Reactive power compensation is one of the practical tools that can be used to improve power systems and reduce costs. These benefits are achieved when the compensators are installed in a suitable place with optimal capacity. This study solves the issues of optimal supply and the purchase of reactive power in the IEEE 30-bus power system, especially when considering voltage stability and reducing total generation and operational costs, including generation costs, reserves, and the installation of reactive power control devices. The modified version of the artificial bee colony (MABC) algorithm is proposed to solve optimization problems and its results are compared with the artificial bee colony (ABC) algorithm, the particle swarm optimization (PSO) algorithm and the genetic algorithm (GA). The simulation results showed that the minimum losses in the power system requires further costs for reactive power compensation. Also, optimization results proved that the proposed MABC algorithm has a lower active power loss, reactive power costs, a better voltage profile and greater stability than the other three algorithms.

In this research work, a user-friendly decision support framework is developed to analyze the behavior of Pakistani students in academics. The purpose of this article is to analyze the performance of the Pakistani students using an intelligent decision support system (DSS) based on the three-level machine learning (ML) technique. The neural network used a three-level classifier approach for the prediction of Pakistani student achievement. A self-recorded dataset of 1,011 respondents of graduate students of English and Physics courses are used. The ten interviews along with ten questions were conducted to determine the perception of the individual student. The chi-squared ( χ ) \left(\chi ) test was applied to test statistical significancy of the questionnaire. The statistical calculations and computation of data were performed by using the statistical package of IBMM SPSS version 21.0. The seven different algorithms were tested to improve the data classification. The Java-based environment was used for the development of numerous prediction classifiers. C4.5 algorithm shows the finest accuracy, whereas Naïve Bayes (NB) algorithm shows the least. The results depict that the classifier’s efficiency was improved by using a three-level proposed scheme from 83.2% to 88.8%. This prediction has shown remarkable results when compared with the individual level classifier technique of ML. This improvement in the accuracy of DSSs is used to identify more efficiently the gray areas in the education stratum of Pakistan. This will pave a path for making policies in the higher education system of Pakistan. The presented framework can be deployed on different platforms under numerous operating systems.

Deep learning models for diagnostic applications require large amounts of sensitive patient data, raising privacy concerns under centralized training paradigms. We propose FedGAN, a federated learning framework for synthetic medical image generation that combines Generative Adversarial Networks (GANs) with cross-silo federated learning. Our approach pretrains a DCGAN on abdominal CT scans and fine-tunes it collaboratively across clinical silos using diabetic retinopathy datasets. By federating the GAN’s discriminator and generator via the Federated Averaging (FedAvg) algorithm, FedGAN generates high-quality synthetic retinal images while complying with HIPAA and GDPR. Experiments demonstrate that FedGAN achieves a realism score of 0.43 (measured by a centralized discriminator). This work bridges data scarcity and privacy challenges in medical AI, enabling secure collaboration across institutions.

The Social Opportunistic Internet of Things (SO-IoT) is a rapidly emerging paradigm that enables mobile, ad-hoc device communication based on both physical and social interactions. In such networks, routing decisions heavily depend on the selection of intermediate nodes to ensure secure and efficient data dissemination. Traditional approaches relying solely on reliability or social interest fail to capture the multifaceted trustworthiness of nodes in dynamic SO-IoT environments. This paper proposes a trust-based route optimization framework that integrates social interest and behavioral reliability using Bayesian inference and Jeffrey’s conditioning. A composite trust level is computed for each intermediate node to determine its suitability for data forwarding. To validate the framework, we conduct a two-phase simulation-based analysis: a scenario-driven evaluation that demonstrates the model’s behavior in controlled settings, and a large-scale NS-3-based simulation comparing our method with benchmark routing schemes, including random, greedy, and AI-based protocols. Results confirm that our proposed model achieves up to an $88.9\%$ delivery ratio with minimal energy consumption and the highest trust accuracy ($86.5\%$), demonstrating its robustness and scalability in real-world-inspired IoT environments.

To solve problems with limited resources such as power, storage, bandwidth, and connectivity, efficient and effective data management solutions are needed. It is believed that the most successful algorithms for circumventing these constraints are those that self-organise and collaborate. To make the best use of available bandwidth, mobile ad hoc networks (MANETs) employ the strategy of multi-casting. The communication cost of any network can be significantly reduced by multi-casting, and the network can save resources by transmitting only one set of data to numerous receivers at a time. In this study, we implemented multi-casting in the virtual cord protocol (VCP), which uses virtual coordinates (VC) to improve effective routing and control wireless data transmission. We have improved the classic VCP protocol by making it so that intermediate nodes can also forward or re-transmit the dataset to interested nodes. This improves data transmission from the sender to multiple receivers. Simulation results proved efficacy of our proposed enhanced virtual cord protocol-based multi-casting strategy over traditional VCP protocol and helped in reduction of number of MAC transmissions, minimization of end-to-end delay, and maximization of packet delivery ratio.