This paper introduces a Cooperative Model of Salp Swarm Optimization (CMSSO), which combines four algorithms: Salp Swarm Algorithm (SSA), Elite Opposition Learning-based SSA (EOSSA), Elite Opposition Quantum-inspired SSA (EQSSA), and Individual Dependent Approach for Differential Evolution (IDA-DE). These algorithms collaborate to tackle single-objective numerical optimization benchmarks from CEC-2022. SSA is a robust population-based metaheuristic renowned for its efficacy in practical optimization tasks. EOL and Quantum-inspired evolutionary algorithms exhibit enhanced capabilities in navigating search spaces compared to standard evolutionary algorithms. The objective of this cooperative model is to preserve the diversity and computational prowess of SSA while leveraging the strengths of these advanced algorithms. The multiobjective controller placement problem in Software Defined Networks (SDN) involves assigning switches to controllers, impacting network Quality of Service (QoS). Previous studies often focused on propagation latency for this assignment. However, our paper addresses this problem considering propagation latency between switches and controllers, inter-controller latency, and load balancing as multiobjective optimization. The experimental results confirmed the effectiveness of the proposed approach and showed that CMSSO is competitive with the standard SSA approaches.
With increased demand of quicker travel, both for passengers and cargo, there has been major advancements in commercial airlines and number of flights have increased significantly over the last few years. Novel challenges have been introduced due to the rising number of flights in the areas of safety, route planning and maintenance. In addition, for commercial flights, the surge in the number of passengers have also exposed avenues for improving the quality of flight travel, from entering the airport premises to leaving the same at the destination. Although there are many areas of flight and airport operations that can benefit from leveraging technological advancements, choosing safe flight path and making dynamic modifications to it is the critical aspect that needs to be addressed. Comprehending available information to adhere to the provided route and also avoiding known areas of air turbulence, adds to the financial benefit of the commercial airline as well as the safety of the airplane and the passengers are ensured. In this paper, the various aspects of improving the flight routing by providing dynamic intelligent path options to ensure adherence to the provided flight path possible is studied; options for improving the flight safety and turbulence avoidance, which benefits both the passengers and the aircraft are also explored. In addition, keeping aircraft away from conflict zones or war zones, and also from areas of natural disaster, like erupting volcanic ash or forest fires is relevant. Although these issues have been studied before, most of the techniques depend heavily on infrastructure that is on the ground. The basic model requires constant communication with an air traffic control tower, that would provide updates and changes to the flight path as necessary. This leads to some of these methods being unusable on flights operating on oceanic routes and away from the communication zone of the devices placed on land masses. Therefore, in this paper an Internet of Things based framework is proposed to address and handle the above mentioned issues. The framework is structured on the communication model of information exchange among aircraft within the range, as well as taking advantage of ground infrastructure if there is a possible network link to the same. A number of algorithms are proposed for dynamic intelligent routing of flights as well as detection and avoidance of air turbulence. The implementations of the proposed algorithms show improvements ranging from 10% to 30% in the methods as compared to using the infrastructure based conventional techniques.
Recent advances in artificial intelligence have significantly improved credit card fraud detection, with deep learning emerging as an effective approach for learning complex transaction patterns. However, as financial transaction datasets continue to grow, training deep learning models on a single computing node becomes increasingly computationally expensive, motivating the adoption of cloud-based distributed learning. Because distributed deep learning partitions training data across multiple worker nodes, this study evaluates how different data partitioning strategies influence predictive performance, computational efficiency, and scalability. The proposed framework was evaluated under both independently and identically distributed (IID) and non-independent and identically distributed (non-IID) data partitioning strategies, including random, stratified, label skew, quantity skew, temporal skew, and amount skew, using single-node, three-worker, and seven-worker configurations. Experimental results demonstrate a maximum training speedup of 4.181× and a 76.084% reduction in average epoch training time while maintaining consistently high recall across all partitioning strategies; however, the -score decreased from 0.696 to 0.587 (approximately 16%), due to increased false-positive predictions. The evaluated partitioning strategies exhibited different trade-offs between predictive performance and computational efficiency. These findings demonstrate that the proposed framework provides a scalable solution for cloud-based credit card fraud detection while offering practical insights into the influence of data partitioning strategies on distributed deep learning performance.
With the growth of commercial aviation over the last few decades there have been many applications designed to improve the efficiency of flight operations as well as safety and security. A number of these applications are based on the gathered data from flights; the data is usually acquired from the various sensors available on the aircraft. There are numerous sensors among the electrical and electronics devices on an aircraft, most of which are essential for the proper functioning of the same. With the sensors being operational throughout the time of movement of the aircraft, a large amount of data is collected during each flight. Normally, most of the gathered data are stored on a storage device on the aircraft, and are analyzed and studied later off-site for research purposes focusing on improving airline operation and efficiently maintaining the same. In certain cases, when there is data transfer during the flight, it is between the aircraft and an air-traffic-control (ATC) tower, which serves as the base station. The aircraft equipped with all these sensors, which can gather and exchange data, form a framework of Internet of things (IoT). Detecting and avoiding any form of turbulence for an aircraft is vital; it adds to the safety of both passengers and aircraft while reducing the operating cost of the airline. Therefore, in this paper, we study techniques to detect and avoid Clear Air Turbulence (CAT), which is a specific type of turbulence, based on the IoT framework of aircraft. We propose algorithms that consider both direct and indirect communication between aircraft within a specific region. Using simulation results, we show that our proposed techniques of direct communication using the IoT framework is faster than conventional techniques involving radio communication via both single ATC tower and multiple ATC towers.