About Me

I am Chair of the Department of Computer Science and co-coordinator for the Cybersecurity program at Central Connecticut State University. I have a BS in CS from Cornell University, a MS in CS from DePaul University, and a PhD in Computer Science at the University of Illinois at Chicago (UIC).  I'm into pretty much any sport or outdoor physical activity (lacrosse, volleyball, football, hockey, soccer, running particularly XC, skiing, just to name a few).  I also love photography.

My current research addresses three different threads of investigation.  The first is related to my study of using machine learning, data mining, and artificial intelligence methods in security applications, particularly in realm of intrusion detection.  The second is related to generalizing our success of using community focused project based learning for CS students to a model that can be easily adopted across computer science programs to benefit both students and their community partners .  Finally, I am also passionate about computer science education methods.

Intrusion Detection

This research focuses on creating new ways to identify previously unseen attacks in a more targeted fashion.  Specifically, one of the key weaknesses associated with the majority of current detection methods is they rely on detecting abnormal behavior from raw sensor data such as the amount of network traffic, processor usage, and sources and destinations.  The result is often slight changes in these can easily go unnoticed as fluctuations in the system regularly observed under normal conditions.  My current work in this area is focused on improving our ability to detect new attacks faster and more reliably.

Scaffolded Software Projects for the Social Good

 Leveraging the knowledge and skills of future software engineers to help non-profits and community organizations with their software projects. The outcome is a sustainable studio-based framework where students can build and demonstrate their professional competencies in computing while serving the greater social good. The goal of this research is to generalize the framework and best practices that have allowed our team to facilitate over 65 distinct projects and engaged over 500 students with these types of projects to a model that can be widely adopted by higher education institutions to benefit both student learning and their communities.  This research is supported by NSF.

Computer Science Education Methods

I have also started research into computer science educational methods.  One of the greatest social challenges in computer science has been the gender gap in Computer Science majors.  Specifically, less than 20% of all Computer Science majors throughout the United States are women and many have theorized this gap is due to girls in elementary school beginning to perceive programming computers as more of a “boy activity.”  In the past year, I have been working in this area on developing better ways to introduce kids to programming concepts that are fun for both boys and girls.  The latest version of this work can be tested out here http://tinyurl.com/train-a-robot   

I also have an ongoing study at CCSU on ways to fairly evaluate individual contribution on team projects, and mechanisms to motivate effectively team work.  A large part of this effort is to not only improve the way students work on teams, but to also increase the student’s perception that their efforts are being fairly evaluated.

Much of my data mining work focuses on a new field, Computational Transportation Science, that combines the cutting-edge of several fields in a multi-disciplinary effort to improve surface transportation systems. My PhD advisors were Peter Nelson (Computer Science) and Abolfazl (Kouros) Mohammadian (Civil and Materials Engineering).  These problems include everything from real-time route planning based on traffic congestion patterns to multi-modal commuting options integrating live public transit location information. 

My dissertation research involved developing algorithms and techniques for quickly learning activity patterns of individuals. The focus of this study was leveraging transferable aspects of travel behavior and patterns to reduce learning time, while also creating a richer model of the individual traveler. This research effort identified algorithms and techniques needed to address the problem of learning and predicting the activity needs of an individual for anticipating their associated travel demands with little input required from the traveler. A major component of this work was the theoretical aspect of making better time series projections of discrete sets despite missing data. The goal of this work was to enable intelligent travel applications by providing insight into an individual’s future travel plans and scheduling preferences. A major component of this effort was to provide this insight without compromising user privacy.

During my masters research with Dr. Bamshad Mobasher at DePaul University, we examined techniques for securing recommender systems. This project focused on identifying weaknesses of existing recommendation algorithms, exploring more robust recommendation techniques, and limiting the impact of attacks on these systems.