arXiv subjects

Samir Brahim Belhaouari

Publications and source records attributed to Samir Brahim Belhaouari.

14 recordsLinked to original sources

arXiv2026

Fractal Cross Product: Theory, Differentiable Implementation and Application to Medical Image Analysis

The magnitude of the generalized Euclidean cross product is a Gram volume whose degree under common scaling is fixed by the integer dimension of the spanning frame. We formulate a generalized Fractal Cross Product (FCP) as a nonlinear radial deformation with a prescribed positive degree $D$, which may be non-integer. The scalar construction applies in any ambient dimension $m\geq k$, while its canonically oriented vector form requires codimension one. It recovers the classical generalized cross product exactly at $D=k$ and retains orthogonality, alternation, rotation equivariance, and $D$-homogeneity, but is generally not multilinear. For exact self-similar frame systems, the construction also obeys a scale-balance law at the similarity dimension. We derive a differentiable, dimensionless image response and a non-circular empirical accumulation exponent obtained by regressing raw angular Gram responses across patch widths. Binary64 calculations recover the finite-frame identities to roundoff, while raster experiments recover the Sierpiński-triangle value 1.5849625 at three resolutions. In five-seed medical-imaging comparisons, FCP-centered fusion increased mean area under the receiver operating characteristic curve from 0.7264 to 0.8135 and from 0.5843 to 0.6765 on the random and hospital-separated Retinal Image Database for Optic Nerve Evaluation partitions, respectively, and from 0.7403 to 0.7475 on FracAtlas. On FracAtlas, balanced accuracy increased from 0.6186 to 0.6721 and the harmonic mean of precision and sensitivity from 0.3669 to 0.4457. These results support the utility of the complete fusion framework, but do not isolate the effect of FCP from that of its complementary descriptors and fusion head.

cs.CV↗

arXiv2026

MirrorDistill: Illumination-Aware Latent Distillation for Efficient Low-Light Restoration

Low-light image enhancement (LLIE) is an im- portant component of visual sensing systems operating under degraded illumination, including nighttime surveillance, au- tonomous navigation, remote sensing, and inspection in poorly lit industrial environments. Most LLIE methods rely on output- level reconstruction losses that supervise only the final restored image, leaving the intermediate feature recovery process weakly constrained. This paper proposes MirrorDistill, an illumination- aware latent distillation framework that links the low-light and clean domains through feature mirroring. During training, a shared encoder and an exponential-moving-average teacher decoder process the clean reference image to generate clean- domain latent targets. These targets supervise the low-light student at two levels: raw encoder features and standardized multi-scale decoder projections. The alignment is applied layer by layer, while a proposed illumination-aware weighting scheme gives greater emphasis to underexposed regions. The teacher and reference branches are used only during training, so inference requires only the lightweight student encoder-decoder and in- troduces no teacher-side computational cost. Under evaluation on the standard LOL benchmarks, MirrorDistill outperforms the state-of-the-art methods on the real-captured LOL-v2-Real set, while having the lowest compute complexity (GMACs) and while remaining competitive on the LOL-v1 and LOL-v2-Synthetic datasets. Ablation studies further show the contributions of the encoder mirror, decoder mirror, and illumination-aware weighting. Finally, we release our code as open-source for the benefit of future research.

cs.CV↗

arXiv2026

Focus on What Matters: Two-Stage ROI-Aware Refinement for Anatomy-Preserving Fetal Ultrasound Reconstruction

Measurement-critical ultrasound tasks often depend on a small anatomical region, making global reconstruction metrics an unreliable proxy for clinical fidelity. We propose an ROI-aware representation learning framework and instantiate it for first-trimester nuchal translucency (NT) screening under multi-hospital domain shift. A two-phase convolutional autoencoder (CAE) first learns a globally faithful 128-D latent code via MS-SSIM, then refines the NT ROI using intensity (L1) and normalized Sobel-edge constraints. To combine these heterogeneous objectives without manual tuning, we initialize loss weights via gradient-based calibration from per-term gradient magnitudes. Under strict hospital-wise evaluation with one hospital held out, ROI refinement improves both global and measurement-relevant quality: on the standard dev split it increases PSNR by +0.27 dB (val) and +0.29 dB (held-out test), reduces ROI MAE by 8.87% (val) and 6.43% (held-out test), and reduces ROI Edge-MAE by 11.10% on source hospitals and 4.90% on the unseen hospital. Beyond reconstruction, frozen-latent probes provide additional evidence of generalization: hospital provenance becomes less confidently predictable on the unseen site (0.556 to 0.541 max-softmax; 0.684 to 0.688 entropy) while OOD detection remains strong across site-held-out protocols (Mahalanobis AUROC up to 0.9956, with modest KNN gains in challenging splits). The same ROI-aware refinement principle is anatomy-agnostic and can be adopted for other fetal biometry targets (e.g., crown-rump length (CRL), nasal bone (NB)) and broader medical imaging settings where small ROIs dominate clinical decisions.

cs.CV↗

arXiv2025

Oversampling and Downsampling with Core-Boundary Awareness: A Data Quality-Driven Approach

The effectiveness of machine learning models, particularly in unbalanced classification tasks, is often hindered by the failure to differentiate between critical instances near the decision boundary and redundant samples concentrated in the core of the data distribution. In this paper, we propose a method to systematically identify and differentiate between these two types of data. Through extensive experiments on multiple benchmark datasets, we show that the boundary data oversampling method improves the F1 score by up to 10\% on 96\% of the datasets, whereas our core-aware reduction method compresses datasets up to 90\% while preserving their accuracy, making it 10 times more powerful than the original dataset. Beyond imbalanced classification, our method has broader implications for efficient model training, particularly in computationally expensive domains such as Large Language Model (LLM) training. By prioritizing high-quality, decision-relevant data, our approach can be extended to text, multimodal, and self-supervised learning scenarios, offering a pathway to faster convergence, improved generalization, and significant computational savings. This work paves the way for future research in data-efficient learning, where intelligent sampling replaces brute-force expansion, driving the next generation of AI advancements. Our code is available as a Python package at https://pypi.org/project/adaptive-resampling/ .

cs.LG↗

arXiv2025

Bio-Inspired Adaptive Neurons for Dynamic Weighting in Artificial Neural Networks

Traditional neural networks employ fixed weights during inference, limiting their ability to adapt to changing input conditions, unlike biological neurons that adjust signal strength dynamically based on stimuli. This discrepancy between artificial and biological neurons constrains neural network flexibility and adaptability. To bridge this gap, we propose a novel framework for adaptive neural networks, where neuron weights are modeled as functions of the input signal, allowing the network to adjust dynamically in real-time. Importantly, we achieve this within the same traditional architecture of an Artificial Neural Network, maintaining structural familiarity while introducing dynamic adaptability. In our research, we apply Chebyshev polynomials as one of the many possible decomposition methods to achieve this adaptive weighting mechanism, with polynomial coefficients learned during training. Out of the 145 datasets tested, our adaptive Chebyshev neural network demonstrated a marked improvement over an equivalent MLP in approximately 8\% of cases, performing strictly better on 121 datasets. In the remaining 24 datasets, the performance of our algorithm matched that of the MLP, highlighting its ability to generalize standard neural network behavior while offering enhanced adaptability. As a generalized form of the MLP, this model seamlessly retains MLP performance where needed while extending its capabilities to achieve superior accuracy across a wide range of complex tasks. These results underscore the potential of adaptive neurons to enhance generalization, flexibility, and robustness in neural networks, particularly in applications with dynamic or non-linear data dependencies.

cs.NE↗

arXiv2025

Large Language Model Enhanced Particle Swarm Optimization for Hyperparameter Tuning for Deep Learning Models

Determining the ideal architecture for deep learning models, such as the number of layers and neurons, is a difficult and resource-intensive process that frequently relies on human tuning or computationally costly optimization approaches. While Particle Swarm Optimization (PSO) and Large Language Models (LLMs) have been individually applied in optimization and deep learning, their combined use for enhancing convergence in numerical optimization tasks remains underexplored. Our work addresses this gap by integrating LLMs into PSO to reduce model evaluations and improve convergence for deep learning hyperparameter tuning. The proposed LLM-enhanced PSO method addresses the difficulties of efficiency and convergence by using LLMs (particularly ChatGPT-3.5 and Llama3) to improve PSO performance, allowing for faster achievement of target objectives. Our method speeds up search space exploration by substituting underperforming particle placements with best suggestions offered by LLMs. Comprehensive experiments across three scenarios -- (1) optimizing the Rastrigin function, (2) using Long Short-Term Memory (LSTM) networks for time series regression, and (3) using Convolutional Neural Networks (CNNs) for material classification -- show that the method significantly improves convergence rates and lowers computational costs. Depending on the application, computational complexity is lowered by 20% to 60% compared to traditional PSO methods. Llama3 achieved a 20% to 40% reduction in model calls for regression tasks, whereas ChatGPT-3.5 reduced model calls by 60% for both regression and classification tasks, all while preserving accuracy and error rates. This groundbreaking methodology offers a very efficient and effective solution for optimizing deep learning models, leading to substantial computational performance improvements across a wide range of applications.

cs.AI↗

arXiv2025

Systematic Weight Evaluation for Pruning Large Language Models: Enhancing Performance and Sustainability

The exponential growth of large language models (LLMs) like ChatGPT has revolutionized artificial intelligence, offering unprecedented capabilities in natural language processing. However, the extensive computational resources required for training these models have significant environmental implications, including high carbon emissions, energy consumption, and water usage. This research presents a novel approach to LLM pruning, focusing on the systematic evaluation of individual weight importance throughout the training process. By monitoring parameter evolution over time, we propose a method that effectively reduces model size without compromising performance. Extensive experiments with both a scaled-down LLM and a large multimodal model reveal that moderate pruning enhances efficiency and reduces loss, while excessive pruning drastically deteriorates model performance. These findings highlight the critical need for optimized AI models to ensure sustainable development, balancing technological advancement with environmental responsibility.

cs.CL↗

arXiv2024

Automated Model Training (AMT) GUI: An Opportunity for integrating AI in the Laboratory Experiment

In the field of materials science, comprehending material properties is often hindered by the complexity of datasets originating from various sources. This study introduces the Automated Model Training (AMT) Graphical User Interface (GUI), specifically crafted for the use of researchers and scientists without a programming background to design the next set of experiments either in a chemistry lab or on the computer. The GUI integrates diverse machine learning models, such as XG-Boost, Random Forest, Support Vector Regression, Linear Regression, Generalized Additive Model (GAM), and Stack Regressors, offering a robust toolkit for data analysis. It facilitates the exploration of complex relationships, non-linear patterns, and predictive accuracy optimization. To further enhance its utility, the GUI integrates the Particle Swarm Optimization (PSO) technique, allowing researchers to systematically explore vast parameter spaces and identify optimal experimental conditions. This synergy between machine learning and PSO empowers material scientists through a user-friendly platform for data-driven discovery. The AMT GUI bridges the gap between traditional experimentation and machine learning, enabling precise and efficient exploration of the materials research space.

cond-mat.mtrl-sci↗

arXiv2023

Pushing Boundaries: Exploring Zero Shot Object Classification with Large Multimodal Models

$ $The synergy of language and vision models has given rise to Large Language and Vision Assistant models (LLVAs), designed to engage users in rich conversational experiences intertwined with image-based queries. These comprehensive multimodal models seamlessly integrate vision encoders with Large Language Models (LLMs), expanding their applications in general-purpose language and visual comprehension. The advent of Large Multimodal Models (LMMs) heralds a new era in Artificial Intelligence (AI) assistance, extending the horizons of AI utilization. This paper takes a unique perspective on LMMs, exploring their efficacy in performing image classification tasks using tailored prompts designed for specific datasets. We also investigate the LLVAs zero-shot learning capabilities. Our study includes a benchmarking analysis across four diverse datasets: MNIST, Cats Vs. Dogs, Hymnoptera (Ants Vs. Bees), and an unconventional dataset comprising Pox Vs. Non-Pox skin images. The results of our experiments demonstrate the model's remarkable performance, achieving classification accuracies of 85\%, 100\%, 77\%, and 79\% for the respective datasets without any fine-tuning. To bolster our analysis, we assess the model's performance post fine-tuning for specific tasks. In one instance, fine-tuning is conducted over a dataset comprising images of faces of children with and without autism. Prior to fine-tuning, the model demonstrated a test accuracy of 55\%, which significantly improved to 83\% post fine-tuning. These results, coupled with our prior findings, underscore the transformative potential of LLVAs and their versatile applications in real-world scenarios.

cs.CV↗

arXiv2023

Can ChatGPT be Your Personal Medical Assistant?

The advanced large language model (LLM) ChatGPT has shown its potential in different domains and remains unbeaten due to its characteristics compared to other LLMs. This study aims to evaluate the potential of using a fine-tuned ChatGPT model as a personal medical assistant in the Arabic language. To do so, this study uses publicly available online questions and answering datasets in Arabic language. There are almost 430K questions and answers for 20 disease-specific categories. GPT-3.5-turbo model was fine-tuned with a portion of this dataset. The performance of this fine-tuned model was evaluated through automated and human evaluation. The automated evaluations include perplexity, coherence, similarity, and token count. Native Arabic speakers with medical knowledge evaluated the generated text by calculating relevance, accuracy, precision, logic, and originality. The overall result shows that ChatGPT has a bright future in medical assistance.

cs.CL↗

arXiv2022

IJCB 2022 Mobile Behavioral Biometrics Competition (MobileB2C)

This paper describes the experimental framework and results of the IJCB 2022 Mobile Behavioral Biometrics Competition (MobileB2C). The aim of MobileB2C is benchmarking mobile user authentication systems based on behavioral biometric traits transparently acquired by mobile devices during ordinary Human-Computer Interaction (HCI), using a novel public database, BehavePassDB, and a standard experimental protocol. The competition is divided into four tasks corresponding to typical user activities: keystroke, text reading, gallery swiping, and tapping. The data are composed of touchscreen data and several background sensor data simultaneously acquired. "Random" (different users with different devices) and "skilled" (different user on the same device attempting to imitate the legitimate one) impostor scenarios are considered. The results achieved by the participants show the feasibility of user authentication through behavioral biometrics, although this proves to be a non-trivial challenge. MobileB2C will be established as an on-going competition.

cs.CV↗

arXiv2022

Supervised Class-pairwise NMF for Data Representation and Classification

Various Non-negative Matrix factorization (NMF) based methods add new terms to the cost function to adapt the model to specific tasks, such as clustering, or to preserve some structural properties in the reduced space (e.g., local invariance). The added term is mainly weighted by a hyper-parameter to control the balance of the overall formula to guide the optimization process towards the objective. The result is a parameterized NMF method. However, NMF method adopts unsupervised approaches to estimate the factorizing matrices. Thus, the ability to perform prediction (e.g. classification) using the new obtained features is not guaranteed. The objective of this work is to design an evolutionary framework to learn the hyper-parameter of the parameterized NMF and estimate the factorizing matrices in a supervised way to be more suitable for classification problems. Moreover, we claim that applying NMF-based algorithms separately to different class-pairs instead of applying it once to the whole dataset improves the effectiveness of the matrix factorization process. This results in training multiple parameterized NMF algorithms with different balancing parameter values. A cross-validation combination learning framework is adopted and a Genetic Algorithm is used to identify the optimal set of hyper-parameter values. The experiments we conducted on both real and synthetic datasets demonstrated the effectiveness of the proposed approach.

cs.LG↗

arXiv2021

Contact Tracing Apps for COVID-19: Access Permission and User Adoption

Contact tracing apps are powerful software tools that can help control the spread of COVID-19. In this article, we evaluated 53 COVID-19 contact tracing apps found on the Google Play Store in terms of their usage, rating, access permission, and user privacy. For each app included in the study, we identified the country of origin, number of downloads, and access permissions to further understand the attributes and ratings of the apps. Our results show that contact tracing apps had low overall ratings and nearly 40% of the included apps were requesting dangerous access permission including access to storage, media files, and camera permissions. We also found that user adoption rates were inversely correlated to access permission requirements. To the best of our knowledge, our article summarizes the most extensive collection of contact tracing apps for COVID-19. We recommend that future contact tracing apps should be more transparent in permission requirements and should provide justification for permissions requested to preserve the app users privacy.

cs.SE↗

arXiv2016

A new enlightenment about gaps between primes

The idea of generating prime numbers through sequence of sets of co-primes was the starting point of this paper that ends up by proving two conjectures, the existence of infinitely many twin primes and the Goldbach conjecture. The main idea of our approach is summarized on the creation and on the analyzing sequence of sets of distinct co-primes with the first $n$ primes, $\left\{ p_i :\, i\leq n \right\}$, and the important properties of the modulus linear combination of the co-prime sets, $H=\left(1,p_{n+1},..., Π_{i=1}^n p_i-1\right) $, that gives sets of even numbers $\{0,2,4,..., Π_{i=1}^n p_i -2 \}$. Furthermore, by generalizing our approach, the Polignac conjecture "the existence of infinitely many cousin primes, $p_{n+1}-p_{n}=4$," and the statement that "every even integer can be expressed as a difference of two primes," are derived as well.

math.GM↗