Abstract
T-junction is one of the types of intersections that often results in congestion, and long queues. Therefore, it is necessary to identify the traffic flow to determine vehicles per hour, Passenger Car Unit (PCU) per hour, traffic fluctuations, vehicle composition, trip composition and traffic flow at peak hours at T-junction. The process of identifying traffic flow is complex and involves many variables. The process is currently still using Microsoft Excel which requires a lot of time and energy and allows for human error. Therefore, the purpose of this research is to design and build a traffic flow identification system at T-junction using NoSQL database. NoSQL is useful for complex data because NoSQL eliminates repetitive data. The results of this research are the traffic flow identification system at T-junction using NoSQL database which consists of vehicles per hour, PCU per hour, traffic fluctuations, vehicle composition, trip composition, and traffic flow during peak hours.