CV

Research Assistant

IoThink Lab, HSTU

Conducting research in image processing and machine learning. Aiding my supervisor in facilitating research work.

• Biomedical Image Processing

Lecturer of Computer Science and Engineering

Govt. Shahid Akbar Ali Science and Technology College (SASTC)

Taught: Theory of Computation, Computer Graphics, Machine Learning.

• Designed and delivered courses.
• Supervised project works

Mentor

QBangladesh (QWorld)

Mentoring students and promoting quantum literacy in Bangladesh.

M.Sc.(Engineering) in Computer Science and Engineering

Hajee Mohammad Danesh Science and Technology University (HSTU)

Computer Science and Engineering

• GPA: 3.625/4.00 (Thesis in progress)

B.Sc.(Engineering) in Computer Science and Engineering

Hajee Mohammad Danesh Science and Technology University (HSTU)

Computer Science and Engineering

• GPA: 3.31/4.00

Unitary Hack 2025: For Open Source Contributions

Unitary Foundation

YQuantum 2025: Solved BlueQubit's Peaked Circuits Challenge

BlueQubit & Yale University

MIT iQuHACK 2025: Solved IONQ's Max Cut problem

MIT

Womanium Quantum + Al 2024: Program finalist and QSL fellowship nominee

Womanium Foundation

IBM Quantum Challenge 2024: Ranked 11th globally

IBM

6th BAS Science Olympiad: Division 3rd and National level nominee

BAS

5th DSA Physics Olympiad: 7th Place

DSA

Mitigating Noise from Biomedical Images Using Wavelet Transform Techniques

2025 International Conference on Electrical, Computer and Communication Engineering (ECCE)

Medical imaging plays a pivotal role in modern healthcare, enabling accurate diagnosis and effective treatment planning across various medical conditions. Advanced modalities, such as magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound, offer critical insights into the structure and function of the human body. However, these images are often degraded by noise introduced during acquisition or processing, potentially obscuring vital diagnostic details and impacting clinical decision-making. Furthermore, enhancement techniques like histogram equalization, while improving visual appeal, may inadvertently amplify existing noise, such as salt-and-pepper distortions. This study investigates wavelet transform-based denoising methods to mitigate noise in medical images effectively. Our primary goal is to identify the optimal combination of threshold values, decomposition levels, and wavelet types to achieve superior denoising performance, ensuring enhanced diagnostic accuracy. Our study finds that the db3 wavelet with universal thresholding achieved the best denoising effect across various noise levels. For noise standard deviations of σ = 10, 15, and 25, the best PSNR values obtained are 29.203 dB, 27.791 dB, and 25.194 dB, respectively. These results establish a foundation for developing hybrid wavelet-deep learning approaches for medical image denoising.

Enhanced Brain Tumor Classification from MRI Images Using Deep Learning Model

2023 26th International Conference on Computer and Information Technology (ICCIT)

In the realm of image classification, traditional algorithms, encompassing both machine learning and deep learning, grapple with formidable challenges arising from uneven pixel ranges and dimensionality reduction. This results in a significant impediment to achieving accurate image categorization.Numerous examples of such traditional methods, including KNN, Random Forest, SVM, DNN, CNN etc, have encountered persistent issues such as inefficient performance of feature engineering, limited accuracy, etc. In response to these challenges, this paper introduces a novel image classification method that integrates pixel mapping, DWT, and CNN for improved efficiency and reliability. By resolving irregular pixel ranges through initial pixel mapping, our method establishes uniformity as a foundation for subsequent image analysis. Subsequently, DWT is employed to dissect and reduce image dimensionality, extracting essential features while lowering computational complexity. This two-step preprocessing approach forms a robust foundation for effective data classification. Within this framework, our proposed CNN architecture plays a pivotal role, utilizing both spectral and spatial information to address image categorization challenges. The network's capacity to learn complex patterns enhances classification accuracy. In extensive evaluations, our methodology surpasses conventional classification techniques, yielding impressive results. With an Overall Accuracy (OA) of 96.9% and a Kappa statistic of 95.16%, our method showcases excellence and practical potential. These compelling achievements underscore the significance of our approach in tackling image classification challenges, paving the way for enhanced precision and efficiency across various domains.

Guava Fruit Disease Dataset @ IoThink Lab

Collaborated on dataset collection for interdisciplinary research.

MRI Image Denoising using Wavelet Transform

Applying wavelet transform techniques to reduce noise in MRI images and comparing results using metrics such as MSE, PSNR, and SSIM.

• Explored various wavelet functions (db3, bior6.8, sym4), decomposition leveds, optimal threshold value estimation (universal/bayes), thresholding methods (hard/soft) to find the best combination that can mitigate gaussian noise from image

Quantum Variational Classifier @ Womanium Program

Implemented a quantum classifier for Penguin Species Classification.

Quanvolutional Neural Networks @ Womanium Program

Developed a hybrid quantum convolutional model for MNIST Digit Classification.

Quantum Regression Model @ Womanium Program

Implemented a Quantum Machine Learning Model to learn and predict the sine function on the interval [0, 2π].

QML for Conspicuity Detection in Production

Final project for the Womanium Quantum + AI 2024 program that earned me the QSL fellowship nomination. I implemented a Hybrid Quantum Convolutional Neural Network to detect anomalies in production.

• MNIST Digit Classification
• Implemented a 3x3 kernel using Quantum Circuit along with a classical CNN.
• Implemented various layers as ansatz(e) for a Quantum Regression Model and performed comparison.