arXiv subjects

Md. Abdur Rahman

Publications and source records attributed to Md. Abdur Rahman.

16 recordsLinked to original sources

arXiv2026

Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR

Lightweight speech recognition models are critical for edge deployment, yet highly optimized architectures like Moonshine often fail on morphologically rich, non-Latin languages such as Bengali. This study identifies the root cause of this failure as the model's English-centric byte-level tokenizer, which fragments Bengali words into high-fertility byte chains and triggers catastrophic autoregressive collapse during inference. To resolve this, a novel vocabulary transplantation pipeline is proposed to replace the decoder vocabulary with the native-script BanglaBERT WordPiece vocabulary and resize the corresponding token embedding matrix. Experimental results demonstrate a reduction in token fertility from 9.16 to 1.30. By decreasing autoregressive sequence length by 85.8%, decoding instability is entirely mitigated. When evaluated on the 882-hour Lipi-Ghor dataset, the modified architecture achieves a competitive 21.54% Word Error Rate (WER) and a Real-Time Factor (RTF) of 0.0053. Ultimately, this research provides a scalable, reproducible blueprint for cross-script adaptation of compact ASR models without the need for resource-intensive pre-training.

cs.CL↗

arXiv2026

A fine-grained attention and geometric correspondence model for musculoskeletal risk classification in athletes using multimodal visual and skeletal features

Musculoskeletal disorders pose significant risks to athletes, and early risk assessment is essential for prevention. However, most existing methods are designed for controlled settings and fail to reliably assess risk in complex environments due to their reliance on a single type of data. This research introduces ViSK-GAT (Visual-Skeletal Geometric Attention Transformer), a novel multimodal deep learning framework that classifies musculoskeletal risk using both visual and skeletal coordinate-based features. A custom multimodal dataset (MusDis-Sports) was created by combining images and skeletal coordinates, with each sample labeled into eight risk categories based on the Rapid Entire Body Assessment (REBA) system. ViSK-GAT integrates two innovative modules: the Fine-Grained Attention Module (FGAM), which refines intra-modal features through self-attention before fusion, and the Multimodal Geometric Correspondence Module (MGCM), which enhances cross-modal alignment between image features and coordinates. The model achieved robust performance, with all key metrics exceeding 93%. Probability distribution error metrics also showed a low Root Mean Squared Error (RMSE) of 0.1205 and a Mean Absolute Error (MAE) of 0.0156. ViSK-GAT consistently outperformed state-of-the-art (SOTA) deep learning backbones and showed its potential to advance artificial intelligence-driven musculoskeletal risk assessment and enable timely interventions in sports.

cs.CV↗

arXiv2026

GHTM: A Graph-based Hybrid Topic Modeling Approach with a Benchmark Dataset for the Low-Resource Bengali Language

Topic modeling is a Natural Language Processing (NLP) technique used to discover latent themes and abstract topics from text corpora by grouping co-occurring keywords. Although widely researched in English, topic modeling remains understudied in Bengali due to a lack of adequate resources and initiatives. Existing Bengali topic modeling research lacks standardized evaluation frameworks with comprehensive baselines and diverse datasets, exploration of modern methodological approaches, and reproducible implementations, with only three Bengali-specific architectures proposed to date. To address these gaps, this study presents a comprehensive evaluation of traditional and contemporary topic modeling approaches across three Bengali datasets and introduces GHTM (Graph-based Hybrid Topic Model), a novel architecture that strategically integrates TF-IDF-weighted GloVe embeddings, Graph Convolutional Networks (GCN), and Non-negative Matrix Factorization (NMF). GHTM represents text documents using hybrid TF-IDF-weighted GloVe embeddings. It builds a document-similarity graph and leverages GCN to refine the representations through neighborhood aggregation. Then, it finally decomposes the refined representations using NMF to extract interpretable topics. Experimental results demonstrate that GHTM achieves superior topic coherence (NPMI: 0.27-0.28) and diversity compared to existing methods while maintaining computational efficiency across datasets of varying scales. The model also demonstrates strong cross-lingual generalization, outperforming established graph-based models on the English 20Newsgroups benchmark. Additionally, we introduce NCTBText, a diverse Bengali textbook-based dataset comprising 8,650 text documents, curated from eight subject areas, providing much-needed topical diversity beyond newspaper-centric Bengali corpora and serving as a benchmark for future research.

cs.CL↗

arXiv2026

Learning to Weigh Waste: A Physics-Informed Multimodal Fusion Framework and Large-Scale Dataset for Commercial and Industrial Applications

Accurate weight estimation of commercial and industrial waste is important for efficient operations, yet image-based estimation remains difficult because similar-looking objects may have different densities, and the visible size changes with camera distance. Addressing this problem, we propose Multimodal Weight Predictor (MWP) framework that estimates waste weight by combining RGB images with physics-informed metadata, including object dimensions, camera distance, and camera height. We also introduce Waste-Weight-10K, a real-world dataset containing 10,421 synchronized image-metadata collected from logistics and recycling sites. The dataset covers 11 waste categories and a wide weight range from 3.5 to 3,450 kg. Our model uses a Vision Transformer for visual features and a dedicated metadata encoder for geometric and category information, combining them with Stacked Mutual Attention Fusion that allows visual and physical cues guide each other. This helps the model manage perspective effects and link objects to material properties. To ensure stable performance across the wide weight range, we train the model using Mean Squared Logarithmic Error. On the test set, the proposed method achieves 88.06 kg Mean Absolute Error (MAE), 6.39% Mean Absolute Percentage Error (MAPE), and an R2 coefficient of 0.9548. The model shows strong accuracy for light objects in the 0-100 kg range with 2.38 kg MAE and 3.1% MAPE, maintaining reliable performance for heavy waste in the 1000-2000 kg range with 11.1% MAPE. Finally, we incorporate a physically grounded explanation module using Shapley Additive Explanations (SHAP) and a large language model to provide clear, human-readable explanations for each prediction.

cs.CV↗

arXiv2026

A Source-Free Approach for Domain Adaptation via Multiview Image Transformation and Latent Space Consistency

Domain adaptation (DA) addresses the challenge of transferring knowledge from a source domain to a target domain where image data distributions may differ. Existing DA methods often require access to source domain data, adversarial training, or complex pseudo-labeling techniques, which are computationally expensive. To address these challenges, this paper introduces a novel source-free domain adaptation method. It is the first approach to use multiview augmentation and latent space consistency techniques to learn domain-invariant features directly from the target domain. Our method eliminates the need for source-target alignment or pseudo-label refinement by learning transferable representations solely from the target domain by enforcing consistency between multiple augmented views in the latent space. Additionally, the method ensures consistency in the learned features by generating multiple augmented views of target domain data and minimizing the distance between their feature representations in the latent space. We also introduce a ConvNeXt-based encoder and design a loss function that combines classification and consistency objectives to drive effective adaptation directly from the target domain. The proposed model achieves an average classification accuracy of 90. 72\%, 84\%, and 97. 12\% in Office-31, Office-Home and Office-Caltech datasets, respectively. Further evaluations confirm that our study improves existing methods by an average classification accuracy increment of +1.23\%, +7.26\%, and +1.77\% on the respective datasets.

cs.CV↗

arXiv2025

ReFRM3D: A Radiomics-enhanced Fused Residual Multiparametric 3D Network with Multi-Scale Feature Fusion for Glioma Characterization

Gliomas are among the most aggressive cancers, characterized by high mortality rates and complex diagnostic processes. Existing studies on glioma diagnosis and classification often describe issues such as high variability in imaging data, inadequate optimization of computational resources, and inefficient segmentation and classification of gliomas. To address these challenges, we propose novel techniques utilizing multi-parametric MRI data to enhance tumor segmentation and classification efficiency. Our work introduces the first-ever radiomics-enhanced fused residual multiparametric 3D network (ReFRM3D) for brain tumor characterization, which is based on a 3D U-Net architecture and features multi-scale feature fusion, hybrid upsampling, and an extended residual skip mechanism. Additionally, we propose a multi-feature tumor marker-based classifier that leverages radiomic features extracted from the segmented regions. Experimental results demonstrate significant improvements in segmentation performance across the BraTS2019, BraTS2020, and BraTS2021 datasets, achieving high Dice Similarity Coefficients (DSC) of 94.04%, 92.68%, and 93.64% for whole tumor (WT), enhancing tumor (ET), and tumor core (TC) respectively in BraTS2019; 94.09%, 92.91%, and 93.84% in BraTS2020; and 93.70%, 90.36%, and 92.13% in BraTS2021.

cs.CV↗

arXiv2025

WeCKD: Weakly-supervised Chained Distillation Network for Efficient Multimodal Medical Imaging

Knowledge distillation (KD) has traditionally relied on a static teacher-student framework, where a large, well-trained teacher transfers knowledge to a single student model. However, these approaches often suffer from knowledge degradation, inefficient supervision, and reliance on either a very strong teacher model or large labeled datasets. To address these, we present the first-ever Weakly-supervised Chain-based KD network (WeCKD) that redefines knowledge transfer through a structured sequence of interconnected models. Unlike conventional KD, it forms a progressive distillation chain, where each model not only learns from its predecessor but also refines the knowledge before passing it forward. This structured knowledge transfer further enhances feature learning and addresses the limitations of one-step KD. Each model in the chain is trained on only a fraction of the dataset and shows that effective learning can be achieved with minimal supervision. Extensive evaluation on six imaging datasets across otoscopic, microscopic, and magnetic resonance imaging modalities shows that it generalizes and outperforms existing methods. Furthermore, the proposed distillation chain resulted in cumulative accuracy gains of up to +23% over a single backbone trained on the same limited data, which highlights its potential for real-world adoption.

cs.CV↗

arXiv2025

ARIONet: An Advanced Self-supervised Contrastive Representation Network for Birdsong Classification and Future Frame Prediction

Automated birdsong classification is essential for advancing ecological monitoring and biodiversity studies. Despite recent progress, existing methods often depend heavily on labeled data, use limited feature representations, and overlook temporal dynamics essential for accurate species identification. In this work, we propose a self-supervised contrastive network, ARIONet (Acoustic Representation for Interframe Objective Network), that jointly optimizes contrastive classification and future frame prediction using augmented audio representations. The model simultaneously integrates multiple complementary audio features within a transformer-based encoder model. Our framework is designed with two key objectives: (1) to learn discriminative species-specific representations for contrastive learning through maximizing similarity between augmented views of the same audio segment while pushing apart different samples, and (2) to model temporal dynamics by predicting future audio frames, both without requiring large-scale annotations. We validate our framework on four diverse birdsong datasets, including the British Birdsong Dataset, Bird Song Dataset, and two extended Xeno-Canto subsets (A-M and N-Z). Our method consistently outperforms existing baselines and achieves classification accuracies of 98.41%, 93.07%, 91.89%, and 91.58%, and F1-scores of 97.84%, 94.10%, 91.29%, and 90.94%, respectively. Furthermore, it demonstrates low mean absolute errors and high cosine similarity, up to 95\%, in future frame prediction tasks. Extensive experiments further confirm the effectiveness of our self-supervised learning strategy in capturing complex acoustic patterns and temporal dependencies, as well as its potential for real-world applicability in ecological conservation and monitoring.

cs.SD↗

arXiv2025

HANS-Net: Hyperbolic Convolution and Adaptive Temporal Attention for Accurate and Generalizable Liver and Tumor Segmentation in CT Imaging

Accurate liver and tumor segmentation on abdominal CT images is critical for reliable diagnosis and treatment planning, but remains challenging due to complex anatomical structures, variability in tumor appearance, and limited annotated data. To address these issues, we introduce Hyperbolic-convolutions Adaptive-temporal-attention with Neural-representation and Synaptic-plasticity Network (HANS-Net), a novel segmentation framework that synergistically combines hyperbolic convolutions for hierarchical geometric representation, a wavelet-inspired decomposition module for multi-scale texture learning, a biologically motivated synaptic plasticity mechanism for adaptive feature enhancement, and an implicit neural representation branch to model fine-grained and continuous anatomical boundaries. Additionally, we incorporate uncertainty-aware Monte Carlo dropout to quantify prediction confidence and lightweight temporal attention to improve inter-slice consistency without sacrificing efficiency. Extensive evaluations of the LiTS dataset demonstrate that HANS-Net achieves a mean Dice score of 93.26%, an IoU of 88.09%, an average symmetric surface distance (ASSD) of 0.72 mm, and a volume overlap error (VOE) of 11.91%. Furthermore, cross-dataset validation on the AMOS 2022 dataset obtains an average Dice of 85.09%, IoU of 76.66%, ASSD of 19.49 mm, and VOE of 23.34%, indicating strong generalization across different datasets. These results confirm the effectiveness and robustness of HANS-Net in providing anatomically consistent, accurate, and confident liver and tumor segmentation.

eess.IV↗

arXiv2025

Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models

Large Language Models (LLMs) are trained on vast and diverse internet corpora that often include inaccurate or misleading content. Consequently, LLMs can generate misinformation, making robust fact-checking essential. This review systematically analyzes how LLM-generated content is evaluated for factual accuracy by exploring key challenges such as hallucinations, dataset limitations, and the reliability of evaluation metrics. The review emphasizes the need for strong fact-checking frameworks that integrate advanced prompting strategies, domain-specific fine-tuning, and retrieval-augmented generation (RAG) methods. It proposes five research questions that guide the analysis of the recent literature from 2020 to 2025, focusing on evaluation methods and mitigation techniques. Instruction tuning, multi-agent reasoning, and RAG frameworks for external knowledge access are also reviewed. The key findings demonstrate the limitations of current metrics, the importance of validated external evidence, and the improvement of factual consistency through domain-specific customization. The review underscores the importance of building more accurate, understandable, and context-aware fact-checking. These insights contribute to the advancement of research toward more trustworthy models.

cs.CL↗

arXiv2025

Detection of Distributed Denial of Service Attacks based on Machine Learning Algorithms

Distributed Denial of Service (DDoS) attacks make the challenges to provide the services of the data resources to the web clients. In this paper, we concern to study and apply different Machine Learning (ML) techniques to separate the DDoS attack instances from benign instances. Our experimental results show that forward and backward data bytes of our dataset are observed more similar for DDoS attacks compared to the data bytes for benign attempts. This paper uses different machine learning techniques for the detection of the attacks efficiently in order to make sure the offered services from web servers available. This results from the proposed approach suggest that 97.1% of DDoS attacks are successfully detected by the Support Vector Machine (SVM). These accuracies are better while comparing to the several existing machine learning approaches.

cs.CR↗

arXiv2024

A Novel Word Pair-based Gaussian Sentence Similarity Algorithm For Bengali Extractive Text Summarization

Extractive Text Summarization is the process of selecting the most representative parts of a larger text without losing any key information. Recent attempts at extractive text summarization in Bengali, either relied on statistical techniques like TF-IDF or used naive sentence similarity measures like the word averaging technique. All of these strategies suffer from expressing semantic relationships correctly. Here, we propose a novel Word pair-based Gaussian Sentence Similarity (WGSS) algorithm for calculating the semantic relation between two sentences. WGSS takes the geometric means of individual Gaussian similarity values of word embedding vectors to get the semantic relationship between sentences. It compares two sentences on a word-to-word basis which rectifies the sentence representation problem faced by the word averaging method. The summarization process extracts key sentences by grouping semantically similar sentences into clusters using the Spectral Clustering algorithm. After clustering, we use TF-IDF ranking to pick the best sentence from each cluster. The proposed method is validated using four different datasets, and it outperformed other recent models by 43.2% on average ROUGE scores (ranging from 2.5% to 95.4%). It is also experimented on other low-resource languages i.e. Turkish, Marathi, and Hindi language, where we find that the proposed method performs as similar as Bengali for these languages. In addition, a new high-quality Bengali dataset is curated which contains 250 articles and a pair of summaries for each of them. We believe this research is a crucial addition to Bengali Natural Language Processing (NLP) research and it can easily be extended into other low-resource languages. We made the implementation of the proposed model and data public on https://github.com/FMOpee/WGSS.

cs.CL↗

arXiv2020

Performance Evaluation of t-SNE and MDS Dimensionality Reduction Techniques with KNN, ENN and SVM Classifiers

The central goal of this paper is to establish two commonly available dimensionality reduction (DR) methods i.e. t-distributed Stochastic Neighbor Embedding (t-SNE) and Multidimensional Scaling (MDS) in Matlab and to observe their application in several datasets. These DR techniques are applied to nine different datasets namely CNAE9, Segmentation, Seeds, Pima Indians diabetes, Parkinsons, Movement Libras, Mammographic Masses, Knowledge, and Ionosphere acquired from UCI machine learning repository. By applying t-SNE and MDS algorithms, each dataset is transformed to the half of its original dimension by eliminating unnecessary features from the datasets. Subsequently, these datasets with reduced dimensions are fed into three supervised classification algorithms for classification. These classification algorithms are K Nearest Neighbors (KNN), Extended Nearest Neighbors (ENN), and Support Vector Machine (SVM). Again, all these algorithms are implemented in Matlab. The training and test data ratios are maintained as ninety percent: ten percent for each dataset. Upon accuracy observation, the efficiency for every dimensionality technique with availed classification algorithms is analyzed and the performance of each classifier is evaluated.

cs.LG↗

arXiv2020

The Potential Short- and Long-Term Disruptions and Transformative Impacts of 5G and Beyond Wireless Networks: Lessons Learnt from the Development of a 5G Testbed Environment

The anticipated deployment cost of 5G communication networks in the UK is predicted to be in between £30bn- £50bn, whereas the current annual capital expenditure of the mobile network operators (MNOs) is £2.5bn. This prospect has vastly impacted and has become one of the major delaying factors for building the 5G physical infrastructure, whereas other areas of 5G developments are progressing at their speed. In this paper, an extensive study is conducted to explore the possibilities of reducing the 5G deployment cost and developing business models. This study suggests that the use of existing public infrastructure has a great potential to contribute to a reduction of about 40% to 60% in the anticipated cost. Also, the recent Ofcom initiative of location-based licensing of radio spectrum is reviewed. Our study suggests that simplification of infrastructure and spectrum will encourage the exponential growth of scenario-specific cellular networks and will potentially disrupt the current business models of telecommunication stakeholders -- specifically MNOs and TowerCos. Moreover, the dense network connectivity will encourage extensive data harvesting as a business opportunity and function within small and medium-sized enterprises as well as within large social networks. Consequently, the rise of new infrastructures and spectrum stakeholders is anticipated. This will fuel the development of a 5G data exchange ecosystem where data transactions are deemed to be high-value business commodities. Also, a data economy-oriented business model is proposed. The study found that with the potential commodification of data and data transactions along with the low-cost physical infrastructure and spectrum, the 5G network will introduce significant disruption in the Telco business ecosystem.

cs.NI↗

arXiv2019

Performance Analysis of Deep Autoencoder and NCA Dimensionality Reduction Techniques with KNN, ENN and SVM Classifiers

The central aim of this paper is to implement Deep Autoencoder and Neighborhood Components Analysis (NCA) dimensionality reduction methods in Matlab and to observe the application of these algorithms on nine unlike datasets from UCI machine learning repository. These datasets are CNAE9, Movement Libras, Pima Indians diabetes, Parkinsons, Knowledge, Segmentation, Seeds, Mammographic Masses, and Ionosphere. First of all, the dimension of these datasets has been reduced to fifty percent of their original dimension by selecting and extracting the most relevant and appropriate features or attributes using Deep Autoencoder and NCA dimensionality reduction techniques. Afterward, each dataset is classified applying K-Nearest Neighbors (KNN), Extended Nearest Neighbors (ENN) and Support Vector Machine (SVM) classification algorithms. All classification algorithms are developed in the Matlab environment. In each classification, the training test data ratio is always set to ninety percent: ten percent. Upon classification, variation between accuracies is observed and analyzed to find the degree of compatibility of each dimensionality reduction technique with each classifier and to evaluate each classifier performance on each dataset.

cs.LG↗

arXiv2010

Modeling Spammer Behavior: Naïve Bayes vs. Artificial Neural Networks

Addressing the problem of spam emails in the Internet, this paper presents a comparative study on Naïve Bayes and Artificial Neural Networks (ANN) based modeling of spammer behavior. Keyword-based spam email filtering techniques fall short to model spammer behavior as the spammer constantly changes tactics to circumvent these filters. The evasive tactics that the spammer uses are themselves patterns that can be modeled to combat spam. It has been observed that both Naïve Bayes and ANN are best suitable for modeling spammer common patterns. Experimental results demonstrate that both of them achieve a promising detection rate of around 92%, which is considerably an improvement of performance compared to the keyword-based contemporary filtering approaches.

cs.IR↗