Research 









  • Sentiment Analysis of User-Generated Content
          Sentiment analysis is an exciting research area using the latest techniques in natural language processing and machine learning to identify sentiments/opinions expressed in text. For instance, identifying sentiments in Amazon customer reviews can be useful to other customers as well as merchants selling similar items. Particulary, I am interested in indentifying sentiments expressed in a sentence. While other approaches have attempted to solve the problem 'as a whole', I am interested in developing techniques that are applicable to particular categories of sentences. A study on conditional sentences was published in EMNLP 2009. I am also interested in learning how sentiments on topics propagate through social networks.
  • Knowledge extraction from Biomedical Literature
          As the sizes of Biomedical literature databases like PubMed increase, it becomes important to develop algorithms and systems which are able to efficiently and accurately extract information about biological entities. I am interested in applying text mining techniques to find protein-protein interactions in Biomedical literature
  •  Acceleration of Data Mining Applications
          Data mining is the process of gathering useful information from vast amounts of data. As data mining algorithms become increasingly complex, and data sets grow exponentially, the performance of data mining systems suffer. My earlier research focused on understanding the bottlenecks in data mining applications, and discovering hardware/software techniques to improve performance of data mining systems and algorithms.

       Publications

  • Ramanathan Narayanan, Bing Liu and Alok Choudhary. "Sentiment Analysis of Conditional Sentences." Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP-09). August 6-7, 2009. Singapore.
  • Ramanathan Narayanan, Sanchit Misra, Simon Lin and Alok Choudhary. Mining Protein Interactions from Text using Convolution Kernels. In AIBDM 09, held in conjunction with Pacific Asia Conference on Knowledge Discovery and Data mining (PAKDD 2009), April 27-30, 2009, Bangkok.
  • Ramanathan Narayanan, Sanchit Misra, Simon Lin and Alok Choudhary. Mining Protein Interactions from Text using Convolution Kernels. In Intelligent Systems for Molecular Biology (ISMB)[Poster], July 2008.
  • Sanchit Misra, Ramanathan Narayanan, Simon Lin and Alok Choudhary. HiSSS: A High Speed Sequence Search Method for Next Generation Sequences. In Intelligent Systems for Molecular Biology (ISMB)[Poster], July 2008.
  • Sanchit Misra, Ramanathan Narayanan, Daniel Honbo and Alok Choudhary. (Book Chapter) High Performance Distributed Data Mining. To appear in Next Generation of Data Mining, CRC Press.
  • Sailesh Pati, Ramanathan Narayanan, Gokhan Memik, Alok Choudhary, and Joseph Zambreno . Design and Implementation of an FPGA Architecture for High-Speed Network Feature Extraction. In Proceedings of the International Conference on Field-Programmable Technology (ICFPT), December 2007.
  • Ramanathan Narayanan, Berkin Ozisikyilmaz, Joseph Zambreno, Gokhan Memik, and Alok Choudhary. MineBench: A Benchmark Suite for Data Mining Workloads. In Proceedings of the IEEE International Symposium on Workload Characterization (IISWC), October 2006. PDF
  • Berkin Ozisikyilmaz, Ramanathan Narayanan, Joseph Zambreno, Gokhan Memik, and Alok Choudhary. An Architectural Characterization Study of Data Mining and Bioinformatics Workloads. In Proceedings of the IEEE International Symposium on Workload Characterization (IISWC), October 2006.
  • A.Choudhary, R.Narayanan, B.Ozisikyilmaz, J.Pisharath, J.Zambreno and G.Memik. Optimizing Data Mining Workloads using Hardware Accelerators. In 10th Workshop On Computer Architecture Evaluation using Commercial Workloads (CAECW), February 2007.
  • R.Narayanan, D.Honbo, J.Zambreno, G.Memik and A.Choudhary. An FPGA Implementation of Decision Tree Classification. In Proceedings of IEEE International Conference on Design, Automation and Test in Europe (DATE), April 2007.
  • R.Narayanan, B.Ozisikyilmaz, J.Zambreno, G.Memik and A.Choudhary. Quantization Error and Accuracy-Performance Tradeoffs for Embedded Data Mining Workloads. In High Performance Data Mining (HPDM) workshop, to be held in conjunction with ICCS, May 2007.