Classification of underwater images is a challenging task due to wavelength-dependent light propagation, absorption, and dispersion distort the visibility of images, which produces low contrast and degraded images in difficult operating environments. Deep learning algorithms are suitable to classify the turbid images, for that softmax activation function used for classification and minimize cross-entropy loss. The proposed deep underwater image classification model (DUICM) uses a convolutional neural network (CNN), a machine learning algorithm, for automatic underwater image classification. It helps to train the image and apply the classification techniques to categorise the turbid images for the selected features from the Benchmark Turbid Image Dataset. The proposed system was trained with several underwater images based on CNN models, which are independent to each sort of underwater image formation. Experimental results show that DUICM provides better classification accuracy against turbid underwater images. The proposed neural network model is validated using turbid images with different characteristics to prove the generalization capabilities.

Genetic algorithms (GAs) are a population-based meta-heuristic global optimization technique for dealing with complex problems with a very large search space. The population initialization is a crucial task in GAs because it plays a vital role in the convergence speed, problem search space exploration, and also the quality of the final optimal solution. Though the importance of deciding problem-specific population initialization in GA is widely recognized, it is hardly addressed in the literature. In this article, different population seeding techniques for permutation-coded genetic algorithms such as random, nearest neighbor (NN), gene bank (GB), sorted population (SP), and selective initialization (SI), along with three newly proposed ordered-distance-vector-based initialization techniques have been extensively studied. The ability of each population seeding technique has been examined in terms of a set of performance criteria, such as computation time, convergence rate, error rate, average convergence, convergence diversity, nearest-neighbor ratio, average distinct solutions and distribution of individuals. One of the famous combinatorial hard problems of the traveling salesman problem (TSP) is being chosen as the testbed and the experiments are performed on large-sized benchmark TSP instances obtained from standard TSPLIB. The scope of the experiments in this article is limited to the initialization phase of the GA and this restricted scope helps to assess the performance of the population seeding techniques in their intended phase alone. The experimentation analyses are carried out using statistical tools to claim the unique performance characteristic of each population seeding techniques and best performing techniques are identified based on the assessment criteria defined and the nature of the application.

Home automation systems are expanding increasingly popular because they can conveniently be employed to manage devices and appliances via voice or focused on physical activity utilizing sensor. From the various research, it shows that affording cost in bringing smartness to small organizations as well as normal users is challenging and there is a requirement for a better obvious and convenient method of connecting and managing equipment with mobile applications. The proposed system is created and built with the aim of enhancing control system performance and reliability. This technology may operate on any system and manage devices by connecting with home appliances and connected devices via a Wi-Fi device. The system involves a central processing module to manage devices via a home Wi-Fi connection that is linked to the internet for internet of things operations. It is recommended that an application be developed to connect, and configure new and current home appliances for control, which will lead to the connection and handling of other third-party devices via their software development kits. The suggested system enables additional features via a mobile application that allows the user to install new features created by the user to execute any activity with the system.

The Internet of Vehicles (IoV) is an important idea in developing intelligent transportation systems and self-driving cars. Vehicles with various wireless networking options can communicate both inside and outside the vehicles. IoVs with cognitive radio (CR) enable communication between vehicles in a variety of communication scenarios, increasing the rate of data transfer and bandwidth. The use of CR can meet the future need for quicker data transport between vehicles and infrastructure (V2I). Vehicles with CR capabilities on VANET have a different appearance than regular VANET vehicles. This paper aims to develop effective spectrum management for CR-equipped automobiles. An improved channel decision model has been proposed with proven outcomes to boost the pace of transmission, eliminate end-to-end delays, and minimize the number of handoffs. Many high-bandwidth channels will be used in the near future to communicate large-sized multimedia content between vehicles and roadside units (RSU) for both entertainment and safety purposes. Co-operative sensing promotes energy-constrained CR vehicles for sensing a wide spectrum, resulting in high-quality communication channels for requesting vehicles. Our research on the CR-VANET focuses on channel decision instead of spectrum sensing and it differs from previous studies. We used the DAHP–TOPSIS model under multi-criteria decision analysis (MCDA), a sub-domain of operations research, to boost profits, i.e., transmission rate with less computing time. We constructed a test-bed in MATLAB and carried out several analyses to demonstrate that the suggested model performs better than other parallel MCDA models because there has been a limited amount of research work conducted with CR-VANET