http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
정보 엔트로피를 이용한 택시 추적 데이터의 시각적 분석
피민규(Mingyu Pi),정성민(Seongmin Jeong),연한별(Hanbyul Yeon),장윤(Yun Jang) 한국정보과학회 2018 정보과학회 컴퓨팅의 실제 논문지 Vol.24 No.9
교통과 관련된 연구에서 많이 사용되는 데이터로 택시 추적 데이터가 있다. 여러 대의 택시가 이동한 경로를 특정 주기별로 샘플링하여 속도, 방향, 승객여부를 기록한 데이터이다. 교통 연구는 주로 GPS의 한 점만 보는 것이 아니라 일정 범위 단위로 분석하기 때문에 원본 데이터의 GPS 값을 실제 도로 네트워크 데이터에 적용하여 분석하는 등 추가적인 작업이 필요하다. 본 논문에서는 정보 엔트로피를 활용한 교통체증 탐지 시각적 분석을 제안한다. 이를 통해 특정 시간동안의 전체적인 교통 상황과 각 범위 내에서의 차량의 속도의 변화정도를 파악할 수 있다. There are taxi trajectory data that are widely used in traffic-related research. These data record the speed and the direction of a taxi and the occupation (whether passengers are boarding) it has by sampling the route along which several taxis traveled in a specific time. Traffic research is mainly focused on a certain range of GPS rather than on just one point. Therefore, additional work, such as analyzing GPS data by applying it to actual road network data is needed. In this paper, we propose a visual analysis system for traffic-jam detection using information entropy. This analysis can identify the overall traffic flow during a specific time period and the changes in the speed of the vehicle in each area.
현실 제약 조건을 반영한 강화학습 기반 교통 신호 제어
피민규(Mingyu Pi),이훈순(Hunsoon Lee),정문영(Moonyoung Chung) Korean Institute of Information Scientists and Eng 2021 정보과학회논문지 Vol.48 No.8
Traffic signal control plays an important role in efficiently using the limited capacity of the road. Since traditional traffic signal control methods operate based on preset signals, it is difficult to cope with frequently changing traffic conditions. Recently, as reinforcement learning has attracted attention as a method for solving complex problems, studies using reinforcement learning for efficient traffic signal control are being conducted. Compared to the traditional method, it has been proved through simulation that waiting time and travel time were improved. However, since most of the studies did not reflect the limitations of the actual signal, it was designed inappropriately for practical application. In this paper, we proposed a signal control method based on reinforcement learning that could be applied to real situations by reflecting the constraints of the signal operating system that exist in reality, and that could respond to changes in traffic volume.