People

• Shah Muhammad Hamdi, Assistant Professor, CS, USU

• Reza EskandariNasab, PhD student, CS, USU

• Onur Vural, PhD student, CS, USU

• Santosh Chapagain, PhD student, CS, USU

• Khaznah Alshammari, PhD, CS, NMSU 

Current projects

• Solar flare prediction from multivariate time series-based solar magnetic field parameters: In our research on solar flare prediction using multivariate time series of solar magnetic field parameters, we have made significant contributions to understanding and forecasting solar activity. Our work involves analyzing complex datasets to identify patterns and develop predictive models for solar flares. By leveraging advanced statistical techniques and machine learning algorithms, we have improved the accuracy of solar flare forecasts, which is crucial for mitigating the impact of space weather on technological systems. Our publications in this area have been well-received in the scientific community, highlighting the importance of our contributions to solar physics and space weather prediction. 

  • Funding: NSF Award # 2301397: SHINE: Understanding the Relationships of Photospheric Vector Magnetic Field Parameters in Solar Flare Occurrences using Graph-based Machine Learning Models

• ML cyberinfrastructure development of multivariate time series and functional networks: Our research focuses on developing a comprehensive machine learning (ML) cyberinfrastructure tailored for multivariate time series and functional networks. We aim to create a unified framework that facilitates both supervised and unsupervised ML tasks across various data representations. By customizing and applying advanced ML techniques, our project seeks to enhance the analysis and interpretation of complex datasets, thereby advancing the capabilities of ML applications in diverse scientific domains. 

  • Funding: NSF Award # 2305781: CRII: OAC: Cyberinfrastructure for Machine Learning on Multivariate Time Series Data and Functional Networks

Publications

• EskandariNasab, M., Hamdi, S.M. and Boubrahimi, S.F., 2024. Impacts of Data Preprocessing and Sampling Techniques on Solar Flare Prediction from Multivariate Time Series Data of Photospheric Magnetic Field Parameters. The Astrophysical Journal Supplement Series.

• Alshammari, K., Hamdi, S.M. and Boubrahimi, S.F., 2024. Identifying Flare-indicative Photospheric Magnetic Field Parameters from Multivariate Time-series Data of Solar Active Regions. The Astrophysical Journal Supplement Series, 271(2), p.39. 

• EskandariNasab, M., Hamdi, S.M. and Boubrahimi, S.F., 2024. AVATAR: Adversarial Autoencoders with Autoregressive Refinement for Time Series Generation. SIAM International Conference on Data Mining (SDM25). 

• EskandariNasab, M., Hamdi, S.M. and Boubrahimi, S.F., 2024. SeriesGAN: Time Series Generation via Adversarial and Autoregressive Learning. In 2024 IEEE International Conference on Big Data (BigData). IEEE.

• Vural, O., Hamdi, S.M. and Boubrahimi, S.F., 2024. EXCON: Extreme Instance-based Contrastive Representation Learning of Severely Imbalanced Multivariate Time Series for Solar Flare Prediction Tasks. In 2024 IEEE International Conference on Big Data (BigData). IEEE. 

• Vural, O., Hamdi, S.M. and Boubrahimi, S.F., 2024. Contrastive Representation Learning for Predicting Solar Flares from Extremely Imbalanced Multivariate Time Series Data. In 23rd IEEE International Conference on Machine Learning and Applications (ICMLA), 2024, in press.

• EskandariNasab, M., Hamdi, S.M. and Boubrahimi, S.F., 2024. Enhancing Multivariate Time Series-based Solar Flare Prediction with Multifaceted Preprocessing and Contrastive Learning. In 23rd IEEE International Conference on Machine Learning and Applications (ICMLA), 2024, in press.

• EskandariNasab, M., Hamdi, S.M. and Boubrahimi, S.F., 2024. ChronoGAN: Supervised and Embedded Generative Adversarial Networks for Time Series Generation. In 23rd IEEE International Conference on Machine Learning and Applications (ICMLA), 2024, in press.

• Alshammari, K., Hamdi, S.M. and Boubrahimi, S.F., 2024, December. Transformer Model for Multivariate Time Series Classification: A Case Study of Solar Flare Prediction. In International Conference on Pattern Recognition (pp. 238-254). Cham: Springer Nature Switzerland. 

• S. Chapagain, Y. Zhao, T. K. Rohleen, S. M. Hamdi, S. F. Boubrahimi, R. E. Flinn, E. M. Lund, D. Klooster, J. R. Scheer, and C. J. Cascalheira, 2024. Predictive insights into lgbtq+ minority stress: A transductive exploration of social media discourse.” In 2024 IEEE 11th International Conference on Data Science and Advanced Analytics (DSAA). IEEE, 2024, October. (In Press). 

• Cascalheira, C.J., Chapagain, S., Flinn, R.E., Klooster, D., Laprade, D., Zhao, Y., Lund, E.M., Gonzalez, A., Corro, K., Wheatley, R. and Gutierrez, A., 2024, May. The lgbtq+ minority stress on social media (missom) dataset: A labeled dataset for natural language processing and machine learning. In Proceedings of the International AAAI Conference on Web and Social Media (Vol. 18, pp. 1888-1899). 

• Alshammari, K., Saini, K., Hamdi, S.M. and Boubrahimi, S.F., 2023, December. End-to-End Attention/Transformer Model for Solar Flare Prediction from Multivariate Time Series Data. In 2023 International Conference on Machine Learning and Applications (ICMLA) (pp. 558-565). IEEE. 

• Muzaheed, A.A.M., Hamdi, S.M. and Boubrahimi, S.F., 2021, December. Sequence model-based end-to-end solar flare classification from multivariate time series data. In 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 435-440).