A hybridization of deep learning techniques to predict and control traffic disturbances
- PDF / 3,198,661 Bytes
- 30 Pages / 439.37 x 666.142 pts Page_size
- 98 Downloads / 175 Views
A hybridization of deep learning techniques to predict and control traffic disturbances Ali Louati1,2
© Springer Nature B.V. 2020
Abstract Predicting traffic disturbances is a challenging problem in urban cities. Emergency vehicles (EV) is one of the biggest disturbances that affect traffic fluidity. The goal of this paper is to provide a machine learning application to deal with emergency cases in traffic networks. Particularly, we investigate the use of deep learning techniques coupled with Artificial Immune System to tackle the issue of EV guidance at signalized intersections. To accomplish this goal, we develop a traffic signal control system capable to estimate traffic status, guide EV to reach their destinations while assuming better traffic condition, control traffic signals, and adapt to new disturbances. For traffic forecasting, the suggested system inherits the advantages of convolutional neural networks, classification, and long short term memory. To control traffic signals, the suggested system uses the immune memory algorithm. To enhance and adapt control decisions to traffic disturbances, the suggested system uses a continuous learning approach assumed by an adapted reinforcement learning algorithm. Assessments using well-known algorithms from the literature are detailed in this work. The benchmarking algorithms are the preemptive longest queue first matching weight matrix system, the pre-emptive immune memory algorithm inspired case-based reasoning, and the preemptive optimized stage based fixed time algorithm. Experiments show a competitive performance of the suggested system compared to benchmarking algorithms. Keywords Deep learning · Convolutional neural networks · Long short term memory · Immune memory algorithm · Reinforcement learning · Case-based reasoning · Preemptive LQF-MWM · Traffic signal control system
* Ali Louati [email protected]; [email protected] 1
Information Systems Department, Prince Sattam Bin Abdulaziz University, 11942 Alkharj, Kingdom of Saudi Arabia
2
University of Tunis, ISG, SMART Lab, 41, Avenue de la Liberté, Bouchoucha, Le Bardo, 2000 Tunis, Tunisia
13
Vol.:(0123456789)
A. Louati
1 Introduction Construction of smart transportation systems influences significantly residents’ lives in future cities. Intersections management is a key aim of such systems and is assumed via traffic signals control. Existing Traffic Signal Control Systems (TSCSs) deploy either fixed or adaptive control strategies. Adaptive TSCSs integrate information, communication, and technologies to build an integrated system of roads and vehicles. The rapid growth of urbanization brought remarkable challenges such as congestion leading to accidents, and incidents. When such phenomena occur clearing the way for Emergency Vehicles (EV) to reach an accident become critical for people lives. In the recent literature, there are some attempt to develop TSCSs that prioritize EV while maintaining traffic fluidity (Houli et al. 2010; Louati et al. 2020; Louati et al. 2018b; Qin and Khan 201
Data Loading...
