Balamurugan Balusamy

The non-invasive skin cancer, especially that of the basal cell carcinoma and squamous cell carcinoma, is an increasing global health burden. Traditional m

Cloud computing is a fundamental paradigm in modern computing; however, its distributed and multi-tenant nature increases exposure to cyber threats, making effective intrusion detection essential. Despite recent advances in artificial intelligence–based intrusion detection systems (IDS), many existing approaches remain sensitive to class imbalance, computationally demanding, and insufficiently robust under large-scale network traffic conditions. To address these challenges, this paper proposes an AI-driven intrusion detection framework, termed Secured Deep Generative Adversarial Rat-Optimized Diagonal Matrix (SDGA-RODM), designed for efficient intrusion detection in large-scale cloud network traffic environments. The proposed framework integrates three key components: (i) a mean divergence regularization (MDR)–based preprocessing strategy to mitigate class imbalance without altering intrinsic data distributions; (ii) a rat-optimized diagonal matrix score (RODMS)–based feature selection mechanism to derive compact and discriminative feature subsets; and (iii) a Wasserstein generative adversarial learning–based classifier (DWGALC) to enhance robustness under complex and imbalanced attack patterns. Extensive experiments conducted on the LUFlow and CIC-IDS-2017 benchmark datasets demonstrate that SDGA-RODM achieves improved performance compared with the evaluated representative IDS methods, including deep learning, ensemble-based, and optimization-driven approaches, achieving up to 6–8% improvement in detection accuracy, 15–40% reduction in classification error, and up to 30% reduction in training time under imbalanced traffic conditions. These results indicate that SDGA-RODM provides an effective and computationally efficient intrusion detection framework, demonstrating promising performance and robustness under controlled benchmark and simulation-based settings representative of cloud network traffic environments.

Sepsis is a prominent cause of death in intensive care units, and delayed diagnosis greatly worsens fatal outcomes due to the complex, irregular, and uneven character of clinical time-series data. Hence we proposed an interpretable and uncertainty-aware deep learning architecture that solves data quality, temporal irregularity, and clinical explainability restrictions, which are frequently addressed separately by existing models. The suggested method combines Bidirectional Recurrent Imputation for Time Series (BRITS)-based imputation, hybrid Conditional Tabular Generative Adversarial Network-Synthetic Minority Over-sampling Technique (CTGAN-SMOTE) data augmentation, a Temporal Convolutional Networks (TCN)-Attention architecture, and continuous-time neural Ordinary Differential Equations (ODEs), along with SHapley Additive exPlanations (SHAP)-based feature attribution and uncertainty quantification. The experimental evaluation on a large ICU dataset reveals greater predictive accuracy, with an AUROC of 0.926 and accurate early warnings up to six hours before clinical onset, all while maintaining strong interpretability and calibration. The proposed framework demonstrates strong predictive performance and provides early warnings up to six hours before clinical onset, while maintaining interpretability and calibration. While the results are promising, further validation across multiple clinical settings is required to confirm its generalisability and real-world applicability.

Background: Lyme disease is the most widespread tick-borne infection in the Northern Hemisphere and is challenging to diagnose and treat due to its changing clinical presentation, antigenic variation, tissue tropism, and the expanding distribution of vectors. This review includes ecology, pathogenesis, diagnostics, treatment, post-treatment, prevention, and novel translational approaches. Methods: A literature review was conducted to include literature published between January 2000 and March 2026 in PubMed/MEDLINE, Scopus, and Web of Science, with landmark studies used where applicable. Original research, clinical trials, systematic reviews, and major public health reports were prioritised. Results: Two-tier serology is the most common diagnostic technique, but it has limited sensitivity in early infection and does not distinguish between active and past infection. Culture and PCR are only useful in a few instances. The use of new technologies such as multiomics biomarkers, metagenomics, T-cell assays, and AI-enhanced diagnostics is promising but has not yet been tested in a prospective multicentre study. Most of the early and disseminated disease can be treated with standard antibiotics, whereas the long-term therapy of PTLD is not justified and can cause more adverse effects. These preventive and curative advancements involve VLA15 vaccination, anti-tick and reservoir-specific approaches, microbiome-engineered vectors, and anti-persister/ biofilm. Conclusion: Lyme disease requires combined prevention, improved diagnostics, enhanced biomarker research, and well-designed PTLD trials. The short-term benefits will be based on the optimisation of existing diagnostics and vector control, and the long-term benefits will be based on rigorous validation of vaccines, biomarkers, and specific therapies.

The increasing heterogeneity of cloud, enterprise, and Internet of Things (IoT) environments raises concerns about the long-term reliability of machine-learning-based intrusion detection systems (IDSs). This study evaluates temporal robustness and cross-domain generalization using four publicly available datasets collected between 2017 and 2024. Five representative models—Random Forest, Gradient Boosting, Multi-Layer Perceptron, Autoencoder, and a lightweight 1D-CNN—are assessed under in-dataset, forward temporal, enterprise-to-IoT transfer, and dataset-agnostic evaluation protocols without retraining. In the dataset evaluation, models achieve Macro-F1 scores between 0.84 and 0.96. However, forward temporal testing reveals consistent degradation, with performance reductions reaching ΔF1 ≈ 0.20–0.27 when models trained on 2017 enterprise traffic are applied to IoT datasets from 2023 to 2024. Under cross-domain transfer, Macro-F1 decreases to 0.69–0.78, and benign false-positive rates increase up to 0.30, indicating substantial sensitivity to traffic distribution shifts. Tree-based ensemble models show comparatively lower degradation (≈6–23%) and reduced performance variance across datasets. Semantic feature analysis further indicates that flow intensity and temporal activity features exhibit higher cross-dataset stability than protocol-dependent indicators. These findings demonstrate that IDS robustness in evolving Internet environments depends strongly on evaluation methodology and feature stability, highlighting the need for generalization-oriented assessment strategies.

Oropouche virus (OROV) is a re-emerging arthropod-borne virus of the genus Orthobunyavirus (family Peribunyaviridae) that poses an increasing public health