For my PhD research at the Robotics Institute at CMU from 2010-2015, I worked with the CMU Auton Lab on the Academic Research Initiative (ARI) project developing the Bayesian Aggregation (BA) data processing framework.

Bayesian Aggregation (BA) is a method for characterizing variability in noisy sensor data, allowing robots to better perceive the world in terms of detecting sources and signals of interest. The machine learning framework  allows extracting maximal information from single sensor observations and then fusing multiple observations together to detect and characterize the properties of a signal generating source or process of interest.

The research is illustrated with application to the Nuclear Threat Detection domain, allowing Homeland Security and the Domestic Nuclear Detection Office (DNDO) to analyze the large amounts of spectrometry data that can collected by mobile sensors in real time to keep the U.S. safe from threats. We are also working to generalize it to many other domains. Check out some of our contributions below.

I successfully defended my PhD thesis on July 13, 2015! You can download my PhD thesis below:

My PhD Thesis
Thesis Presentation Slides
CMU Robotics Institute Page for Dissertation (for citation purposes)

You can also view my earlier thesis proposal (November 2014) and quals (March 2013) materials here:

Thesis Proposal Document
Thesis Proposal Presentation Slides
Research Qualifier Paper
Research Qualifier Presentation

Here are my journal papers related to Bayesian Aggregation research:

Tandon, Prateek, Peter Huggins, Rob Maclachlan, Artur Dubrawski, Karl Nelson, and Simon Labov. Detection of Radioactive Sources in Urban Scenes Using Bayesian Aggregation of Evidence from Mobile Spectrometers. Elsevier Special Issue on Mining Urban Data. Information Systems. 2015.

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Karl Nelson, and Simon Labov. Poisson Modeling and Bayesian Estimation of Low Photon Count Signal and Noise Components. (In Submission)

Here are my publicly available conference presentations:

Tandon et al. Bayesian Aggregation for Detection of Radioactive Sources and Inference of their Properties. ARI Annual Review 2013.

Tandon et al. Simultaneous mapping of intensity and location of radiological threats using mobile spectrometers. INFORMS 2012.

The work has produced no fewer than 17 conference posters in 5 years! Is that a PhD record? Here are most of the poster presentations (broken up by topic area):

Presenting Bayesian Aggregation (BA) and Poisson Modeling capabilities to neural big data and experimental physics communities for generalization of method:

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Simon Labov, and Karl Nelson. Poisson and Bayesian Estimation of Low Photon Count Signal Source and Noise Components. BigNeuro Workshop at Neural Information Processing Systems Conference 2015.

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Simon Labov, and Karl Nelson. Building a Robust Detector Algorithm: Application of Bayesian, Nonparametric, and Poisson Methods to Improve Photon Denoising. Aleph Workshop on Machine Learning for Experimental Physics at Neural Information Processing Systems 2015.

On a Joint Anomaly-Match Bayesian Aggregation Strategy (AM-BA) for Searching the Space of Source Hypotheses:

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Simon Labov, and Karl Nelson. Anomaly-Match Bayesian Aggregation (AM-BA) for Efficient Radiation Source Search. IEEE Nuclear Science Symposium 2015.

On Using Bayesian Sensor Reliability Models in Detecting Possible Spectrometer Faults and Failures:

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Simon Labov, and Karl Nelson. Fault-Tolerant Source Detection Using Bayesian Sensor Reliability Models. IEEE Nuclear Science Symposium 2015.

On an Augmented PCA Approach for Incorporating new Background and Nuisance Source Fluctuations into Anomaly Model:

Tandon, Prateek, Artur Dubrawski, Peter Huggins, Robert Maclachlan, Karl Nelson, and Simon Labov. Multi-Modal Principal Component Analysis for Robust Threat Detection. ARI Annual Review 2015.

On Poisson Match Filtering for Boosting Detection Power of Low Count Photon Data from Inexpensive Wearable Spectrometers:

Tandon, Prateek, Artur Dubrawski, Peter Huggins, Robert Maclachlan, Karl Nelson, and Simon Labov. Poisson Match Filter for Low Photon Count Data from Portable Spectrometers. ARI Annual Review 2014.

On Bayesian Aggregation to Boost Detection of Sources and Infer Source Properties:

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Simon Labov, and Karl Nelson. Simultaneous Detection of Radioactive Sources and Inference of their Properties. IEEE Nuclear Science Symposium 2013.

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Simon Labov, and Karl Nelson. Source Location via Bayesian Aggregation of Evidence with Mobile Sensors. Symposium on Radiation Measurements and Application 2012.

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Jeff Schneider, Simon Labov, and Karl Nelson. Bayesian Aggregation for Radiation Source Detection. Pittsburgh Chapter of the American Statistical Association. Spring Banquet 2012.

On Bayesian Aggregation for Detecting Sources of Varying Intensity and Type:

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Jeff Schneider, Simon Labov, and Karl Nelson. ARI-MA: Machine Learning for Effective Nuclear Search and Broad Area Monitoring. ARI Annual Review 2013.

On Adaptive Grid Bayesian Aggregation for Efficient Multi-Resolution Source Search

Huggins, Peter, Prateek Tandon, Artur Dubrawski, Simon Labov, and Karl Nelson. Dynamic Placement of Sensors for Rapid Characterization of Radiation Threat. DTRA Review July 2013.

On using Poisson Principal Component Analysis to Boost Detection of Low Count and Weak Sources:

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Simon Labov, and Karl Nelson. Suppressing Background Radiation using Poisson Principal Component Analysis. IEEE Nuclear Science Symposium 2012.

Tandon, Prateek, Peter Huggins, Artur Dubrawski, Simon Labov, and Karl Nelson. Modeling Variation of Background Radiation using Poisson Principal Component Analysis. ARI Annual Review 2012.

On a (team-built!) prototype robotic radiation sensing hardware backpack system useful for spectrometry controllable with an Android phone app:

Tandon, Prateek, Vladimir Ermakov, Aashish Jindia, Artur Dubrawski, Simon Labov, and Karl Nelson. Portable Radiation Monitoring Platform for Effective Nuclear Search. ARI Annual Review 2012.

On Use of Active Learning to Plan Routes for a Single Agent Robotic Vehicle to Detect a Radioactive Source:

Tandon, Prateek, Artur Dubrawski, Jeff Schneider, Adam Zagorecki, Simon Labov, and Karl Nelson. Machine Learning for Effective Nuclear Search and Broad Area Monitoring. ARI Annual Review 2011.

On Use of Active Learning to Plan Routes for a Multi-agent Robot Team of Autonomous Vehicles to Detect a Mobile Radioactive Source in Traffic:

Tandon, Prateek. Multi-agent Planning for Mobile Radiation Source Tracking and Active City-wide Surveillance. Graduate Artificial Intelligence Project (published in ARI Annual Report). Spring 2013.

Thanks to the sponsors behind the ARI and DTRA projects that have funded my PhD work.