Hello, readers! Over the past year, I've been focusing on applying machine learning and AI to real-world challenges in healthcare and environmental science, particularly in resource-constrained settings like Bangladesh and smart cities. These works are currently in preprint form and slated for publication in 2026.

1. AI Chatbots for Dengue Symptom Triage in Bangladesh

AI Chatbots for Dengue Symptom Triage in Bangladesh: A Decision Tree Classifier Approach
To be published in Springer Lecture Notes in Networks and Systems | Presented at DASGRI 2026

Overview: Dengue fever remains a major public health crisis in Bangladesh. This paper explores an AI-powered chatbot for preliminary symptom triage.

Methodology: Decision Tree classifier trained with GridSearchCV and SMOTE on public datasets (n=4,700). Includes confidence threshold and NLTK for natural language processing.

Key Results: 0.79 accuracy, 0.802 F1-score. Pilot study (n=50) showed 75% user satisfaction with minimal demographic bias.
Read Preprint →

2. Evolving Health Indicators in Bangladesh

Evolving Health Indicators in Bangladesh: A Comparative Analysis of 2019 and 2023 Health Bulletins
Co-authored with Nusrat Shirmin | Presented at DASGRI 2026

Overview: Comparative analysis of Bangladesh’s healthcare progress using official Health Bulletins.

Key Results: Maternal mortality down 11%, malaria cases reduced 42%, stunting from 31% to 24%. Persistent challenges include workforce shortages and high out-of-pocket spending.
Read Preprint →

3. Optimized Hybrid ML for Air Quality Prediction

Optimized Hybrid Machine Learning Framework for Real-Time Air Quality Prediction in IoT-Enabled Smart Cities
Presented at DASGRI 2026

Overview: Hybrid XGBoost + LSTM framework for real-time PM2.5 prediction optimized for edge devices.

Key Results: RMSE=0.1153, R²=0.8524 (12% better than standalone LSTM). Low latency on simulated edge devices.
Read Preprint →

4. Fairness-Aware ECG Representation Learning

Fairness-Aware Representation Learning for ECG-Based Disease Prediction in Wearable Systems
Co-authored with Nusrat Shirmin | To appear at EAI HealthWear 2025

Overview: Addresses bias in ECG models using adversarial debiasing for equitable wearable diagnostics.

Key Results: AUROC=0.8472 with significant improvement in fairness metrics (Demographic Parity improved from 0.23 to 0.71 for sex).
Read Preprint →

Conclusion

These papers reflect my commitment to impactful, ethical, and accessible AI. I'm particularly excited about their potential in low-resource settings. Feel free to reach out for collaboration or discussions!