Abdullah Mamun

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:

1. Poster: HydraSense: Personalized Hydration Monitoring with Wearables and Machine Learning (IEEE BSN 2024)
2. Poster: Glysigma: Personalized Glucose Forecasting Enhanced by Bayesian Optimization on CGM Data (IEEE BSN 2024)
3. 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)