Raihan Tanvir
Raihan Tanvir

Learner | Teacher | Researcher

About Me

I am Raihan Tanvir, currently serving as a Lecturer in the Department of Computer Science and Engineering at Ahsanullah University of Science and Technology (AUST) in Dhaka, Bangladesh. I hold a Bachelor of Science in Computer Science and Engineering from AUST. My research interests encompass a broad spectrum of artificial intelligence, with a particular focus on computer vision, natural language processing, and federated learning. The majority of my research is focused on leveraging generative adversarial networks (GANs) to address various practical challenges, particularly in the context of our local environment.

Before joining AUST, I served as a Lecturer at Stamford University Bangladesh, where I contributed sincerely through my efforts in teaching and development of curriculum. I am passionate about teaching and mentoring students, and I strive to foster a collaborative learning environment.

In addition to my teaching responsibilities, I am actively engaged in multiple research projects in collaboration with my students and peers. I am excited about the potential of technology to drive innovation and improve lives, and I am committed to contributing to this field through both my teaching and research efforts.

For more information please see my CV.

Download CV
Interests
  • Computer Vision
  • Natural Language Processing
  • Federated Learning
Education
  • BSc in CSE

    Ahsanullah University of Science and Technology, Dhaka, Bangladesh

Recent News


  • [March 28, 2024] Promoted to Senior Lecturer @ CSE, AUST.
  • [December 20, 2022] Presented a Paper in 2022 4th International Conference on Sustainable Technologies for Industry 4.0, Dhaka, Bangladesh.
  • [December 7, 2022] Joined as Lecturer @ CSE, AUST.
  • [June 06, 2022] Presented a Paper in 2022 19th International Conference on Distributed Computing and Artificial Intelligence, L’Aquila, Italy.
  • [June 04, 2022] Team Jamdani Reached the Top 50 at UNIBATOR.
  • [March 10, 2022] Joined as Lecturer @ CSE, Stamford University Bangladesh
  • [June 24, 2022] Joined as Part-time Faculty @ CSE, AUST
  • [January 7, 2021] Completed Graduation with Magna Cum Laude
  • [December 20, 2020] Participated in 2020 23rd International Conference on Computer and Information Technology (ICCIT), Dhaka, Bangladesh
  • [December 3, 2020] Successfully defended my Undergraduate Thesis
  • [November 20, 2020] One paper got accepted at ICCIT 2020

Experience

  1. Senior Lecturer

    Ahsanullah University of Science and Technology

    Courses:

    • CSE 4138: Soft Computing Lab [Fall'23]
    • CSE 1231 : Numerical Methods and Computer Programming [Fall'23]
  2. Lecturer

    Ahsanullah University of Science and Technology

    Courses:

    • CSE 4138: Soft Computing Lab [Fall'23]
    • CSE 4107 : Artificial Intelligence [Spring'22]
    • CSE 4108 : Artificial Intelligence Lab [Spring'22, Fall'22]
    • CSE 3214 : Operating Systems Lab [Spring'22]
    • CSE 2207 : Algorithms [Fall'22]
    • CSE 2208 : Algorithms Lab [Fall'22, Spring'23]
    • CSE 1102 : Structured Programming Language Lab [Spring'22]
  3. Lecturer

    Stamford University Bangladesh

    Courses:

    • MATH 135 : Discrete Mathematics [Summer'22]
    • CSI 311 : Visual and Internet Programming [Spring'22]
    • CSI 323 : System Analysis and Design [Summer'22]

Education

  1. BSc in CSE

    Ahsanullah University of Science and Technology, Dhaka, Bangladesh
    GPA: 3.81 out of 4.0
    Thesis: Jamdani Motif Generation using Conditional Generative Adversarial Network.
    Supervised by Mr. Imrul Jubair. Presented a paper at an IEEE conferences.
    Read Thesis
Featured Publications
Publications

Bengali Handwritten Digit Recognition using CNN with Explainable AI

Handwritten character recognition is a significant research area, especially for languages like Bengali where quality OCR applications are scarce. Merging machine learning and deep learning techniques, including CNN, improves accuracy. The use of Grad-CAM as an XAI method enhances model interpretability.

DSE Stock Price Prediction using Hidden Markov Model

This work uses Hidden Markov Models (HMM) to predict next-day stock prices based on historical data, focusing on fractional price changes and intraday highs and lows. The Maximum a Posteriori HMM method showed satisfactory results and can generalize to predict stock prices for any company with proper training.

Projects