Abdullah Mamun
-
6161 E Mayo Blvd #319 Phoenix, AZ 85054
-
Mail code: 8620Campus: Dtphx
-
Student Information
Graduate StudentComputer Science
Ira A Fulton Engineering
I am currently pursuing my Ph.D. in Computer Science at Arizona State University. I work as a Graduate Research Associate at Dr. Hassan Ghasemzadeh's lab. My research interests are Deep Learning, Mobile Health, Explainable AI, and Generative Models. Previously I worked as a Lecturer at United International University and a Software Developer at HLC Technologies Ltd. in Dhaka, Bangladesh. Currently, my work includes building prediction and forecasting models on time-series data, especially for special circumstances, e.g. uncontrolled environment, low-quality, missing, or unlabeled data, etc.
- Ph.D. in Computer Science, Arizona State University (Jan 2022 - present)
- Ph.D. in Computer Science, Washington State University (Jan 2021 - Dec 2021)
- B.Sc. in Computer Science, Bangladesh University of Engineering and Technology (2014-2018)
- Deep learning
- Mobile health
- Generative Models
- Explainable AI
Embedded Machine Intelligence Lab (EMIL)
- Director: Hassan Ghasemzadeh
Accepted peer-reviewed publications:
1. Domain-Informed Label Fusion Surpasses LLMs in Free-Living Activity Classification. S. B. Soumma, A. Mamun, H. Ghasemzadeh. AAAI Conference on Artificial Intelligence (AAAI’25) Extended Abstract.
2. Neonatal Risk Modeling and Prediction. A. Mamun, C.-C. Kuo, D. W. Britt, L. D. Devoe, M. I. Evans, H. Ghasemzadeh, & J. Klein-Seetharaman. IEEE Conference on Body Sensor Networks (BSN 2023).
3. Multimodal Time-Series Activity Forecasting for Adaptive Lifestyle Intervention Design. A. Mamun, K. S. Leonard, M. P. Buman, & H. Ghasemzadeh. IEEE Wearable and Implantable Body Sensor Networks (BSN 2022).
4. Designing Deep Neural Networks Robust to Sensor Failure in Mobile Health Environments. A. Mamun, S. I. Mirzadeh, & H. Ghasemzadeh. IEEE Engineering in Medicine and Biology Conference (EMBC 2022).
Journal submissions under review:
1. AIMEN: AIMEN uses an ensemble of fully-connected neural networks as the backbone for its classification with the data augmentation supported by either ADASYN or CTGAN. AIMEN can predict a high risk for adverse labor outcomes with an average F1 score of 0.784. It also provides counterfactual explanations that can be achieved by changing 2 to 3 attributes on average. Preprint: https://arxiv.org/abs/2410.09635.
2. MoveSense: Our multimodal LSTM with early fusion achieves 33% and 37% lower mean absolute errors than linear regression and ARIMA respectively on the prediabetes dataset. LSTM also outperforms linear regression and ARIMA with a margin of 13% and 32% on the sleep dataset. Preprint: https://arxiv.org/abs/2410.09643.
3. AIMI: We designed and developed CNN and LSTM-based forecasting models with various combinations of input features and found that LSTM models can forecast medication adherence with an accuracy of 0.93 and an F1 score of 0.93 (under review).
Accepted abstracts for conference presentations:
- Poster: HydraSense: Personalized Hydration Monitoring with Wearables and Machine Learning (IEEE BSN 2024)
- Poster: Glysigma: Personalized Glucose Forecasting Enhanced by Bayesian Optimization on CGM Data (IEEE BSN 2024)
- An empirical approach to understand mHealth application engagement and its associations with daily changes in physical activity in a lifestyle intervention among US Veterans with Prediabetes (ICAMPAM 2022)
- [2024-11] Abdullah has received both the Outstanding Research Award and the Teaching Excellence Award at the Fall 2024 ASU Graduate Student Government (GSG) Awards Program.
- [2024-10] Our extended abstract titled “Domain-Informed Label Fusion Surpasses LLMs in Free-Living Activity Classification” has been accepted to the AAAI'25 conference for publication and presentation.
- [2024-10] Abdullah’s preprint “Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal Health” is now available on arXiv.
- [2024-10] Abdullah’s preprint “Multimodal Physical Activity Forecasting in Free-Living Clinical Settings: Hunting Opportunities for Just-in-Time Interventions” is now available on arXiv.
- [2024-9] Two 1-page abstracts co-authored by Abdullah got accepted at IEEE BSN'24.
- [2024-8] Abdullah Mamun started teaching the Fall 2024 course, BMI 311: Modeling Biomedical Knowledge at Arizona State University as the sole instructor.
- [2023-10] Abdullah received the IEEE Student Travel Award to attend IEEE BSN'23.
- [2023-7] Abdullah’s paper titled “Neonatal Risk Modeling and Prediction” got accepted at the IEEE-EMBS International Conference on Body Sensor Networks: Sensor and Systems for Digital Health (BSN'23).
- [2023-4] Abdullah Mamun was invited as a panelist for the AI for Good session at the Machine Learning Day 2023 at ASU West Campus.
- [2022-9] Abdullah’s paper, “Multimodal Time-Series Activity Forecasting for Adaptive Lifestyle Intervention Design,” has been awarded Honorable Mention at the Best Paper Award of the IEEE BSN 2022 conference in Ioannina, Greece.
- [2022-7] Our paper titled "Multimodal Time-Series Activity Forecasting for Adaptive Lifestyle Intervention Design" has been accepted at IEEE International Conference on Wearable and Implantable Body Sensor Networks (BSN 2022).
Authors: A. Mamun, K.S. Leonard, M.P. Buman, and H. Ghasemzadeh - [2022-3] Our paper titled "Designing Deep Neural Networks Robust to Sensor Failure in Mobile Health Environments" has been accepted at IEEE Engineering in Medicine and Biology Conference (EMBC 2022).
Authors: A. Mamun, S.I. Mirzadeh, and H. Ghasemzadeh - [2022-3] Our abstract has been accepted at ISMPB ICAMPAM 2022 conference for oral presentation.
Authors: K.S. Leonard, A. Mamun, H. Ghasemzadeh, and M.P. Buman
- Outstanding Research Award by Arizona State University Graduate Student Government (2024).
- Teaching Excellence Award by Arizona State University Graduate Student Government (2024).
- Invited Talk: Time-Series Wearable Activity Forecasting at ASU Machine Learning Day (2023).
- IEEE Student Travel Award to attend the IEEE BSN 2023 conference (2023).
- Best paper (honorable mention) award at the IEEE BSN 2022 conference (2022).
- University Merit List Scholarship by Bangladesh University of Engineering and Technology (2017).
Reviewed 4 IEEE JBHI, 1 PerCom’23, 1 IEEE BHI’23, 5 CHIL’24, 6 IEEE BHI’24, and 4 ML4H’24 submissions.
- IEEE Graduate Student Member
- Mentored an ASU SCENE Intern, Fatimah Amer, in her SCENE research.
- Mentored an undergraduate student, Sanyam Paresh Shah, in his BMI 311 Honors Contract.
- Course Instructor, Arizona State University (Aug 2024 - present)
- Graduate Research Associate, Arizona State University (Dec 2021 - present)
- Teaching and Research Assistant, Washington State University (Jan 2021 - Dec 2021)
- Lecturer, United International University, Dhaka, Bangladesh (Sep 2019 - Jan 2021)
- Software Developer, HLC Technologies Ltd., Dhaka, Bangladesh (Nov 2018 - Sep 2019)
Software Developer at HLC Technologies Ltd. (Nov 2018 - Sep 2019)