College of Staten Island
 The City University of New York
 
  
    
  Susan Imberman
Associate Professor
Computer Science

Susan Imberman
Associate Professor

Office : Building 1N Room 208
Phone : 718.982.3273
Fax : 718.982.2856
susan.imberman@csi.cuny.edu


Degrees :
BA, Queens College
MS, College of Staten Island
M.Phil, Graduate Center of the City University of NY
Ph.D., Graduate Center of the City University of NY


Biography / Academic Interests :
Susan Imberman, a professor of Computer Science at the college, has taught here since 1986. She is known for her infusion of low platform intelligent robots into the computer science curriculum.  Students are introduced to robots from their very first computer science course.  In Professor Imberman's Artificial Intelligence course, students build robots with the intelligence to learn.  Her enthusiastic teaching style and rapport with students has encouraged many of them to participate in the college's robot soccer team.  Professor Imberman is also advisor to the Computer Science Club.  She has involved the club in service projects such as maintaining a student server and tutoring, along with many extracurricular educational experiences including robot soccer, and trips to the Trenton Computer fair.   Professor Imberman is an expert in the field of data mining.  Her course in this area is well attended at the CUNY graduate center.  Professor Imberman's students gain much from her high energy teaching style and her expertise in the fields of robotics, artificial intelligence, and data mining.  

Scholarship / Publications :
Professor Imberman's research interests span several areas within the domain of Artificial Intelligence. Her most notable work deals with the use of data mining to analyze medical data.  Data mining is a field that deals with the automated analysis of large amounts of data. Most medical data sets are not as large, with respect to the number of records, as that which is usually analyzed using data mining. Notwithstanding, medical data is highly dimensional, containing large numbers of variables. Thus, data mining techniques are well suited for finding hidden patterns in medical data.  Her papers dealing with surgical risk factors in accommodative esotropia (crossed eyes) have appeared in several highly ranked medical and computer journals. Dr. Imberman has also received the Computer Measurement Group's best journal article award for her paper titled, "The KDD Process and Data Mining For Computer Performance Professionals." Her second research focus involves the use of low platform (inexpensive) intelligent robots to teach programming and Artificial Intelligence concepts.  Dr. Imberman has been able to incorporate robots into the computer science curriculum in new and innovative ways.