Project Highlights
Advanced Machine Learning for Clinical Informatics
The multifactorial complexity of clinical data complicates prediction and prevention of undesired outcomes. This project aims to investigate the value of more advanced machine learning methods by simultaneously considering all the factors, to develop better predictive and prevention methods.
To read the project abstract, click here.
Emergence of Social Norms and Conventions in Multiagent Systems
In this project, we study the importance and challenges of establishing cooperation among self-interested agents in multiagent systems (MAS). The hypothesis of this work is that equipping agents in networked MAS with “network thinking" capabilities and using this contextual knowledge to form social norms in an effective and efficient manner improves the performance of the MAS. We investigate the social norm emergence problem in conventional norms (where there is no conflict between individual and collective interests) and essential norms (where agents need to explicitly cooperate to achieve socially-efficient behavior) from a game-theoretic perspective
Visit the project website here.
Decision Making in Partially Observable Environments
Design, develop and evaluate stochastic transition probability function, cost effectiveness analysis and sensitivity analysis to support decision making in uncertain environments. We will study this in the context of prevention of undesired outcomes in clinical informatics.
Coordinating Meta-level Control Across Agent Boundaries
The fundamental question addressed in this work is how to determine and obtain the minimal overlapping context among decentralized decision makers required to make their decisions more consistent. Our approach is a two-phased learning process where agents first learn their policies offline within the context of a simplified environment where it is not necessary to know detailed context information about neighbors. We evaluate our approach by addressing meta-level decisions in a complex multiagent weather tracking domains.
Visit the project website here.
Modeling Cascading Risk in Interdependent Networks
Networked applications often operate under uncertainty in environmental response and the temporal state and action choices of the nodes are captured in the form of structured and unstructured text data as well as image data. We propose a network-centric approach that will contribute to advances in reasoning about uncertainty, large-scale text and image data analysis as well understanding of complex networks. This work is expected to lead to innovative extensions in the following research areas: combining topic modeling and information extraction from text data and image extraction for data foraging, identification of topological features for network analysis and studying the interactions between stakeholders at varying levels of the network. Specifically, we plan to study this problem in the context of Major Defense Acquisition Program (MDAP) network.
Visit the project website for the previously funded phase here.
WLAN Management using DCOPS
This research investigates cooperative resource management in WLAN (wireless local area networks) /WPAN (wireless personal area networks) interference environments. The objective of this research is to manage shared system resources fairly among multiple WLANs to optimize the overall performance. Results from the project are expected to impact next generation WLAN network management based on employing algorithms of agent interaction and coordination to facilitate resource management, predictive models for parameter estimation, and dynamic load balancing algorithms.
Visit the project website here.