Technology Transfer Offices (TTOs) play a critical role in converting university research into commercial impact, yet many face severe operational strain from manual workflows and limited staffing. This paper presents an Ethical AI-Enabled University Technology Transfer architecture, developed as a Design Science Research (DSR) case study based on the ICCubeX framework at Universiti Teknologi Malaysia (UTM). Positioned at the operational micro-layer to complement macro enterprise frameworks like COBIT, TOGAF, and SAFe, the modular architecture integrates a secure Retrieval-Augmented Generation (RAG) framework via access-controlled REST APIs to safeguard institutional data sovereignty. It employs a deterministic 85% mathematical confidence threshold to automatically route codified inquiries while directing complex, cross-disciplinary cases to an asynchronous Human-in-the-Loop governance layer to preserve officer validation and override authority. To ensure empirically testable outcomes, the framework establishes a Transformation Success Matrix targeting quantifiable benchmarks across inquiry turnaround agility, triage automation rates, and legacy database interoperability. The study contributes a theoretically grounded, governance-aware digital transformation blueprint for scalable and secure university technology transfer ecosystems.
Muhammad Arif Harun, Noor Azurati Ahmad, N. Maarop et al.· 2026 IEEE International Conf...· 0 citations
Machine learning-based Distributed Denial-of-Service (DDoS) detection has been widely studied, with many approaches reporting very high detection performance on public benchmark datasets. However, benchmark performance does not necessarily demonstrate operational readiness because synthetic and laboratory-generated traffic may not reflect the noise, overlap, temporal variation, and class imbalance of real cloud environments. This paper evaluates the generalization gap between controlled benchmark traffic and long-term real-world unsolicited traffic. A Random Forest classifier is evaluated using a common experimental protocol on CIC-DDoS2019, BoT-IoT, and a real-world dataset collected for 28 months from a private cloud server. The benchmark datasets maintain approximately 99% accuracy, precision, recall, and F1-score across evaluated class distributions. In contrast, the real-world dataset shows lower balanced performance and a clear recall decline under severe imbalance: accuracy reaches 98.6%, but recall decreases to 84.8% and F1-score to 90.4%. The results show that accuracy alone can overstate practical DDoS detection reliability and that recall and F1-score are essential when evaluating detectors for deployment in cloud and IoT environments.
A. Alnahari, Noor Azurati Ahmad, Essa A. Hizzam· 2026 6th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
