Ann Zsilavetz | Department of Computer Science

Computer Science Colloquium: September 5

Posted on September 3, 2014 by Ann Zsilavetz • 0 Comments

The Computer Science Department will be holding the first colloquium of the academic year on Friday, September 5. Dr. David G. Cooper, adjunct professor and instructor of CSC 320: Information Retrieval, will be giving at talk entitled “Affect Detection for a Classroom Computerized Geometry Tutoring System”. Dr. Cooper’s biography and an abstract of his talk can be found below. Please join Dr. Cooper, faculty, and students on Friday in Forcina 408 from 12:30 PM – 1:30 PM. Pizza will be provided and all are welcome to attend.

Abstract:

Minimally invasive sensor technology is mature enough to equip classrooms of up to 25 students with four sensors at the same time while using a computer based intelligent tutoring system. The sensors, which are on each student’s chair, mouse, monitor, and wrist, provide data about posture, movement, grip tension, arousal, and facially expressed mental states. Accurate affect detection can provide an intelligent tutoring system with cues to give feedback to individual students using the system. We discuss a method to clarify classifier ranking for the purpose of affective models. The method begins with a careful collection of a training and testing set, each from a separate population, and concludes with a non-parametric ranking of the trained classifiers on the testing set. The talk will conclude with a discussion of future directions that affective sensing could go for education and beyond.

Bio:

David G. Cooper is a lecturer at Ursinus College in the Math and Computer Science Department and at The College of New Jersey in the Department of Computer Science. He holds an M.S. and a Ph.D. in Computer Science from the University of Massachusetts Amherst. His Ph.D. dissertation focused on computational affect (emotion) detection. He earned his B.S. in Cognitive Science from Carnegie Mellon University. While working as a software engineer at Lockheed Martin, David was on a team to prototype distributed data fusion software for helicopter communication, and was able to test the software while in flight on a Black Hawk helicopter. David’s research has ranged from human robot interaction in the Robot Tug of War project to emotion detection for a computerized geometry tutor for middle and high school students.

MUSE 2014

Posted on August 29, 2014 by Ann Zsilavetz • 0 Comments

TCNJ’s MUSE (Mentored Undergraduate Summer Experience) program runs every summer. This year, Dr. Dimitris Papamichail worked with Joie Murphy, Nathan Gould, and Dylan Wulf – all rising sophomore Computer Science Majors – to complete their specific projects, described below by Dr. Papamichail:

Joie Murphy and Dylan Wulf worked on a project that aims to develop a set of computational tools to aid the computational textual criticism of Latin texts. An ultimate goal of traditional textual criticism is the reconstruction of the archetype of a given work, where various manuscripts from different time periods and from different regions are available as the source of texts for reconstruction; some are only fragments. To tackle this goal, it is important to figure out, by comparing differences and similarities among multiple versions the work, whether one version is derived from another, and whether two or more versions descend from a hypothetical version that is now lost. The students worked on methods to construct and evaluate trees representing the relationships of extant and hypothetical extinct documents.

Nathan Gould and Oliver Hendy (senior Biology major) studied algorithmic issues behind synthetic gene optimization and the approaches that different computational tools have adopted to redesign gene DNA sequences and maximize desired coding features. The students studied an extended bibliography in synthetic biology and gene redesign, and utilized test cases to demonstrate the efficiency of each gene design approach, as well as identify their strengths and limitations of the available tools. This study resulted in a manuscript that has been submitted for publication.

For more information on MUSE, please visit TCNJ’s webpage: http://fscollab.pages.tcnj.edu/muse/

Three CS Students Receive CREU Funding

Posted on August 29, 2014 by Ann Zsilavetz • 0 Comments

Joie Murphy (class of 2017), Kate Evans (2017), and J.R. Villari (2016) have received Collaborative Research Experience for Undergraduates (CREU) funding to perform research during the 2014-15 academic year under the supervision of Dr. Dimitris Papamichail. They will work on a project that aims to create efficient algorithms and computational tools for the construction of optimized, rationally-designed synthetic genes.

The funding is provided by the Computer Research Association’s Committee on the Status of Women in Computing Research (CRA-W) and the Coalition to Diversify Computing (CDC), with support from the National Science Foundation (NSF).

Congratulations to J.R., Kate, and Joie on their achievements!

Dr. Salgian to Present in Athens, Greece

Posted on August 29, 2014 by Ann Zsilavetz • 0 Comments

On September 18, Dr. Andrea Salgian will present her paper “Teaching Robots to Conduct: Automatic Extraction of Conducting Information from Sheet Music” at the 40^th International Computer Music Conference in Athens, Greece. This year’s conference will be jointly held with the 11^th Sound and Music Computing Conference and will run September 14 – 20. Dr. Salgian’s paper was accepted for presentation by the International Computer Music Association (ICMA), an international organization of individual researchers and institutions who are involved in the technical, creative, and performance aspects of computer music.

Coauthored by TCNJ alumnus Laurence Agina and Dr. Teresa Nakra, Associate Professor in TCNJ’s Music Department, the paper was written as part of a project sponsored by the National Science Foundation. Students who majored in Computer Science, Mechanical Engineering, Music, and Interactive Multimedia worked together in a semester-long class to build robots that could conduct a real orchestra and were later utilized during performances by TCNJ’s music ensembles. The culminating paper describes an algorithm that can parse sheet music encoded in MIDI files in order to extract conducting information such as tempo, dynamics, and entrance cues. This process is the robotic equivalent of a human conductor reading the sheet music and deciding which gestures to perform and when. Current TCNJ students continue to work on improving the conducting robots technology in mentored research projects.

For more on the International Computer Music Conference, please visit the conference’s webpage: http://www.computermusic.org/

Author Archives: Ann Zsilavetz

Computer Science Colloquium: September 5

MUSE 2014

Three CS Students Receive CREU Funding

Dr. Salgian to Present in Athens, Greece

Schools