Machine learning‐based traffic scheduling techniques for intelligent transportation system: Opportunities and challenges

Abstract

Summary The rise in traffic congestion has become a significant concern in the urban city environment. The conventional traffic control systems with inefficient human resources management fail to control the traffic discipline, leading to increased traffic density and road offenses. However, the intelligent transportation system (ITS) can provide safety, efficiency, and sustainability for large‐scale vehicular traffic dilemmas. ITS unites machine learning with the available traffic control force and performs real‐time police scheduling to ensure the smooth flow of traffic. Many researchers have demonstrated notable work in intelligent traffic police scheduling and deployment using various optimization algorithms. However, the compilation of such praiseworthy work as a whole is still missing. Motivated by these facts, we provide a comprehensive review of the machine learning‐based state‐of‐the‐art technologies that can be used to form a three‐tier solution taxonomy. The first tier describes various tools and technologies that can be utilized to collect traffic data. The second tier highlights the machine learning algorithms and their accuracy, which forms a pattern in the collected data and then yields some crucial information about traffic flow, congestion levels, and so forth. In the third tier, the most vital taxonomy layer, various traffic police scheduling strategies are discussed. The proposed survey also presents the use of cases of traffic police scheduling that elaborates this review's applicability in various domains. Finally, some of the key challenges in the subject being reviewed are discussed, which initiates a further scope of improvement.

Machine Learning for Physical Layer in 5G and beyond Wireless Networks: A Survey

“…Some other hybrid solutions involve saving the shortest paths throughout the routing process while considering the number of hops in the path and modulation format. ML-based approaches optimize transmission quality, and resource allocation has been implemented in [299]. Several ML-based algorithms can learn the distribution of input samples, which depends upon data types and availability, and classify the topology of the input vector.…”

An improved public transportation system for effective usage of vehicles in intelligent transportation system

“…This hotness score is predicted for each time‐step and the top‐k hotspots are recommended that are nearer to the user location in conjunction with the driver's location. Ensemble weights are modified during the prediction process and individual predictions depend on previous time‐steps 22,23 . This system provides prediction with the short‐term request using 63 taxi stands in Portugal, Porto.…”

“…Ensemble weights are modified during the prediction process and individual predictions depend on previous time-steps. 22,23 This system provides prediction with the short-term request using 63 taxi stands in Portugal, Porto. Likewise, the predictive model to find the taxi demand within the city of Bengaluru, India shows the result of the peak demand of every weekday and weekend.…”

PF‐ITS: Intelligent traffic service recommendation based on DeepAFM model

“…3,4 Currently, the ITSS plays major roles in reducing traffic pressure, ensuring driving safety and saving fuel consumption, which makes a significant contribution to the construction and management of modern traffic networks. 5 At present, the technologies of data communication, traffic simulation and travel information modeling 6 are applied to achieve intelligent traffic service (ITS). Li et al 7 presented an improved SVR model which performs outstanding accuracy for short-term traffic flow prediction since optimal parameter combination is obtained faster and better than that in prior works.…”