Student Spotlight July 2016

    Tegjyot (TJ) Singh Sethi

    TJ received his Bachelor of Technology degree in Computer Science and Engineering from GITAM University, India in 2012. He had multiple job offers in India but instead decided to pursue his graduate studies, as he was passionate about research. In 2013, TJ graduated with a Master of Science degree in Computer Science from the University of Louisville JB Speed School. His thesis topic was titled “The GC3 Framework: Grid Density Based Clustering for Classification of Streaming Data with Concept Drift”, which he completed under the guidance of Dr. Mehmed Kantardzic. TJ began his PhD studies under Dr. Kantardzic in 2013 and they been working in the Data Mining Lab ever since. Over the past two summers, 2015 and 2016, TJ has had the opportunity of interning at Google which has been a valuable learning experience.

     

     

    Interview:

    1. What brought you to the University of Louisville?

    I became interested in data mining and predictive analytics through research in my undergrad studies. I wanted to pursue my interest further and as such applied to the University of Louisville, which not only had a graduate level certificate in Data Mining but also had multiple faculty members working actively in this area. The Data Mining Lab, and especially Dr. Kantardzic's work in this domain, was a motivating factor in my decision process.

    2. Specific areas of research (how you chose this research, why it interested you):

    I am working in the area of Dynamic Streaming Data Mining, where data can keep changing constantly so the models need to adapt over time. This general area was introduced to me when I first arrived at UofL and I found the problem challenging and interesting. I am developing models for machines to be aware of their own limitations and ask for limited human assistance, over time, to provide continuous prediction. Recently, I also started applying these models to the area of cybersecurity systems and found promising results towards safer machine learning.

    3. How would you describe your area of study/ specific research to your grandmother?

    I am teaching computers a valuable life lesson: times change, and they need to keep up.

    4. What made you go into this field of study?

    I worked on Swarm Optimization techniques as part of my undergrad research and was fascinated by how we could incorporate behavior of ants and birds to make better predictive machines. I wanted to explore this area more and found that we have barely scratched the surface when it comes to data mining research. I wanted to contribute my bit to the development of this field.

    5. Awards, honors, publications:

    Awards:
    IEEE Outstanding Student Award, University of Louisville, 2016
    Finalist in Linkedin Economic Graph Challenge, 2015
    University of Louisville Doctoral Fellowship Award, 2013-2015
    Winner of HackKentucky 2014
    CECS Master of Science Award, University of Louisville, 2013
    Publications:
    Sethi, Tegjyot Singh, Mehmed Kantardzic, and Hanquing Hu. "A grid density based framework for classifying streaming data in the presence of concept drift." Journal of Intelligent Information Systems 46.1 (2016): 179-211.
    Sethi, Tegjyot Singh, and Mehmed Kantardzic. "Don’t pay for validation: Detecting drifts from unlabeled data using margin density." Procedia Computer Science 53 (2015): 103-112.
    Sethi, Tegjyot Singh, et al. "An ensemble classification approach for handling spatio-temporal drifts in partially labeled data streams." Information Reuse and Integration (IRI), 2014 IEEE 15th International Conference on. IEEE, 2014.
    Sethi, Tegjyot Singh, et al. "Cluster Analysis & Pso for Software Cost Estimation." Information Technology and Mobile Communication. Springer Berlin Heidelberg, 2011. 281-286.

    6. How do you think this advanced degree will change your role in society?

    Data science as a discipline has immense potential. However, its usefulness is often shrouded by the hype/buzz that it receives. I believe that this degree is teaching me discipline and perseverance, which is crucial to making a principled contribution to this field.

    7. Long term goals/aspirations?

    I want to be an expert data scientist, who can derive intuition and develop models over a variety of data at a global scale. I want to be able to use data mining to solve social problems and create a better living for everyone around the world.

    8. What accomplishment, academic or otherwise, are you most proud of?

    I am most proud of being able to make progress in my PhD studies. Even at times when it would have been easy just to give up, continually looking for inspiration and staying motivated is definitely something I am thankful for.

    9. What has been your favorite part of the graduate school experience at UofL?

    UofL has a vibrant and welcoming community of awesome people, which has made the entire experience wonderful.  Go Cards!!

    10. What do you feel is the greatest challenge that graduate students face and how have you dealt with this challenge?

    As an international graduate student, it is challenging to start from scratch: socially, academically and professionally. It is important to develop a support group at school, at home and also of peers across the globe. This takes time and effort, but looking back I feel that it is an important part of the experience and is essential for doing well graduate school.

    11. Family Life:

    My parents and my sister (Ankita) live in Visakhapatnam, India. My extended family members live in Chicago; my cousins (Angad and Jia) are always fun to hang out with (as you can see from the picture). I am thankful for everyone’s love and encouragement, and I owe all of my achievements to the support of my family.

     


    Fun Facts
    A talent you have always wanted: I have always wanted to learn to make the perfect cup of cappuccino.
    Favorite book: The Alchemist, is one of my earliest favorites.
    Favorite quote: Not a conventional source but: “Life is a lesson, you learn it when you're through” – Limp Bizkit
    Role Model: My Dad, for leading by example and for teaching me the value of humility.
    Favorite Vacation Destination: Home (Chicago/Visakhapatnam)
    If you weren’t in graduate school, what would you be doing now? Reading papers and trying to do research on my own, while applying for graduate school.