As infrastructural systems rapidly grow in scale, complexity and interconnectedness, legacy operations driving the systems have shown to be limited in their ability to handle large-scale disasters that can occur either through natural extreme events, or through carefully orchestrated attacks, and in particular cyber-attacks. Advances in sensing and communication technologies allow diverse data collection at massive scale, granting unprecedented visibility into system operations and provide enormous potential to overhaul the operational paradigms towards increased safety, security and sustainability. It is towards this end that we are conducting data-intensive data-driven research for inference and control in large scale cyber physical infrastructural networks. In particular, our multi-disciplinary research focuses on developing explainable learning approaches through physics-informed or domain-informed graph learning for prediction, and causal graphs for explainable anomaly detection.
Sun, Y., Blum, R. S., & Venkitasubramaniam, P. (2025). Unifying Explainable Anomaly Detection and Root Cause Analysis in Dynamical Systems. AAAI Workshop on Artificial Intelligence for Cyber-Security, Feb. 2025, Philadelphia PA.
Sun, Y., Chen, C., Xu, Y., Xie, S., Blum, R. S., & Venkitasubramaniam, P. (2024). Incorporating Domain Differential Equations into Graph Convolutional Networks to Lower Generalization Discrepancy. AAAI Workshop on Artificial Intelligence for Time-Series Analysis, Feb. 2024, Vancouver, Canada.
Sun, Yue, Chao Chen, Yuesheng Xu, Sihong Xie, Rick S. Blum, and Parv Venkitasubramaniam. “On the generalization discrepancy of spatiotemporal dynamics-informed graph convolutional networks.” Frontiers in Mechanical Engineering10 (2024): 1397131.
Sun, Y., Chen, C., Xu, Y., Xie, S., Blum, R. S., & Venkitasubramaniam, P. (2023, August). Reaction-diffusion graph ordinary differential equation networks: Traffic-law-informed speed prediction under mismatched data. The 12th International Workshop on Urban Computing, held in conjunction with the 29th ACM SIGKDD 2023.
LaRosa, N., Farber, J., Venkitasubramaniam, P., Blum, R., & Al Rashdan, A. (2022). Separating Sensor Anomalies From Process Anomalies in Data-Driven Anomaly Detection. IEEE Signal Processing Letters, 29, 1704-1708.
Yao, Ruigen, et al. “Iterative spatial compressive sensing strategy for structural damage diagnosis as a BIG DATA problem.” Dynamics of Civil Structures, Volume 2: Proceedings of the 33rd IMAC, A Conference and Exposition on Structural Dynamics, 2015. Springer International Publishing, 2015.
Yao, Ruigen, Shamim N. Pakzad, and Parvathinathan Venkitasubramaniam. “Compressive sensing based structural damage detection and localization using theoretical and metaheuristic statistics.” Structural Control and Health Monitoring 24, no. 4 (2017): e1881.