Electric load forecasting plays an important role in the planning and operation of the power system for high productivity in any institution of learning. A short-term electrical energy forecast for Gidan Kwano campus, Federal University of Technology Minna, Nigeria was carried out using GMDH-type neural network and the result was compared to that of regression analysis. GMDH-type neural network was used to train and test weekly energy consumed in the campus from September 2010 to December 2014. The neural network was trained using quadratic neural function. Root mean square error (RMSE) and mean absolute percentage error (MAPE) were used as performance indices to test the accuracy of the forecast. The neural network model gave a root mean square error (RMSE) of 0.1189, a mean absolute percentage error (MAPE) of 0.0922 and a correlation (R) value of 0.8995 while the regression analysis method gave a standard error of 10968.1 and a correlation (R) value of 0.1137. Results obtained show the efficacy of the GMDH-type neural network model in forecasting over the regression analysis method.

Machine-learning-based intrusion detection for Internet of Things systems has often been evaluated through model-centered pipelines that use weakly governed partitioning, limited leakage auditing, and closed-set assumptions. Consequently, reported performance could reflect data-handling artifacts rather than reliable security intelligence. This paper introduces a scientific integrity framework that treats preprocessing as a primary research object for open-set Internet of Things intrusion detection. The framework integrated device-disjoint split governance, feasibility-aware zero-day isolation, quantified leakage control, train-only preprocessing, shared-safe feature selection, diagnostic-harness verification, baseline split comparison, and auditable artifact generation. Applied to the CICIoT-DIAD 2024 corpus with Institute of Electrical and Electronics Engineers Organizationally Unique Identifier-based vendor enrichment, the protocol locked 28 canonical classes, eight semantic attack families, and five policy labels before constructing a device-disjoint, vendor-aware grouped split. When strict device-level zero-day holdout was infeasible, the framework activated an audited row-level fallback that preserved contamination-free holdout isolation without claiming strict device-novel zero-day evaluation. On 35,672,407 flows from 180 files, the accepted run achieved zero device overlap, zero flow-signature Jaccard leakage risk, 100 percent zero-day purity, a Feature Distribution Stability Score of 0.00518, a Device-Feature Dependency Index of 0.00000, an Attack Invariance Score of 0.92964, and an Attack Semantic Consistency Score of 0.90714. The diagnostic harness produced zero hard failures and zero warnings, while baseline comparison showed stronger preprocessing integrity than random stratified and simple device-disjoint splitting. This study did not claim downstream classifier superiority; rather, it established an auditable preprocessing substrate for later classifier-level experiments.

When interference is reduced, the benefits of using a macrocell and femtocell heterogeneous network (Macro-Femto) heterogeneous network (HetNet) can be increased to their full potential. In this study, Enhanced Active Power Control (EAPC), Active Power Control (APC), and Power Control (PC1) interference mitigation strategies are applied, and their performances in uplink and downlink transmission of 5G Non-Stand-Alone (NSA) architecture are compared. According to the findings of a MATLAB simulation, the EAPC technique utilized a lower amount of transmit power for the Macro User Equipment (MUE), the Home User Equipment (HUE), and the femtocell logical node (Hen-gNB), in comparison to the APC and PC1 techniques. While PC1 approach required less en-gNB transmission power. The MUE, HUE, hen-gNB, and en-gNB throughput of the EAPC approach was much higher. This work will enable wireless system designers and network engineers know the appropriate technique to utilize to achieve desired Quality of Service (QoS) while conserving network resources.

This study explores the application of JAYA optimization algorithms to significantly enhance the performance of indoor optical wireless communication (OWC) systems. By strategically optimizing photo-signal parameters, the system was able to improve signal distribution and reception within a confined space using circular and randomly positioned diffuse spots. The primary objective was to maximize signal-to-noise ratio (SNR) and minimize delay spread (DS), two critical factors affecting transmission quality in OWC systems. Given the challenges posed by background noise and multipath dispersion, an effective optimization strategy was essential to ensure robust signal integrity at the receiver end. Key Achievements of JAYA Optimization include: Significant Performance Gains are 29% improvement in SNR, enhancing signal clarity and reception and 23.3% reduction in delay spread, ensuring stable and efficient transmission. There was also improved System Stability, with the Standard deviation of SNR improved by up to 5%, leading to more consistent performance and the Standard deviation of delay spread improved by up to 9.9%, minimizing variations across receivers. Resilience against Environmental Challenges: Optimization proved effective even in the presence of ambient light noise and complex multipath dispersion effects, reinforcing its adaptability in real-world applications. The findings of this study confirm that JAYA optimization algorithms offer a powerful solution for overcoming noise and dispersion issues in indoor OWC systems, leading to more reliable and high-quality optical wireless communications. These results underscore the importance of algorithmic precision in enhancing system performance, paving the way for further advancements in indoor optical networking technologies.

The primary aim of a cognitive radio (CR) system is to optimize spectrum usage by exploiting the existing spectrum holes. Nevertheless, the success of cognitive radio technology is significantly threatened by the primary user emulation attack (PUEA). A rogue secondary user (SU) known as the primary user emulator (PUE) impersonates a legitimate primary user (PU) in a PUEA, thereby preventing other SUs from accessing the spectrum holes. Which leads to the decrease in quality of service (QoS), connection undependability, degraded throughput, energy depletion, and the network experiences a deterioration in its overall performance. In order to alleviate the impact of PUEA on Cognitive Radio Networks (CRNs), it is necessary to detect and isolate the threat agent (PUE) from the network. In this paper, a method for finding and isolating the PUE is proposed. MATLAB simulation results showed that the presence of PUE caused a significant decrease in the throughput of SUs, from 1 7 10   to 2 56 10  . The throughput was highest at a false alarm (FA) probability of 0.0, indicating no PUE, and decreased as the FA probability increased. At a FA probability of 1, the throughput reached zero, indicating complete takeover of the spectrum by PUE. By isolating the PUE from the network, the other SUs can access the spectrum holes, leading to increased QoS, connection reliability, improved throughput, and efficient energy usage. The presented technique is an important step towards enhancing the security and reliability of CRNs.