Browsing by Author "Khaled Shaalan"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4
    (Springer Cham, 2025) Mohammed Rasol Al Saidat; Khaled Shaalan; Suliman Yemria
    In this study, we investigate the role of Generative Pre-trained Transformer 4 (GPT-4) in enhancing interpretability of sequential predictions in Natural Language Processing (NLP). Our study introduces a hybrid model that integrates traditional sequential prediction models with GPT-4, aiming to generate detailed, context-sensitive explanations for model outputs. This approach is rooted in the use of advanced transformer architectures and a specialized tokenization method that maintains semantic coherence, allowing for deep contextual analysis by GPT-4. Additionally, we devise a rationale generation algorithm that achieves a balance between succinctness and informativeness. Our experimental validation spans across various high-dimensional datasets, including financial time-series and multilingual texts, employing both qualitative and quantitative metrics to evaluate the model’s performance. These metrics focus on the plausibility and consistency of the rationales, as well as the model’s predictive accuracy. Preliminary results demonstrate that our approach not only enhances the accuracy of sequential predictions but also significantly improves their interpretability. This finding highlights the potential of generative AI to bridge the gap between complex AI decision-making processes. This research underscores the viability of employing generative AI to elucidate the underlying mechanisms of sequential prediction models, paving the way for more transparent AI systems.
  • No Thumbnail Available
    Item
    Exploring AI Conversational Chatbot UX Design: Insights from High School
    (Springer Cham, 2025) Suha Khalil Assayed; Daniel Woods; Manar Alkahtib; Khaled Shaalan
    Advancements in state-of-the-art models and algorithms for chatbots have significantly driven the growth and evolution of human–computer interaction (HCI) in recent years. As a result, numerous authors are inspired to study the most effective interactive chatbot design that can maximize students’ experiences. Despite the fact that high school is one of the most critical stage in a student’s life, there is a lack of studies that focused on developing effective interactive high school advising chatbots. To address this current gap, this study aims to elicit the main effective features for high school advising chatbot. The authors in this study conducted a semi-structured qualitative interview with six high school students in UAE and the MAXQDA Analytics software—ver. 22.6.0 is implemented by processing the thematic analysis to study the findings. The results revealed that high school students recommended the same general interaction design characteristics that was derived from the previous systematic review with emphasizing more into accurate, reliable, and trustworthy short answers with having minimal conversational issues. In addition to that, emotions and empathic factors are less important for high school students.
  • No Thumbnail Available
    Item
    Leveraging Network Traffic Byte-Streams for Machine Learning Based Early Botnet Attack Detection
    (Springer Cham, 2025) Rajesh Thomas; Suleiman Yerima; Khaled Shaalan
    Botnet attacks can overwhelm networks and severely affect the availability of services. Anomaly based detection techniques using machine learning are effective against zero-day attacks. However, they require complex data preprocessing and feature extraction which can affect the early detection of botnet attacks. In this paper we propose a novel approach, for early detection of botnet attacks using machine learning models that learn from byte representation of raw network traffic flows. The study departs from the traditional approach of network-based intrusion detection which relies on flow statistics and other hand-crafted features. We discuss our framework which includes light weight network traffic pre-processing, transformation, and model training. We used the CTU-13 dataset to evaluate the proposed byte-based botnet detection system. Our results show that byte-based representation can provide an effective and ultra lightweight means of developing network intrusion detection systems that can match the performance of traditional approaches, while also enabling early detection of botnet attacks. In our experiments we achieved accuracy of 99.9% consistently across different byte stream sizes for the Decision Tree and Logistic Regression classifiers.