Abdullah Mamun

Graduate Research Associate

Arizona State University

About Me

I am a Ph.D. student in Computer Science at Arizona State University. I work as a Graduate Research Associate at Embedded Machine Intelligence Lab (EMIL) under the supervision of Dr. Hassan Ghasemzadeh.

Currently, my work includes building and optimizing deep learning models for time-series data. My works have been published in EMBC'22, BSN'22, BSN'23, and AAAI'25 conferences and I have multiple journal and confernce submissions under review. I also actively peer-review conference and journal submissions.

Interests

Deep Learning
Explainable AI
Time-Series Forecasting
Generative Models
Counterfactual Explanations

Education

Ph.D. in Computer Science, Jan 2022 - present
Arizona State University
Ph.D. in Computer Science, Jan 2021 - Dec 2021
Washington State University
B.Sc. in Computer Science & Engineering, 2014 - 2018
Bangladesh University of Engineering and Technology

Publications

Domain-Informed Label Fusion Surpasses LLMs in Free-Living Activity Classification

By integrating BERT-based word embeddings with domain-specific knowledge (i.e., MET values), FUSE-MET optimizes label merging, reducing label complexity and improving classification accuracy.

The 39th Annual AAAI Conference on Artificial Intelligence (AAAI'25) - Student Abstract and Poster Program

Shovito Barua Soumma, Abdullah Mamun, Hassan Ghasemzadeh

Domain-Informed Label Fusion Surpasses LLMs in Free-Living Activity Classification

Neonatal Risk Modeling and Prediction

We propose an automated risk prediction system that can make recommendations to clinicians in real-time with machine learning classifiers that predict the risk of developing neurological impairment.

IEEE-EMBS International Conference on Body Sensor Networks: Sensor and Systems for Digital Health (BSN'23)

Abdullah Mamun, Chia-Cheng Kuo, David W. Britt, Lawrence D. Devoe, Mark I. Evans, Hassan Ghasemzadeh, Judith Klein-Seetharaman

Multimodal Time-Series Activity Forecasting for Adaptive Lifestyle Intervention Design

We focus on devising algorithms that combine data about physical activity and engagement with the app to predict future physical activity performance.

IEEE International Conference on Wearable and Implantable Body Sensor Networks (BSN), 2022

Abdullah Mamun, Krista S. Leonard, Matthew P. Buman, Hassan Ghasemzadeh

Multimodal Time-Series Activity Forecasting for Adaptive Lifestyle Intervention Design

Designing Deep Neural Networks Robust to Sensor Failure in Mobile Health Environments

We propose an algorithm that can reconstruct the missing input data for unavailable sensors.

IEEE Engineering in Medicine and Biology Conference (EMBC), 2022

Abdullah Mamun, Seyed Iman Mirzadeh, Hassan Ghasemzadeh

Designing Deep Neural Networks Robust to Sensor Failure in Mobile Health Environments

Preprints

Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal Health

We propose “Artificial Intelligence (AI) for Modeling and Explaining Neonatal Health” (AIMEN), a deep learning framework that not only predicts adverse labor outcomes from maternal, fetal, obstetrical, and intrapartum risk factors but also provides the model’s reasoning behind the predictions made.

arXiv preprint

Abdullah Mamun, Lawrence D. Devoe, Mark I. Evans, David W. Britt, Judith Klein-Seetharaman, Hassan Ghasemzadeh

Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal Health

Multimodal Physical Activity Forecasting in Free-Living Clinical Settings: Hunting Opportunities for Just-in-Time Interventions

This research aims to develop a lifestyle intervention system, called MoveSense, that forecasts a patient’s activity behavior to allow for early and personalized interventions in real-world clinical environments.

arXiv preprint

Abdullah Mamun, Krista S. Leonard, Megan E. Petrov, Matthew P. Buman, Hassan Ghasemzadeh

Multimodal Physical Activity Forecasting in Free-Living Clinical Settings: Hunting Opportunities for Just-in-Time Interventions

ActSafe: Predicting Violations of Medical Temporal Constraints for Medication Adherence

ActSafe utilizes a context-free grammar based approach for extracting and mapping MTCs from patient education materials.

arXiv preprint

Parker Seegmiller, Joseph Gatto, Abdullah Mamun, Hassan Ghasemzadeh, Diane Cook, John Stankovic, Sarah Masud Preum

ActSafe: Predicting Violations of Medical Temporal Constraints for Medication Adherence

Experience

Instructor

Arizona State University

Aug 2024 – Present Phoenix, Arizona

I am currently teaching the Fall 2024 course BMI 311 - Modeling Biomedical Knowledge at Arizona State University.

Graduate Research Associate

Arizona State University

Dec 2021 – Present Phoenix, Arizona

I am currently working on a few projects concurrently. My work mostly includes time-series data analysis with machine learning, explainable AI, data generation with generative models, counterfactual explanations, etc.

Teaching Assistant

Washington State University

Aug 2021 – Dec 2021 Pullman, Washington

I was a TA for a semester for the course Advanced Data Structures in C++ (Fall 2021 Cpt_S 223). I helped the students with their queries and difficulties related to programming and theory, graded homeworks and programming assignments, and held office hours. Dr. Yan Yan was the instructor of the course.

Research Assistant

Washington State University

Jan 2021 – Aug 2021 Pullman, Washington

Lecturer

United International University

Sep 2019 – Jan 2021 Dhaka, Bangladesh

Software Developer

HLC Technologies Ltd.

Nov 2018 – Sep 2019 Dhaka, Bangladesh