I am a member of PNNL’s computing research division. Here are some problems keeping us inspired.

Latest News

Knowledge Graphs

The ability to construct domain specific knowledge graphs is critical to drive needs for question-answering or hypothesis generation. Despite their value, automated construction of knowledge graphs remains an expensive technical challenge that is beyond the reach for most enterprises and academic institutions. We propose an end-to-end framework for developing custom knowledge graph driven analytics for arbitrary application domains.

Streaming Algorithms

StreamWorks is a graph analytics system designed to detect patterns from massive data streams. This video shows a demonstration of StreamWorks’s capability to detect exfiltration events from a network traffic flow data stream. StreamWorks was selected by US Department of Homeland Security as the 2017 graduate of its Transition-To-Practice program.

Autonomous Systems Design

Resilience is the ability of a system to continue to function, even in a degraded manner, in the face of impediments that affect the proper operation of some of its components. For a cyber-network impediments can be randomly occurring failures of software services or hardware systems in an enterprise, or it may be unavailability of services or systems as the consequence of a cyber attack.

Sensor Networks

In my prior life I had implemented a sensor network protocol named PakBus. Developed by Campbell Scientific, PakBus is universally used by data collection devices. Our open-source version of a C++/Linux version of PakBus is available here.

Recent Publications

  1. Choudhury, S., Agarwal, K., Purohit, S., Zhang, B., Pirrung, M., Smith, W. and Thomas, M., 2017, April. Nous: Construction and querying of dynamic knowledge graphs. In Data Engineering (ICDE), 2017 IEEE 33rd International Conference on (pp. 1563-1565). IEEE.
  2. Zhang, B., Choudhury, S., Hasan, M.A., Ning, X., Agarwal, K., Purohit, S. and Cabrera, P.P., 2016. Trust from the past: Bayesian personalized ranking based link prediction in knowledge graphs.. In 2016 SIAM Data Mining Workshop on Mining Networks and Graphs
  3. Chen, P.Y., Choudhury, S. and Hero, A.O., 2016, March. Multi-centrality graph spectral decompositions and their application to cyber intrusion detection. In Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on (pp. 4553-4557). IEEE.
  4. Choudhury, S., Rodriguez, L., Curtis, D., Oler, K., Nordquist, P., Chen, P.Y. and Ray, I., 2015, October. Action recommendation for cyber resilience. In Proceedings of the 2015 Workshop on Automated Decision Making for Active Cyber Defense (pp. 3-8). ACM.
  5. Choudhury S, L Holder, G Chin, K Agarwal, JT Feo. 2015. A Selectivity based approach to Continuous Pattern Detection in Streaming Graphs, In Proceedings of the 18th International Conference on Extending Database Technology. CODE
  6. Ray, A., Holder, L. and Choudhury, S., 2014, August. Frequent Subgraph Discovery in Large Attributed Streaming Graphs. In BigMine/Special Issue of Journal of Machine Learning Research (pp. 166-181).
  7. Lieberman, M.D., Choudhury, S., Hughes, M., Patrone, D., Hider Jr, R.T., Piatko, C.D., Chapman, M., Marple, J.P. and Silberberg, D., 2014, June. Parasol: An Architecture for Cross-Cloud Federated Graph Querying. In Proceedings of Workshop on Data analytics in the Cloud (pp. 1-4). ACM.
  8. Morari, A., Castellana, V.G., Villa, O., Tumeo, A., Weaver, J., Haglin, D., Choudhury, S. and Feo, J., 2014. Scaling semantic graph databases in size and performance. IEEE Micro, 34(4), pp.16-26.
  9. Joslyn, C., Choudhury, S., Haglin, D., Howe, B., Nickless, B. and Olsen, B., 2013, June. Massive scale cyber traffic analysis: a driver for graph database research. In First International Workshop on Graph Data Management Experiences and Systems (p. 3). ACM.