Search

Abstract The novelty and growing sophistication of cyber threats mean that high accuracy and interpretable machine learning models are needed more than ever before for Intrusion Detection and Prevention Systems. This study aims to solve this challenge by applying Explainable AI techniques, including Shapley Additive explanations feature selection, to improve model performance, robustness, and transparency. The method systematically employs different classifiers and proposes a new hybrid method called Hybrid Bagging-Boosting and Boosting on Residuals. Then, performance is taken in four steps: the multistep evaluation of hybrid ensemble learning methods for binary classification and fine-tuning of performance; feature selection using Shapley Additive explanations values retraining the hybrid model for better performance and reducing overfitting; the generalization of the proposed model for multiclass classification; and the evaluation using standard information metrics such as accuracy, precision, recall, and F1-score. Key results indicate that the proposed methods outperform state-of-the-art algorithms, achieving a peak accuracy of 98.47% and an F1 score of 96.19%. These improvements stem from advanced feature selection and resampling techniques, enhancing model accuracy and balancing precision and recall. Integrating Shapley Additive explanations-based feature selection with hybrid ensemble methods significantly boosts the predictive and explanatory power of Intrusion Detection and Prevention Systems, addressing common pitfalls in traditional cybersecurity models. This study paves the way for further research on statistical innovations to enhance Intrusion Detection and Prevention Systems performance.

Abstract Background Precise identification, discrimination and assessment of central nervous system (CNS) tumors is of critical importance to brain neoplasm treatment. Due to the complexity and limited resolutions of the existing diagnostic tools, however, it is difficult to identify the tumors and their boundaries precisely in clinical practice, and thus, the conventional way of brain neoplasm treatment relies mainly on the experiences of neurosurgeons to make resection decisions in the surgery process. The purpose of this study is to explore the potential of Micro-optical coherence tomography (μOCT) as an intraoperative diagnostic imaging tool for identifying and discriminating glioma and meningioma with their microstructure imaging ex vivo, which thus may help neurosurgeons to perform precise surgery with low costs and reduced burdens. Methods Fresh glioma and meningioma samples were resected from patients, and then slices of such samples were excised and imaged instantly ex vivo with a lab-built μOCT, which achieves a spatial resolution of ~ 2.0 μm (μm). The acquired optical coherence tomography (OCT) images were pathologically evaluated and compared to their corresponding histology for both tumor type and tumor grade discriminations in different cases. Results By using the lab-built μOCT, both the cross-sectional and en face images of glioma and meningioma were acquired ex vivo. Based upon the morphology results, both the glioma and meningioma types as well as the glioma grades were assessed and discriminated. Comparisons between OCT imaging results and histology showed that typical tissue microstructures of glioma and meningioma could be clearly identified and confirmed the type and grade discriminations with satisfactory accuracy. Conclusions μOCT could provide high-resolution three-dimensional (3D) imaging of the glioma and meningioma tissue microstructures rapidly ex vivo. μOCT imaging results could help discriminate both tumor types and grades, which illustrates the potential of μOCT as an intraoperative diagnostic imaging tool to help neurosurgeons perform their surgery precisely in tumor treatment process.