Plants are fundamental to global food security; however, plant diseases significantly reduce agricultural productivity, making early and accurate detection essential. Traditional inspection approaches rely heavily on manual observation, which is labor-intensive, subjective, difficult to scale, and susceptible to human error. In contrast, artificial intelligence (AI) combined with computer vision (CV) offers an effective solution for early-stage disease detection, minimizing yield losses while overcoming the limitations of manual monitoring systems. In this study, a novel deep learning architecture, the Swin Transformer with Harmonic Densely Connected Network (STHarDNet), is proposed. The framework integrates a Swin Transformer (ST) as the initial skip connection within a HarDNet-based U-Net architecture to precisely localize diseased regions in leaf images. Subsequently, a modified ResNet-152 model is employed for disease classification. The ST component captures long-range dependencies at high resolution, enabling enhanced feature representation and more accurate boundary delineation. To ensure robustness and reliability, extensive statistical validation techniques are applied, including 5-fold cross-validation, bootstrap confidence intervals, Gelman-Rubin convergence diagnostics, Cohen’s d effect size, and paired t-tests with Bonferroni correction. These analyses confirm both the statistical stability and practical effectiveness of the proposed model. Experiments conducted on the hybrid PlantVillage dataset, comprising 20,798 images across 17 classes, demonstrate that STHarDNet achieves an outstanding classification accuracy of 99.81%, outperforming existing methods across multiple evaluation metrics. This research establishes a reproducible and statistically validated benchmark for automated plant disease detection (PDD), supporting its scalability in precision agriculture. Furthermore, the proposed system highlights the potential of intelligent, high-accuracy tools to assist non-expert users in identifying plant diseases at early stages, thereby enabling timely intervention and improved crop management.

The growing use of Portable Document Format (PDF) files across various sectors such as education, government, and business has inadvertently turned them into a major target for cyberattacks. Cybercriminals take advantage of the inherent flexibility and layered structure of PDFs to inject malicious content, often employing advanced obfuscation techniques to evade detection by traditional signature-based security systems. These conventional methods are no longer adequate, especially against sophisticated threats like zero-day exploits and polymorphic malware. In response to these challenges, this study introduces a machine learning-based detection framework specifically designed to combat such threats. Central to the proposed solution is a stacked ensemble learning model that combines the strengths of four high-performing classifiers: Random Forest (RF), Extreme Gradient Boosting (XGB), LightGBM (LGBM), and CatBoost (CB). These models operate in parallel as base learners, each capturing different aspects of the data. Their outputs are then refined by a Gradient Boosting Classifier (GBC), which serves as a meta-learner to enhance prediction accuracy. To ensure the model remains both efficient and effective, Principal Component Analysis (PCA) is applied to reduce feature dimensionality while preserving critical information necessary for malware classification. The model is trained and validated using the CIC-Evasive PDFMalware2022 dataset, which includes a wide range of both malicious and benign PDF samples. The results demonstrate that the framework achieves impressive performance, with 97.10% accuracy and a 97.39% F1-score, surpassing several existing techniques. To enhance trust and interpretability, the system incorporates Local Interpretable Model-agnostic Explanations (LIME), which provides user-friendly insights into the rationale behind each prediction. This research emphasizes how the integration of ensemble learning, feature reduction, and explainable AI can lead to a practical and scalable solution for detecting complex PDF-based threats. The proposed framework lays the foundation for the next generation of intelligent, resilient cybersecurity systems that can address ever-evolving attack strategies.

The escalating complexity of modern malware continues to undermine the effectiveness of traditional signature-based detection techniques, which are often unable to adapt to rapidly evolving attack patterns. To address these challenges, this study proposes X-MalNet, a lightweight Convolutional Neural Network (CNN) framework designed for static malware classification through image-based representations of binary executables. By converting malware binaries into grayscale images, the model extracts distinctive structural and texture-level features that signify malicious intent, thereby eliminating the dependence on manual feature engineering or dynamic behavioral analysis. Built upon a modified AlexNet architecture, X-MalNet employs transfer learning to enhance generalization and reduce computational cost, enabling efficient training and deployment on limited hardware resources. To promote interpretability and transparency, the framework integrates Gradient-weighted Class Activation Mapping (Grad-CAM) and Deep SHapley Additive exPlanations (DeepSHAP), offering spatial and pixel-level visualizations that reveal how specific image regions influence classification outcomes. These explainability components support security analysts in validating the model’s reasoning, strengthening confidence in AI-assisted malware detection. Comprehensive experiments on the Malimg and Malevis benchmark datasets confirm the superior performance of X-MalNet, achieving classification accuracies of 99.15% and 98.72%, respectively. Further robustness evaluations using Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) adversarial attacks demonstrate the model’s resilience against perturbed inputs. In conclusion, X-MalNet emerges as a scalable, interpretable, and robust malware detection framework that effectively balances accuracy, efficiency, and explainability. Its lightweight design and adversarial stability position it as a promising solution for real-world cybersecurity deployments, advancing the development of trustworthy, automated, and transparent malware classification systems.

The convergence of Software Defined Networking (SDN) in Internet of Vehicles (IoV) enables a flexible, programmable, and globally visible network control architecture across Road Side Units (RSUs), cloud servers, and automobiles. While this integration enhances scalability and safety, it also raises sophisticated cyberthreats, particularly Distributed Denial of Service (DDoS) attacks. Traditional rule-based anomaly detection methods often struggle to detect modern low-and-slow DDoS patterns, thereby leading to higher false positives. To this end, this study proposes an explainable hybrid framework to detect DDoS attacks in SDN-enabled IoV (SDN-IoV). The hybrid framework utilizes a Residual Network (ResNet) to capture spatial correlations and a Bi-Long Short-Term Memory (BiLSTM) to capture both forward and backward temporal dependencies in high-dimensional input patterns. To ensure transparency and trustworthiness, the model integrates the Explainable AI (XAI) technique, i.e., SHapley Additive exPlanations (SHAP). SHAP highlights the contribution of each feature during the decision-making process, facilitating security analysts to understand the rationale behind the attack classification decision. The SDN-IoV environment is created in Mininet-WiFi and SUMO, and the hybrid model is trained on the CICDDoS2019 security dataset. The simulation results reveal the efficacy of the proposed model in terms of standard performance metrics compared to similar baseline methods.

Recent studies indicate that millions of individuals suffer from renal diseases, with renal carcinoma, a type of kidney cancer, emerging as both a chronic illness and a significant cause of mortality. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) have become essential tools for diagnosing and assessing kidney disorders. However, accurate analysis of these medical images is critical for detecting and evaluating tumor severity. This study introduces an integrated hybrid framework that combines three complementary deep learning models for kidney tumor segmentation from MRI images. The proposed framework fuses a customized U-Net and Mask R-CNN using a weighted scheme to achieve semantic and instance-level segmentation. The fused outputs are further refined through edge detection using Stochastic Feature Mapping Neural Networks (SFMNN), while volumetric consistency is ensured through Improved Mini-Batch K-Means (IMBKM) clustering integrated with an Encoder-Decoder Convolutional Neural Network (EDCNN). The outputs of these three stages are combined through a weighted fusion mechanism, with optimal weights determined empirically. Experiments on MRI scans from the TCGA-KIRC dataset demonstrate that the proposed hybrid framework significantly outperforms standalone models, achieving a Dice Score of 92.5%, an IoU of 87.8%, a Precision of 93.1%, a Recall of 90.8%, and a Hausdorff Distance of 2.8 mm. These findings validate that the weighted integration of complementary architectures effectively overcomes key limitations in kidney tumor segmentation, leading to improved diagnostic accuracy and robustness in medical image analysis.

Numerous sectors, such as education, the IT sector, and corporate organizations, transitioned to virtual meetings after the COVID-19 crisis. Organizations now seek to assess participants’ fatigue levels in online meetings to remain competitive. Instructors cannot effectively monitor every individual in a virtual environment, which raises significant concerns about participant fatigue. Our proposed system monitors fatigue, identifying attentive and drowsy individuals throughout the online session. We leverage Dlib’s pre-trained facial landmark detector and focus on the eye landmarks only, offering a more detailed analysis for predicting eye opening and closing of the eyes, rather than focusing on the entire face. We introduce an Eye Polygon Area (EPA) formula, which computes eye activity from Dlib eye landmarks by measuring the polygonal area of the eye opening. Unlike the Eye Aspect Ratio (EAR), which relies on a single distance ratio, EPA adapts to different eye shapes (round, narrow, or wide), providing a more reliable measure for fatigue detection. The VMFD system issues a warning if a participant remains in a fatigued condition for 36 consecutive frames. The proposed technology is tested under multiple scenarios, including low- to high-lighting conditions (50–1400 lux) and both with and without glasses. This study builds an OpenCV application in Python, evaluated using the iBUG 300-W dataset, achieving 97.5% accuracy in detecting active participants. We compare VMFD with conventional methods relying on the EAR and show that the EPA technique performs significantly better.

The cloud-fog computing paradigm has emerged as a novel hybrid computing model that integrates computational resources at both fog nodes and cloud servers to address the challenges posed by dynamic and heterogeneous computing networks. Finding an optimal computational resource for task offloading and then executing efficiently is a critical issue to achieve a trade-off between energy consumption and transmission delay. In this network, the task processed at fog nodes reduces transmission delay. Still, it increases energy consumption, while routing tasks to the cloud server saves energy at the cost of higher communication delay. Moreover, the order in which offloaded tasks are executed affects the system’s efficiency. For instance, executing lower-priority tasks before higher-priority jobs can disturb the reliability and stability of the system. Therefore, an efficient strategy of optimal computation offloading and task scheduling is required for operational efficacy. In this paper, we introduced a multi-objective and enhanced version of Cheeta Optimizer (CO), namely (MoECO), to jointly optimize the computation offloading and task scheduling in cloud-fog networks to minimize two competing objectives, i.e., energy consumption and communication delay. MoECO first assigns tasks to the optimal computational nodes and then the allocated tasks are scheduled for processing based on the task priority. The mathematical modelling of CO needs improvement in computation time and convergence speed. Therefore, MoECO is proposed to increase the search capability of agents by controlling the search strategy based on a leader’s location. The adaptive step length operator is adjusted to diversify the solution and thus improves the exploration phase, i.e., global search strategy. Consequently, this prevents the algorithm from getting trapped in the local optimal solution. Moreover, the interaction factor during the exploitation phase is also adjusted based on the location of the prey instead of the adjacent Cheetah. This increases the exploitation capability of agents, i.e., local search capability. Furthermore, MoECO employs a multi-objective Pareto-optimal front to simultaneously minimize designated objectives. Comprehensive simulations in MATLAB demonstrate that the proposed algorithm obtains multiple solutions via a Pareto-optimal front and achieves an efficient trade-off between optimization objectives compared to baseline methods.

Android smartphones have become an integral part of our daily lives, becoming targets for ransomware attacks. Such attacks encrypt user information and ask for payment to recover it. Conventional detection mechanisms, such as signature-based and heuristic techniques, often fail to detect new and polymorphic ransomware samples. To address this challenge, we employed various ensemble classifiers, such as Random Forest, Gradient Boosting, Bagging, and AutoML models. We aimed to showcase how AutoML can automate processes such as model selection, feature engineering, and hyperparameter optimization, to minimize manual effort while ensuring or enhancing performance compared to traditional approaches. We used this framework to test it with a publicly available dataset from the Kaggle repository, which contains features for Android ransomware network traffic. The dataset comprises 392,024 flow records, divided into eleven groups. There are ten classes for various ransomware types, including SVpeng, PornDroid, Koler, WannaLocker, and Lockerpin. There is also a class for regular traffic. We applied a three-step procedure to select the most relevant features: filter, wrapper, and embedded methods. The Bagging classifier was highly accurate, correctly getting 99.84% of the time. The FLAML AutoML framework was even more accurate, correctly getting 99.85% of the time. This is indicative of how well AutoML performs in improving things with minimal human assistance. Our findings indicate that AutoML is an efficient, scalable, and flexible method to discover Android ransomware, and it will facilitate the development of next-generation intrusion detection systems.

Wireless Sensor Networks (WSNs) play a vital role in smart city Internet of Things (IoT) applications, including environmental monitoring, intelligent transportation, and infrastructure management. However, limited battery capacity, uneven energy consumption, and inefficient clustering and routing mechanisms significantly reduce network lifetime, reliability, and scalability, especially in large-scale IoT deployments. Traditional routing protocols often rely on single-objective optimization or static clustering strategies, which fail to maintain long-term energy balance and stable communication performance. To address these challenges, this paper proposes iPAFAR, a Pareto-based multi-objective clustering and routing framework designed for IoT-enabled WSNs. The proposed model formulates cluster-head selection as a multi-objective optimization problem that considers residual energy, node centrality, load variance, and fairness. A Non-Dominated Sorting Artificial Algae Algorithm (NS-AAA) is used to obtain Pareto-optimal cluster-head configurations, followed by a fuzzy inference system for refined decision-making. To ensure long-term energy stability, a Lyapunov-based routing model is incorporated, and an adaptive re-clustering mechanism is introduced to reduce unnecessary control overhead under dynamic network conditions. The performance of the proposed framework is evaluated through MATLAB-based simulations and compared with existing protocols, including LEACH-M, ME-LEACH, FQA, MKNDPC, RANP-PSO, and BKA-TOA. Experimental results show that iPAFAR achieves approximately 40% lower end-to-end delay, 15%–20% higher packet delivery ratio, and 45%–50% improvement in residual energy while maintaining nearly twice the number of active nodes after 1000 simulation rounds. These results confirm that the proposed framework provides improved energy efficiency, load balancing, and routing stability, making it suitable for long-term smart city IoT deployments.

This paper presents a novel blockchain-embedded cybersecurity framework for industrial solar power systems, integrating immutable machine learning (ML) with distributed ledger technology. Our contribution focused on three factors, Quantum-resistant feature engineering using the UNSW-NB15 dataset adapted for solar infrastructure anomalies. An enhanced Light Gradient Boosting Machine (LightGBM) classifier with blockchain-validated decision thresholds, and A cryptographic proof-of-threat (PoT) consensus mechanism for cyber attack verification. The proposed Immutable LightGBM model with majority voting and cryptographic feature encoding achieves 96.9% detection accuracy with 0.97 weighted average of precision, recall and F1-score, outperforming conventional intrusion detection systems (IDSs) by 12.7% in false positive reduction. The blockchain layer demonstrates a 2.4-s average block confirmation time with 256-bit SHA-3 hashing, enabling real-time threat logging in photovoltaic networks. Experimental results improve in attack traceability compared to centralized security systems, establishing new benchmarks for trustworthy anomaly detection in smart grid infrastructures. This study also compared traditional and hybrid ML based blockchian driven IDSs and attained better classification results. The proposed framework not only delivers a resilient, adaptable threat mitigation system (TMS) for Industry 4.0 solar powered infrastructure but also attains high explainability, scalability with tamper-proof logs, and remarkably exceptional ability of endurance to cyber attacks.