Recent advances in high-throughput DNA sequencing have enabled the generation of extensive microarray datasets from tissue samples, facilitating the identification of disease-specific biomarkers. The high dimensionality of these datasets, characterised by a large number of genomic features and limited sample sizes, poses significant challenges for conventional feature selection methods in identifying robust, biologically relevant biomarkers within practical computational timeframes. To address these limitations, this study proposes a hybrid computational framework that integrates Kernel Principal Component Analysis (KPCA) with an enhanced Gravitational Search Algorithm (GSA), termed OBKGSA. KPCA is initially applied to extract biologically meaningful, nonlinearly separable gene subsets from high-dimensional expression data. Subsequently, opposition-based learning (OBL) is integrated into the GSA, yielding the OBKGSA algorithm that improves population diversity and convergence efficiency during the search for optimal biomarker combinations. The proposed OBKGSA method was validated on six publicly available microarray cancer datasets and benchmarked against four established nature-inspired classification approaches. Experimental results demonstrate that OBKGSA consistently achieves superior classification accuracy using minimal feature subsets, outperforming existing methods in cancer identification and classification. Specifically, the model achieved good accuracies of 98.80% using only 10 optimal genes on the SRBCT dataset and 97.89% using 9 genes on the Lung Cancer dataset.

The swift improvement of wireless communication technology has aided the creation of vehicular ad hoc networks (VANETs) as a revolutionary option for the realization of intelligent transportation systems (ITSs). VANETs facilitate seamless communication between vehicles and infrastructure (V2I) and among the vehicles themselves (V2V). These networks can enhance safety and traffic control while providing various infotainment options. To ensure stable and efficient communication in highly dynamic and quickly changing vehicular contexts, effective data packet routing is a crucial component of VANETs. This survey delves further into the VANET routing algorithms for ITS. The study aims to evaluate the effectiveness and acceptability of various routing protocols suggested for VANETs while considering their unique requirements and difficulties. The review covers ad hoc on-demand distance vector (AODV) and dynamic source routing (DSR), as well as more current strategies designed specifically for VANETs, such as geographic routing, cluster-based routing, and hybrid routing protocols. The review assesses the routing algorithms based on several vital parameters, including packet delivery ratio (PDR), end-to-end delay, throughput, network overhead, scalability, and robustness. This detailed assessment supports aspiring researchers in acquiring a better knowledge of the benefits and drawbacks of the routing algorithms currently used in VANETs.

Intelligent Transport Systems (ITS) rely heavily on Vehicular Ad hoc Networks (VANET) to facilitate effective communication, especially Vehicle-to-Everything (V2X) communication. However, current research has identified challenges in node management, security, and routing within VANET, calling for bespoke solutions to address these issues. This study introduces an innovative cluster-based routing strategy using Enhanced Slap Swarm Optimization (ESSO) and Evaluation with Mixed Data Multi-criteria Decision-Making (EVAmix MCDM) Method tailored to optimize routing in V2X communication. Unlike existing meta-heuristic methods, which often face slow convergence, premature convergence, and local optima stability, the proposed approach demonstrates striking results. Notably, it enhances throughput by 6278 kbps, elevates the Packet Delivery Ratio (PDR) by 95.77%, and reduces end-to-end delay by 1856ms in the 300th iteration, outperforming existing cluster routing methodologies. Our findings suggest a substantial leap toward surmounting the existing challenges in V2X communication. This innovative solution advances the field and sets a course for real-time applications. This approach allows vehicles to continually monitor, adjust their position, and control their speed on highways, enhancing safety and traffic control.

Dynamic auto node configuration with Adhoc features is an advanced concept for vehicle communication. It is the modern internet-based data transmission in Intelligent Transport Systems. Different node auto-configuration schemas and node address-related approaches were used to improve network infrastructure and robust data communication between vehicles in Transport Intelligence-based wireless vehicle Adhoc networks. To address the problem of vehicle node auto-configuration with reduction of delay in transmission is an emerging research concept in data forwarding between vehicles in Adhoc networks, so this paper proposes an Automatic Dynamic User Allocation based Data Forwarding with Opportunistic Routing (ADUADFOR) approach with the assistance of mobility of vehicle association concerning the forwarding of data between vehicles in Adhoc networks. In this approach, each vehicle node carries a replica of other vehicle information, which decides the route based on this collective dynamic information of vehicles. Extensive simulated results of the proposed approach give better performance to improve Quality of service (QoS) through decreased overhead when compared to traditional mobility-based routing calculation methods in vehicle Adhoc networks.

Intelligence Transport System (ITS) is a wirelessly connected, self-configurable structureless network with multiple sensor hosts. Here, all the hosts in the network follow centralized authority present at all the hosts in the network, which are moving independently with available mobility. Sensor networks have various random features, such as unreliability in wireless connections between multiple hosts and the potential to change the network’s topology at any time. For effectively solving the metrics mentioned above, a variety of algorithms have been developed. However, challenges like intermittent connectivity, heterogeneous vehicle management, energy consumption, and support of network intelligence remain unanswered. To support random data transference, energy consumption, and mobility management issue in intelligent transport networks, “A New Optimal Searchable Multi-metric Routing (NOSMR)” is proposed. This approach controls mobility from a new perspective to manage load maintenance of each host in intelligence sensor networks. Power-aware advanced routing scenarios are introduced for efficient connection between wireless hosts and to manage efficient mobility in ad hoc networks. Extensive simulations are done using NS3 to evaluate the performance of the proposed approach. The performance metrics used to analyze the proposed approach’s efficiency are throughput, time, and end-to-end delay. The proposed study is compared with state-of-the-art studies in the literature.