Research Intern

Xerox Research Center Europe, France

Advisor : Dr. Matthias Galle

Worked on inferring templates in documents using grammar induction algorithms. We used document classification as evaluation metric for usefulness of grammar learnt from documents.

Research Assistant

Coral Lab, University of Maryland Baltimore County

Advisor : Dr. Tim Oates

Developed Symbolic Trajectory Analysis and VIsualization System (STAVIS), a system analysis of trajectories using grammar induction algorithm and SAX representation. Also worked on project for noticing changes in the utility oflearned knowledge as detecting changes in streaming data. This will be helpful in monitoring performance of neural machine learning algorithms.

Denoising Time Series Data Using Asymmetric Generative Adversarial Networks

Sunil Gandhi, Tim Oates, Tinoosh Mohsenin, David Hairston
In Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2018.

Visual Entity Linking

Tilak Neha, Sunil Gandhi, Tim Oates
In International Joint Conference on Neural Networks (IJCNN), 2017

An EEG Artifact Identification Embedded System Using ICA and Multi-Instance Learning

Ali Jafari, Sunil Gandhi, Harsha Konuru, David Hairston, Tim Oates, Tinoosh Mohsenin
In Ultra-efficient Approaches Enabling Long-term, Mobile EEG for Brain Monitoring Session at IEEE International Symposium on Circuits & Systems (ISCAS), 2017.

RPM: Representative Pattern Mining for Efficient Time Series Classification

Xing Wang, Jessica Lin, Pavel Senin, Tim Oates, Sunil Gandhi, Arnold Boedihardjo Crystal Chen, Susan Frankenstein
19th International Conference on Extending Database Technology (EDBT). 2016

Robust Semantic Text Similarity Using LSA, Machine Learning, and Linguistic Resources

Abhay Kashyap, Lushan Han, Roberto Yus, Jennifer Sleeman, Taneeya Satyapanich, Sunil Gandhi, Tim Finin
Language Resources and Evaluation, pp. 125-161, v50, n1, Springer, March 2016

A generative model for time series based on multiple normal distributions

Sunil Gandhi
Masters Thesis

A Generative Model For Time Series Discretization Based On Multiple Normal Distributions

Sunil Gandhi, Tim Oates, Arnold Boedihardjo, Crystal Chen, Jessica Lin, Pavel Senin, Susan Frankenstein, and Xing Wang
In Proceedings of the 8th Workshop on Ph.D. Workshop in Information and Knowledge Management (PIKM '15). ACM, New York, NY, USA, 19-25.

Time series anomaly discovery with grammar-based compression

Senin, Pavel, Jessica Lin, Xing Wang, Tim Oates, Sunil Gandhi, Arnold P. Boedihardjo, Crystal Chen, Susan Frankenstein
In Proceedings of 18th International Conference on Extending Database Technology (EDBT). Brussels, Belgium. Mar 26, 2015

Meerkat mafia: Multilingual and cross-level semantic textual similarity systems

Kashyap, Abhay, Lushan Han, Roberto Yus, Jennifer Sleeman, Taneeya Satyapanich, Sunil Gandhi, and Tim Finin
In Proceedings of the 8th International Workshop on Semantic Evaluation, pp. 416-423. Association for Computational Linguistics, 2014

GrammarViz 2.0: a tool for grammar-based pattern discovery in time series

Senin, Pavel, Jessica Lin, Xing Wang, Tim Oates, Sunil Gandhi, Arnold P. Boedihardjo, Crystal Chen, Susan Frankenstein, and Manfred Lerner
In Machine Learning and Knowledge Discovery in Databases, pp. 468-472. Springer Berlin Heidelberg, 2014

Motif discovery in spatial trajectories using grammar inference

Tim Oates, Arnold Boedihardjo, Jessica Lin, Crystal Chen, Susan Frankenstein, Sunil Gandhi
In Proceedings of ACM International Conference on Information and Knowledge Management (CIKM). San Francisco, CA. Oct 27, 2013

On-demand loading of code in MMUless embedded systems

Sunil Gandhi, Swapnil Khorate, Chetan Pachange, Mandar Vaidya
Undergraduate Thesis at Pune Institute of Computer Technology May 2012.