arXiv subjects

Yassine Himeur

Publications and source records attributed to Yassine Himeur.

At least 19 recordsLinked to original sources

arXiv2026

What Do Medical Vision-Language Models Learn in Radiology? Transfer, Alignment, and Source-Proxy Leakage Under Distribution Shift

Medical vision-language models (VLMs) can appear reliable in-domain while failing when acquisition domain, paired supervision, or evaluation protocol changes. We study this failure mode as a representation-level blind spot relevant to epistemic intelligence, without claiming a formal estimator of epistemic uncertainty. Using NIH ChestXray14 and CheXpert, we first isolate source-only cross-dataset visual transfer from unsupervised domain-adaptation diagnostics. Using PadChest and OpenI, we then evaluate multimodal alignment under strict pair-index retrieval and quantify metadata-derived source-proxy information retained in frozen embeddings. Self-supervised visual initialization improves NIH-to-CheXpert transfer over supervised ImageNet initialization in matched ResNet-18 comparisons, whereas adversarial adaptation is useful only in a narrow regime and becomes unstable as adversarial pressure increases. Multimodal exact-pair retrieval remains low under external OpenI stress testing, and source-proxy information remains recoverable from learned representations. Qualitative nearest-neighbor and Grad-CAM analyses show clinically plausible cross-dataset structure and thoracic attention patterns in many cases, while device-heavy and false-positive cases remain ambiguous. Auxiliary architecture checks are task-dependent and do not support a universal backbone ranking. Overall, the study shows that apparent competence under a single protocol can conceal transfer, alignment, and shortcut-related failure modes, motivating stress-tested evaluation of medical VLMs under distribution shift.

cs.CV↗

arXiv2026

A Review on Quantum Satellite Communications: Challenges and Future Directions

Quantum satellite communication (QSC) is emerging as a strategic technology for secure global networking and long-distance quantum connectivity. This review prioritizes the major challenges that still hinder large-scale deployment, including atmospheric loss, beam pointing and tracking, payload constraints, synchronization, scalability, and integration with terrestrial infrastructure. To contextualize these issues, we provide only a concise overview of the core concepts and enabling technologies behind QSC, together with representative milestones such as the Micius mission. Building on this background, the paper surveys recent advances in protocols, hybrid space--terrestrial architectures, turbulence mitigation, and AI-assisted optimization. It then examines future directions, including quantum Internet integration, daylight operation, satellite-supported repeaters, and space-based quantum computing. By centering the discussion on open technical bottlenecks and emerging research trajectories, this review aims to support researchers and engineers working toward practical and resilient QSC systems.

eess.SP↗

arXiv2026

BreathAI: Transfer Learning-Based Thermal Imaging for Automated Breathing Pattern Recognition

This study presents an Adaptive Transfer Learning and Thresholding-based Deep Learning Model (ATL-TDLM) for automated breathing pattern recognition using thermal imaging. Unlike conventional methods that rely on sound-based respiratory data, our approach leverages hierarchical deep feature extraction and adaptive multi-thresholding (AMT) to enhance feature segmentation. The model integrates knowledge distillation-based fine-tuning (KD-FT) to optimize learning transfer and contrastive representation learning (CRL) to improve inter-class separability between inhalation (INH) and exhalation (EXH) phases. The ATL-TDLM framework achieves an accuracy of 98.8%, significantly outperforming state-of-the-art models while ensuring computational efficiency. This approach has potential applications in respiratory disorder detection, including sleep apnea and asthma monitoring.

eess.IV↗

arXiv2025

Federated Learning with Gramian Angular Fields for Privacy-Preserving ECG Classification on Heterogeneous IoT Devices

This study presents a federated learning (FL) framework for privacy-preserving electrocardiogram (ECG) classification in Internet of Things (IoT) healthcare environments. By transforming 1D ECG signals into 2D Gramian Angular Field (GAF) images, the proposed approach enables efficient feature extraction through Convolutional Neural Networks (CNNs) while ensuring that sensitive medical data remain local to each device. This work is among the first to experimentally validate GAF-based federated ECG classification across heterogeneous IoT devices, quantifying both performance and communication efficiency. To evaluate feasibility in realistic IoT settings, we deployed the framework across a server, a laptop, and a resource-constrained Raspberry Pi 4, reflecting edge-cloud integration in IoT ecosystems. Experimental results demonstrate that the FL-GAF model achieves a high classification accuracy of 95.18% in a multi-client setup, significantly outperforming a single-client baseline in both accuracy and training time. Despite the added computational complexity of GAF transformations, the framework maintains efficient resource utilization and communication overhead. These findings highlight the potential of lightweight, privacy-preserving AI for IoT-based healthcare monitoring, supporting scalable and secure edge deployments in smart health systems.

cs.LG↗

arXiv2025

A Novel Hybrid Deep Learning and Chaotic Dynamics Approach for Thyroid Cancer Classification

Timely and accurate diagnosis is crucial in addressing the global rise in thyroid cancer, ensuring effective treatment strategies and improved patient outcomes. We present an intelligent classification method that couples an Adaptive Convolutional Neural Network (CNN) with Cohen-Daubechies-Feauveau (CDF9/7) wavelets whose detail coefficients are modulated by an n-scroll chaotic system to enrich discriminative features. We evaluate on the public DDTI thyroid ultrasound dataset (n = 1,638 images; 819 malignant / 819 benign) using 5-fold cross-validation, where the proposed method attains 98.17% accuracy, 98.76% sensitivity, 97.58% specificity, 97.55% F1-score, and an AUC of 0.9912. A controlled ablation shows that adding chaotic modulation to CDF9/7 improves accuracy by +8.79 percentage points over a CDF9/7-only CNN (from 89.38% to 98.17%). To objectively position our approach, we trained state-of-the-art backbones on the same data and splits: EfficientNetV2-S (96.58% accuracy; AUC 0.987), Swin-T (96.41%; 0.986), ViT-B/16 (95.72%; 0.983), and ConvNeXt-T (96.94%; 0.987). Our method outperforms the best of these by +1.23 points in accuracy and +0.0042 in AUC, while remaining computationally efficient (28.7 ms per image; 1,125 MB peak VRAM). Robustness is further supported by cross-dataset testing on TCIA (accuracy 95.82%) and transfer to an ISIC skin-lesion subset (n = 28 unique images, augmented to 2,048; accuracy 97.31%). Explainability analyses (Grad-CAM, SHAP, LIME) highlight clinically relevant regions. Altogether, the wavelet-chaos-CNN pipeline delivers state-of-the-art thyroid ultrasound classification with strong generalization and practical runtime characteristics suitable for clinical integration.

cs.CV↗

arXiv2025

Extracting Actionable Insights from Building Energy Data using Vision LLMs on Wavelet and 3D Recurrence Representations

The analysis of complex building time-series for actionable insights and recommendations remains challenging due to the nonlinear and multi-scale characteristics of energy data. To address this, we propose a framework that fine-tunes visual language large models (VLLMs) on 3D graphical representations of the data. The approach converts 1D time-series into 3D representations using continuous wavelet transforms (CWTs) and recurrence plots (RPs), which capture temporal dynamics and localize frequency anomalies. These 3D encodings enable VLLMs to visually interpret energy-consumption patterns, detect anomalies, and provide recommendations for energy efficiency. We demonstrate the framework on real-world building-energy datasets, where fine-tuned VLLMs successfully monitor building states, identify recurring anomalies, and generate optimization recommendations. Quantitatively, the Idefics-7B VLLM achieves validation losses of 0.0952 with CWTs and 0.1064 with RPs on the University of Sharjah energy dataset, outperforming direct fine-tuning on raw time-series data (0.1176) for anomaly detection. This work bridges time-series analysis and visualization, providing a scalable and interpretable framework for energy analytics.

cs.LG↗

arXiv2025

LLM-Augmented and Fair Machine Learning Framework for University Admission Prediction

Universities face surging applications and heightened expectations for fairness, making accurate admission prediction increasingly vital. This work presents a comprehensive framework that fuses machine learning, deep learning, and large language model techniques to combine structured academic and demographic variables with unstructured text signals. Drawing on more than 2,000 student records, the study benchmarks logistic regression, Naive Bayes, random forests, deep neural networks, and a stacked ensemble. Logistic regression offers a strong, interpretable baseline at 89.5% accuracy, while the stacked ensemble achieves the best performance at 91.0%, with Naive Bayes and random forests close behind. To probe text integration, GPT-4-simulated evaluations of personal statements are added as features, yielding modest gains but demonstrating feasibility for authentic essays and recommendation letters. Transparency is ensured through feature-importance visualizations and fairness audits. The audits reveal a 9% gender gap (67% male vs. 76% female) and an 11% gap by parental education, underscoring the need for continued monitoring. The framework is interpretable, fairness-aware, and deployable.

cs.CY↗

arXiv2025

Interpretable Deep Transfer Learning for Breast Ultrasound Cancer Detection: A Multi-Dataset Study

Breast cancer remains a leading cause of cancer-related mortality among women worldwide. Ultrasound imaging, widely used due to its safety and cost-effectiveness, plays a key role in early detection, especially in patients with dense breast tissue. This paper presents a comprehensive study on the application of machine learning and deep learning techniques for breast cancer classification using ultrasound images. Using datasets such as BUSI, BUS-BRA, and BrEaST-Lesions USG, we evaluate classical machine learning models (SVM, KNN) and deep convolutional neural networks (ResNet-18, EfficientNet-B0, GoogLeNet). Experimental results show that ResNet-18 achieves the highest accuracy (99.7%) and perfect sensitivity for malignant lesions. Classical ML models, though outperformed by CNNs, achieve competitive performance when enhanced with deep feature extraction. Grad-CAM visualizations further improve model transparency by highlighting diagnostically relevant image regions. These findings support the integration of AI-based diagnostic tools into clinical workflows and demonstrate the feasibility of deploying high-performing, interpretable systems for ultrasound-based breast cancer detection.

cs.CV↗

arXiv2025

Leveraging Transfer Learning and Mobile-enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognition

The study explores the integration of transfer learning (TL) with mobile-enabled convolutional neural networks (MbNets) to enhance Arabic Handwritten Character Recognition (AHCR). Addressing challenges like extensive computational requirements and dataset scarcity, this research evaluates three TL strategies--full fine-tuning, partial fine-tuning, and training from scratch--using four lightweight MbNets: MobileNet, SqueezeNet, MnasNet, and ShuffleNet. Experiments were conducted on three benchmark datasets: AHCD, HIJJA, and IFHCDB. MobileNet emerged as the top-performing model, consistently achieving superior accuracy, robustness, and efficiency, with ShuffleNet excelling in generalization, particularly under full fine-tuning. The IFHCDB dataset yielded the highest results, with 99% accuracy using MnasNet under full fine-tuning, highlighting its suitability for robust character recognition. The AHCD dataset achieved competitive accuracy (97%) with ShuffleNet, while HIJJA posed significant challenges due to its variability, achieving a peak accuracy of 92% with ShuffleNet. Notably, full fine-tuning demonstrated the best overall performance, balancing accuracy and convergence speed, while partial fine-tuning underperformed across metrics. These findings underscore the potential of combining TL and MbNets for resource-efficient AHCR, paving the way for further optimizations and broader applications. Future work will explore architectural modifications, in-depth dataset feature analysis, data augmentation, and advanced sensitivity analysis to enhance model robustness and generalizability.

cs.CV↗

arXiv2025

A Review on Deep Learning Autoencoder in the Design of Next-Generation Communication Systems

Traditional mathematical models used in designing next-generation communication systems often fall short due to inherent simplifications, narrow scope, and computational limitations. In recent years, the incorporation of deep learning (DL) methodologies into communication systems has made significant progress in system design and performance optimisation. Autoencoders (AEs) have become essential, enabling end-to-end learning that allows for the combined optimisation of transmitters and receivers. Consequently, AEs offer a data-driven methodology capable of bridging the gap between theoretical models and real-world complexities. The paper presents a comprehensive survey of the application of AEs within communication systems, with a particular focus on their architectures, associated challenges, and future directions. We examine 120 recent studies across wireless, optical, semantic, and quantum communication fields, categorising them according to transceiver design, channel modelling, digital signal processing, and computational complexity. This paper further examines the challenges encountered in the implementation of AEs, including the need for extensive training data, the risk of overfitting, and the requirement for differentiable channel models. Through data-driven approaches, AEs provide robust solutions for end-to-end system optimisation, surpassing traditional mathematical models confined by simplifying assumptions. This paper also summarises the computational complexity associated with AE-based systems by conducting an in-depth analysis employing the metric of floating-point operations per second (FLOPS). This analysis encompasses the evaluation of matrix multiplications, bias additions, and activation functions. This survey aims to establish a roadmap for future research, emphasising the transformative potential of AEs in the formulation of next-generation communication systems.

eess.SP↗

arXiv2025

Deep Transfer Learning for Kidney Cancer Diagnosis

Incurable diseases continue to pose major challenges to global healthcare systems, with their prevalence shaped by lifestyle, economic, social, and genetic factors. Among these, kidney disease remains a critical global health issue, requiring ongoing research to improve early diagnosis and treatment. In recent years, deep learning (DL) has shown promise in medical imaging and diagnostics, driving significant progress in automatic kidney cancer (KC) detection. However, the success of DL models depends heavily on the availability of high-quality, domain-specific datasets, which are often limited and expensive to acquire. Moreover, DL models demand substantial computational power and storage, restricting their real-world clinical use. To overcome these barriers, transfer learning (TL) has emerged as an effective approach, enabling the reuse of pre-trained models from related domains to enhance KC diagnosis. This paper presents a comprehensive survey of DL-based TL frameworks for KC detection, systematically reviewing key methodologies, their advantages, and limitations, and analyzing their practical performance. It further discusses challenges in applying TL to medical imaging and highlights emerging trends that could influence future research. This review demonstrates the transformative role of TL in precision medicine, particularly oncology, by improving diagnostic accuracy, lowering computational demands, and supporting the integration of AI-powered tools in healthcare. The insights provided offer valuable guidance for researchers and practitioners, paving the way for future advances in KC diagnostics and personalized treatment strategies.

eess.IV↗

arXiv2025

Hybrid Vision Transformer-Mamba Framework for Autism Diagnosis via Eye-Tracking Analysis

Accurate Autism Spectrum Disorder (ASD) diagnosis is vital for early intervention. This study presents a hybrid deep learning framework combining Vision Transformers (ViT) and Vision Mamba to detect ASD using eye-tracking data. The model uses attention-based fusion to integrate visual, speech, and facial cues, capturing both spatial and temporal dynamics. Unlike traditional handcrafted methods, it applies state-of-the-art deep learning and explainable AI techniques to enhance diagnostic accuracy and transparency. Tested on the Saliency4ASD dataset, the proposed ViT-Mamba model outperformed existing methods, achieving 0.96 accuracy, 0.95 F1-score, 0.97 sensitivity, and 0.94 specificity. These findings show the model's promise for scalable, interpretable ASD screening, especially in resource-constrained or remote clinical settings where access to expert diagnosis is limited.

cs.CV↗

arXiv2025

Exploring Image Transforms derived from Eye Gaze Variables for Progressive Autism Diagnosis

The prevalence of Autism Spectrum Disorder (ASD) has surged rapidly over the past decade, posing significant challenges in communication, behavior, and focus for affected individuals. Current diagnostic techniques, though effective, are time-intensive, leading to high social and economic costs. This work introduces an AI-powered assistive technology designed to streamline ASD diagnosis and management, enhancing convenience for individuals with ASD and efficiency for caregivers and therapists. The system integrates transfer learning with image transforms derived from eye gaze variables to diagnose ASD. This facilitates and opens opportunities for in-home periodical diagnosis, reducing stress for individuals and caregivers, while also preserving user privacy through the use of image transforms. The accessibility of the proposed method also offers opportunities for improved communication between guardians and therapists, ensuring regular updates on progress and evolving support needs. Overall, the approach proposed in this work ensures timely, accessible diagnosis while protecting the subjects' privacy, improving outcomes for individuals with ASD.

eess.IV↗

arXiv2025

Complexity of Post-Quantum Cryptography in Embedded Systems and Its Optimization Strategies

With the rapid advancements in quantum computing, traditional cryptographic schemes like Rivest-Shamir-Adleman (RSA) and elliptic curve cryptography (ECC) are becoming vulnerable, necessitating the development of quantum-resistant algorithms. The National Institute of Standards and Technology (NIST) has initiated a standardization process for PQC algorithms, and several candidates, including CRYSTALS-Kyber and McEliece, have reached the final stages. This paper first provides a comprehensive analysis of the hardware complexity of post-quantum cryptography (PQC) in embedded systems, categorizing PQC algorithms into families based on their underlying mathematical problems: lattice-based, code-based, hash-based and multivariate / isogeny-based schemes. Each family presents distinct computational, memory, and energy profiles, making them suitable for different use cases. To address these challenges, this paper discusses optimization strategies such as pipelining, parallelization, and high-level synthesis (HLS), which can improve the performance and energy efficiency of PQC implementations. Finally, a detailed complexity analysis of CRYSTALS-Kyber and McEliece, comparing their key generation, encryption, and decryption processes in terms of computational complexity, has been conducted.

cs.CR↗

arXiv2025

Machine Learning and Transformers for Thyroid Carcinoma Diagnosis: A Review

The growing interest in developing smart diagnostic systems to help medical experts process extensive data for treating incurable diseases has been notable. In particular, the challenge of identifying thyroid cancer (TC) has seen progress with the use of machine learning (ML) and big data analysis, incorporating Transformers to evaluate TC prognosis and determine the risk of malignancy in individuals. This review article presents a summary of various studies on AI-based approaches, especially those employing Transformers, for diagnosing TC. It introduces a new categorization system for these methods based on artificial intelligence (AI) algorithms, the goals of the framework, and the computing environments used. Additionally, it scrutinizes and contrasts the available TC datasets by their features. The paper highlights the importance of AI instruments in aiding the diagnosis and treatment of TC through supervised, unsupervised, or mixed approaches, with a special focus on the ongoing importance of Transformers and large language models (LLMs) in medical diagnostics and disease management. It further discusses the progress made and the continuing obstacles in this area. Lastly, it explores future directions and focuses within this research field.

cs.LG↗

arXiv2025

Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detection

The rapid advancement of deep learning (DL) has transformed healthcare, particularly in cancer detection and diagnosis. DL surpasses traditional machine learning and human accuracy, making it a critical tool for identifying diseases. Despite numerous reviews on DL in healthcare, a comprehensive analysis of its role in cancer detection remains limited. Existing studies focus on specific aspects, leaving gaps in understanding its broader impact. This paper addresses these gaps by reviewing advanced DL techniques, including transfer learning (TL), reinforcement learning (RL), federated learning (FL), Transformers, and large language models (LLMs). These approaches enhance accuracy, tackle data scarcity, and enable decentralized learning while maintaining data privacy. TL adapts pre-trained models to new datasets, improving performance with limited labeled data. RL optimizes diagnostic pathways and treatment strategies, while FL fosters collaborative model development without sharing sensitive data. Transformers and LLMs, traditionally used in natural language processing, are now applied to medical data for improved interpretability. Additionally, this review examines these techniques' efficiency in cancer diagnosis, addresses challenges like data imbalance, and proposes solutions. It serves as a resource for researchers and practitioners, providing insights into current trends and guiding future research in advanced DL for cancer detection.

eess.IV↗

arXiv2025

Deep Learning Autoencoders for Reducing PAPR in Coherent Optical Systems

This paper presents an innovative approach to mitigating the peak-to-average power ratio (PAPR). The proposed method uses a deep learning model called autoencoders (AEs) to simplify the process and avoid the complex calculations of traditional methods such as selective mapping (SLM). Unlike SLM, our approach does not need side information about the PAPR distribution. Through simulations of coherent optical orthogonal frequency division multiplexing (CO-OFDM) systems, the AE-based model offers substantial enhancements in both PAPR reduction and bit error rate (BER) performance when compared to conventional techniques. An error-free transmission can be acheived with a reduction in PAPR exceeding 10 dB compared to the original signal and a 1 dB advantage over SLM. In particular, the AE model achieves the best BER performance of \(2 \times 10^{-6}\) at 44 dB OSNR, surpassing traditional methods. Furthermore, the model demonstrates robustness against noise and nonlinear distortions, making it appropriate for optical channels experiencing diverse levels of impairment. This innovative technique has the potential to revolutionize next-generation optical communication systems by enabling efficient and reliable data transmission.

eess.SP↗

arXiv2025

End-to-End Deep Learning in Phase Noisy Coherent Optical Link

In coherent optical orthogonal frequency-division multiplexing (CO-OFDM) fiber communications, a novel end-to-end learning framework to mitigate Laser Phase Noise (LPN) impairments is proposed in this paper. Inspired by Autoencoder (AE) principles, the proposed approach trains a model to learn robust symbol sequences capable of combat LPN, even from low-cost distributed feedback (DFB) lasers with linewidths up to 2 MHz. This allows for the use of high-level modulation formats and large-scale Fast Fourier Transform (FFT) processing, maximizing spectral efficiency in CO-OFDM systems. By eliminating the need for complex traditional techniques, this approach offers a potentially more efficient and streamlined solution for CO-OFDM systems. The most significant achievement of this study is the demonstration that the proposed AE-based model can enhance system performance by reducing the bit error rate (BER) to below the threshold of forward error correction (FEC), even under severe phase noise conditions, thus proving its effectiveness and efficiency in practical deployment scenarios.

eess.SP↗