arXiv subjects

Mohamed Ehab

Publications and source records attributed to Mohamed Ehab.

4 recordsLinked to original sources

arXiv2026

Uncertainty-Guided Attention and Entropy-Weighted Loss for Precise Plant Seedling Segmentation

Plant seedling segmentation supports automated phenotyping in precision agriculture. Standard segmentation models face difficulties due to intricate background images and fine structures in leaves. We introduce UGDA-Net (Uncertainty-Guided Dual Attention Network with Entropy-Weighted Loss and Deep Supervision). Three novel components make up UGDA-Net. The first component is Uncertainty-Guided Dual Attention (UGDA). UGDA uses channel variance to modulate feature maps. The second component is an entropy-weighted hybrid loss function. This loss function focuses on high-uncertainty boundary pixels. The third component employs deep supervision for intermediate encoder layers. We performed a comprehensive systematic ablation study. This study focuses on two widely-used architectures, U-Net and LinkNet. It analyzes five incremental configurations: Baseline, Loss-only, Attention-only, Deep Supervision, and UGDA-Net. We trained UGDA-net using a high-resolution plant seedling image dataset containing 432 images. We demonstrate improved segmentation performance and accuracy. With an increase in Dice coefficient of 9.3% above baseline. LinkNet's variance is 13.2% above baseline. Overlays that are qualitative in nature show the reduced false positives at the leaf boundary. Uncertainty heatmaps are consistent with the complex morphology. UGDA-Net aids in the segmentation of delicate structures in plants and provides a high-def solution. The results showed that uncertainty-guided attention and uncertainty-weighted loss are two complementing systems.

cs.CV↗

arXiv2026

CAMO: A Class-Aware Minority-Optimized Ensemble for Robust Language Model Evaluation on Imbalanced Data

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.

cs.CL↗

arXiv2026

Adaptive Multi-Expert Reasoning via Difficulty-Aware Routing and Uncertainty-Guided Aggregation

Large language models (LLMs) demonstrate strong performance in math reasoning benchmarks, but their performance varies inconsistently across problems with varying levels of difficulty. This paper describes Adaptive Multi-Expert Reasoning (AMR), a framework that focuses on problem complexity by reasoning with dynamically adapted strategies. An agile routing system that focuses on problem text predicts problems' difficulty and uncertainty and guides a reconfigurable sampling mechanism to manage the breadth of generation. Three specialized experts create candidate responses, which are modified during multiple correction and finalization phases. A neural verifier assesses the correctness of responses, while a clustering-based aggregation technique identifies the final candidate answer based on a combination of consensus and answer quality. When evaluated on the GSM8K dataset, AMR achieved 75.28% accuracy while only using the original training data. This result outperformed the majority of comparable 7B models that were trained on synthetic data. This showcases that models using difficulty-based routing and uncertainty-driven aggregation are efficient and effective in improving math reasoning models' robustness.

cs.CL↗

arXiv2026

TOSHFA: A Mobile VR-Based System for Pose-Guided Exercise Rehabilitation for Low Back Pain

Low back pain (LBP) is a pervasive global health challenge, affecting approximately 80% of adults and frequently progressing into chronic or recurrent episodes. While exercise therapy is a primary clinical intervention, traditional at-home programs suffer from low adherence rates and the absence of professional supervision. This study introduces TOSHFA, an accessible mobile VR-based rehabilitation system that bridges this gap by combining computer vision with affordable hardware. The system utilizes a laptop webcam to perform real-time pose estimation via the MediaPipe framework, tracking 33 skeletal landmarks to provide immediate biofeedback. This data is streamed via low-latency UDP protocols to a smartphone mounted in a cardboard-style VR headset, where patients interact with a gamified 3D environment. A pilot study with 20 participants evaluated the system's performance and user engagement. Quantitative results yielded a mean System Usability Scale (SUS) score of 47.4, indicating marginal usability and a need for interface optimization. However, Game Experience Questionnaire (GEQ) data revealed high scores in positive affect and enjoyment, suggesting that the gamification elements--such as coin rewards and streak tracking--successfully maintained user motivation despite technical friction. These findings validate the feasibility of a smartphone-based tele-rehabilitation model and establish a technical foundation for future clinical trials involving multi-exercise protocols.

cs.HC↗