Shan Suthaharan is a professor of computer science at the University of North Carolina at Greensboro (UNCG). In administrative roles, he served as Director of Undergraduate Studies for more than 10 years and as Interim Head in Fall 2015. He was also Director of Computer Science Division from 2004 to 2006 at UNCG. He played a major role in leading the committee and maintaining ABET accreditation of the undergraduate program successfully at UNCG. In teaching role, he taught both undergraduate and graduate courses in computer networks, cryptography and network security, big data and machine learning, software engineering, and capstone projects. He also supervised many graduate projects and thesis.
Suthaharan is also the author of the high impact and high quality textbook on the state-of-the-art topics of big data analytics and machine learning. Notably this book was reviewed by ACM Computing Reviews and received a “Reviewer Recommended” rating. Suthaharan is also an inventor of a key management and encryption technology that has been patented in Australia, Japan, and Singapore. He also received several research awards and visited several universities, including University of Melbourne (Australia), University of Sydney (Australia), UC-Berkeley, UC-Irvine, and Emory University. He published more than 100 research papers in reputed journals and refereed international conference proceedings.
Suthaharan's research interests fall predominantly under the state-of-the-art themes: big data analytics and machine learning. In big data analytics research, he enthusiastically studies various data characteristics - data heterogeneity, complexity, scalability, and unpredictability - of big data for extracting knowledge to understand the data source that produced the big data. In this research, he also interested in optimizing the big data systems that help big data analytics. In machine learning research, He studies advanced mathematical, statistical, and computational techniques to formulate efficient machine learning models and algorithms that can help accomplish big data analytics research. His research includes the selection and optimization of hyperparameters of machine learning models using Bayesian analysis to make machine learning highly usable in big data analytics in interdisciplinary settings. He is also interested in exploring software engineering models and designs to support big data analytics and machine learning research and applications. The applications that his research focuses on are vast and interdisciplinary in nature, and they include: access control models (data privacy) for big data environment, computer vision and deep learning, intrusion detection in a large-scale computer networks, anomaly detection in heterogeneous networks, and social media data fusion for spatio-temporal traffic safety analytics.
Suthaharan is currently a member of the ACM. He has been a member of the ACM's Computer Science Teachers Association (CSTA) since September 2011. He published and presented his research work at several ACM sponsored conferences, including ACM SIGMETRICS 2014, SIGITE/RIIT 2014, and ACMSE 2018. In 2007, he also co-organized a special session on "Computer and Network Security" at the ACMSE 2007 conference.
To request a single lecture/event, click on the desired lecture and complete the Request Lecture Form.
Differentially Private Logistic Regression and its characterization for big data privacy
This talk will present the topics that enlighten data owners on the selection processes of privacy parameters for differentially private logistic regression (DPLR) techniques. This knowledge will...
Perceptually inspired deep learning: a low-dimensional visual understanding of deep learning's learning strategy
This lecture will discuss the modern deep learning techniques, called the no-drop, the dropout and the dropconnect, in detail using programming examples that can help one to understand the...
Software engineering schema for data science and big data
This talk will present a newly created software development framework called SETh - it stands for software engineering theoretical framework. It comprises six visual models - TBoSE, TCoSE, TDoSE,...
To request a tour with this speaker, please complete this online form.
If you are not requesting a tour, click on the desired lecture and complete the Request this Lecture form.
All requests will be sent to ACM headquarters for review.