Ashraful Islam, PhD

Sharmin Islam Shroddha, Sumaia Anjum Shaba, Sudipto Biswas, Siam Tahsin Bhuiyan, Rashedur Rahman, Saadia Binte Alam, Ashraful Islam

A Multilingual Deep Learning Framework for Sign Language Recognition and Translation

Proceedings of the Seventh International Conference on Trends in Computational and Cognitive Engineering, pp. 115-124, 2027

• sign language recognition
• sign language translation
• Bangla Sign Language
• Indian Sign Language
• Arabic Sign Language
• American Sign Language
• image classification
• interlingual communication
• deaf and hard of hearing
• vision transformer
• ResNet50
• VGG16
• EfficientNetB0

Siam Tahsin Bhuiyan, Rashedur Rahman, Sefatul Wasi, Halima Khatun, Ashraful Islam, AKM Mahbubur Rahman, Saadia Binte Alam, M Ashraful Amin

PelviNeXt: A Modality-Agnostic Hybrid Network for Pelvic Imaging in Women's Health

arXiv (Cornell University), 2026

• perceptual hashing
• pelvic radiography
• multi-scale feature fusion
• polycystic ovary syndrome
• channel and spatial attention
• pelvic fractures
• pelvic ultrasound
• multi-head self-attention

• SDG 3Good Health and Well-being
• SDG 5Gender Equality

Siam Tahsin Bhuiyan, Rashedur Rahman, Sefatul Wasi, Riyadul Islam, Syoji Kobashi, Ashraful Islam, Saadia Binte Alam

SecondOpinion: Anatomy-Aware Gated Reasoning for Efficient Medical Image Analysis

arXiv (Cornell University), 2026

• cross-attention fusion
• chest X-ray classification
• dual-stream architecture
• gating mechanism
• task difficulty
• confidence calibration

• SDG 3Good Health and Well-being

Siam Tahsin Bhuiyan, Rashedur Rahman, Ashraful Islam

Benchmarking CNN Architectures Using Transfer Learning for Lipomatous Tumor Classification: A Comprehensive Study

Advances and Trends in Artificial Intelligence. Theory and Applications: 39th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2026, Kuala Lumpur, Malaysia, July 6-8, 2026, Proceedings, Part II, pp. 171, 2026

In: Advances and Trends in Artificial Intelligence. Theory and Applications

• well-differentiated liposarcoma
• DenseNet121
• transfer learning
• InceptionV3
• T1-weighted imaging
• ResNet50
• EfficientNetB3
• MobileNetV2
• benign lipoma
• false positive rate

• SDG 3Good Health and Well-being

Istiaq Ahmed, Faiza Omar Arpita, Md Asif Bin Khaled, Ashraful Islam, M Ashraful Amin

Can Small LLMs Replace Fine-Tuned BERT for Bangla Natural Language Inference?

2026 Third International Conference on Innovations in Cybersecurity and Data Science (ICICDS), pp. 853-859, 2026

• small language models
• Bengali language
• natural language inference
• fine-tuned BERT
• multilingual language models

Mustaqueem Alam, J. M. Sadik-Ul Islam Smaron, Rashedur Rahman, Md Asif Bin Khaled, Ashraful Islam, M. Ashraful Amin

Evaluating the Impact of Image Preprocessing on Deep Learning-Based Fetal Ultrasound Classification Under Class Imbalance

2026 Third International Conference on Innovations in Cybersecurity and Data Science (ICICDS), pp. 128-135, 2026

• image preprocessing
• class imbalance
• deep learning classification
• prenatal ultrasound
• medical image classification
• prenatal diagnosis

• SDG 3Good Health and Well-being

Siam Tahsin Bhuiyan, Zayan Zaman, Rashedur Rahman, Manosh Sur Choudhury, Sefatul Wasi, Ashraful Islam, Saadia Binte Alam, Syoji Kobashi

CheXNet-CBAM: Enhancing Large-scale Medical Pre-training with Attention for Lung Disease Diagnosis

2026 IEEE 56th International Symposium on Multiple-Valued Logic (ISMVL), pp. 105-110, 2026

• CBAM
• CheXNet
• DenseNet121
• lung disease classification
• Grad-CAM
• chest radiography
• computer-aided diagnosis
• multi-class classification
• attention mechanism

• SDG 3Good Health and Well-being

Farzana Islam, Ashraful Islam, M Ashraful Amin, Moinul Zaber

A proposed participatory framework for explainable AI in mHealth: Mixed methods study integrating user and stakeholder requirements

Journal of Medical Internet Research 28, pp. e87158, 2026

• Explainable AI
• clinical validation
• South Asia
• stakeholder needs
• human-AI collaboration
• Bangladesh
• resource-limited settings
• mobile health
• trust in AI
• participatory approach

• SDG 3Good Health and Well-being
• SDG 10Reduced Inequalities

Md Shakil Ahmed, Shohan Islam Joy, Nabarun Halder, Ashraful Islam, Sanzar Adnan Alam

Decentralizing Reputation Scoring Using Blockchain Behavioral Data and Machine Learning

2026 International Conference on Artificial Intelligence, Systems, and Emerging Technologies (ICAISET), pp. 1-6, 2026

• behavioral data
• Blockchain
• Machine learning
• reputation scoring
• decentralization
• reputation systems

Ayesha Siddika, Ahnaf Atif Rafi, Maria Jahan Noon, Md Junayed Hossain, Ashraful Islam, Sanzar Adnan Alam

The Hidden Complexity of Mental Health: Multi-Entropy Analysis of Response Patterns in Depression Severity Assessment

2026 International Conference on Artificial Intelligence, Systems, and Emerging Technologies (ICAISET), pp. 1-6, 2026

• permutation entropy
• multiscale entropy
• sample entropy
• PHQ-9
• Shannon entropy
• depression severity
• depression screening
• response patterns
• entropy features
• digital mental health

• SDG 3Good Health and Well-being