Abstract – Traffic problems are an important thing that everyone cares about. In Miami- Dade, the time during go to work and after work is the peak period of traffic jams. In order to solve this problem, use graph theory to analyze the conditions of each road and the time required for the route, and choose the best route to go. The most suitable and fast travel route of travel to reach the destination, the time, the choice of transportation, and energy saving are all within the target range to be achieved. Keywords – Miami-Dade, traffic jam, transportation, graph theory, travel route. 1. PROBLEM STATEMENT Traffic problems are very troublesome. In large cities, it is very difficult to walk to the destination without transportation since the destination is often far away. Visualize the coordinates of each location through the method of graph theory, optimize the travel route, integrate it into the route and stop points of public transport to choose a more efficient and fast travel mode for people. Effective route planning of vehicles not only can improve road traffic efficiency, but also achieve the purpose of energy saving and emission reduction. 2. MOTIVATION With the growth of population, especially in countries like the United States, every family has at least one car, so the growth rate of vehicles is also growing continuously, and the situation of traffic jams will become more and more serious. In Miami- Dade County, traffic jams are serious every day, because some places have to pass through a certain arterial road, and some viaducts become very congested because there is only one road. Solving traffic congestion is a very important problem, which can help people save time, urban traffic planning will be better, and travel efficiency will be improved. It is a good choice to plan the driving route through graph theory and use other feasible transportation to replace driving by analyzing the road conditions. 3. PREVIOUS WORK I have checked several articles on Road Network Detection and traffic route optimization from IEEE website. Up to now, the research on this topic has been very mature, using graph theory to implement road network and UAV route efficiency detection. These two articles are Road Network Detection Using Probabilistic and Graph Theoretical Methods [1] and A Simple Approach for Sustainable Transportation Systems in Smart Cities: A Graph Theory Model [2]. The first article basically did the research on road network using the probabilistic and graph theory method to achieve road center detection, road shape extraction and road network formation based on graph theory. The second article is about the shuttle route planning for the three campuses of the University of Nebraska Omaha, which shortens the running time of the shuttle and achieves the goal of energy saving. These two articles included what I want to do in this project, however I will do more different research such as combine route analysis and selection of efficient tools. 4. TECHNICAL APPROACH Base on graph theory, the road map of the entire Dade County is obtained through the location coordinates of each destination, and then the route with the shortest driving time is calculated by analyzing the traffic time of each road. 5. EXPERIMENTAL VERIFICATION The dataset I will use including Miami Annual average daily traffic [3], Miami landmark [4]. The annual average daily traffic dataset including the column that represent the traffic time for each road, and a column including the address of each road. The second dataset including the x, y coordinate of each public location which can implement the road network. 6. REFERENCE [1] Unsalan, C., & Sirmacek, B. (2012). Road Network Detection Using Probabilistic and Graph Theoretical Methods. IEEE Transactions on Geoscience and Remote Sensing, 50(11), 4441-4453. [2] Landmark. (n.d.). Retrieved October 07, 2020, from https://gismdc.opendata.arcgis.com/ datasets/landmark/data [3] 2014 Annual Average Daily Traffic. (n.d.). Retrieved October 07, 2020, from https://gis mdc.opendata.arcgis.com/datasets/33dbad80039 b4892a29490b8b7cc1b28_0 [4] Landmark. (n.d.). Retrieved October 07, 2020, from https://gis mdc.opendata.arcgis.com/ datasets/landmark/data