I am a graduate research assistant at Ohio Center of Excellence in Knowledge-enabled Computing (Kno.e.sis), Wright State University. I am pursuing Master's in Computer Science, advised by Dr.Krishnaprasad Thirunarayan . My interests encompass Machine Learning, Big data, Software Engineering, Natural Language Processing, and Information Retrieval.
365 Joshi Research Center
Wright State University
3640 Colonel Glenn Hwy
Dayton, Ohio 45435
Tel : (937) 986-9256
Email : venkatesh at knoesis dot org|
venkatesh dot edupuganti at gmail dot com
Graduate Studies • August 2015 - December 2017
Masters in Computer Science, Wright State University, Dayton, OH.
Undergraduate Studies • 2010 - 2014
Bachelor of Technology in Information Technology, Sagi Rama Krishnam Raju Engineering college, Andhra University, India. Completed with distinction honours.
The aim of this project is to develop comprehensive and reliable context-aware techniques to glean information about the people involved and their interconnected network of relationships to determine and evaluate potential harassment and harassers. My work focuses on automatically classifying tweets containing curse words posted on Twitter into harassing tweets or not.
I worked as Graduate Research Assistant (January 2016 - December 2017) at Kno.e.sis Center.
I successfully completed an internship (ServiceNow Developer Intern) at Vsoft Consulting, Louisville, KY (June 2016 - August 2016). Developed a service desk and service catalog applications for V-Soft consulting using ServiceNow tool. This application automates all the operations of service desk and service catalog tasks in V-soft consulting group.
I worked as a Graduate Teaching Assistant for CS7100 Advanced Programming Languages in Fall 2017.
Java, LISP, C, C++, R (beginner)
Deep/Machine Learning Tools/Packages
scikit-learn, Weka, TensorFlow (beginner)
Matplotlib, Seaborn, Pandas
MySQL, Oracle SQL, MongoDB
Windows and Linux
IDE and Other Software
Eclipse, Netbeans, PyCharm, Dr.Racket, MATLAB
The source of training data set is kaggle, which contains 3128 data points and 21 features. After experimenting with various combinations of features with various algorithms, the reduced feature set which gives the best result is found. By using reduced feature set, we are able to identify the gender with the less complex algorithm and more accurately.Information retrieval system using Lucene
Developed an search engine using Java and Lucene for the carnﬁeld and medline datasets. Lucene APIs are used to create a index ﬁles for the datasets. Evaluating the performance of the search engines by using the benchmark results for those datasets.Developed Interpreter code using LISP
Developed an Interpreter code for the given grammar using List In Scheme Programming (LISP).