arXiv subjects

M. Sohel Rahman

Publications and source records attributed to M. Sohel Rahman.

At least 19 recordsLinked to original sources

arXiv2026

To Remove or Not to Remove Clouds: A Comparative Analysis and Fusion of Raw SAR and Synthetic NDWI for Overcast Water Segmentation

Persistent clouds blind optical satellites during floods. While Synthetic Aperture Radar (SAR) penetrates clouds, its raw data is noisy and lacks clear contrast. To mitigate this, recent studies utilize deep learning models to translate SAR into cloud-free synthetic optical imagery for downstream tasks like water body segmentation. However, because raw SAR is the original source for both of these operations, a critical methodological dilemma arises: during complete overcast should segmentation models process the raw SAR directly, or rely on a translated synthetic Normalized Difference Water Index (NDWI) proxy? This study resolves the debate by demonstrating that synthetic NDWI yields better results, as the translation process acts as a powerful filter against radar noise. This raises a natural second question: what if we utilize both? Building on our findings, we introduce a Combined Framework that integrates both raw SAR and synthetic NDWI into a unified model. By fusing the sharp physical boundaries of raw SAR with the high contrast of synthetic NDWI, this hybrid approach consistently outperforms all standalone methods.

cs.CV↗

arXiv2026

Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models

Genomic foundation models are increasingly reused as frozen feature extractors for downstream sequence prediction, offering a compute-efficient alternative to full fine-tuning. However, it remains unclear when biological information encoded by these models is accessible without task-specific adaptation. We present a representation-accessibility analysis of frozen genomic language models across regulatory, epigenetic, promoter, splice-site, and variant-effect prediction tasks. We evaluate DNABERT-2, Nucleotide Transformer, HyenaDNA, GENERATOR-v2, and Omni-DNA under unified frozen-probing protocols, while separating diagnostic readout analyses from validation-selected checks. Our results reveal a consistent task-dependent pattern: frozen probes recover 95-100 % of fine-tuned performance on promoter tasks, but average splice-site recovery drops to 60-88 %. Frozen embeddings are also competitive on broad Genomic Benchmark tasks such as coding-region and species-discrimination classification, but show larger gaps on some regulatory and OCR tasks. Layer-wise probing, in-silico mutagenesis, variant-effect prediction, and embedding geometry show that local biological signal is partially present in frozen representations, but is not always accessible through final pooled embeddings.

q-bio.GN↗

arXiv2026

Counting the Cost of War Under Satellite Embargo: Zero-Shot Estimation of Impacted Infrastructure

Rapid estimation of impacted structures - critical for conflict-zone humanitarian response - is frequently hindered by post-strike satellite data embargoes and imagery blackouts. We bypass this operational bottleneck by reframing impacted building mapping as a zero-shot geometric projection task on archival, pre-strike maps. Using coordinate and incident text from LiveUAMap and ArcGIS, Large Language Models extract weapon payloads (W) to project kinetic blast perimeters via Hopkinson-Cranz scaling (R_base = Z * W^(1/3)). To count exposed structures within these zones without post-strike imagery, we introduce two technical innovations: Adaptive Field-of-View to eliminate resolution (zoom) bias in 2D segmentation (SAMGeo), and 2.5D pseudo-height depth maps combined with segmentation masks to help Large Vision-Language Models (LVLMs) resolve overlapping, dense rooftops. Evaluated on 2026 Middle East conflict data, depth-augmented LVLMs dramatically outperform traditional segmentation in congested urban centers. This establishes a powerful hybrid paradigm for zero-shot crisis mapping: ultra-fast 2D segmentation for sparse rural zones, and depth-augmented LVLMs for dense urban environments.

cs.CV↗

arXiv2026

Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations

Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressing high-precision floating-point weights into low-precision representations without requiring retraining. Past research has demonstrated that quantization largely preserves classification accuracy; however, whether it also preserves the model's internal reasoning remains an open question. This study presents a systematic evaluation on how static PTQ affects the interpretability / explainability of five widely used CNN architectures: VGG19, ResNet18, EfficientNet-B0, DenseNet161, and MobileNetV2 at INT8 and INT4 precision. We employ a dual interpretability framework that combines Grad-CAM for spatial attention analysis with LIME for input-level feature attribution, and systematically compare full-precision and quantized models on two binary classification datasets. Interpretability is evaluated using three complementary metrics: the Pearson correlation coefficient, structural similarity index, and top-20% IoU to capture distributional and structural variations in model explanations, supplemented by deletion/insertion faithfulness analysis. The results show that classification accuracy is not a reliable indicator of interpretability stability under reduced precision. DenseNet161 maintains strong feature consistency across both precision levels, whereas EfficientNet-B0, despite achieving competitive spatial attention and classification accuracy at INT8 precision, exhibits a substantial degradation in input-level feature attribution. These findings have direct implications for the trustworthy deployment of quantized models in applications with high interpretability requirements, demonstrating that architecture selection is as important as the quantization strategy.

cs.LG↗

arXiv2026

Enlight: Fast Low-Light Image Enhancement via Multi-Objective Optimization and Shadow-Aware Refinement

We present ENLIGHT, a fast and training free framework for low-light image enhancement based on direct optimization of a perceptual objective. Unlike deep learning approaches that require large scale training data and supervision, ENLIGHT operates in a zero-shot manner by optimizing image quality at inference time. The method employs a two stage global to local optimization strategy. In the first stage, ENLIGHT performs global illumination adjustment to improve visibility while maintaining structural consistency and avoiding excessive noise enhancement. In the second stage, a shadow aware refinement selectively improves low-intensity regions through masked local optimization, enhancing visibility without overexposure. To balance quality and efficiency, we introduce two modes: Fast, which uses a multi-objective formulation combining entropy, gradient preservation, and noise regularization, and Ultrafast, which reduces computational cost via a lightweight approximation of the same objective. The framework is optimizer agnostic and supports both evolutionary and lightweight local search methods. Experiments on BAID, Backlit300, LIME, MEF, NPE, and DICM demonstrate that ENLIGHT achieves competitive perceptual quality (MUSIQ, NIQE, BRISQUE) with significantly lower inference time. Qualitative results further show improved contrast, preserved structural details, and controlled noise amplification, making ENLIGHT a practical and interpretable alternative to learning based methods.

cs.CV↗

arXiv2025

BrainRotViT: Transformer-ResNet Hybrid for Explainable Modeling of Brain Aging from 3D sMRI

Accurate brain age estimation from structural MRI is a valuable biomarker for studying aging and neurodegeneration. Traditional regression and CNN-based methods face limitations such as manual feature engineering, limited receptive fields, and overfitting on heterogeneous data. Pure transformer models, while effective, require large datasets and high computational cost. We propose Brain ResNet over trained Vision Transformer (BrainRotViT), a hybrid architecture that combines the global context modeling of vision transformers (ViT) with the local refinement of residual CNNs. A ViT encoder is first trained on an auxiliary age and sex classification task to learn slice-level features. The frozen encoder is then applied to all sagittal slices to generate a 2D matrix of embedding vectors, which is fed into a residual CNN regressor that incorporates subject sex at the final fully-connected layer to estimate continuous brain age. Our method achieves an MAE of 3.34 years (Pearson $r=0.98$, Spearman $ρ=0.97$, $R^2=0.95$) on validation across 11 MRI datasets encompassing more than 130 acquisition sites, outperforming baseline and state-of-the-art models. It also generalizes well across 4 independent cohorts with MAEs between 3.77 and 5.04 years. Analyses on the brain age gap (the difference between the predicted age and actual age) show that aging patterns are associated with Alzheimer's disease, cognitive impairment, and autism spectrum disorder. Model attention maps highlight aging-associated regions of the brain, notably the cerebellar vermis, precentral and postcentral gyri, temporal lobes, and medial superior frontal gyrus. Our results demonstrate that this method provides an efficient, interpretable, and generalizable framework for brain-age prediction, bridging the gap between CNN- and transformer-based approaches while opening new avenues for aging and neurodegeneration research.

cs.CV↗

arXiv2025

LogStamping: A blockchain-based log auditing approach for large-scale systems

Log management is crucial for ensuring the security, integrity, and compliance of modern information systems. Traditional log management solutions face challenges in achieving tamper-proofing, scalability, and real-time processing in distributed environments. This paper presents a blockchain-based log management framework that addresses these limitations by leveraging blockchain's decentralized, immutable, and transparent features. The framework integrates a hybrid on-chain and off-chain storage model, combining blockchain's integrity guarantees with the scalability of distributed storage solutions like IPFS. Smart contracts automate log validation and access control, while cryptographic techniques ensure privacy and confidentiality. With a focus on real-time log processing, the framework is designed to handle the high-volume log generation typical in large-scale systems, such as data centers and network infrastructure. Performance evaluations demonstrate the framework's scalability, low latency, and ability to manage millions of log entries while maintaining strong security guarantees. Additionally, the paper discusses challenges like blockchain storage overhead and energy consumption, offering insights for enhancing future systems.

cs.CR↗

arXiv2025

Improving MSA Estimation through Adaptive Weight Vectors in MOEA/D

Accurate phylogenetic inference from biological sequences depends critically on the quality of multiple sequence alignments, yet optimal alignment for many sequences is computationally intractable and sensitive to scoring choices. In this work we introduce MOEA/D-ADF, a novel variant of MOEA/D that adaptively adjusts subproblem weight vectors based on fitness variance to improve the exploration-exploitation trade-off. We combine MOEA/D-ADF with PMAO (PASTA with many application-aware optimization criteria) to form PMAO++, where PMAO-generated solutions are used to seed MOEA/D-ADF, which then evolves a population using 30 weight vectors to produce a diverse ensemble of alignment-tree pairs. PMAO++ outperforms the original PMAO on a majority of benchmark cases, achieving better false-negative (FN) rates on 12 of 17 BAliBASE-derived datasets and producing superior best-case trees, including several instances with zero FN rate. Beyond improving single best alignments, the rich set of alignment-tree pairs produced by PMAO++ is especially valuable for downstream summary methods (for example, consensus and summary-tree approaches), allowing more robust phylogenetic inference by integrating signal across multiple plausible alignments and trees. Certain dataset features, such as large terminal N/C extensions found in the RV40 group, remain challenging, but overall PMAO++ demonstrates clear advantages for sequence-based phylogenetic analysis. Future work will explore parameter tuning, larger benchmark suites, and tighter integration with summary-tree pipelines to further enhance applicability for biological sequence studies.

cs.NE↗

arXiv2025

CloudBreaker: Breaking the Cloud Covers of Sentinel-2 Images using Multi-Stage Trained Conditional Flow Matching on Sentinel-1

Cloud cover and nighttime conditions remain significant limitations in satellite-based remote sensing, often restricting the availability and usability of multi-spectral imagery. In contrast, Sentinel-1 radar images are unaffected by cloud cover and can provide consistent data regardless of weather or lighting conditions. To address the challenges of limited satellite imagery, we propose CloudBreaker, a novel framework that generates high-quality multi-spectral Sentinel-2 signals from Sentinel-1 data. This includes the reconstruction of optical (RGB) images as well as critical vegetation and water indices such as NDVI and NDWI. We employed a novel multi-stage training approach based on conditional latent flow matching and, to the best of our knowledge, are the first to integrate cosine scheduling with flow matching. CloudBreaker demonstrates strong performance, achieving a Frechet Inception Distance (FID) score of 0.7432, indicating high fidelity and realism in the generated optical imagery. The model also achieved Structural Similarity Index Measure (SSIM) of 0.6156 for NDWI and 0.6874 for NDVI, indicating a high degree of structural similarity. This establishes CloudBreaker as a promising solution for a wide range of remote sensing applications where multi-spectral data is typically unavailable or unreliable

cs.CV↗

arXiv2025

Leveraging Complementary Attention maps in vision transformers for OCT image analysis

Optical Coherence Tomography (OCT) scan yields all possible cross-section images of a retina for detecting biomarkers linked to optical defects. Due to the high volume of data generated, an automated and reliable biomarker detection pipeline is necessary as a primary screening stage. We outline our new state-of-the-art pipeline for identifying biomarkers from OCT scans. In collaboration with trained ophthalmologists, we identify local and global structures in biomarkers. Through a comprehensive and systematic review of existing vision architectures, we evaluate different convolution and attention mechanisms for biomarker detection. We find that MaxViT, a hybrid vision transformer combining convolution layers with strided attention, is better suited for local feature detection, while EVA-02, a standard vision transformer leveraging pure attention and large-scale knowledge distillation, excels at capturing global features. We ensemble the predictions of both models to achieve first place in the IEEE Video and Image Processing Cup 2023 competition on OCT biomarker detection, achieving a patient-wise F1 score of 0.8527 in the final phase of the competition, scoring 3.8\% higher than the next best solution. Finally, we used knowledge distillation to train a single MaxViT to outperform our ensemble at a fraction of the computation cost.

eess.IV↗

arXiv2025

Entropy-Driven Genetic Optimization for Deep-Feature-Guided Low-Light Image Enhancement

Image enhancement methods often prioritize pixel level information, overlooking the semantic features. We propose a novel, unsupervised, fuzzy-inspired image enhancement framework guided by NSGA-II algorithm that optimizes image brightness, contrast, and gamma parameters to achieve a balance between visual quality and semantic fidelity. Central to our proposed method is the use of a pre trained deep neural network as a feature extractor. To find the best enhancement settings, we use a GPU-accelerated NSGA-II algorithm that balances multiple objectives, namely, increasing image entropy, improving perceptual similarity, and maintaining appropriate brightness. We further improve the results by applying a local search phase to fine-tune the top candidates from the genetic algorithm. Our approach operates entirely without paired training data making it broadly applicable across domains with limited or noisy labels. Quantitatively, our model achieves excellent performance with average BRISQUE and NIQE scores of 19.82 and 3.652, respectively, in all unpaired datasets. Qualitatively, enhanced images by our model exhibit significantly improved visibility in shadowed regions, natural balance of contrast and also preserve the richer fine detail without introducing noticable artifacts. This work opens new directions for unsupervised image enhancement where semantic consistency is critical.

cs.CV↗

arXiv2025

GroundHog: Revolutionizing GLDAS Groundwater Storage Downscaling for Enhanced Recharge Estimation in Bangladesh

Long-term groundwater level (GWL) measurement is vital for effective policymaking and recharge estimation using annual maxima and minima. However, current methods prioritize short-term predictions and lack multi-year applicability, limiting their utility. Moreover, sparse in-situ measurements lead to reliance on low-resolution satellite data like GLDAS as the ground truth for Machine Learning models, further constraining accuracy. To overcome these challenges, we first develop an ML model to mitigate data gaps, achieving $R^2$ scores of 0.855 and 0.963 for maximum and minimum GWL predictions, respectively. Subsequently, using these predictions and well observations as ground truth, we train an Upsampling Model that uses low-resolution (25 km) GLDAS data as input to produce high-resolution (2 km) GWLs, achieving an excellent $R^2$ score of 0.96. Our approach successfully upscales GLDAS data for 2003-2024, allowing high-resolution recharge estimations and revealing critical trends for proactive resource management. Our method allows upsampling of groundwater storage (GWS) from GLDAS to high-resolution GWLs for any points independently of officially curated piezometer data, making it a valuable tool for decision-making.

cs.LG↗

arXiv2025

A light-weight model to generate NDWI from Sentinel-1

The use of Sentinel-2 images to compute Normalized Difference Water Index (NDWI) has many applications, including water body area detection. However, cloud cover poses significant challenges in this regard, which hampers the effectiveness of Sentinel-2 images in this context. In this paper, we present a deep learning model that can generate NDWI given Sentinel-1 images, thereby overcoming this cloud barrier. We show the effectiveness of our model, where it demonstrates a high accuracy of 0.9134 and an AUC of 0.8656 to predict the NDWI. Additionally, we observe promising results with an R2 score of 0.4984 (for regressing the NDWI values) and a Mean IoU of 0.4139 (for the underlying segmentation task). In conclusion, our model offers a first and robust solution for generating NDWI images directly from Sentinel-1 images and subsequent use for various applications even under challenging conditions such as cloud cover and nighttime.

cs.CV↗

arXiv2024

Algorithms for Parameterized String Matching with Mismatches

Two strings are considered to have parameterized matching when there exists a bijection of the parameterized alphabet onto itself such that it transforms one string to another. Parameterized matching has application in software duplication detection, image processing, and computational biology. We consider the problem for which a pattern $p$, a text $t$ and a mismatch tolerance limit $k$ is given and the goal is to find all positions in text $t$, for which pattern $p$, parameterized matches with $|p|$ length substrings of $t$ with at most $k$ mismatches. Our main result is an algorithm for this problem with $O(α^2 n\log n + n α^2 \sqrtα \log \left( n α\right))$ time complexity, where $n = |t|$ and $α= |Σ|$ which is improving for $k=\tildeΩ(|Σ|^{5/3})$ the algorithm by Hazay, Lewenstein and Sokol. We also present a hashing based probabilistic algorithm for this problem when $k = 1$ with $O \left( n \log n \right)$ time complexity, which we believe is algorithmically beautiful.

cs.DS↗

arXiv2024

ConVerSum: A Contrastive Learning-based Approach for Data-Scarce Solution of Cross-Lingual Summarization Beyond Direct Equivalents

Cross-lingual summarization (CLS) is a sophisticated branch in Natural Language Processing that demands models to accurately translate and summarize articles from different source languages. Despite the improvement of the subsequent studies, This area still needs data-efficient solutions along with effective training methodologies. To the best of our knowledge, there is no feasible solution for CLS when there is no available high-quality CLS data. In this paper, we propose a novel data-efficient approach, ConVerSum, for CLS leveraging the power of contrastive learning, generating versatile candidate summaries in different languages based on the given source document and contrasting these summaries with reference summaries concerning the given documents. After that, we train the model with a contrastive ranking loss. Then, we rigorously evaluate the proposed approach against current methodologies and compare it to powerful Large Language Models (LLMs)- Gemini, GPT 3.5, and GPT 4o proving our model performs better for low-resource languages' CLS. These findings represent a substantial improvement in the area, opening the door to more efficient and accurate cross-lingual summarizing techniques.

cs.CL↗

arXiv2024

GraphAge: Unleashing the power of Graph Neural Network to Decode Epigenetic Aging

DNA methylation is a crucial epigenetic marker used in various clocks to predict epigenetic age. However, many existing clocks fail to account for crucial information about CpG sites and their interrelationships, such as co-methylation patterns. We present a novel approach to represent methylation data as a graph, using methylation values and relevant information about CpG sites as nodes, and relationships like co-methylation, same gene, and same chromosome as edges. We then use a Graph Neural Network (GNN) to predict age. Thus our model, GraphAge, leverages both structural and positional information for prediction as well as better interpretation. Although we had to train in a constrained compute setting, GraphAge still showed competitive performance with a Mean Absolute Error (MAE) of 3.207 and a Mean Squared Error (MSE) of 25.277, slightly outperforming the current state of the art. Perhaps more importantly, we utilized GNN explainer for interpretation purposes and were able to unearth interesting insights (e.g., key CpG sites, pathways, and their relationships through Methylation Regulated Networks in the context of aging), which were not possible to 'decode' without leveraging the unique capability of GraphAge to 'encode' various structural relationships. GraphAge has the potential to consume and utilize all relevant information (if available) about an individual that relates to the complex process of aging. So, in that sense, it is one of its kind and can be seen as the first benchmark for a multimodal model that can incorporate all this information in order to close the gap in our understanding of the true nature of aging.

q-bio.QM↗

arXiv2023

RamanNet: A generalized neural network architecture for Raman Spectrum Analysis

Raman spectroscopy provides a vibrational profile of the molecules and thus can be used to uniquely identify different kind of materials. This sort of fingerprinting molecules has thus led to widespread application of Raman spectrum in various fields like medical dignostics, forensics, mineralogy, bacteriology and virology etc. Despite the recent rise in Raman spectra data volume, there has not been any significant effort in developing generalized machine learning methods for Raman spectra analysis. We examine, experiment and evaluate existing methods and conjecture that neither current sequential models nor traditional machine learning models are satisfactorily sufficient to analyze Raman spectra. Both has their perks and pitfalls, therefore we attempt to mix the best of both worlds and propose a novel network architecture RamanNet. RamanNet is immune to invariance property in CNN and at the same time better than traditional machine learning models for the inclusion of sparse connectivity. Our experiments on 4 public datasets demonstrate superior performance over the much complex state-of-the-art methods and thus RamanNet has the potential to become the defacto standard in Raman spectra data analysis

cs.LG↗

arXiv2023

Image Contrast Enhancement using Fuzzy Technique with Parameter Determination using Metaheuristics

In this work, we have presented a way to increase the contrast of an image. Our target is to find a transformation that will be image specific. We have used a fuzzy system as our transformation function. To tune the system according to an image, we have used Genetic Algorithm and Hill Climbing in multiple ways to evolve the fuzzy system and conducted several experiments. Different variants of the method are tested on several images and two variants that are superior to others in terms of fitness are selected. We have also conducted a survey to assess the visual improvement of the enhancements made by the two variants. The survey indicates that one of the methods can enhance the contrast of the images visually.

cs.CV↗