Mohammad Ashrafuzzaman Khan

Ahmed Faizul Haque Dhrubo, Souvik Pramanik, Most. Aysha Siddika Sumona et al.

This study introduces a novel architecture of KAN-based BiGRU model for the task of classification and summarization of legal documents in a low-resource multilingual setup. In order to tackle problems associated with domain language, the usage of different languages, long dependencies within context, and class imbalance, we employ the dataset composed of legal documents from Bangladesh and taken from Manupatra, which include Bengali, English, and transliterated Bengali languages. Our classification task involves BiGRU model, along with Kolmogorov-Arnold Network (KAN) module, while the summarization part utilizes attention-based GRU, combined with a KAN model head. Classification model yields 67.96% of accuracy and 0.65 F1 score; while ROUGE-1, ROUGE-2, and ROUGE-L measures for summarization yield 0.38, 0.23, and 0.31 F1 scores, correspondingly. Ablation study shows that the use of KAN increases classification accuracy from 57.34% to 67.96%. Moreover, our proposed technique is compared to several baselines, including classical ML algorithms and pretrained language models.

Ishrat Jahan Ananya, Sarah Suad, Shadab Hafiz Choudhury et al.

Acoustic scene classification is a process of characterizing and classifying the environments from sound recordings. The first step is to generate features (representations) from the recorded sound and then classify the background environments. However, different kinds of representations have dramatic effects on the accuracy of the classification. In this paper, we explored the three such representations on classification accuracy using neural networks. We investigated the spectrograms, MFCCs, and embeddings representations using different CNN networks and autoencoders. Our dataset consists of sounds from three settings of indoors and outdoors environments - thus the dataset contains sound from six different kinds of environments. We found that the spectrogram representation has the highest classification accuracy while MFCC has the lowest classification accuracy. We reported our findings, insights as well as some guidelines to achieve better accuracy for environment classification using sounds.

Abu Adnan Sadi, Mohammad Ashrafuzzaman Khan, Lubaba Binte Saber

As the field of artificial intelligence progresses, assistive technologies are becoming more widely used across all industries. The healthcare industry is no different, with numerous studies being done to develop assistive tools for healthcare professionals. Automatic diagnostic systems are one such beneficial tool that can assist with a variety of tasks, including collecting patient information, analyzing test results, and diagnosing patients. However, the idea of developing systems that can provide a differential diagnosis has been largely overlooked in most of these research studies. In this study, we propose a transformer-based approach for providing differential diagnoses based on a patient's age, sex, medical history, and symptoms. We use the DDXPlus dataset, which provides differential diagnosis information for patients based on 49 disease types. Firstly, we propose a method to process the tabular patient data from the dataset and engineer them into patient reports to make them suitable for our research. In addition, we introduce two data modification modules to diversify the training data and consequently improve the robustness of the models. We approach the task as a multi-label classification problem and conduct extensive experiments using four transformer models. All the models displayed promising results by achieving over 97% F1 score on the held-out test set. Moreover, we design additional behavioral tests to get a broader understanding of the models. In particular, for one of our test cases, we prepared a custom test set of 100 samples with the assistance of a doctor. The results on the custom set showed that our proposed data modification modules improved the model's generalization capabilities. We hope our findings will provide future researchers with valuable insights and inspire them to develop reliable systems for automatic differential diagnosis.

Md Rafid Islam, Rafsan Jany, Akib Ahmed et al.

Diabetic retinopathy (DR) remains a leading cause of preventable blindness, yet large-scale screening is constrained by limited specialist availability and variable image quality across devices and populations. This work investigates whether feature-level fusion of complementary convolutional neural network (CNN) backbones can deliver accurate and efficient binary DR screening on globally sourced fundus images. Using 11,156 images pooled from five public datasets (APTOS, EyePACS, IDRiD, Messidor, and ODIR), we frame DR detection as a binary classification task and compare three pretrained models (ResNet50, EfficientNet-B0, and DenseNet121) against pairwise and tri-fusion variants. Across five independent runs, fusion consistently outperforms single backbones. The EfficientNet-B0 + DenseNet121 (Eff+Den) fusion model achieves the best overall mean performance (accuracy: 82.89\%) with balanced class-wise F1-scores for normal (83.60\%) and diabetic (82.60\%) cases. While the tri-fusion is competitive, it incurs a substantially higher computational cost. Inference profiling highlights a practical trade-off: EfficientNet-B0 is the fastest (approximately 1.16 ms/image at batch size 1000), whereas the Eff+Den fusion offers a favorable accuracy--latency balance. These findings indicate that lightweight feature fusion can enhance generalization across heterogeneous datasets, supporting scalable binary DR screening workflows where both accuracy and throughput are critical.

Mohammed Aman Bhuiyan, Md Sazzad Hossain Adib, Samiul Basir Bhuiyan et al.

Automatic Speech Recognition (ASR) and speaker diarization in Bangla remain challenging due to long form recordings, diverse acoustic conditions, and significant speaker variability. This work addresses these two core tasks in Bangla spoken language understanding by developing robust systems for long form ASR and speaker diarization. For ASR (Problem 1), we fine tune the tugstugi bengaliai regional asr whisper medium model on a custom-curated dataset of approximately 15,000 chunked and aligned Bangla audio segments, employing full weight training with extensive data augmentation including noise injection, reverb simulation, echo, clipping distortion, and pitch/time perturbation. For speaker diarization (Problem 2), we fine-tune the pyannote/segmentation-3.0 model using PyTorch Lightning on the competition annotated diarization dataset, swapping the fine-tuned segmentation backbone into the pyannote/speaker-diarization-community-1 pipeline while retaining the pretrained speaker embedding and clustering components. Our ASR system achieves a Word Error Rate (WER) of 0.2441, while our diarization system achieves a Diarization Error Rate (DER) of 0.2392, both evaluated on the test set, demonstrating notable improvements over the respective pretrained baselines. We describe our complete pipeline, including data preprocessing, text normalization, audio augmentation, training strategies, inference optimization, and post-processing for both tasks.

Mohammad Junayed Hasan, Suhra Noor, Mohammad Ashrafuzzaman Khan

Clinical texts, such as admission notes, discharge summaries, and progress notes, contain rich and valuable information that can be used for clinical decision making. However, a severe bottleneck in using transformer encoders for processing clinical texts comes from the input length limit of these models: transformer-based encoders use fixed-length inputs. Therefore, these models discard part of the inputs while processing medical text. There is a risk of losing vital knowledge from clinical text if only part of it is processed. This paper proposes a novel method to preserve the knowledge of long clinical texts in the models using aggregated ensembles of transformer encoders. Previous studies used either ensemble or aggregation, but we studied the effects of fusing these methods. We trained several pre-trained BERT-like transformer encoders on two clinical outcome tasks: mortality prediction and length of stay prediction. Our method achieved better results than all baseline models for prediction tasks on long clinical notes. We conducted extensive experiments on the MIMIC-III clinical database's admission notes by combining multiple unstructured and high-dimensional datasets, demonstrating our method's effectiveness and superiority over existing approaches. This study shows that fusing ensemble and aggregation improves the model performance for clinical prediction tasks, particularly the mortality and the length of hospital stay.

Muhammad Rafsan Kabir, Md. Mohibur Rahman Nabil, Mohammad Ashrafuzzaman Khan

Sentence-level embedding is essential for various tasks that require understanding natural language. Many studies have explored such embeddings for high-resource languages like English. However, low-resource languages like Bengali (a language spoken by almost two hundred and thirty million people) are still under-explored. This work introduces two lightweight sentence transformers for the Bangla language, leveraging a novel cross-lingual knowledge distillation approach. This method distills knowledge from a pre-trained, high-performing English sentence transformer. Proposed models are evaluated across multiple downstream tasks, including paraphrase detection, semantic textual similarity (STS), and Bangla hate speech detection. The new method consistently outperformed existing Bangla sentence transformers. Moreover, the lightweight architecture and shorter inference time make the models highly suitable for deployment in resource-constrained environments, making them valuable for practical NLP applications in low-resource languages.

Dipta Neogi, Nourash Azmine Chowdhury, Muhammad Rafsan Kabir et al.

The rapid growth of visual content consumption across platforms necessitates automated video classification for age-suitability standards like the MPAA rating system (G, PG, PG-13, R). Traditional methods struggle with large labeled data requirements, poor generalization, and inefficient feature learning. To address these challenges, we employ contrastive learning for improved discrimination and adaptability, exploring three frameworks: Instance Discrimination, Contextual Contrastive Learning, and Multi-View Contrastive Learning. Our hybrid architecture integrates an LRCN (CNN+LSTM) backbone with a Bahdanau attention mechanism, achieving state-of-the-art performance in the Contextual Contrastive Learning framework, with 88% accuracy and an F1 score of 0.8815. By combining CNNs for spatial features, LSTMs for temporal modeling, and attention mechanisms for dynamic frame prioritization, the model excels in fine-grained borderline distinctions, such as differentiating PG-13 and R-rated content. We evaluate the model's performance across various contrastive loss functions, including NT-Xent, NT-logistic, and Margin Triplet, demonstrating the robustness of our proposed architecture. To ensure practical application, the model is deployed as a web application for real-time MPAA rating classification, offering an efficient solution for automated content compliance across streaming platforms.