Abstract Aim To develop and identify an optimal stacking ensemble model for predicting breast cancer, using combinations of Support Vector Machines (SVM), Naïve Bayes, and K-Nearest Neighbours (KNN) as base models with a rotating meta-classifier. Method An open-source breast cancer dataset of 569 patients (357 benign, 212 malignant) from UCI Machine Learning Repository was analysed. Ten predictive cell nucleus features were selected, and all other irrelevant variables were excluded. Exploratory Data Analysis included detection of outliers (addressed via Winsorization), assessment of normality (square root transformation applied), and correlation analysis to identify multicollinearity. Independent sample t-tests evaluated differences in features by diagnosis. Multicollinear features were assessed using Binary Logistic Regression, retaining the features with the highest Pseudo for modelling. Three stacking models were constructed using combinations of SVM, Naïve Bayes, KNN as base and meta-classifiers. Models were evaluated using 10-fold cross-validation with performance metrics including accuracy, precision, recall, F1-score, and ROC AUC. All analyses were conducted using Python and R. Results Significant differences were found between malignant and benign cases for all features ( p < 0.001), except for fractal dimension ( p = 0.98), which was then excluded from the analysis. Multicollinearity was observed among five features, and “area” was retained for modelling as it demonstrated the strongest predictive power for diagnosis, with a Pseudo $$ R^{2} $$ of 81%. Model 2 with Naïve Bayes and KNN as the base models and SVM as the meta-model achieved the best performance (95% accuracy, 90% recall, and 93% F1-score). The ROC-AUC analysis showed strong predictive ability, with an average AUC of 0.97 across 10-fold cross-validation. Conclusion The stacking ensemble model, integrating SVM, Naïve Bayes, and KNN, achieved improved accuracy and robustness in breast cancer prediction with Model 2 performing the best. This approach demonstrates potential for enhancing early detection and reducing breast cancer mortality. Its application in broader clinical and diverse healthcare settings may further advance disease prediction efforts.

Abstract This paper has developed the advanced QIMNSO for enhancement in the DTC of induction motors through a set of proposed schemes on quantum computing, memetic algorithms, adaptiveness of a neural network, and swarm intelligence. The proposed QIMNSO-DTC is designed to avoid main drawbacks inherent in traditional DTC, which are named as torque ripple, response lag, and energy inefficiency-evidently committed under dynamic load conditions. Application of QIMNSO results in prompt torque and flux adjustment, smaller ripples, and reduction of mechanical stress to the motor. This neural network part allows the real-time adaptation of parameters to achieve the best performance for all operating conditions and load variations. Simulation results indicate that QIMNSO-DTC enjoys some merits in comparison to classical control methods, including FOC, SMC, and PID controllers in terms of torque stability, response speed, energy efficiency, and self-adaptiveness. Such enhancements render QIMNSO-DTC very fit for applications where induction motors should be precisely, efficiently, and reliably controlled, such as robotics, electric vehicles, and high-performance industrial drives. QIMNSO represents a promising, scalable control approach in the present research that gives classical methods a large margin of improvement and contributes to further innovation related to intelligent motor control.

Abstract The rapid growth of electric vehicle (EV) adoption demands intelligent, secure, and resilient charging infrastructures capable of operating reliably under cyber-physical uncertainties. This paper designs a Composite Vulnerability Index (CVI)-based mitigation-aware control law for real-time, resilient management of multiple EV charging systems. The CVI quantifies the aggregated risk level of each EV’s charging context by fusing multiple factors such as cyber threats, communication latency, thermal stress, and power quality disturbances. The paper proposes a Digital-Twin enhanced Reinforcement Learning (RL) framework that integrates a Composite Vulnerability Index (CVI) with a mitigation-aware control law for large-scale multi-EV charging networks. A physics-informed EV Charging Digital Twin (DT) continuously predicts system evolution and identifies discrepancies using a learned residual model, enabling real-time characterization of operational uncertainty and cyber-attack impacts. The DT outputs both corrected state estimates and a risk cost that penalizes model uncertainty and elevated vulnerability levels. A Dreamer-V3 world-model-based RL agent uses these DT signals to learn an optimal control policy that adaptively allocates charging power, mitigates risks, and preserves grid safety under DDoS, MITM, spoofing, voltage instability, thermal overload, and communication delays. The proposed CVI integrates cyber, physical, and communication vulnerabilities into a unified state-aware metric, enabling coordinated power redistribution among multiple EV stations through a distributed primal-dual scheme. Simulation results with distributed EV charging stations demonstrate the system’s ability to ensure adaptive charging, equitable energy distribution, and successful convergence to target state-of-charge (SOC) levels while mitigating potential threats. The findings validate the CVI-based strategy as an effective framework for secure, scalable, and risk-aware EV energy management in next-generation smart grids.

Abstract Sequential Orthogonal Frequency Division Multiplexing (SeqOFDM) is a modulation scheme riding on OFDM and shown to provide a better spectral efficiency without introducing undesirable degradation in the Bit Error Rate (BER). In the scheme, a mapper is added at the input of an OFDM transmitter. This mapper is a lookup table that helps select three carriers for every four bits (or symbols) presented. These carriers form the OFDM subcarriers for signal transmission. At the receiver output is a demapper that maps the received carriers to the table of the equivalent bits effectively doing the opposite of the mapper. This paper presents a theoretical analysis of the scheme, deriving closed-form expressions for BER over Additive White Gaussian Noise (AWGN) channel. Theoretical results are benchmarked against Monte Carlo simulations under identical configurations, with findings demonstrating a strong agreement between theoretical predictions and simulated outcomes, particularly in the mid-to-high Signal to Noise Ratio (SNR) regime, confirming the accuracy of the derived model. An extension of the derivation is made to Rician and Rayleigh channels, The results offer a reliable foundation for the design and optimization of SeqOFDM communication systems which at the same time circumvents the computationally intensive and time-consuming process of BER estimation through Monte Carlo methods. Thus, the objective of providing a fast and scalable alternative for performance evaluation is met.

Abstract This paper introduces a novel methodology for determining the photovoltaic (PV) hosting capacity of distribution networks by integrating short-circuit impedance analysis with maximum PV penetration assessment under dynamic stability, inverter control, and grid code considerations. This methodology utilizes Power System Simulation for Engineering (PSS/E) software by applying multiple equivalent Thevenin impedance values to a typical distribution network. The findings of this methodology are then applied to a part of Egypt’s distribution network to validate the obtained results and find the maximum hosting capacity. The second objective is to increase the PV hosting capacity by applying different control techniques to PV inverters. Results show that the PV inverter can provide voltage support and act as an active source in the power system to achieve the grid code requirements. It is also concluded that we can predict the hosting capacity of any bus in a distribution network. The results obtained from the typical system are in good agreement with those obtained from the conventional analytical method applied to the fundamental part of the Egyptian distribution network. Based on static and dynamic assessments, this research helps utility operators make decisions about large-scale PV integration into the distribution network.

Abstract Malnutrition and food insecurity have remained critical issues faced in Africa. According to the 2023 statistical data in Nigeria, for instance, approximately 87 million out of the country’s 220 million people (39.5 per cent) still live below the poverty line. From this trajectory, it is safe to say that the continent of Africa is not yet on the path to Zero Hunger (SDG 2) by 2030. While several successive government administrations have proposed various intervention programs such as Operation Feed the Nation, the Green Revolution, and Lower Niger River Basin Development Authority, fertiliser support, among others, in Nigeria, little attention has been given to plant diseases, one of the root causes of low productivity among smallholder farmers. Therefore, this research leveraged the inherent characteristics of deep learning models and developed an improved deep learning Plant Doctor based on MobileNetV3-Small architecture with a user-friendly interface that enables the drag and drop of plant images or direct upload. The developed system was tailored towards the computational demands of smallholder farmers’ low computing devices. The developed MobileNetV3-Small architecture uses a smart patch-based scanning process that focuses on the leaf regions, resizes the image to 224 × 224 as input size, and unfreezes 20 layers for feature learning from the patches. The patches are augmented using brightness, contrast, and slight rotation to ease the detection of tiny symptoms. This allows for detailed symptom analysis without overwhelming memory or processing power. The developed, improved MobileNetV3-based plant doctor easily detects plant diseases through their visual symptoms on their leaves, prescribes treatments, and broadcasts detected diseases to farmers within the same region for preventive control measures. The evaluation of the developed MobileNetV3-small showed that the system can detect plant disease with an accuracy of 99.85% on the merged PlantVillageDoc dataset, with the added advantage of broadcasting detected plant diseases to other farmers within the same cluster through their registered email. This system offers a paradigm shift in educating smallholder farmers by providing timely disease detection and expert guidance, thereby reducing crop losses, improving yields, and strengthening national food security.

Abstract The increasing popularity of multimedia applications, such as video classification, has underscored the need for efficient methods to manage and categorize vast video datasets. Video classification simplifies video categorization, enhancing searchability and retrieval by leveraging distinctive features extracted from textual, audio, and visual components. This paper introduces an automated video recognition system that classifies video content based on motion types (low, medium, and high) derived from visual component characteristics. The proposed system utilizes advanced artificial intelligence techniques with four feature extraction methods; MFCC alone, (2) MFCC after applying DWT, (3) denoised MFCC, and (4) MFCC after applying denoised DWT. And seven classification algorithms to optimize accuracy. A novel aspect of this study is the application of Mel Frequency Cepstral Coefficients (MFCC) to extract features from the video domain rather than their traditional use in audio processing, demonstrating the effectiveness of MFCC for video classification. Seven classification techniques, including K-Nearest Neighbors (KNN), Radial Basis Function Support Vector Machines (SVM-RBF), Parzen Window Method, Neighborhood Components Analysis (NCA), Multinomial Logistic Regression (ML), Linear Support Vector Machines (SVM Linear), and Decision Trees (DT), are evaluated to establish a robust classification framework. Experimental results indicate that this denoising-enhanced system significantly improves classification accuracy, providing a comprehensive framework for future applications in multimedia management and other fields.

Abstract Pneumonia is a major cause of death worldwide, with nearly 2.2 million deaths every year, including over 700,000 children aged five years and below. Chest X-ray (CXR) imaging is the standard method taken up to diagnose pneumonia; however, such image inspection is shown to be difficult even for expert radiologists. The intricacy in the visual patterns generated in X-ray images often results in misdiagnosis, indicating the importance of efficient and accurate automated substitutes. In this paper, we present a new machine learning-based system that incorporates deep learning combined with handcrafted feature extraction techniques for sophisticated pneumonia detection. We use ResNet-50 for deep feature extraction, with the integration of 2D-discrete wavelet transform (DWT) and Gray-Level Co-occurrence Matrix (GLCM) for texture feature extraction, for the intention of gaining helpful spatial and frequency-domain features. The features obtained are inputted into a Support Vector Machine (SVM) classifier, which is optimized for high accuracy and robust prediction. The experimental findings indicate that the proposed model produces a classification accuracy of 97%, accompanied by an F1-score of 0.97, over traditional methods. Through the synergistic integration of handcrafted and deep learning-based feature extraction techniques, our approach presents a trustworthy and efficient solution for automated pneumonia detection. The proposed method has the potential to aid radiologists in providing timely and accurate diagnoses, thus enhancing patient outcomes and curtailing the global burden of pneumonia-related mortality.