The world's population has exponentially grown, which has an effect on usage of vehicles by individuals and leads to an increase in the number of cars in urbans. With the direct relationship between population and car usage, traffic management has become an important issue to be solved. For this purpose, an intelligent traffic signaling with a rapid urbanization is required to overcome the traffic congestions, and reduce cost and time of traveling. To overcome these problems, emerging computer vision and deep learning are vital candidates to handle this issue because they take an important role for managing and controlling traffic signals with great success. Nevertheless, detecting and distinguishing between objects are helpful for counting vehicles and other objects which avoid crowds and controlling signals in the traffic areas. Besides, detecting emergency vehicles and giving the priority to them is required for intelligent traffic signaling system.

The main objective of this study is to design and implement an efficient system for traffic signal systems based on custom vehicle detection.  Furthermore, the proposed system involves four phases; the first one is capturing images from both simulated and real time cameras from the roads. In the second phase, different image preprocessing algorithms are performed to the captured images as a pre-processing step. In addition, the deep learning techniques are applied to detect objects such as (regular car, police car, ambulance, and firefighter, etc..). In the last phase, the proposed system is tested to evaluate the performance accuracy of the detected vehicles.

A modified transfer learning approach has been applied to the DenseNet201 model for multiple classifications, including non-emergency cars, ambulances, police, and firefighters. The approach involves freezing the architecture of the model's layers. A high accuracy rate is obtained with this model and reaches 98.6%. Also, various optimization methods, including (Adam, Adamax, Nadam, and RMSprob) are used to improve the detection performance based on the best optimizer selection and yielded an accuracy of 98.84%. In addition, a modified version of YOLOv5 was proposed for vehicle detection, which aims to enhance the mean average precision (mAP) detection by 3%. Finally, the proposed system was simulated to reduce the waiting time at traffic signal. The experimental results demonstrate a significant reduction in waiting time, ranging from 30 to 100 seconds depending on the status.

ABSTRACT

The fifth generation (5G) mobile communication technology intends to address the massively increasing data rate requirements as well as the massive growth in traffic volume. The 5G technologies achieve higher performance, reduced latency, higher density, and higher mobility minus of sacrificing reliability. However, as the mobile core networks are facing exponential growth in traffic and computing demand as smart devices and mobile applications become more popular. One of the most promising solutions to the challenges is caching. Non-Orthogonal Multiple Access (NOMA) is one of the promising radio access techniques for performance enhancement in next-generation cellular communications. Especially the 5G networks are expected to provide a massively increased number of users at a thousand times higher data rates at lower power consumption because NOMA provides a higher spectral efficiency and higher system throughput.  For more improvement, power domain (PD-NOMA), code domain (CD-NOMA) and cooperative (C- NOMA) techniques are proposed and implemented in the 5G to overcome the future network demands. The PD-NOMA, employs Successive Interference Cancellation (SIC) at the receiver and Superposition Coding (SC) at the transmitter.

The proposed systems implemented with the help of MATLAB and NYUSIM simulations. The results of simulation show that the proposed techniques meet the various needs of improved user fairness, quality-of-service (QoS), high reliability, high spectral efficiency, extensive connectivity, raising data rates, high flexibility, low transmission latency, massive connectivity, low delay, higher cell-edge throughput, and superior performance.

For more improvement, caching techniques, as a storing popular reusable information at intermediate nodes to reduce backhauling load in wireless networks, have been integrated with C-NOMA to reduce the delay of storing planned content needs, relieve backhaul traffic and to alleviate the delay caused by handovers.  The results of simulation of caching integrated with C-NOMA technique have shown promise in maximizing throughput, minimizing latency, and optimizing resource efficiency. In C-NOMA, dynamic resource allocation refers to the process of dynamically modifying the power required to transmit rates and resource blocks allocated to users under their QoS requirements and channel conditions.

Finally, a novel approach is proposed by integrating C-NOMA, massive multiple-input multiple-output (m-MIMO) with caching as a strategic technique to overcome the exponential growth in data demand, spectrum scarcity, mitigation of interference, energy efficiency and sustainability. The simulation and evaluation results proved that the proposed system provides significantly a higher performance in terms of data rate, bit error rate (BER), and outage probability and reduces the power consumption to 52.6% and 54.7% compared to NOMA without cooperative and without NOMA, respectively, which is higher than the related works. The results of simulation verify the achievement of low-latency required by the sixth generation (6G) mobile communication networks cause to operate bandwidth-intensive applications such as high-definition video streaming, augmented reality, virtual reality, and Internet of Things (IoT) devices.