http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
FlexRay 프로토콜을 이용한 차량용 SoC 고장 진단 기법
강승엽(Seung-Yeop Kang),정지훈(Ji-Hun Jung),박성주(Sung-Ju Park) 한국컴퓨터정보학회 2016 韓國컴퓨터情報學會論文誌 Vol.21 No.1
In this paper, we propose vehicle SoC fault diagnosis platform using FlexRay protocol in order to detect the faults of semiconductor control chip even after vehicle production. Before FlexRay protocol by sending NFI (Null Frame Indicator) bit among the header segment and a specific identifier in the payload segment of FlexRay frame, this technique can be distinguishable from normal mode and test mode. By using this technique, it is possible to detect the faults such as performance degradation of vehicle network system caused by the aging or several problems of vehicle semiconductor chip. Also high reliability and safety of vehicle can be maintained by using structural test for vehicle SoC fault detection.
자전거 교통사고 다발지역 예측을 위한 딥러닝 모형의 적용
전희정(Jun, Hee-Jung),강서윤(Kang, Seoyoon),강승엽(Kang, Seung Yeop),조철호(Cho, Cheol-Ho) 한국지역개발학회 2022 한국지역개발학회 학술대회 Vol.2022 No.11
A rising importance of bicycle as the paradigm shift in transportation has led to the need for an action to ensure the bicycle users’ safety by preventing bicycle collisions. This study aims to predict bicycle collision hot spots in Korea using collected Google Street View(GSV) images of bicycle collision hot spots and non-hot spots. We’ve conducted experiments with five deep learning models(VGG16, 19, ResNet50, 101, and Inception), and employed the CAM analysis to visualize the factors contributing to bicycle collisions. The VGG19 model is turned out to be the best model for predicting bicycle collision hot spots, and the CAM analysis shows that roads with larger scale, and with more vehicles and physical facilities(such as crosswalks, traffic lights, pillars) are related to bicycle collision hot spots. This study indicatess the effectiveness of using GSV images and deep learning model, and suggests more concrete and specific political implications for building safer environment for bicycle users.