Publications internationales

2026
Bouslah Ayoub, Mekhilef Ilyes, Taleb Nora, and Khaoucha Aicha. (2026), Towards Transparent AI-Aided Neurology: Detection and Lateralization of Parkinson's Disease. Biomedical Materials & Devices : Springer, https://www.researchsquare.com/article/rs-7528990/v1
2024
Khaoucha Aicha, Taleb Nora, Ahmim Ahmed, Bouslah Ayoub,. (2024), Predicting Parkinson's disease from typing patterns using shapely additive explanations and machine learning
2023
Bouslah Ayoub, Talab Nora. (2023), A new Parkinson detection system based on evolutionary fast learning networks and voice measurements. International Journal of Medical Engineering and Informaticshttps://www.inderscienceonline.com/doi/abs/10.1504/IJMEI.2023.130731
2022
Bouslah Ayoub, Talab Nora. (2022), An Optimized Parkinson's disorder identication through evolutionary fast learning network. international journal of intelligent computing and cyberneticshttps://www.emerald.com/insight/content/doi/10.1108/IJICC-07-2021-0138/full/html?skipTracking=true

Communications internationales

2026
Bouslah Ayoub, Khaoucha Aicha, Medjabri Mohamed, Taleb Nora. (2026), Speech Disfluency Removal and Augmentation for Enhanced Voice Technology Interaction. 2025 International Conference on Networking and Advanced Systems (ICNAS) : IEEE, https://ieeexplore.ieee.org/abstract/document/11298091/

Résumé: Speech disfluencies, such as repetitions and pro- longations common in stuttering, hinder effective interaction with voice technologies due to limitations in Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) systems. This paper presents an end-to-end pipeline to transform disfluent speech into fluent, natural-sounding audio while preserving speaker identity and affective qualities. The system integrates a fine- tuned Whisper ASR model, achieving a 33% Word Error Rate (WER) reduction (from 18.5% to 12.3%), a hybrid disfluency detection framework with 89.5% accuracy, a T5-based text reconstruction module with high semantic fidelity (BLEU: 0.78, ROUGE-L: 0.82), and a zero-shot TTS stage (Bark/YourTTS) yielding fluent speech with strong speaker similarity (cosine similarity: 0.86) and naturalness (Mean Opinion Score: 4.1). Evaluated on datasets like SEP-28k and UCLASS, the system achieves real-time performance (latency < 500 ms), enhancing accessibility for voice assistants and communication aids.

Bouslah Ayoub, Taleb Nora, Khaoucha Aicha. (2026), Graph-Based Framework with GNNs for Neurodegenerative Disorder Detection. The International Conference on Technologies & Organization (ICTO 2025)
2024
Amina Benelhadj Saïd, Taleb Nora, Bouslah Ayoub. (2024), Revolutionizing Queue Management: Empowering Scalability with a Cutting-Edge Technology Stack. The 8th International Conference on Technologies & Organization

Résumé: This article delves into the integration of smart queue management applications with state-of-the-art technology, navigating the transition from traditional monolithic architectures to agile microservices. Powered by Supabase, Next.js, Drizzle ORM, Traefik, and Docker, the application achieves unprecedented scalability and security, revolutionizing user experience and operational efficiency through server-side rendering. Through meticulous integration, the article offers tangible insights into how these tools transform the queue management landscape, enhancing adaptability and performance in handling data, traffic, and deployment. It highlights the paradigm shift in application development, emphasizing the transformative potential of modern technologies. By strategically harnessing Supabase, Next.js, Drizzle ORM, Traefik, and Docker, the application stays at the forefront of innovation while navigating the complexities of modern queue management. This exploration offers practical insights and strategies for developers and businesses seeking to enhance their applications' scalability, security, and performance using cutting-edge technologies.

2023
Bouslah Ayoub, Khaoucha Aicha, Taleb Nora, Messaoud Bouthaina. (2023), Lax-net: Freezing of Gait Detection in Parkinson's Disease Using LSTM with Attention and XGBoost. Decision Aid Sciences and Application (DASA)https://ieeexplore.ieee.org/abstract/document/10286631
Ouartani Siouar, Taleb Nora, Bouslah Ayoub. (2023), Integrating Ontology and Machine Learning for Enhanced Decision Support in Thyroid Disease Prediction. Decision Aid Sciences and Application (DASA)https://ieeexplore.ieee.org/abstract/document/10286675
2019
Bouslah Ayoub, Taleb Nora. (2019), A genetic approach wrapped Support vector machine for feature selection applied to Parkinson's disease diagnosis. CITCS Conference on Innovative Trends in Computer Science Guelma Algiershttps://dergipark.org.tr/en/pub/ijiam/issue/54619/655417
Chelbi Sara, Taleb Nora, Bouslah Ayoub. (2019), Enterprise Ontologies: Theories and Applications. CITCS Conference on Innovative Trends in Computer Science Guelma Algiershttps://www.researchgate.net/publication/337773072_Enterprise_Ontologies-_Theories_and_Applications