Md. Shahat Akash

Final-Year Computer Science Undergraduate | Passionate about AI, Data, and Building Smart Systems

A final-year B.Sc. student in Computer Science and Engineering at Chittagong Independent University (CIU) . I’m passionate about AI, Data Science, and building intelligent systems using technologies like Machine Learning, Deep Learning, Computer Vision, NLP, LLMs, and RAGs. My interests lie in applying advanced AI to solve real-world problems, and I enjoy working at the intersection of research and software engineering. I’m currently seeking opportunities in AI research, software development, or collaborative tech projects that push the boundaries of innovation.

Md. Shahat Akash

Recent News

2025

January 2025

Volunteered at the CIU Convocation 2025, assisting with event coordination and guest management. This experience enhanced my organizational and teamwork skills, and provided valuable insight into large-scale academic event planning.

October 2024

Participated in ICPC Dhaka Regional Preliminary Round 2023-2024, representing my university in a prestigious programming competition that challenged my problem-solving and teamwork skills in a high-pressure environment.

Old News

August 2023

Participated in Ideathon-2023 organized by Premier University Chittagong, where my team showcased an innovative project idea addressing real-world challenges. This experience enhanced my skills in ideation, teamwork, and presenting technical solutions to a diverse audience of peers and industry experts.

August 2022

Participated in IIUC Intra university Programming Contest (IUPC) 2022 as a contestant, showcasing problem-solving skills and algorithmic thinking in a competitive programming environment.

Education

2022 - Present

B.Sc. in Computer Science and Engineering

Chittagong Independent University (CIU)

Relevant Coursework: Data Structures, OOP, Algorithms Analysis, Database Management System, Numerical Methods for Engineering, Operating Systems, Software Engineering, Artificial Intelligence, Robotics

Extracuricular Activities

2025 - Present

Vice-Chair

IEEE CIU Student Branch (IEEE-CIUB)

  • Conducted meeting collaborating with branch chair and executives.
  • Organized seminar, workshop and events!
  • Report the branch counselor timely, everything done during the tenure!
  • More!
2024 - 2025

Treasurer

IEEE CIU Student Branch (IEEE-CIUB)

  • Managed the branch's financial records, budgets, and expense tracking
  • Prepared and maintained financial reports for organizational activities.
  • Collaborated with the executive committee to ensure responsible use of organizational funds.
2023 - 2024

Asst. General Secretary

Student Robotics Club (CIURC)

  • Assisted in coordinating club activities, meetings, workshops, and technical events.
  • Maintained documentation, schedules, and records for club activities.
  • Supported communication and coordination among executive members and club participants.
  • Contributed to organizing robotics projects, competitions, and student learning activities.

Research & Publications

View Complete Publication List on Google Scholar

Ongoing Hybrid Neural Network Approach for Cancer Cell Classification. [Thesis]

June 2025 - Present

This ongoing research focuses on cancer cell classification using a hybrid neural network approach. The goal is to improve diagnostic accuracy by leveraging the strengths of multiple deep learning architectures for robust and efficient cell type identification.

Ongoing Multiclass Classification of Knee Osteoporotic Conditions from X-ray Images Using Transfer Learning, Knowledge Distillation, and Explainable AI Techniques.

August 2024 - Present

This research aims to classify multiple knee osteoporotic conditions from X-ray images by integrating transfer learning, knowledge distillation, and explainable AI. The approach seeks to enhance diagnostic accuracy and interpretability, supporting clinicians in making informed decisions.

Resubmitting Osteoporosis Risk Prediction: Machine Learning Approaches Highlighting MUAC and HRR

Submitted to: 28th International Conference on Computer and Information Technology

This study explores machine learning approaches for early osteoporosis risk assessment using mid-upper arm circumference (MUAC) and hemoglobin-to-red cell distribution width ratio (HRR) as key indicators. Using NHANES data and various ML models, the research demonstrates that while MUAC and HRR alone aren't definitive predictors, they contribute valuable insights when combined with traditional risk factors, potentially enabling more accessible early screening methods.

Technical Skills

Programming Languages

  • C/C++
  • Python
  • PHP
  • HTML & CSS
  • JavaScript

Libraries & Frameworks

  • NumPy
  • Pandas
  • Matplotlib
  • Seaborn
  • Scikit-learn
  • PyTorch

Tools & Platforms

  • GitHub & Git
  • LaTeX
  • UML
  • Figma
  • Anaconda Navigator
  • Visual Studio Code

Databases

  • MySQL
  • MongoDB

Academic Projects

End-to-End Chatbot.

End-to-End Mental Health Chatbot

Developed an end-to-end AI-powered chatbot to support mental health and wellbeing. The system uses natural language processing to provide empathetic responses, resources, and guidance for users seeking mental health support. Built with Python, machine learning, and web technologies for real-time, confidential conversations.

GitHub
Mental Health and Wellbeing

Mentis!

Mentis! is a web-based platform designed to promote mental health awareness and provide users with resources, self-assessment tools, and supportive information. Built with modern web technologies, it aims to make mental wellbeing accessible and stigma-free.

GitHub
ev_dashboard_overview

EV Dashboard: Electric Vehicle Data Visualization Platform

Developed a web-based dashboard for visualizing and analyzing electric vehicle (EV) data. The platform displays key metrics such as battery status, charging history, energy consumption, and trip statistics using interactive charts and tables. Built with Python, Flask, and modern JavaScript libraries, it enables users to monitor EV performance and make data-driven decisions for efficient vehicle management.

GitHub

Contact