PURPOSES : This study develops a model that can estimate travel speed of each movement flow using deep-learning-based probe vehicles at urban intersections. METHODS : Current technologies cannot determine average travel speeds for all vehicles passing through a specific real-world area under obseravation. A virtual simulation environment was established to collect information on all vehicles. A model estimate turning speeds was developed by deep learning using probe vehicles sampled during information processing time. The speed estimation model was divided into straight and left-turn models, developed as fully-offset, non-offset, and integrated models. RESULTS : For fully-offset models, speed estimation for both straight and left-turn models achieved MAPE within 10%. For non-offset models, straight models using data drawn from four or more probe vehicles achieved a MAPE of less than 15%. The MAPE for left turns was approximately 20%. CONCLUSIONS : Using probe-vehicle data(PVD), a deep learning model was developed to estimate speeds each movement flow. This, confirmed the viability of real-time signal control information processing using a small number of probe vehicles.

1. 서론
    1.1. 논문개요
2. 선행 연구 검토
    2.1. 딥러닝 관련 연구
    2.2. 프로브 차량 관련 연구
    2.3. 기존 연구와의 차별성
3. 연구 방법 및 데이터 구축
    3.1. 통행속도에 영향을 미치는 요소 검토
    3.2. 데이터 구축을 위한 시뮬레이션 모델 선정
    3.3. 데이터 추출 및 분석
4. 딥러닝 모델 개발 및 검증
    4.1. 딥러닝 학습 모델 구조
    4.2. 딥러닝 학습
    4.3. 모형 검증
5. 결론
REFERENCES

• 정현수(명지대학교 교통공학과 석사) | Jeong Hyun su
• 손영태(명지대학교 교통공학과 교수) | Son Young tae (professor Department of Transportation Engineering, University of Myongji 116 Myongji-ro, YongIn, Gyeonggi-do 17058, Korea) Corresponding author
• 홍영석(명지대학교 재난대응교통관리센터 연구교수) | Hong Young seok
• 고광용(도로교통공단 교통과학연구원 처장) | Go Gwang yong