CSEE professor Hillol Kargupta featured in Journeys to Data Mining
CSEE professor Hillol Kargupta is one of fifteen Data Mining experts featured in a new book: Journeys to Data Mining: Experiences from 15 Renowned Researchers (Springer, 2012).
The book assembles the career journeys of fifteen experts in the field, answering questions like: “What are your notable success stories”, “What did you learn from your failures”, and “How would you advise a young researcher to make an impact?” Written in a narrative style, the book is a great tool for current Ph.D. students who are trying to find their own success in the field of Data Mining.
Kargupta, who has been teaching at UMBC since January 2001 is also the co-founder of AGNIK INC, a data analytics company for mobile, distributed, and embedded environments. An IEEE fellow, Kargupta has published more than 100 peer-reviewed articles. He has a host of awards to his name including the IBM Innovation Award (2008), an NSF CAREER award in 2001 for his research on ubiquitous and distributed data mining, and 2010 IEEE Top-10 Data Mining Case Studies Award for his work at Agnik. More information about Dr. Kargupta’s research accomplishments can be found on his website.
In the book, Kargupta’s personal account is called: “Making Data Analysis Ubiquitous: My Journey Through Academia and Industry.”
His account begins:
“It was one of those late fall mornings in Urbana. I was working on some of the final pages of my dissertation. I got a note from Mike Welge of the National Center for Supercomputing Applications (NCSA) whom I came to know during the course of my work with my Ph.D. advisor David Goldberg. Mike was leading a data mining project for Caterpillar, the US heavy duty equipment manufacturer. Caterpillar clients bring their equipment to their worldwide service center for maintenance and repair. Their service staff types in short descriptions of the work done on the equipment and saves that information in the computer. Caterpillar wanted to link this data from different service centers, analyze, and identify which equipment and parts are failing frequently and related decision support tasks. The problem became more challenging because their employees often used different abbreviations and spelled names incorrectly to describe the work done on the equipment. Mike wanted to address this as an unstructured text data mining problem and asked me if I would like to collaborate. I joined their meetings and started thinking about the problem in a bigger context.”
You can continue reading on Springer’s website.
Posted: September 28, 2012, 11:50 AM