SHRUTI KAR

**** ****** **, *** *, Fairborn, OH **324 937-***-****

ac8iis@r.postjobfree.com Shruti-Kar Shruti-Portfolio Shruti-Github EXPERIENCE

Kno.e.sis - Ohio Center of Excellence in Knowledge Enable Computing, Dayton, Ohio January 2017 – December 2018 Graduate Research Assistant

• Collected reliable and relevant data of different modalities (via social media data crawling, web scraping, API interfaces in JSON formats) and extracted knowledge using NLP techniques and Machine learning.

• Developed real-time solutions and provided modules for use as RESTful web API services.

• Techniques- Machine Learning, Natural Language Processing, Text Mining, Information Retrieval, Ontology modeling, Web Development, Data Visualization, Cloud computing, Query processing. EDUCATION

Wright State University, Dayton Ohio August 2016 – December 2018 Master of Science in Computer Science, GPA: 3.857/4.0 Jawaharlal Nehru Technological University, Hyderabad India September 2012 – May 2016 Bachelor of Technology in Information Technology, GPA: 3.25/4.0 PUBLICATION

Kar, S., Al-Olimat, HS . Thirunarayan, K., Shalin, V., Sheth, A., and Parthasarathy, S. “D-record: Disaster Response and Relief Coordination Pipeline”. In Proceedings of the ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities

(ARIC 2018). ACM, 2018.

PROJECTS

Master’s Thesis August 2017 – November 2018

• Developed a Flask application using Javascript, AJAX, JQuery, and Mapbox API. Provided Map visualization of Multi-Scale and Multi-Modal Streaming Data Aggregation and Processing for Decision Support during Natural Disasters.

• Provided features like Need classification ( SMOTE, SVM, Gradient Boosting, Topic Modeling- LDA ), match-making, route guidance (shortest path), situational awareness ( Satellite imagery ), data analysis. Feature Engineering January 2018 – April 2018

• Extracted text features like tf-idf, word embeddings (Word2Vec, FastText, Glove), entity extraction, phrase extraction, sentiment analysis, extracting topics, summarization, sequence labeling and dimensionality reduction. Evaluated against classification algorithms.

Information Retrieval system using Lucene APIs January 2017 – February 2017

• A search engine was designed and implemented using Lucene APIs that indexes the documents in the dataset and query to find hits. Performance of the system was evaluated on the bases of ranking and resource utilization.

• Learned indexing and searching methods, information retrieval models, algorithms for classification and clustering, SVM, latent semantic indexing, link analysis and ranking, Map-Reduce architecture and Hadoop. TECHNICAL SKILLS

• Programming Languages: Python, C++, Java, C

• Web Development: Javascript, HTML5, CSS, JQuery, AJAX

• Frameworks & Libraries: Flask, NumPy, scikit-learn, pandas, NLTK, Gensim, Plotly, matplotlib, ElasticSearch, Keras, TensorFlow, Apache Hadoop, RESTful Web Services, AWS, Git, IBM Watson

• Relational Database Management System: MySQL, SQLite

• Semantic Technologies: Protege, Ontologies, RDF/XML, OWL MOST PROUD OF

Participation

• Led a team of 4 developers to participate in IBM’s CallForCode, a developer’s challenge with the tool DisasterRecord. Tested, evaluated and integrated IBM Cloud services and deployed the tool on IBM Cloud. Talks

• Collection, extraction, evaluation techniques for “Location-centric event ontological modeling” as a guest presenter at Advanced Semantic web class Fall 2018, WSU.

• Extensive talks on word embedding and text feature extraction.