Prof. Ashfaq Khokhar


Biographical Sketch:
Ashfaq A. Khokhar received his B.S. degree in electrical engineering from the University of Engineering and Technology, Lahore, Pakistan, in 1985 and his Ph.D. in computer engineering from University of Southern California, in 1993. After spending two years at Purdue University as a Visiting Assistant Professor, in 1995, he joined the Department of Electrical and Computer Engineering at the University of Delaware and served at assistant and associate professor levels. Dr. Khokhar joined University of Illinois at Chicago (UIC) in Fall 2000 and served there till Summer 2013 as Professor and Director of Graduate Studies. Since Fall 2013, he has joined Illinois Institute of Technology, where he currently serves at the rank of Professor and Department Chair in the Department of Electrical and Computer Engineering.

Dr. Khokhar has published over 210 technical papers in refereed conferences and journals in the areas of parallel computing, image processing, computer vision, and multimedia systems. Dr. Khokhar is a recipient of the NSF CAREER award in 1998.  He has received numerous outstanding paper awards in international conferences. Dr. Khokhar was elevated to be an IEEE Fellow in 2009 for his contributions to multimedia computing and databases. His research interests include: search and retrieval for Internet data, multimedia systems and communication, multidimensional spatial databases, data mining, health informatics, computational biology, and high performance computing.


Title:
Electronic Health Record Systems: An Ideal Platform for Studying Big Data Challenges


Summary: Owing to rapid developments in digital technologies, the use of electronic media to capture, process and accumulate information is witnessing extraordinary developments. The stored information is reaching zeta-bytes, whereas our capability to analyze such large amounts of data lags far behind its rate of growth. One of the impediments is the high dimensionality of the datasets. This includes information in different application areas, such as in electronic health records (EHRs), biology, astronomy, medical imaging, video archiving, and web data. Different data mining techniques have been used to extract knowledge embedded in some of these data sets, albeit with limited success.

One example of high-dimensional and sparse dataset is the electronic health record (EHR) system. The EHRs comprise thousands of variables (high dimensionality), but for a given patient, only a few of them are tracked (sparseness). The importance of a specific variable present in a record depends on the context it has been used. Using data mining techniques for analysis of these datasets can be extremely advantageous. The ability to predict the condition of the patient during a sickness episode is vital for provision of cost-effective care. This depends on diverse factors, such as patient’s other health issues (if any), the care provided, and different psychological and personal characteristics.

In this talk, we will outline issues related to big data analytics while using nursing care data as an example dataset. We will identify challenges posed by such datasets and also point out how lessons learnt can be applied towards big data analytics in general.