arXiv subjects

Tashreef Muhammad

Publications and source records attributed to Tashreef Muhammad.

16 recordsLinked to original sources

arXiv2026

PatiGonit22K: A Comprehensive Dataset for Solving Complex Bengali MWPs

Mathematical Word Problems (MWPs) are an important benchmark for evaluating natural language understanding and quantitative reasoning. Despite recent progress in high resource languages, Bengali remains underexplored due to the limited availability of large scale annotated datasets. In this work, we introduce PatiGonit22K, an expanded Bengali MWP dataset containing 22,441 problems, developed by extending the original PatiGonit dataset with a substantially larger collection of complex mathematical problems. The dataset includes both simple and multi operation equations, providing a balanced benchmark for evaluating mathematical reasoning across different difficulty levels. Each problem is carefully translated, annotated, culturally adapted, and verified to ensure linguistic consistency and mathematical correctness. By increasing both the scale and complexity of Bengali MWPs, PatiGonit22K provides a more comprehensive resource for future research on mathematical reasoning and educational NLP applications in low resource languages.

cs.CL↗

arXiv2026

A Benchmark of Classical and Deep Learning Models for Agricultural Commodity Price Forecasting on A Novel Bangladeshi Market Price Dataset

Accurate short-term forecasting of agricultural commodity prices is critical for food security planning and smallholder income stabilisation in developing economies, yet machine-learning-ready datasets for this purpose remain scarce in South Asia. This paper makes two contributions. First, we introduce AgriPriceBD, a benchmark dataset of 1,779 daily retail mid-prices for five Bangladeshi commodities - garlic, chickpea, green chilli, cucumber, and sweet pumpkin - spanning July 2020 to June 2025, extracted from government reports via an LLM-assisted digitisation pipeline. Second, we evaluate seven forecasting approaches spanning classical models - na\"{i}ve persistence, SARIMA, and Prophet - and deep learning architectures - BiLSTM, Transformer, Time2Vec-enhanced Transformer, and Informer - with Diebold-Mariano statistical significance tests. Commodity price forecastability is fundamentally heterogeneous: na\"{i}ve persistence dominates on near-random-walk commodities. Time2Vec temporal encoding provides no statistically significant advantage over fixed sinusoidal encoding and causes catastrophic degradation on green chilli (+146.1% MAE, p<0.001). Prophet fails systematically, attributable to discrete step-function price dynamics incompatible with its smooth decomposition assumptions. Informer produces erratic predictions (variance up to 50x ground-truth), confirming sparse-attention Transformers require substantially larger training sets than small agricultural datasets provide. All code, models, and data are released publicly to support replication and future forecasting research on agricultural commodity markets in Bangladesh and similar developing economies.

cs.LG↗

arXiv2026

Temporal Coverage Bias in Financial Panel Data: A Coverage-Aware Structuring Framework with Evidence from the Dhaka Stock Exchange

A common practice in empirical finance is to construct calendar-aligned panels that implicitly treat all instruments as having existed for the full observation period. When securities with different listing histories are combined without explicit coverage constraints, price histories can be inadvertently extended before valid trading ever began. This paper formalizes this problem and proposes a coverage-aware structuring framework built around instrument-level observation windows encoded through structured metadata and an availability matrix. Applied to end-of-day data from the Dhaka Stock Exchange spanning October 2012 to January 2026 and covering 486 instruments, the framework reveals substantial distortions from naive temporal alignment. ARIMA-based experiments establish the mechanism through which padded observations corrupt return dynamics, and volatility analysis across 53 instruments shows that forward-filling alone suppresses return volatility by roughly 20% on average, with GARCH unconditional variance distortions exceeding 26% in over 90% of instruments - a lower bound, as backward extension to the panel start produces 36.6% suppression and causes GARCH non-convergence in 41% of instruments. The distortion affects any method requiring calendar alignment of heterogeneous histories, including dynamic time warping, covariance-based portfolio construction, factor model regression, and temporal foundation model fine-tuning. Although demonstrated on financial data, the framework applies to any panel combining entities with heterogeneous entry dates, including sensor networks, clinical cohorts, and country-level economic panels. Listing coverage is not a minor preprocessing detail but a first-order variable in panel construction.

q-fin.ST↗

arXiv2025

BIDWESH: A Bangla Regional Based Hate Speech Detection Dataset

Hate speech on digital platforms has become a growing concern globally, especially in linguistically diverse countries like Bangladesh, where regional dialects play a major role in everyday communication. Despite progress in hate speech detection for standard Bangla, Existing datasets and systems fail to address the informal and culturally rich expressions found in dialects such as Barishal, Noakhali, and Chittagong. This oversight results in limited detection capability and biased moderation, leaving large sections of harmful content unaccounted for. To address this gap, this study introduces BIDWESH, the first multi-dialectal Bangla hate speech dataset, constructed by translating and annotating 9,183 instances from the BD-SHS corpus into three major regional dialects. Each entry was manually verified and labeled for hate presence, type (slander, gender, religion, call to violence), and target group (individual, male, female, group), ensuring linguistic and contextual accuracy. The resulting dataset provides a linguistically rich, balanced, and inclusive resource for advancing hate speech detection in Bangla. BIDWESH lays the groundwork for the development of dialect-sensitive NLP tools and contributes significantly to equitable and context-aware content moderation in low-resource language settings.

cs.CL↗

arXiv2025

An Exploratory Approach Towards Investigating and Explaining Vision Transformer and Transfer Learning for Brain Disease Detection

The brain is a highly complex organ that manages many important tasks, including movement, memory and thinking. Brain-related conditions, like tumors and degenerative disorders, can be hard to diagnose and treat. Magnetic Resonance Imaging (MRI) serves as a key tool for identifying these conditions, offering high-resolution images of brain structures. Despite this, interpreting MRI scans can be complicated. This study tackles this challenge by conducting a comparative analysis of Vision Transformer (ViT) and Transfer Learning (TL) models such as VGG16, VGG19, Resnet50V2, MobilenetV2 for classifying brain diseases using MRI data from Bangladesh based dataset. ViT, known for their ability to capture global relationships in images, are particularly effective for medical imaging tasks. Transfer learning helps to mitigate data constraints by fine-tuning pre-trained models. Furthermore, Explainable AI (XAI) methods such as GradCAM, GradCAM++, LayerCAM, ScoreCAM, and Faster-ScoreCAM are employed to interpret model predictions. The results demonstrate that ViT surpasses transfer learning models, achieving a classification accuracy of 94.39%. The integration of XAI methods enhances model transparency, offering crucial insights to aid medical professionals in diagnosing brain diseases with greater precision.

cs.CV↗

arXiv2025

An Approach Towards Identifying Bangladeshi Leaf Diseases through Transfer Learning and XAI

Leaf diseases are harmful conditions that affect the health, appearance and productivity of plants, leading to significant plant loss and negatively impacting farmers' livelihoods. These diseases cause visible symptoms such as lesions, color changes, and texture variations, making it difficult for farmers to manage plant health, especially in large or remote farms where expert knowledge is limited. The main motivation of this study is to provide an efficient and accessible solution for identifying plant leaf diseases in Bangladesh, where agriculture plays a critical role in food security. The objective of our research is to classify 21 distinct leaf diseases across six plants using deep learning models, improving disease detection accuracy while reducing the need for expert involvement. Deep Learning (DL) techniques, including CNN and Transfer Learning (TL) models like VGG16, VGG19, MobileNetV2, InceptionV3, ResNet50V2 and Xception are used. VGG19 and Xception achieve the highest accuracies, with 98.90% and 98.66% respectively. Additionally, Explainable AI (XAI) techniques such as GradCAM, GradCAM++, LayerCAM, ScoreCAM and FasterScoreCAM are used to enhance transparency by highlighting the regions of the models focused on during disease classification. This transparency ensures that farmers can understand the model's predictions and take necessary action. This approach not only improves disease management but also supports farmers in making informed decisions, leading to better plant protection and increased agricultural productivity.

cs.CV↗

arXiv2025

VR-FuseNet: A Fusion of Heterogeneous Fundus Data and Explainable Deep Network for Diabetic Retinopathy Classification

Diabetic retinopathy is a severe eye condition caused by diabetes where the retinal blood vessels get damaged and can lead to vision loss and blindness if not treated. Early and accurate detection is key to intervention and stopping the disease progressing. For addressing this disease properly, this paper presents a comprehensive approach for automated diabetic retinopathy detection by proposing a new hybrid deep learning model called VR-FuseNet. Diabetic retinopathy is a major eye disease and leading cause of blindness especially among diabetic patients so accurate and efficient automated detection methods are required. To address the limitations of existing methods including dataset imbalance, diversity and generalization issues this paper presents a hybrid dataset created from five publicly available diabetic retinopathy datasets. Essential preprocessing techniques such as SMOTE for class balancing and CLAHE for image enhancement are applied systematically to the dataset to improve the robustness and generalizability of the dataset. The proposed VR-FuseNet model combines the strengths of two state-of-the-art convolutional neural networks, VGG19 which captures fine-grained spatial features and ResNet50V2 which is known for its deep hierarchical feature extraction. This fusion improves the diagnostic performance and achieves an accuracy of 91.824%. The model outperforms individual architectures on all performance metrics demonstrating the effectiveness of hybrid feature extraction in Diabetic Retinopathy classification tasks. To make the proposed model more clinically useful and interpretable this paper incorporates multiple XAI techniques. These techniques generate visual explanations that clearly indicate the retinal features affecting the model's prediction such as microaneurysms, hemorrhages and exudates so that clinicians can interpret and validate.

cs.CV↗

arXiv2025

ANCHOLIK-NER: A Benchmark Dataset for Bangla Regional Named Entity Recognition

Named Entity Recognition (NER) in regional dialects is a critical yet underexplored area in Natural Language Processing (NLP), especially for low-resource languages like Bangla. While NER systems for Standard Bangla have made progress, no existing resources or models specifically address the challenge of regional dialects such as Barishal, Chittagong, Mymensingh, Noakhali, and Sylhet, which exhibit unique linguistic features that existing models fail to handle effectively. To fill this gap, we introduce ANCHOLIK-NER, the first benchmark dataset for NER in Bangla regional dialects, comprising 17,405 sentences distributed across five regions. The dataset was sourced from publicly available resources and supplemented with manual translations, ensuring alignment of named entities across dialects. We evaluate three transformer-based models - Bangla BERT, Bangla BERT Base, and BERT Base Multilingual Cased - on this dataset. Our findings demonstrate that BERT Base Multilingual Cased performs best in recognizing named entities across regions, with significant performance observed in Mymensingh with an F1-score of 82.611%. Despite strong overall performance, challenges remain in region like Chittagong, where the models show lower precision and recall. Since no previous NER systems for Bangla regional dialects exist, our work represents a foundational step in addressing this gap. Future work will focus on improving model performance in underperforming regions and expanding the dataset to include more dialects, enhancing the development of dialect-aware NER systems.

cs.CL↗

arXiv2025

Bridging Dialects: Translating Standard Bangla to Regional Variants Using Neural Models

The Bangla language includes many regional dialects, adding to its cultural richness. The translation of Bangla Language into regional dialects presents a challenge due to significant variations in vocabulary, pronunciation, and sentence structure across regions like Chittagong, Sylhet, Barishal, Noakhali, and Mymensingh. These dialects, though vital to local identities, lack of representation in technological applications. This study addresses this gap by translating standard Bangla into these dialects using neural machine translation (NMT) models, including BanglaT5, mT5, and mBART50. The work is motivated by the need to preserve linguistic diversity and improve communication among dialect speakers. The models were fine-tuned using the "Vashantor" dataset, containing 32,500 sentences across various dialects, and evaluated through Character Error Rate (CER) and Word Error Rate (WER) metrics. BanglaT5 demonstrated superior performance with a CER of 12.3% and WER of 15.7%, highlighting its effectiveness in capturing dialectal nuances. The outcomes of this research contribute to the development of inclusive language technologies that support regional dialects and promote linguistic diversity.

cs.CL↗

arXiv2025

Explainable AI-Enhanced Deep Learning for Pumpkin Leaf Disease Detection: A Comparative Analysis of CNN Architectures

Pumpkin leaf diseases are significant threats to agricultural productivity, requiring a timely and precise diagnosis for effective management. Traditional identification methods are laborious and susceptible to human error, emphasizing the necessity for automated solutions. This study employs on the "Pumpkin Leaf Disease Dataset", that comprises of 2000 high-resolution images separated into five categories. Downy mildew, powdery mildew, mosaic disease, bacterial leaf spot, and healthy leaves. The dataset was rigorously assembled from several agricultural fields to ensure a strong representation for model training. We explored many proficient deep learning architectures, including DenseNet201, DenseNet121, DenseNet169, Xception, ResNet50, ResNet101 and InceptionResNetV2, and observed that ResNet50 performed most effectively, with an accuracy of 90.5% and comparable precision, recall, and F1-Score. We used Explainable AI (XAI) approaches like Grad-CAM, Grad-CAM++, Score-CAM, and Layer-CAM to provide meaningful representations of model decision-making processes, which improved understanding and trust in automated disease diagnostics. These findings demonstrate ResNet50's potential to revolutionize pumpkin leaf disease detection, allowing for earlier and more accurate treatments.

cs.CV↗

arXiv2023

Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language

The Bangla linguistic variety is a fascinating mix of regional dialects that contributes to the cultural diversity of the Bangla-speaking community. Despite extensive study into translating Bangla to English, English to Bangla, and Banglish to Bangla in the past, there has been a noticeable gap in translating Bangla regional dialects into standard Bangla. In this study, we set out to fill this gap by creating a collection of 32,500 sentences, encompassing Bangla, Banglish, and English, representing five regional Bangla dialects. Our aim is to translate these regional dialects into standard Bangla and detect regions accurately. To tackle the translation and region detection tasks, we propose two novel models: DialectBanglaT5 for translating regional dialects into standard Bangla and DialectBanglaBERT for identifying the dialect's region of origin. DialectBanglaT5 demonstrates superior performance across all dialects, achieving the highest BLEU score of 71.93, METEOR of 0.8503, and the lowest WER of 0.1470 and CER of 0.0791 on the Mymensingh dialect. It also achieves strong ROUGE scores across all dialects, indicating both accuracy and fluency in capturing dialectal nuances. In parallel, DialectBanglaBERT achieves an overall region classification accuracy of 89.02%, with notable F1-scores of 0.9241 for Chittagong and 0.8736 for Mymensingh, confirming its effectiveness in handling regional linguistic variation. This is the first large-scale investigation focused on Bangla regional dialect translation and region detection. Our proposed models highlight the potential of dialect-specific modeling and set a new benchmark for future research in low-resource and dialect-rich language settings.

cs.CL↗

arXiv2023

Utilizing Technical Data to Discover Similar Companies in Dhaka Stock Exchange

Stock market investment have been an ideal form of investment for many years. Investing capitals smartly in stock market yields high profit returns. But there are many companies available in a market. Currently there are more than $345$ active companies who have stocks in Dhaka Stock Exchange (DSE). Analyzing all these companies is quite impossible. However, many companies tend to move together. This study aims at finding which companies in DSE have a close connection and move alongside each other. By analyzing this relation, the investors and traders will be able to analyze a lot of companies' statistics from a calculating just a handful number of companies. The conducted experiment yielded promising results. It was found that though the system was not given anything other than technical data, it was able to identify companies that show domain specific outcomes. In other words, a relation between technical data and fundamental data was discovered from the conducted experiment.

q-fin.ST↗

arXiv2022

Frequency Distribution of Prime Numbers between an Integer and its Square: A Case Study

The chronicle of prime numbers travel back thousands of years in human history. Not only the traits of prime numbers have surprised people, but also all those endeavors made for ages to find a pattern in the appearance of prime numbers has been captivating them. Until recently, it was firmly believed that prime numbers do not maintain any pattern of occurrence among themselves. This statement is conferred not to be completely true. This paper is also an attempt to discover a pattern in the occurrence of prime numbers. This work intends to introduce some mathematical well-known equations that point to the existence of a simplistic pattern in the number of primes within the range of a number and its square. We assume that the rigorous evaluation of the perceived pattern may benefit in many aspects such as applications of encryption, algorithms concerning prime numbers, and many more.

math.GM↗

arXiv2022

Can Transformer Models Effectively Detect Software Aspects in StackOverflow Discussion?

Dozens of new tools and technologies are being incorporated to help developers, which is becoming a source of consternation as they struggle to choose one over the others. For example, there are at least ten frameworks available to developers for developing web applications, posing a conundrum in selecting the best one that meets their needs. As a result, developers are continuously searching for all of the benefits and drawbacks of each API, framework, tool, and so on. One of the typical approaches is to examine all of the features through official documentation and discussion. This approach is time-consuming, often makes it difficult to determine which aspects are the most important to a particular developer and whether a particular aspect is important to the community at large. In this paper, we have used a benchmark API aspects dataset (Opiner) collected from StackOverflow posts and observed how Transformer models (BERT, RoBERTa, DistilBERT, and XLNet) perform in detecting software aspects in textual developer discussion with respect to the baseline Support Vector Machine (SVM) model. Through extensive experimentation, we have found that transformer models improve the performance of baseline SVM for most of the aspects, i.e., `Performance', `Security', `Usability', `Documentation', `Bug', `Legal', `OnlySentiment', and `Others'. However, the models fail to apprehend some of the aspects (e.g., `Community' and `Potability') and their performance varies depending on the aspects. Also, larger architectures like XLNet are ineffective in interpreting software aspects compared to smaller architectures like DistilBERT.

cs.SE↗

arXiv2022

An Approach of Adjusting the Switch Probability based on Dimension Size: A Case Study for Performance Improvement of the Flower Pollination Algorithm

Numerous meta-heuristic algorithms have been influenced by nature. Over the past couple of decades, their quantity has been significantly escalating. The majority of these algorithms attempt to emulate natural biological and physical phenomena. This research concentrates on the Flower Pollination algorithm, which is one of several bio-inspired algorithms. The original approach was suggested for pollen grain exploration and exploitation in confined space using a specific global pollination and local pollination strategy. As a "swarm intelligence" meta-heuristic algorithm, its strength lies in locating the vicinity of the optimum solution rather than identifying the minimum. A modification to the original method is detailed in this work. This research found that by changing the specific value of "switch probability" with dynamic values of different dimension sizes and functions, the outcome was mainly improved over the original flower pollination method.

cs.NE↗

arXiv2022

Transformer-Based Deep Learning Model for Stock Price Prediction: A Case Study on Bangladesh Stock Market

In modern capital market the price of a stock is often considered to be highly volatile and unpredictable because of various social, financial, political and other dynamic factors. With calculated and thoughtful investment, stock market can ensure a handsome profit with minimal capital investment, while incorrect prediction can easily bring catastrophic financial loss to the investors. This paper introduces the application of a recently introduced machine learning model - the Transformer model, to predict the future price of stocks of Dhaka Stock Exchange (DSE), the leading stock exchange in Bangladesh. The transformer model has been widely leveraged for natural language processing and computer vision tasks, but, to the best of our knowledge, has never been used for stock price prediction task at DSE. Recently the introduction of time2vec encoding to represent the time series features has made it possible to employ the transformer model for the stock price prediction. This paper concentrates on the application of transformer-based model to predict the price movement of eight specific stocks listed in DSE based on their historical daily and weekly data. Our experiments demonstrate promising results and acceptable root mean squared error on most of the stocks.

q-fin.ST↗