https://www.ijitra.com/index.php/ijitra International Journal of Information Technology, Research and Applications Prisma Publications en-US International Journal of Information Technology, Research and Applications 2583-5343 https://www.ijitra.com/index.php/ijitra/article/view/229 <p><strong>Abstract: </strong>The increasing adoption of Artificial Intelligence (AI) in education has opened new pathways for personalized learning; however, many existing models overlook cultural and contextual relevance. In the Indian educational landscape, Indian Knowledge Systems (IKS) offer time-tested principles such as experiential learning, self-discipline, and holistic development. This study aims to design an intelligent learning framework that meaningfully combines AI technologies with IKS principles to enhance student learning outcomes.&nbsp; The primary objective of this research is to develop and assess an AI-enabled system that integrates traditional Indian pedagogical values with modern data-driven approaches. The proposed method employs a hybrid architecture that analyzes student data—including academic performance, behavioral patterns, and engagement levels—using machine learning techniques. Models such as Random Forest and Neural Networks are utilized to generate personalized learning recommendations, while IKS elements are embedded to ensure balance between cognitive, emotional, and ethical development.&nbsp; To validate the framework, a simulated dataset representing diverse learner profiles is used. The results demonstrate that the integrated model improves student engagement, supports better academic performance, and encourages a more holistic learning experience compared to conventional AI-based systems.&nbsp; The novelty of this work lies in its interdisciplinary approach, blending traditional Indian educational philosophies with advanced AI methodologies. By aligning with the vision of NEP 2020, this study presents a culturally adaptive and scalable framework that contributes to the evolution of personalized education in India.</p> VIMALA S Copyright (c) 2026 VIMALA S https://creativecommons.org/licenses/by-sa/4.0 2026-07-01 2026-07-01 5 2 01 06 10.59461/ijitra.v5i2.229 https://www.ijitra.com/index.php/ijitra/article/view/230 <p>As computer networks become faster, cyberattacks – particularly SSH and FTP brute-force attacks – have become more sophisticated, exposing limitations in traditional detection systems, including high false positive rates. This study proposes a hierarchical hybrid deep learning model integrating Convolutional Neural Networks (CNN) for spatial feature extraction and Bi-directional Long Short-Term Memory (Bi-LSTM) for temporal analysis. Principal Component Analysis (PCA) reduced 82 features to 18 key attributes, improving computational efficiency. The model was implemented using a GPU-enabled TensorFlow framework and evaluated on CIC-IDS 2017 and CSE-CIC-IDS 2018 datasets. Results show that the hybrid CNN–Bi-LSTM model outperforms standalone approaches, achieving 99.27% accuracy, 99.89% precision, 98.19% F1-score, and 97.84% recall, with a low false positive rate of 0.018%. Reliability analysis using Monte Carlo Dropout yielded 92.3% predictive certainty, while a Dietterich 5x2cv paired t-test confirmed statistically significant improvement over the HAST-IDS baseline. These findings demonstrate a scalable and high-accuracy approach for detecting brute-force attacks in modern network environments.</p> Stephen Wanjau Jane Njuki Copyright (c) 2026 Stephen Wanjau, Wanjiru Njuki https://creativecommons.org/licenses/by-sa/4.0 2026-07-01 2026-07-01 5 2 07 23 10.59461/ijitra.v5i2.230