A smart traffic light using a microcontroller based on the fuzzy logic

Abstract

<span lang="EN-US">Traffic jam that is resulted from the buildup of vehicles on the road has become an important problem, which leads to an interference with drivers. The impacts it has on cost and time effectiveness may take the form of increased fuel consumption, traffic emissions, and noise. This paper offers a solution by creating a smart traffic light using a fuzzy-logic-based microcontroller for a greater adaptability of the traffic light to the dynamics of the vehicles that are to cross the intersection. The ATMega2560 microcontroller-based smart traffic light is designed to create a breakthrough in the breakdown of congestions at road junctions, thereby optimizing the real-time happenings in the road. Ultrasonic, infrared, and light sensors are used in this smart traffic light, resulting in the smart traffic light’s effectiveness in parsing jams. The four sets of sensors that are placed in four sections determine the traffic light timing process. When the length of vehicle queue reaches the sensor, a signal is sent as the microcontroller’s digital input. Ultrasonic and infrared sensors can reduce congestions at traffic lights by giving a green light time when one or all of the sensors are active so that the vehicle congestions can be relieved.</span>

Hybrid travel time estimation model for public transit buses using limited datasets

“…In such cases, the 𝐿𝑇𝑇 𝑖,𝑗 is estimated based on the weighted average of preceding trip travel times 𝑇𝑇 𝑘,𝑗 and 𝑇𝑅𝑇 𝑘,𝑗 (preceding trip travel time based on speed 𝑅𝑆 𝑘,𝑗 ). The estimations for 𝛼 𝑗 , 𝑧 1,𝑗 , 𝑧 2,𝑗 , 𝑇𝑅𝑇 𝑘,𝑗 and 𝑇𝐻𝑅𝑆 𝑗 given in (3) to (7).…”

“…In ( 5) and ( 6) the 𝑥 𝑡 , 𝑥 𝑠 are the coefficients estimated using (1). The 𝑇𝑅𝑇 𝑘,𝑗 is the travel time for segment 𝑗 estimated based on the running speed 𝑅𝑆 𝑘,𝑗 of the preceding trip using (7), where 𝑑 𝑗 is the distance and 𝑅𝑆 𝑘,𝑗 is the preceding trip running speed of the respective segments. The 𝐷𝑒𝑙𝑎𝑦 𝑗 is the average delay at the intersection for segment j and it is added to the travel time estimated through running speed.…”

“…Also, the stochastic behavior of the traffic affects the travel time of buses. Delays at intersections [6] due to queuing, non-optimized signals [7], and mixed traffic lanes lead to an excess travel time for buses. Additionally, the bus driver's behavior [8] in  ISSN: 2252-8938 scenarios such as early start, on-time start, and delayed start of the trips will make the prediction process more complicated.…”

Traffic lights time strategy for T-junctions of toll road gate

“…Sabri and El Kamoun [13] stated that conventional traffic light systems offer a distributed solution for managing congestion but usually fail to regulate traffic flow in reality. Desmira et al [14] created an intelligent traffic light using fuzzy logic inference for an adaptive traffic light. It is to manage the dynamics of the vehicles at an intersection.…”

Laboratory prediction energy control system based on artificial intelligence network

“…Moreover, the use of AI positively contributes to evaluate the use of energy in a building [1], [2]. Energy requirements in a room have been widely discussed, including the use of the adaptive neuro-fuzzy inference system (ANFIS) algorithm [3], [4], fuzzy logic [5]- [9], artificial neural network (ANN) [10]- [18], and GA [19], [20]. Several studies have discussed the energy consumption of a building, including comparing ANN algorithms, clustering, statical and machine learning, and support vector machine (SVM).…”