Tech Stack: Python, TensorFlow Lite. 

Project Name: Determine Filling Teeth in Teeth Datasets: Identify the filling teeth in the teeth machine learning model classifier. Implement explainable AI to understand the model biases. 

This project focuses on building a machine learning classifier to accurately identify teeth with fillings from dental image datasets. The workflow includes annotating images to label filled and unfilled teeth, ensuring high-quality training data. The model is designed for efficient and accurate classification, supporting deployment on lightweight systems. To ensure transparency and trust in dental diagnostics, explainable AI techniques are integrated to highlight decision patterns and uncover potential model biases, making the results more interpretable for dental professionals.

Tech Stack: Kotlin, Python, FastAPI, Android, TensorFlow Lite.

Project Name: Using machine learning and algorithms to identify eligible borrowers based on personal and financial data integrated into a mobile application. 

This project aims to develop a machine learning-based system to assess borrower eligibility by analysing personal and financial information. The system leverages advanced algorithms to evaluate creditworthiness and accurately predict loan approval potential. To enhance accessibility and user experience, the solution is implemented in a mobile application, allowing users to input their data and receive real-time eligibility assessments. The project focuses on improving the lending process's speed, fairness, and reliability while reducing human bias and operational costs for financial institutions. 

Funded By:

• Word Bank

• BRAC, Skill Development Program

Supervisor: 

Dr Tanzilur Rahman

Associate Professor

Dept. of Electrical and Computer Engineering

North South University

Dhaka, Bangladesh

Responsibilities:

• Conduct original research and develop novel insights.

• Utilize various sources for comprehensive background studies, including related database publications.

• Meet strict deadlines while ensuring high-quality outputs.

• Collaborate effectively on additional projects as required.

• Maintain an organised research notebook, documenting code, data, and other relevant materials.

• Prepare, draft, and submit proposals and reports accurately and clearly.

•  Travel Assistant application project

  • Developed the core idea, objectives, and architecture of the surface mapping system using smartphone sensors and crowdsourced data.

  • Built the application infrastructure, coded sensor data processing modules, and ensured functional integration of smartphone-based tracking.

  • Designed the methodology for crowdsourced data gathering and conducted thorough analysis to convert raw sensor data into usable map information.

  • Performed field tests and evaluations to measure system accuracy, performance, and usability in real-world scenarios.

  • Composed the research paper, including drafting, editing, and finalizing the manuscript for submission and publication.

• Malaria Detection Using Deep Learning

  • Implement Machine Learning Model into the Mobile Application
  • Analyse the model efficiency and find the errors 
  • Make reports based on results

• Bangladesh Govt. 
• BANBAIS