Research



Computer Science students and faculty are involved in many research projects, such as:

  • Colony Robotics and Robot Development. Gary Parker, Ozgur Izmirli, Art Potter, Max Rollins, Steve Sweriduk, William Tarimo, Jim O’Connor, and Andrew Freedman. An 8x8 foot area has been set aside in the Robotics Lab for colony robotics research. We are working on developing a power supply for the robots, establishing communication links from the learning system computer to the robot, and implementing an overhead camera for colony observation. Several robots are being developed and constructed, including bipeds, quadrupeds, hexapods, two wheel balancing robots, autonomous sailboats, and flying robots.

  • Auction Mechanisms for Admission Control of Datastream Queries. Christine Chung. Amazon, Google, and IBM now sell cloud computing services. With this motivation, we considered the setting of a for-profit business selling data stream monitoring/management services. This work investigated auction-based strategy-proof mechanisms for admission control of continuous queries with the goal of maximizing revenue.

  • Tonal Spaces and Key Finding from Audio. Ozgur Izmirli.This research examines the relationship between music-theoretical concepts and audio based features specifically in the context of tonal music. It employs machine learning methods to construct spaces in which harmonic movement can be tracked. This work falls under a larger area of research concerned with music understanding, cognitive modeling and music information retrieval.

  • DEEP/PLACE. Bridget Baird, Ozgur Izmirli, Andrea Wollensak and Amy Barrett. Multimodal explorations of buildings (including Harkness Chapel and the construction of New London Hall) using architectural plans, video, audio, 3d drawings and geological information. The 3D virtual environment employs gestural interfaces by means of glove/sensors or Kinect.

  • Humanitarian FOSS. Gary Parker, Ozgur Izmirli. This project is dedicated to building and using Free and Open Source Software (FOSS) to benefit humanity. We are participating in collaboration with the Computer Science departments from Trinity College and Wesleyan University. The project involves a community of individuals from academics, social service organizations, and IT corporations. Its main focus is on the use of humanitarian open-source software development for real-world problems and computer science education for undergraduates in the United States.

  • Using Cyclic Genetic Algorithms to Generate Gaits for Hexapod Robots. Gary Parker and William Tarimo. In this project we use CGAs (a form of evolutionary computation) to learn walking patterns for six-legged robots. Learning takes place on a model of the robot with the new control programs downloaded to the actual robot for testing.

  • Motion Capture. Ozgur Izmirli, Bridget Baird and Ajjen Joshi. Research using motion capture of the body and of facial gestures to be used in gesture recognition and arts and technology applications (including dance).

  • Application of Evolutionary Game Theory for Congestion at Internet Routers. Christine Chung. Congestion control at bottleneck routers on the internet is a long standing problem. Many policies have been proposed for effective ways to drop packets from the queues of these routers so that network endpoints will be inclined to share router capacity fairly and minimize the overflow of packets trying to enter the queues. By employing the adaptive learning model of evolutionary game theory, we study existing policies and find the stochastically stable states: the states of the system that will be reached in the long run.

  • Punctuated Anytime Learning in Evolutionary Robotics. Gary Parker, William Tarimo, and Jim O’Connor. This research uses periodic tests on the actual robot to test the control programs learned on the robot model by evolutionary computation and improve the learning process by altering the learning algorithm (Fitness Biasing) or changing the model (Co-Evolving Model Parameters).

  • Online Scheduling Algorithms. Christine Chung. We consider the classical and canonical problem of scheduling preemptible jobs, that arrive over time, on identical parallel machines. The goal in this problem is to minimize the total completion time of the jobs.

  • Tempo and Beat Tracking. Ozgur Izmirli and Bo Xiong. This research involves development of low-latency methods for tempo estimation and beat tracking using audio input. The development is targeted for dedicated signal processing hardware that provides improved mobility and independence from a workstation-like environment.

  • Xpilot-AI. Gary Parker, Evan Gray, Jim O’Connor, and Sarah Penrose. Xpilot is an online computer game that models space combatants in a 2D environment. We have determined how to access the client program to be able to allow agents with artificial intelligence to play the game (Xpilot-AI). With proper configuration, these agents look and act just like those controlled by human players. The long-term goal is to have them continually learn as they join games in progress and compete against human players.

  • Digital Humanities. Bridget Baird. Computers are increasingly being used in the humanities. New research is being conducted that mines digital historical archives; other research explores ways to visualize information and networks.
  • Virtual Reality and Archaeology. Bridget Baird, Erin Okabe-Jawdat. Virtual reality is used to explore the archaeological site Cochasqui in Ecuador. Modeling of the site in 3D and simulations allow users to experience this pre-Incan site as it might have been. Archival footage and oral interviews add to the user experience.

  • Gestural interfaces using video. Ozgur Izmirli and Phoebe Bakanas. This research aims at designing models for controlling parameters of multimedia content through gestural video input. It aims to explore the mappings of intuitive gestures to parameters of media display in different modalities.

  • Multimodal Integration and Way-finding. Bridget Baird, Ann Devlin. The roles of multiple modes such as visual, audio and haptics, are explored to enable a better understanding of spatial cognition. This multidisciplinary research is at the intersections of computer science, psychology and music. Applications of this research are in the area of way-finding in hospitals.

  • Multimodal Connections: Haptics and Audio. Bridget Baird, Ozgur Izmirli. This research seeks to answer the questions of whether there are connections between the audio properties and haptic properties. Experiments are being conducted to test the presence of innate correlations and also whether correlations can be learned. The results of these experiments will have implications for user interfaces and will shed light on the nature of haptic/audio relationships.

  • Conducting a Virtual Ensemble. Bridget Baird and Ozgur Izmirli. The aim of this project is to analyze this relationship between the conductor's movements and the actual tempo as performed by the players, and apply the results from this analysis to construct a computer-based system that will mimic the salient behavior of a real ensemble.

  • Sound and Audio Signal Processing. Click here for additional research topics.

  • Virtual Reality and Multiple Modalities.

  • Artificial Intelligence and Robotics. Click here for additional research topics.

  • Algorithms and Algorithmic Game Theory. Click here for additional info.

Contact information:
Phone:
860-439-2007
Fax:
860-439-2700
Email parker@conncoll.edu
Computer Science
Box 5477
270 Mohegan Avenue
New London, CT 06320-4196
cs.conncoll.edu