Abdullah Al Mamun
Data Scientist | Machine Learning & Artificial Intelligence Researcher | Data Visualization Specialist
Python Expert | Turning Data into Real-World Solutions
I’m Abdullah Al Mamun, a Machine Learning & Data Science researcher with an MSc in Computing for Data Science from Bangor University. My work applies explainable ML and computer vision to real-world problems - from predicting properties of 3D-printed metals (my MSc thesis) to data-driven solutions in healthcare, manufacturing, and social innovation.
Independent Researcher
Artificial Intelligence, Machine Learning & Data Science
MSc Computing for Data Science
Bangor University, UK • 2022–2023
Thesis: Machine Learning Approaches to Predicting Mechanical Properties in 3D-Printed Metal Components
Supervisor: Dr. Abdullah Al Mamun
BSc Computer Science & Engineering
Dhaka International University, Bangladesh • 2016–2019
Final Project: AI Applications on DOF-17 Humanoid Robot (Arduino Mega, C Programming)
Python
Machine Learning
Artificial Intelligence
Data Analysis
Deep Learning
Data Visualization
Statistical Analysis
Research Methodology
Computer Vision
Human–Computer Interaction (HCI) & UX
Robotics & Embedded Systems
Big Data Processing (Pandas, NumPy, SciPy)
building intelligent, adaptive, and scalable systems
ensuring transparency, fairness, and trust in AI models
enabling image, pattern, and signal recognition for real-world tasks
creating intuitive, user-centered digital solutions
combining AI with physical platforms for automation and smart control
applying AI and data-driven methods to improve wellbeing, services, and production quality
My career goal is to advance Artificial Intelligence, Machine Learning, and Data Science by developing explainable and impactful solutions for real-world challenges. I aim to bridge research and application in areas such as healthcare, advanced manufacturing, and intelligent systems, while fostering responsible and human-centered AI.
Looking ahead, I aspire to establish myself as a recognized researcher driving innovative projects, contribute to high-impact publications, build strong collaborations between academia and industry, and mentor the next generation of researchers in AI and Data Science.
I focus on AI, Machine Learning, and Data Science with applications in manufacturing, healthcare, and intelligent systems. My work bridges innovative research with practical real-world impact.
Voice Similarity Detection using MFCC and Cosine Similarity
Developing a system to analyze and compare voice samples by extracting Mel-Frequency Cepstral Coefficients (MFCC) and applying similarity measures.
Key Results:
Built a prototype system for detecting similarity across different speakers. Achieved consistent performance in controlled testing datasets.
Timeline:
Jan 2024 – Present
Technologies:
MSc Thesis – Machine Learning for Predicting Mechanical Properties in 3D-Printed Metal Components
Applied supervised ML models (SVM, Linear Regression, Decision Tree) to predict material properties from process parameters in metal additive manufacturing. Focused on improving quality control and understanding process-property relationships.
Key Results:
Achieved accurate prediction of tensile strength and hardness using experimental datasets. Demonstrated correlations between process parameters and resulting mechanical properties.
Timeline:
Oct 2022 – Sep 2023
Technologies:
Climate Analysis using Machine Learning
Analyzed London’s yearly weather data using data aggregation, regression models, and statistical testing to identify long-term climate patterns.
Key Results:
Built regression models with reliable R² scores for trend analysis. Conducted p-value testing to evaluate statistical significance in climate variations.
Timeline:
Feb 2023 – May 2023
Technologies:
AI Applications on DOF-17 Humanoid Robot
Implemented AI-driven control on a humanoid robot platform using Arduino Mega and C programming, focusing on movement coordination and intelligent response.
Key Results:
Successfully programmed robotic motion and basic AI-driven interactions. Demonstrated integration of AI concepts with physical robotics systems.
Timeline:
2018 – 2019
Technologies:
Upcoming research projects and areas of active exploration
Federated Learning for Healthcare Data
Exploring privacy-preserving machine learning techniques for medical data analysis across multiple hospitals.
Expected: Summer 2025
Explainable AI for Financial Decision Making
Developing interpretable machine learning models for financial risk assessment and investment recommendations.
Expected: Fall 2025
Multimodal Learning for Robotics
Investigating vision-language models for improved human-robot interaction and task understanding.
Expected: Spring 2026
I believe research in AI and Data Science should unite innovation with responsibility, ensuring transparency and human benefit. My work bridges theory and real-world application, focusing on explainable and reliable AI. I value cross-disciplinary collaboration to create solutions that drive scientific progress and positive social impact
Building a research portfolio through conference papers, journal articles, and academic presentations
Predicting Yield Strength of 3D-Printed Metal Components Using Machine Learning and Process Parameters
Abdullah Al Mamun
Springer Lecture Notes in Networks and Systems (LNNS)A machine learning-based approach to predict yield strength in 3D-printed metal components by analyzing process parameters. The study demonstrates strong correlations between input parameters and resulting mechanical properties, supporting improved quality control in additive manufacturing.
Voice Similarity Detection for Audio Authentication
Abdullah Al Mamun
Expected 2025
Developing a system that extracts Mel-Frequency Cepstral Coefficients (MFCC) and applies cosine similarity to detect and compare voice patterns. The project explores applications in speaker verification and potential deepfake audio detection.
Climate Change Analysis using Machine Learning
Abdullah Al Mamun
Expected 2025
Applied regression models, data aggregation, and statistical analysis to evaluate London’s yearly climate data and long-term weather patterns. The study focuses on predicting climate trends and validating results with statistical testing.
A Comparative Study of ML-Based Prediction of Mental Health During Quarantine
Abdullah Al Mamun
Expected 2025
Exploring multiple machine learning models — including Extra Trees, Random Forest, Decision Tree, SVM, KNN, and Logistic Regression — to predict stress, anxiety, and depression during quarantine periods. Ensemble methods such as Extra Trees achieved high predictive performance, demonstrating the potential of ML in mental health support systems
No conference presentations to display at this time. Please check back later!
My goal is to publish high-quality research in AI, Machine Learning, and Data Science, focusing on impactful conference papers and journal articles. I aim to contribute to advancing knowledge while ensuring my work addresses real-world challenges in healthcare, manufacturing, and intelligent systems.
I'm always excited to discuss research opportunities, collaborate on projects, or share insights about machine learning and AI. Let's connect!
Contact Information
You can reach out to me directly through the channels below, or use the form to send a message. I make an effort to respond to all inquiries within 24-48 hours.
Location
Bangor, Gwynedd,
North Wales, United Kingdom.