Saurav Sengupta CV 2019
- 1. Saurav Sengupta [email protected] | https://www.linkedin.com/in/saurav-sengupta/ | https://ssen7.github.io | +1 (434)-284-3794 PROFESSIONAL SUMMARY A graduate student specializing in Data Science with focus on Machine Learning and Deep Learning. Fluent in Python with experience building machine learning projects from scratch. Proficient in Java with previous experience in writing production ready code, deploying to cloud and working in an Agile environment. EDUCATION University of Virginia July 2018-May 2019 Masters of Science in Data Science, 3.96/4 Birla Institute of Technology and Science, Pilani August 2012-May 2016 Bachelors of Engineering in Electrical and Electronics Engineering, 7.2/10 PROJECTS Classify duodenal biopsy images into diseases – Child Health Research Center, UVA • Used Convolutional Neural Networks (CNN) to classify high resolution digitized biopsy images into Celiac Disease, Environmental Enteropathy and Normal tissues. • Used pretrained Resnet50 in our analysis, performs well on diverse set of images. • Achieved close to 98% biopsy level accuracy. Paper accepted in IEEE BHI 2019 conference. • Backed by the Bill and Melinda Gates Foundation and Aga Khan University. Music Genre Classification • Classification of songs into one of 13 genres like rock/pop and country etc. using ensemble models for song features and lyrical data. • Captured data from Million Songs Database. Created AWS EC2 instance, mounted snapshot, ran Jupyter notebooks on EC2 to get data. Used genre data from different Kaggle datasets. • Used Random Forests, SVM, Naïve Bayes for model using song features. Used tf-idf and topic modeling for lyrical data. • Around 58.06% accuracy, close to the original paper on music classification of 61% but we classify more genres. Modeling Brain Wave Activity using Muse™ headset • Used Logistic Regression for real time classification of brain wave signals like alpha waves into left- right, up-down motion. Tested model by moving objects in a game environment. PROFESSIONAL EXPERIENCE Capgemini (Cloud Foundation Services) August 2016 – October 2017 Associate Consultant • Responsible for developing REST based APIs using Spring Boot. • Used cloud platform Pivotal Cloud Foundry® (VMWare) to deploy code to production. • Worked on making CI/CD pipelines and setting up test environments. • Wrote micro-service for sending scheduled emails to parameterized receivers based on the output of a database query using Spring JPA. • Worked on implementing BPMN2 based workflows on Camunda Modeler for business process automation of bank reporting processes. STMicroelectronics July 2015 - December 2015 Trainee • Interned with team designing an embedded neural network based ASIC. • Wrote code to interface Random Access Memory with peripherals like I/O and buses. • Worked in Unix environment and wrote Bash shell and Tcl/Tk scripts for code synthesis and design verification. TECHNICAL SKILLS • Languages: R, Python, Java 7 (Oracle Certified Associate), C, Verilog • Database: MySQL, MariaDB • Packages/Tools: pandas, numpy, sklearn, caret(R), RShiny, TensorFlow, PyTorch, GitHub, Jenkins, AWS EC2, Apache Spark and EMR (Spark Cluster), Pivotal Cloud Foundry® • Operating Systems: Windows, Linux