I’m a Fullstack Engineer at Wavelet Solutions in Malaysia, where I focus on building scalable ERP software solutions for businesses. I have a strong background in AI and data science, and published a paper on using Deep Learning for Ecoacoustic analysis to help with ecosystem management.
Right now, I’m leading the development of a large-scale event management ERP system using Angular and Spring Boot.
Worked on several ERP applets for B2B clients to enhance features, fix bugs using Angular and Java Spring Boot.
Developed an Inventory Management System using Laravel and PHP, replacing a previously manual process by automating the process of warehousing and tracking warranty.
Designed and Improved WordPress website using TutorLMS and Elementor plugins to create an interactive educational platform.
Implemented Fourier Neural Operators (FNO) to improve computation time for Radio Frequency Ablation (RFA) treatment simulations.
Grade: High 2nd Upper
Awards: Deans List & High Achievers Scholarship
Extracurriculars: President of Bangladesh Society, Treasurer of International Students Bureau, Member of Student Council
Subjects: Physics (A*), Pure Mathematics (A*), Economics (A*), Chemistry (A)
Link: Check GitHub Repo
Link: Read the paper
Reference: Loo, Y. Y., Lee, M. Y., Shaheed, S., Maul, T., & Clink, D. J. (2025). Temporal patterns in Malaysian rainforest soundscapes demonstrated using acoustic indices and deep embeddings trained on time-of-day estimation. The Journal of the Acoustical Society of America, 157(1), 1–16. https://doi.org/10.1121/10.0034638
Description: This project uses a deep learning regression model using Convolutional Neural Networks (CNNs) to study rainforest audio data for temporal patterns. Using tools helps pick up things like daily and monthly rainfall and species activity from sound data. It converts the audio data to Mel-Spectrograms and predicts the time of day the audio was recorded. This experiment led to exciting findings on the learnt patterns of the model.
Tools & Frameworks: PyTorch, Jupyter Notebook, Raven Pro
Skills: Python, R, Machine Learning, Data Science, Data Analysis
Link: Check GitHub Repo
Description: Implemented Fourier Neural Operators (FNO) to improve computation time for Radio Frequency Ablation (RFA) treatment simulations. Created custom data generation scripts on MATLAB to generate synthetic datasets to facilitate further research into RFA simulations using FNOs. Developed and integrated custom training optimizers, including an Adam optimizer variant, to improve model convergence during FNO training by 30%.
Tools & Frameworks: PyTorch, MATLAB
Skills: Data Science, Optimization, Dataset Generation, R&D
Link: Check GitHub Repo
Description: Developed Python-based reinforcement learning algorithms with dynamic state-space discretization and policy evaluation techniques to optimize learning efficiency across diverse environments. Using OpenAI Gym environments to investigate the impact of discretization granularities on Q-Learning performance, enhancing understanding of state-action representation in reinforcement learning.
Tools & Frameworks: OpenAI Gym, Matplotlib, NumPy.
Skills: Reinforcement Learning, Data Visualization
Link: Check GitHub Repo
Description: This project presents an intelligent agent developed to play the Snake Game using Genetic Algorithms and Neural Networks. The project investigates the impact of the number of hidden layers, the number of neurons, and the mutation rate on the efficacy of this intelligent agent. Multiple experiments were conducted to find the most efficient combination of parameters.
Tools & Frameworks: Processing Development Environment
Skills: Java, Neural Networks, Genetic Algorithms, Intelligent Agents
Link: Check GitHub Repo
Description: An image processing pipeline for extracting cell nuclei from images using techniques like contrast enhancement, median filtering, and watershed segmentation for precise segmentation of overlapping nuclei
Tools & Frameworks: MATLAB
Skills: Image Processing, Data Preprocessing, Data Visualization
Link: Play Here!
Description: Submission to the GMTK 2024 Game Jam. Received Top 0.5% among 7500 entries. A physics-based platformer where the user controls different metrics instead of the player to navigate the level.
Tools: Godot Game Engine, Asperite
Skills: Game Development, OOP, Pixel Art, Computer Graphics
I love connecting with different people so if you want to say hi, I'll be happy to meet you more!