / 299 ~ 307페이지
· 저자명 : 이성문, 피승훈, 한승호, 조용운, 오도창

초록

In this paper, we propose a pre-processing method that converts to Spider Chart image data for classi- fication of gripping movement using EMG (electromyography) sensors and Convolution Neural Networks (CNN) deep learning. First, raw data for six hand gestures are extracted from five test subjects using an 8-channel armband and converted into Spider Chart data of octagonal shapes, which are divided into several sliding windows and are learned. In classifying six hand gestures, the classification performance is compared with the proposed pre-processing method and the existing methods. Deep learning was performed on the dataset by dividing 70% of the total into train- ing, 15% as testing, and 15% as validation. For system performance evaluation, five cross-validations were applied by dividing 80% of the entire dataset by training and 20% by testing. The proposed method generates 97% and 94.54% in cross-validation and general tests, respectively, using the Spider Chart preprocessing, which was better results than the conventional methods.

영어초록

In this paper, we propose a pre-processing method that converts to Spider Chart image data for classi- fication of gripping movement using EMG (electromyography) sensors and Convolution Neural Networks (CNN) deep learning. First, raw data for six hand gestures are extracted from five test subjects using an 8-channel armband and converted into Spider Chart data of octagonal shapes, which are divided into several sliding windows and are learned. In classifying six hand gestures, the classification performance is compared with the proposed pre-processing method and the existing methods. Deep learning was performed on the dataset by dividing 70% of the total into train- ing, 15% as testing, and 15% as validation. For system performance evaluation, five cross-validations were applied by dividing 80% of the entire dataset by training and 20% by testing. The proposed method generates 97% and 94.54% in cross-validation and general tests, respectively, using the Spider Chart preprocessing, which was better results than the conventional methods.

참고자료

· 없음