Pramod Varshney: Distributed Inference and Information Fusion in Human-Sensor Networks

Distributed inference when the participants are only machines or electronic devices, e.g., sensors, has been explored extensively in the signal processing and machine learning literature. However, there are fundamental differences between such rational systems and systems where the agents include humans due to their cognitive limitations, imperfect rationality as well as behavioral uncertainties. In information fusion systems that include humans, modeling and analysis need to take several factors into account, including cognitive biases of humans, mechanisms to handle uncertainties and noise, and unpredictability of humans, in contrast to inference processes consisting of only machine agents.

In this talk, we discuss aspects of human-sensor networks by focusing on specific problems, including collaborative human decision-making with random local thresholds, decision fusion in integrated human-machine networks, prospect theoretic human decision-making in multi-agent systems, and portfolio theory-based resource management. In each case, we aim to optimize the system performance based on appropriate modeling of human behavior. We also summarize current challenges and research directions related to this problem domain.

PRAMOD K. VARSHNEY (S’72–M’77–SM’82– F’97–LF’18) is currently a Distinguished Professor of electrical engineering and computer science at Syracuse University and the Director of the Center for Advanced Systems and Engineering. As the Director of CASE, he is responsible for the technology transition of university expertise to make an economic impact in the high-tech economy of New York. He is the author of Distributed Detection and Data Fusion (New York, NY, USA: Springer-Verlag, 1997). His current research interests include distributed sensor networks and data fusion, detection and estimation theory, wireless communications, image processing, radar signal processing, physical layer security, and machine learning.