VANETs is a wireless technology where vehicles act as mobile nodes to perform a communication network. All mobile nodes in the VANETs can communicate directly each other. As a wireless network, VANETs is vulnerable to some attacks include black hole attack. This kind of attack causes the VANETs service to be out of order. This attack absorbs and drops all of the data packets in the network. The data packets will not reach their destination because interfered by malicious nodes that perform black hole attack. This research will investigate and analyze the impact of the black hole attack on the performance of AODV and AOMDV routing protocols in VANETs. This study uses simulation software to mimic VANETs with multiple nodes. In the simulation scenario, one node acts as a malicious node that performs black hole attack. The result shows that the performance of both routing protocols decreases during the attack. The throughput of both routing protocols reduced while the packet loss increased. Although both routing protocols are vulnerable to black hole attacks, AOMDV has a better performance compared to AODV.

The perception system is vital for the autonomous navigation of self-driving cars in complex traffic environments. A critical part of this system is object detection, which enables the vehicle to perceive and interpret its surroundings. Object detection in mixed traffic environments becomes particularly problematic due to the increased complexity from diverse interacting objects and other factors such as cluttered, blurred scenes, etc. To address this problem, we present the MXT-Dataset, a novel dataset that captures the complexities of real-world mixed traffic scenarios. We also propose MXT-YOLOv7t, a real-time object detection model designed to efficiently and effectively handle the various challenges in mixed traffic scenarios. This model enhances YOLOv7-tiny P5 by improving the detection rate and reducing inference time. The enhancements include refining the feature extraction network by integrating a lightweight attention mechanism into the ELAN blocks and replacing the activation function in each convolution layer with a sigmoid-weighted linear unit. Then, we evaluate the performance by training and testing the proposed model alongside several other previous YOLO variant models using the same MXT-Dataset. The experimental results show that MXT-YOLOv7t model surpasses YOLOv7-tiny model by up to 6.1%, as measured by mAP@0.5. Furthermore, MXT-YOLOv7t achieves a recall of up to 0.934 and a precision of 0.937, significantly enhancing detection accuracy while maintaining low computational complexity. Therefore, the proposed model effectively performs real-time detection in complex traffic scenarios, offering a lightweight design with high detection accuracy, fast inference times, and minimal computational cost.

Traffic congestion is a natural phenomenon that seems to be a routine for the people who lived in urban areas. The traffic congestion has become a significant factor in disrupting traffic flows. The rate of growth of vehicles in several major cities is increasingly difficult to be balanced by the development of road infrastructure. Various methods have been tested to solve this problem, but there are no ideal results. The presence of Vehicular Ad-hoc Networks (VANETs) can be a promising vehicular communication technology, and so can be implemented for transportation systems management in the future. However, VANETs have several limitations such as mobility pattern, freedom of movement, and limited bandwidth. The implementation of VANETs will have different handling levels in an urban area compared to others. Each urban area has a distinct uniqueness so that an appropriate mobility model is needed to accommodate various attributes and parameters in different urban areas. Based on those limitations, this research proposes the Vehicle-to-Vehicle (V2V) mobility modeling and simulation using Periodic Broadcast (PBC) messages for mitigating traffic congestion on the transportation system. The goal of this research is to provide a better mobility model and simulation that can provide a realistic model to fulfill various attributes and parameters in the different urban area. Another goal is to analyze the using of PBC messages for V2V implementation in a transportation system to mitigate the traffic congestion. The simulation results show that the V2V mobility modeling using PBC messages can parse the congestion at high traffic density points. This model presents a better travel time estimation and average vehicle speed compared to the conventional model. According to network performance test, the packet delivery ratio (PDR) of V2V-PBC is better than that of non-PBC.

In the past few years, cloud computing has became a dominant topic in the IT area. Cloud computing offers hardware, infrastructure, platform and applications without requiring end-users knowledge of the physical location and the configuration of providers who deliver the services. It has been a good solution to increase reliability, reduce computing cost, and make opportunities to IT industries to get more advantages. The purpose of this article is to present a better understanding of cloud delivery service, correlation and inter-dependency. This article compares and contrasts the different levels of delivery services and the development models, identify issues, and future directions on cloud computing. The end-users comprehension of cloud computing delivery service classification will equip them with knowledge to determine and decide which business model that will be chosen and adopted securely and comfortably. The last part of this article provides several recommendations for cloud computing service providers and end-users.