Bangladesh
Machine Learning & Deep Learning Enthusiast
I am a Machine Learning and Deep Learning enthusiast with 2+ years of experience in AI model development, feature optimization, and explainable AI. Currently a final-year CSE student at Daffodil International University, I actively engage in research and competitive programming. My passion lies in advancing AI for healthcare, embedded systems, and power-efficient computing.
I am a passionate Machine Learning and Deep Learning enthusiast with two years of hands-on experience in developing AI models, feature selection techniques, and model explainability. My interest in Artificial Intelligence drives me to explore cutting-edge innovations, optimize models, and contribute to impactful research.
🎓 Academic Background:
I hold a Bachelor’s degree in Computer Science & Engineering (BSc in CSE) from Daffodil International University (DIU), where I actively participated in research initiatives and competitive programming communities.
🔹 Professional & Research Involvement:
✔ Assistant General Secretary, Daffodil AI Club
✔ Executive Member, Competitive Programming Community (CPC), DIU
✔ Research Volume-05 Member, CPC, DIU
As an executive member and researcher at CPC and the Daffodil AI Club, I collaborate with peers to solve complex problems, enhance problem-solving skills, and contribute to AI-driven research projects. My involvement has strengthened my analytical thinking, coding proficiency, and teamwork skills.
💡 Core Expertise & Interests:
✅ Machine Learning & Deep Learning (Scikit-learn, TensorFlow, PyTorch)
✅ Feature Selection & Model Optimization (ANOVA, LASSO, Chi-square, RFE etc)
✅ Explainable AI (SHAP, LIME)
✅ Computer Vision
✅ Federate Learning
✅ Power-Efficient AI & Embedded Systems (ARM-based processors, Raspberry Pi, PowerTOP, Intel VTune)
✅ Data Preprocessing & Model Evaluation
🌟 Passion & Future Goals:
My goal is to advance AI research, particularly in healthcare AI, embedded systems, and low-power computing, ensuring efficient and scalable solutions. I am always eager to collaborate on research projects, participate in AI competitions, and contribute to the AI community.
📩 Let’s Connect!
If you’re interested in AI, ML research, or collaborative projects, feel free to reach out! Let’s explore opportunities and drive innovation together.
Hybrid Vision Transformer & ConvNeXt feature extraction with Gradient Boosting Classifier for ultrasound image classification.
Web dashboard for streaming and visualizing vitals from a health-monitoring device; real-time charts and alerts.
End-to-end ML pipeline with feature selection and model tuning for accurate cirrhosis staging.
This is a dataset for precision agriculture and deep learning research in plant disease detection.
Access DatasetThis dataset provides a comprehensive record of reported rape incidents across Bangladesh from 2020 to 2024. Data were compiled from verified Bangladeshi news portals and include details about victims, offenders, locations, and incident context.
Access DatasetThe Gen-Z Political Perspectives and Engagement Survey 2025 is a comprehensive repository of socio-political data capturing the attitudes, digital behaviors, and governance expectations of Generation Z in Bangladesh. Comprising over 1,250 responses, the dataset serves as a vital barometer for the political climate of a nation undergoing transition. It documents the shift of a "digital-native" generation from passive observers to active stakeholders. By merging demographic markers with deep-dive questions on institutional trust and digital hygiene, this dataset provides an empirical foundation for understanding how the next generation perceives the political landscape.
Access DatasetThis dataset contains clinical and demographic information of patients collected for the purpose of diabetes prediction and analysis using machine learning techniques. The dataset is structured in CSV format and includes several key medical attributes that are widely used in diabetes diagnosis and research studies.
Access DatasetThis dataset contains a comprehensive collection of clinical and demographic information of 1,782 patients diagnosed with lung cancer, gathered from multiple tertiary-level hospitals and medical centers in Dhaka, Bangladesh. The dataset has been carefully designed to reflect real-world hospital-based data collection practices, ensuring clinical realism, statistical consistency, and practical usability for medical data analytics and machine learning research.
Access DatasetPublished in: Data in Brief
Published in: Intelligence-Based Medicine
Prefer LinkedIn? Reach me at
linkedin.com/in/tapon-paul-174267351