Accurate diagnosis and treatment of cardiovascular diseases require the integration of cardiac imaging, which provides crucial information about the structure and function of heart to improve overall patient care. This review explores the role of artificial intelligence (AI) in advancing cardiac imaging analysis, with a focus on unsupervised learning methods. Unlike supervised AI systems, which rely on annotated datasets, the use of unsupervised learning proves to be a game-changer. It effectively tackles issues related to limited datasets and sets the stage for scalable, adaptive solutions in cardiac imaging. This paper gives a comprehensive overview of the limitations of traditional methods and the potential of unsupervised AI in overcoming challenges related to dataset scarcity through an extensive literature review and analysis of unsupervised algorithms including clustering techniques, dimensionality reduction, and generative models. This review study highlights the contributions of unsupervised techniques for enhancing diagnostic accuracy and efficiency in cardiac imaging. By comparing unsupervised and supervised methods, the paper aims to explain the benefits and limitations of each approach, offering valuable insights for advancing AI integration in cardiac healthcare. The findings are expected to guide future research and development, leading to innovative advancements in cardiovascular diagnostics.

The rapid advancement of communication is introducing a new era for the Internet of Vehicles (IoV) in the context of Smart Cities. Although these technologies provide unparalleled connectivity and communication capabilities, they also introduce new security challenges, particularly in terms of Intrusion Detection. This paper presents a robust machine learning (ML) technique to enhance the security of IoV networks by developing an efficient intrusion detection system (IDS). In this paper, we proposed a fine tree-based model to study the complex behavior of network traffic inside the IoV to detect and classify anomalies for securing the IoV. The proposed fine tree-based model can be validated by conducting extensive experiments with benchmark real-world datasets which can simulate emerging IoV scenarios. The proposed Fine Tree-based IDS model, along with other models, has been evaluated using metrics such as mean accuracy, precision, recall, F1-score, specificity and error rate. The proposed model outperformed the others across each metric, achieving near-perfect results with a mean accuracy, precision, recall, F1-score, and specificity of 0.99999. However, the other models achieved mean values ranging from 0.90 to 0.98 across these metrics. Additionally, the proposed model achieved an exceptionally low mean error rate of 0.00001, while the error rates of the other models ranged from 0.02 to 0.05. The experimental findings demonstrate the superior performance of the proposed model in detecting and classifying intrusions within IoV.

The delay in transporting essential goods is primarily attributed to widespread traffic congestion globally. This issue not only results in significant time and fuel wastage but also poses a considerable challenge in efficiently disseminating traffic information and managing road conditions for authorities. Addressing these challenges, vehicular ad hoc networks (VANETs) have emerged as a crucial component of the cognitive intelligent transportation system (C-ITS). To tackle this issue effectively, vehicle-to-vehicle (V2V) communication plays a crucial role in fostering cooperation and optimizing route management within transportation networks. This paper proposes an innovative congestion detection system that integrates the fuzzy k-means (FKM) clustering technique with the fuzzy analytical hierarchy process (FAHP). Utilizing the simulation of urban mobility (SUMO) simulator, a detailed transport network is modeled where vehicle parameters indicative of congestion are collected, integrated using sensor fusion, and analyzed. These parameters are processed using FKM clustering and a mathematical mean algorithm to identify key congestion indicators. Subsequently, FAHP prioritizes these collected parameters, pinpointing congestion hotspots within specific routes. By incorporating cognitive intelligence, the system continuously refines congestion detection and response strategies, enhancing traffic flow efficiency and enabling proactive congestion avoidance. This approach promises a more effective congestion detection methodology with minimal installation costs. Moreover, it can be effortlessly integrated into vehicles to facilitate congestion avoidance strategies, thereby enhancing overall traffic flow efficiency and mitigating the negative impacts of traffic congestion on transportation networks globally.

Due to developments in vehicle engineering and communication technologies, vehicular networks have become an attractive and feasible solution for the future of electric, autonomous, and connected vehicles. Electric autonomous vehicles will require more data, computing resources, and communication capabilities to support them. The combination of vehicles, the Internet, and cloud computing together to form vehicular cloud computing (VCC), vehicular edge computing (VEC), and vehicular fog computing (VFC) can facilitate the development of electric autonomous vehicles. However, more connected and engaged nodes also increase the system’s vulnerability to cybersecurity and privacy breaches. Various security and privacy challenges in vehicular cloud computing and its variants (VEC, VFC) can be efficiently tackled using machine learning (ML). In this paper, we adopt a semi-systematic literature review to select 85 articles related to the application of ML for cybersecurity and privacy protection based on VCC. They were categorized into four research themes: intrusion detection system, anomaly vehicle detection, task offloading security and privacy, and privacy protection. A list of suitable ML algorithms and their strengths and weaknesses is summarized according to the characteristics of each research topic. The performance of different ML algorithms in the literature is also collated and compared. Finally, the paper discusses the challenges and future research directions of ML algorithms when applied to vehicular cloud computing.

The need to compute data in real-time and manage resources in environments with distributed computing has given edge computing significant importance. However, one of the most critical tasks regarding resources has been to schedule and optimize them in accordance with energy consumption and delay time. These challenges has been addressed in this paper with the introduction of a new integrated method that assumes the Cellular Potts Model and Particle Swarm Optimization. The Cellular Potts Model is used to capture local interaction and dependencies of resources, while PSO acts as a global optimizer for scheduling reducing latency and energy consumption. Based on these considerations, the primary research goal of this work is to mitigate the QoS requirements like energy consumption and end-to-end delay using CPM—spatial modeling complemented by PSO - the global optimization. Based on experimental analysis, the authors of the paper argue that the newly proposed Hybrid model consumes less energy and has less processing time than Round-Robin, Random Offloading, and Threshold-Based techniques. In addition, the approach achieves higher scalability and can perform a large of tasks and edge nodes with a high QoS while working in a resource-limited environment. This paper contributes to presenting the integration procedure of the CPM’s local optimization with the PSO’s global search, which offers high-performance and real-time solutions for resource scheduling in the edge computing environment. The results presented in the paper show that the proposed hybrid CPM-PSO model can offer greater potential as a tool for energy-constrained and time-sensitive applications within the future development of edge computing.