Khaled Shaban

Mohamed Ehab, Ali Hamdi, Khaled Shaban

Real-world categorization is severely hampered by class imbalance because traditional ensembles favor majority classes, which lowers minority performance and overall F1-score. We provide a unique ensemble technique for imbalanced problems called CAMO (Class-Aware Minority-Optimized).Through a hierarchical procedure that incorporates vote distributions, confidence calibration, and inter model uncertainty, CAMO dynamically boosts underrepresented classes while preserving and amplifying minority forecasts.We verify CAMO on two highly unbalanced, domain-specific benchmarks: the DIAR-AI/Emotion dataset and the ternary BEA 2025 dataset. We benchmark against seven proven ensemble algorithms using eight different language models (three LLMs and five SLMs) under zero-shot and fine-tuned settings .With refined models, CAMO consistently earns the greatest strict macro F1-score, setting a new benchmark. Its benefit works in concert with model adaptation, showing that the best ensemble choice depends on model properties .This proves that CAMO is a reliable, domain-neutral framework for unbalanced categorization.

Omama Hamad, Ali Hamdi, Khaled Shaban

Effective feature representations play a critical role in enhancing the performance of text generation models that rely on deep neural networks. However, current approaches suffer from several drawbacks, such as the inability to capture the deep semantics of language and sensitivity to minor input variations, resulting in significant changes in the generated text. In this paper, we present a novel solution to these challenges by employing a mixture of experts, multiple encoders, to offer distinct perspectives on the emotional state of the user's utterance while simultaneously enhancing performance. We propose an end-to-end model architecture called ASEM that performs emotion analysis on top of sentiment analysis for open-domain chatbots, enabling the generation of empathetic responses that are fluent and relevant. In contrast to traditional attention mechanisms, the proposed model employs a specialized attention strategy that uniquely zeroes in on sentiment and emotion nuances within the user's utterance. This ensures the generation of context-rich representations tailored to the underlying emotional tone and sentiment intricacies of the text. Our approach outperforms existing methods for generating empathetic embeddings, providing empathetic and diverse responses. The performance of our proposed model significantly exceeds that of existing models, enhancing emotion detection accuracy by 6.2% and lexical diversity by 1.4%.

Abdulrahman Allam, Seif Ahmed, Ali Hamdi et al.

The development of medical chatbots in Arabic is significantly constrained by the scarcity of large-scale, high-quality annotated datasets. While prior efforts compiled a dataset of 20,000 Arabic patient-doctor interactions from social media to fine-tune large language models (LLMs), model scalability and generalization remained limited. In this study, we propose a scalable synthetic data augmentation strategy to expand the training corpus to 100,000 records. Using advanced generative AI systems ChatGPT-4o and Gemini 2.5 Pro we generated 80,000 contextually relevant and medically coherent synthetic question-answer pairs grounded in the structure of the original dataset. These synthetic samples were semantically filtered, manually validated, and integrated into the training pipeline. We fine-tuned five LLMs, including Mistral-7B and AraGPT2, and evaluated their performance using BERTScore metrics and expert-driven qualitative assessments. To further analyze the effectiveness of synthetic sources, we conducted an ablation study comparing ChatGPT-4o and Gemini-generated data independently. The results showed that ChatGPT-4o data consistently led to higher F1-scores and fewer hallucinations across all models. Overall, our findings demonstrate the viability of synthetic augmentation as a practical solution for enhancing domain-specific language models in-low resource medical NLP, paving the way for more inclusive, scalable, and accurate Arabic healthcare chatbot systems.

Omar Walid, Mohamed T. Younes, Khaled Shaban et al.

This paper presents MSLEF, a multi-segment ensemble framework that employs LLM fine-tuning to enhance resume parsing in recruitment automation. It integrates fine-tuned Large Language Models (LLMs) using weighted voting, with each model specializing in a specific resume segment to boost accuracy. Building on MLAR , MSLEF introduces a segment-aware architecture that leverages field-specific weighting tailored to each resume part, effectively overcoming the limitations of single-model systems by adapting to diverse formats and structures. The framework incorporates Gemini-2.5-Flash LLM as a high-level aggregator for complex sections and utilizes Gemma 9B, LLaMA 3.1 8B, and Phi-4 14B. MSLEF achieves significant improvements in Exact Match (EM), F1 score, BLEU, ROUGE, and Recruitment Similarity (RS) metrics, outperforming the best single model by up to +7% in RS. Its segment-aware design enhances generalization across varied resume layouts, making it highly adaptable to real-world hiring scenarios while ensuring precise and reliable candidate representation.

Mohamed T. Younes, Omar Walid, Khaled Shaban et al.

This paper presents a novel approach to recruitment automation. Large Language Models (LLMs) were fine-tuned to improve accuracy and efficiency. Building upon our previous work on the Multilayer Large Language Model-Based Robotic Process Automation Applicant Tracking (MLAR) system . This work introduces a novel methodology. Training fine-tuned LLMs specifically tuned for recruitment tasks. The proposed framework addresses the limitations of generic LLMs by creating a synthetic dataset that uses a standardized JSON format. This helps ensure consistency and scalability. In addition to the synthetic data set, the resumes were parsed using DeepSeek, a high-parameter LLM. The resumes were parsed into the same structured JSON format and placed in the training set. This will help improve data diversity and realism. Through experimentation, we demonstrate significant improvements in performance metrics, such as exact match, F1 score, BLEU score, ROUGE score, and overall similarity compared to base models and other state-of-the-art LLMs. In particular, the fine-tuned Phi-4 model achieved the highest F1 score of 90.62%, indicating exceptional precision and recall in recruitment tasks. This study highlights the potential of fine-tuned LLMs. Furthermore, it will revolutionize recruitment workflows by providing more accurate candidate-job matching.

Ali Hamdi, Malak Mohamed, Rokaia Emad et al.

Social telehealth has made remarkable progress in healthcare by allowing patients to post symptoms and participate in medical consultations remotely. Users frequently post symptoms on social media and online health platforms, creating a huge repository of medical data that can be leveraged for disease classification. Large language models (LLMs) such as LLAMA3 and GPT-3.5, along with transformer-based models like BERT, have demonstrated strong capabilities in processing complex medical text. In this study, we evaluate three Arabic medical text preprocessing methods such as summarization, refinement, and Named Entity Recognition (NER) before applying fine-tuned Arabic transformer models (CAMeLBERT, AraBERT, and AsafayaBERT). To enhance robustness, we adopt a majority voting ensemble that combines predictions from original and preprocessed text representations. This approach achieved the best classification accuracy of 80.56%, thus showing its effectiveness in leveraging various text representations and model predictions to improve the understanding of medical texts. To the best of our knowledge, this is the first work that integrates LLM-based preprocessing with fine-tuned Arabic transformer models and ensemble learning for disease classification in Arabic social telehealth data.

Youssef Maklad, Fares Wael, Ali Hamdi et al.

Traditional protocol fuzzing techniques, such as those employed by AFL-based systems, often lack effectiveness due to a limited semantic understanding of complex protocol grammars and rigid seed mutation strategies. Recent works, such as ChatAFL, have integrated Large Language Models (LLMs) to guide protocol fuzzing and address these limitations, pushing protocol fuzzers to wider exploration of the protocol state space. But ChatAFL still faces issues like unreliable output, LLM hallucinations, and assumptions of LLM knowledge about protocol specifications. This paper introduces MultiFuzz, a novel dense retrieval-based multi-agent system designed to overcome these limitations by integrating semantic-aware context retrieval, specialized agents, and structured tool-assisted reasoning. MultiFuzz utilizes agentic chunks of protocol documentation (RFC Documents) to build embeddings in a vector database for a retrieval-augmented generation (RAG) pipeline, enabling agents to generate more reliable and structured outputs, enhancing the fuzzer in mutating protocol messages with enhanced state coverage and adherence to syntactic constraints. The framework decomposes the fuzzing process into modular groups of agents that collaborate through chain-of-thought reasoning to dynamically adapt fuzzing strategies based on the retrieved contextual knowledge. Experimental evaluations on the Real-Time Streaming Protocol (RTSP) demonstrate that MultiFuzz significantly improves branch coverage and explores deeper protocol states and transitions over state-of-the-art (SOTA) fuzzers such as NSFuzz, AFLNet, and ChatAFL. By combining dense retrieval, agentic coordination, and language model reasoning, MultiFuzz establishes a new paradigm in autonomous protocol fuzzing, offering a scalable and extensible foundation for future research in intelligent agentic-based fuzzing systems.

Mohamed Basem, Islam Oshallah, Ali Hamdi et al.

Quranic Question Answering presents unique challenges due to the linguistic complexity of Classical Arabic and the semantic richness of religious texts. In this paper, we propose a novel two-stage framework that addresses both passage retrieval and answer extraction. For passage retrieval, we ensemble fine-tuned Arabic language models to achieve superior ranking performance. For answer extraction, we employ instruction-tuned large language models with few-shot prompting to overcome the limitations of fine-tuning on small datasets. Our approach achieves state-of-the-art results on the Quran QA 2023 Shared Task, with a MAP@10 of 0.3128 and MRR@10 of 0.5763 for retrieval, and a pAP@10 of 0.669 for extraction, substantially outperforming previous methods. These results demonstrate that combining model ensembling and instruction-tuned language models effectively addresses the challenges of low-resource question answering in specialized domains.

Ali Hamdi, Amr Aboeleneen, Khaled Shaban

Existing learning models often utilise CT-scan images to predict lung diseases. These models are posed by high uncertainties that affect lung segmentation and visual feature learning. We introduce MARL, a novel Multimodal Attentional Representation Learning model architecture that learns useful features from multimodal data under uncertainty. We feed the proposed model with both the lung CT-scan images and their perspective historical patients' biological records collected over times. Such rich data offers to analyse both spatial and temporal aspects of the disease. MARL employs Fuzzy-based image spatial segmentation to overcome uncertainties in CT-scan images. We then utilise a pre-trained Convolutional Neural Network (CNN) to learn visual representation vectors from images. We augment patients' data with statistical features from the segmented images. We develop a Long Short-Term Memory (LSTM) network to represent the augmented data and learn sequential patterns of disease progressions. Finally, we inject both CNN and LSTM feature vectors to an attention layer to help focus on the best learning features. We evaluated MARL on regression of lung disease progression and status classification. MARL outperforms state-of-the-art CNN architectures, such as EfficientNet and DenseNet, and baseline prediction models. It achieves a 91% R^2 score, which is higher than the other models by a range of 8% to 27%. Also, MARL achieves 97% and 92% accuracy for binary and multi-class classification, respectively. MARL improves the accuracy of state-of-the-art CNN models with a range of 19% to 57%. The results show that combining spatial and sequential temporal features produces better discriminative feature.

Ali Hamdi, Khaled Shaban, Abdelkarim Erradi et al.

Spatiotemporal data mining (STDM) discovers useful patterns from the dynamic interplay between space and time. Several available surveys capture STDM advances and report a wealth of important progress in this field. However, STDM challenges and problems are not thoroughly discussed and presented in articles of their own. We attempt to fill this gap by providing a comprehensive literature survey on state-of-the-art advances in STDM. We describe the challenging issues and their causes and open gaps of multiple STDM directions and aspects. Specifically, we investigate the challenging issues in regards to spatiotemporal relationships, interdisciplinarity, discretisation, and data characteristics. Moreover, we discuss the limitations in the literature and open research problems related to spatiotemporal data representations, modelling and visualisation, and comprehensiveness of approaches. We explain issues related to STDM tasks of classification, clustering, hotspot detection, association and pattern mining, outlier detection, visualisation, visual analytics, and computer vision tasks. We also highlight STDM issues related to multiple applications including crime and public safety, traffic and transportation, earth and environment monitoring, epidemiology, social media, and Internet of Things.

Ashraf Tantawy, Abdelkarim Erradi, Sherif Abdelwahed et al.

Traditional techniques for Cyber-Physical Systems (CPS) security design either treat the cyber and physical systems independently, or do not address the specific vulnerabilities of real time embedded controllers and networks used to monitor and control physical processes. In this work, we develop and test an integrated model-based approach for CPS security risk assessment utilizing a CPS testbed with real-world industrial controllers and communication protocols. The testbed monitors and controls an exothermic Continuous Stirred Tank Reactor (CSTR) simulated in real-time. CSTR is a fundamental process unit in many industries, including Oil \& Gas, Petrochemicals, Water treatment, and nuclear industry. In addition, the process is rich in terms of hazardous scenarios that could be triggered by cyber attacks due to the lack of possible mechanical protection. The paper presents an integrated approach to analyze and design the cyber security system for a given CPS where the physical threats are identified first to guide the risk assessment process. A mathematical model is derived for the physical system using a hybrid automaton to enumerate potential hazardous states of the system. The cyber system is then analyzed using network and data flow models to develop the attack scenarios that may lead to the identified hazards. Finally, the attack scenarios are performed on the testbed and observations are obtained on the possible ways to prevent and mitigate the attacks. The insights gained from the experiments result in several key findings, including the expressive power of hybrid automaton in security risk assessment, the hazard development time and its impact on cyber security design, and the tight coupling between the physical and the cyber systems for CPS that requires an integrated design approach to achieve cost-effective and secure designs.

Ramy Baly, Alaa Khaddaj, Hazem Hajj et al.

Sentiment analysis is a highly subjective and challenging task. Its complexity further increases when applied to the Arabic language, mainly because of the large variety of dialects that are unstandardized and widely used in the Web, especially in social media. While many datasets have been released to train sentiment classifiers in Arabic, most of these datasets contain shallow annotation, only marking the sentiment of the text unit, as a word, a sentence or a document. In this paper, we present the Arabic Sentiment Twitter Dataset for the Levantine dialect (ArSenTD-LEV). Based on findings from analyzing tweets from the Levant region, we created a dataset of 4,000 tweets with the following annotations: the overall sentiment of the tweet, the target to which the sentiment was expressed, how the sentiment was expressed, and the topic of the tweet. Results confirm the importance of these annotations at improving the performance of a baseline sentiment classifier. They also confirm the gap of training in a certain domain, and testing in another domain.

Abduljalil Mohamed, Khaled Bashir Shaban, Amr Mohamed

Wireless electroencephalogram (EEG) sensors have been successfully applied in many medical and computer brain interface classifications. A common characteristic of wireless EEG sensors is that they are low powered devices, and hence an efficient usage of sensor energy resources is critical for any practical application. One way of minimizing energy consumption by the EEG sensors is by reducing the number of EEG channels participating in the classification process. For the purpose of classifying EEG signals, we propose a directed acyclic graph (DAG)-based channel selection algorithm. To achieve this objective, the EEG sensor channels are first realized in a complete undirected graph, where each channel is represented by a node. An edge between any two nodes indicates the collaboration between these nodes in identifying the system state; and the significance of this collaboration is quantified by a weight assigned to the edge. The complete graph is then reduced into a directed acyclic graph that encodes the knowledge of the non-increasing order of the channel ranking for each cognitive task. The channel selection algorithm utilizes this directed graph to find a maximum path such that the total weight of this path satisfies a predefined threshold. It has been demonstrated experimentally that channel utilization has been reduced by 50% in the worst case scenario for a three-state system and an EEG sensor with 14 channels; and the best classification accuracy obtained is 81%.