Autonomous vehicles can transform the transportation sector by offering a safer and more effective means of travel. However, the success of self-driving cars depends on their ability to navigate complex road conditions, including the detection of potholes. Potholes pose a substantial risk to vehicles and passengers, leading to potential damage and safety hazards, making their detection a critical task for autonomous driving. In this work, we propose a robust and efficient solution for pothole detection using the “you look only once (YOLO) algorithm of version 8, the newest deep learning object detection algorithm.” Our proposed system employs a deep learning methodology to identify real-time potholes, enabling autonomous vehicles to avoid potential hazards and minimise accident risk. We assess the effectiveness of our system using publicly available datasets and show that it outperforms existing state-of-the-art approaches in terms of accuracy and efficiency. Additionally, we investigate different data augmentation methods to enhance the detection capabilities of our proposed system. Our results demonstrate that YOLO V8-based pothole detection is a promising solution for autonomous driving and can significantly improve the safety and reliability of self-driving vehicles on the road. The results of our study are also compared with the results of YOLO V5.

Intelligent transportation systems (ITSs) derive significant advantages from advanced models like YOLOv8, which excel in predicting traffic incidents in dynamic urban environments. Roboflow plays a crucial role in organizing and preparing image data essential for computer vision models. Initially, a dataset of 1000 images is utilized for training, with an additional 500 images reserved for validation purposes. Subsequently, the Deep Simple Online and Real-time Tracking (Deep-SORT) algorithm enhances scene analyses over time, offering continuous monitoring of vehicle behavior. Following this, the YOLOv8 model is deployed to detect specific traffic incidents effectively. By combining YOLOv8 with Deep SORT, urban traffic patterns are accurately detected and analyzed with high precision. The findings demonstrate that YOLOv8 achieves an accuracy of 98.4%, significantly surpassing alternative methodologies. Moreover, the proposed approach exhibits outstanding performance in the recall (97.2%), precision (98.5%), and F1 score (95.7%), underscoring its superior capability in accurate prediction and analyses of traffic incidents with high precision and efficiency.

The Doubly-Fed Induction Generator (DFIG) is preferred for wind turbines (WTs) due to their variable speed capability, reinforcing energy capture efficiency. Despite its advantages, researchers continually face challenges in managing the DFIG, including overshooting, rising time, and stability under fault conditions. The faults in WTs may stem from the grid or different operational disturbances. The crowbar protection mechanism is an efficient strategy to reduce fault impacts on DFIGs. However, the traditional hysteresis-based methods to detect faults and crowbar activation are prone to false triggering, and to address the challenges posed, this paper presents a novel control strategy that increases the low-voltage ride-through (LVRT) capability of the grid-connected DFIG systems by incorporating Fuzzy Logic Control (FLC) to enhance accuracy in fault detection and employs the Salp Swarm Optimization Algorithm (SSA) to refine controller parameters. The SSA algorithm shows a superior dynamic response and stabilizes the DFIG system efficiently. Besides, the SSA algorithm precisely calibrates the proportional-integral (PI) controller gains and DC-link capacitance values to achieve the optimal transient response between Distributed Generation (DG) integration and fluctuating loads. It is evident by the results that the power quality is improved, and the active power overshoot value is decreased from 10.12 × 10⁶ to 3.78 × 10⁶. Moreover, by implementing the SSA algorithm in which the overshoot value is also decreased from 15.01 × 10⁶ to 6.10 × 10⁶, the best results are achieved. The proposed method is validated by comparative analyses with recent studies that showcase its superiority in refining machine dynamics and decreasing overshoots and transients. Henceforth, the obtained results validate the proposed method’s ability to compete against other conventional methods.

Heterogeneous communication modes in 5G demand integrated device connections, resource availability, and high capacity for meeting user demands. The radio resource allocation and usage for massive users results in interference between the device-to-device (D2D) uplink channels. This issue is addressed using a Non-orthogonal Convex Optimization Problem (NCOP) that identifies the chances of self-interference cancellations. This technique classifies interference and non-interference allocations in the rate of uplink communications. The channel reassignment is addressed as an NCOP based on the available interference levels. The interference levels before and after allocation and reallocation are analyzed under convex optimization. The interference cancellation convergence is computed for both channels wherein the transfer switching is performed. The convergence rate is estimated using the interference level and the number of channels reassigned for the uplink devices. Hence, the self-interference cancellation relies on non-convex channel allocations across various switching in this case. This feature is revisited if the D2D channels exceed their capacity for communication. Therefore, the 5G communication features coexist with the D2D uplinks for interference cancellations to improve channel allocation. For the SNR = 45dBm, the proposed NCOP reduces 12.4% of channel reassignment by augmenting 9.24% of interference cancellation.

The sensitive nature of the data processed by the critical infrastructures of a shared platform like the internet of things (IoT) makes it vulnerable to a wide range of security risks. These infrastructures must have robust security measures to protect the privacy of the user data transmitted to the processing systems that utilize them. However, data loss and complexities are significant issues when handling enormous data in IoT applications. This paper uses a reptile search optimization algorithm to offer attuned data protection with privacy scheme (ADP2S). This study follows the reptiles’ hunting behaviours to find a vulnerability in our IoT service’s security. The system activates the reptile swarm after successfully gaining access to explode ice. An attack of protection and authentication measures explodes at the breach location. The number of swarm densities and the extent to which they explore a new area are both functions of the severity of the breach. Service response and related loss prevention time verify fitness according to the service-level fitness value. The user and the service provider contribute to the authentication, which is carried out via elliptic curve cryptography and two-factor authentication. The reptile’s exploration and exploitation stages are merged by sharing a similar search location across the initialized candidates. The proposed scheme leverages breach detection and protection recommendations by 11.37% and 8.04%, respectively. It reduces the data loss, estimation time, and complexity by 6.58%, 10.9%, and 11.21%, respectively.