FSS-19 Presentation: Slides

Projects related to monitoring tasks:

Underwater Robotic Unit with an Automated Sensing Technology for water quality testing

We build a prototype for an underwater robotic unit equipped with multiple sensors that are able to collect data autonomously and we are working on an enhanced analytics software that uses machine learning to analyze the collected data and predict trends related to water quality.

  Read an Allegheny news story about this project

  Read an Erie News article about this project

Well-being Monitoring with Multiple Collaborating Robots and Wearable Sensors

We developed a system comprising of multiple robots and wearable sensors with a goal of monitoring a person's well-being.

  Read an Allegheny news story about this project

  Slides from AAAI Symposium, 2016

Multi-robot Environmental Monitoring

We developed a Boolean network-based methodology for Consensus in Multi-Robot Environmental Monitoring Tasks.

  Slides from EIT Conference, 2016

A Multi-Agent System for Biomedical Text Mining

We developed a distributed text mining system that uses multiple intelligent, learning software agent to find correlations in the biomedical text.

  Slides from BigLS Workshop, 2015

Projects related to prediction markets:

A Multi-Agent System for Analyzing the Effect of Information on Prediction Markets

We developed a multi-agent system that allows us to study how information affects traders and prediction market price.

  Slides from University of Nebraska at Omaha Research Fair, 2010

Partially Observable Stochastic Game-based Multi-Agent Prediction Markets

We developed a correlated equilibrium strategy for the trading agents within a partially observable stochastic game-based (POSG) model that incentivizes traders to reveal their true beliefs.

  Slides from ICEC Conference, 2011

Boolean Network for Analyzing the Dynamics of the Prediction Market

We apply Boolean network (BN) techniques to study the dynamics of prediction markets under various conditions.

  Slides IAT Conference, 2011

Prediction Market-based Information Aggregation for Multi-sensor Information Processing

We study a decision making problem within a sensor fusion domain where we use prediction market to fuse information from multiple sensors of different types accurately.

  Slides from SPIE Conference, 2012

Distributed Prediction Markets based on Weighted Bayesian Graphical Games

We develop a framework to model a novel, yet practical setting of prediction markets called distributed prediction markets, where the aggregated price of a security of an event in one prediction market is affected dynamically by the prices of securities of similar events in other, simultaneously running prediction markets.

  Slides from AMEC Workshop, 2013

Past projects:

Strategic Capability-Learning

We propose an ad-hoc collaboration framework where each agent strategically selects capabilities to learn from other agents which would help it to improve its expected future utility of performing tasks.

Pricebots: Dynamic Pricing

We propose dynamic pricing algorithms that sellers can use to update the prices of their products online automatically:
-- using multi-attribute minimax regret,

  Slides from AMEC Conference, 2008

-- using distributed synchronization model observed in nature.

  Slides from SASO Conference, 2008