http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
CNN을 이용한 궤적데이터에 대한 이동성 모드 분류 방법
이권동(Gwon-dong Lee),맹주형(Juhyoung Maeng),송석일(Seokil Song) 한국정보기술학회 2019 한국정보기술학회논문지 Vol.17 No.12
Recognizing the mobility modes (bus, car, train, etc.) of the users moving trajectories in trajectory mining is very important for extracting more accurate information. In this paper, we propose a mobility mode classification method for users trajectories based on CNN (Convolution Neural Network). The proposed mobility mode classification method in this paper generates the users’ bus trajectories by using the actual bus trajectories. We use the approach of classifying the mobility modes of the collected user trajectories using the derived learning model through CNN using the collected user trajectories and the generated bus users’ trajectories. We perform the mobility mode classification experiment using the actual user trajectory data. As the result of the mobility mode classification experiment, the classification accuracy was 95.98%. In addition, it was confirmed that the proposed method is more suitable for the mobility mode classification for the users trajectories through a comparison experiment with the previously proposed mobility mode classification method.