RezScore - User Profile

Services
Community
- Blog
- Success Cast
Developer
- API
- Technical Interview Prep
Account
- Login
- Register

We are going to show you a profile for a few seconds.

When we are done we will ask you a few questions about the resume.

Don't worry about remembering everything, we just want you to gauge your first impression of this job seeker.

The timer on the right will count down for you.

Click here when you are ready:

Please Tell Us What You Remember About This Resume
140 Characters or Fewer

None

kaustubhsivalenka@gmail.com

Kaustubh sivalenka<BR>(+1) (XXX) XXX-XXXX<BR>XXXX@XXXX.XXX<BR>Stony Brook, New York<BR>https://github.com/ssivalenka<BR>EDUCATION<BR>Stony Brook University, Stony Brook, New York<BR>Graduation: Spring (May) 2020<BR>Master of Science, Computer and Information Sciences<BR>GPA 3.5/4.0<BR>Courses Computer Vision, Big Data Analytics, Natural Language Processing,<BR>Database Systems, Analysis of Algorithms, Probability and Statistics<BR>Mahindra Ecole Centrale, Hyderabad, India<BR>August 2014 - August 2018<BR>Bachelor of Technology (B.Tech), Computer Science and Engineering<BR>GPA - 8.80/10.0<BR>EXPERIENCE<BR>Dept. of Bio-Medical Informatics, Stony Brook University<BR>January 2019 - Present<BR>Graduate Research Assistant<BR>• Developed a gradient-based adaptive sampling prediction scheme for precise discovery of tumor<BR>regions in tissue images (WSI).<BR>• Currently, integrating this prediction scheme with data pipelines based on InceptionV3 and<BR>VGG-19 networks.<BR>UNICEF - Office of Innovation, New York<BR>June 2019 - September 2019<BR>Machine Learning Intern - Satellite Imagery Analysis<BR>• Land Cover Mapping - Developed a U-Net based segmentation analysis pipeline to identify<BR>land resource usage from satellite imagery. Recorded validation f1-score of 88.53%.<BR>• Poverty mapping - Developed a transfer learning pipeline using VGG-16 to assess poverty<BR>distribution from satellite imagery. Recorded Spearman Correlation of 0.47.<BR>ISRO, National Remote Sensing Center, India<BR>September 2017 - May 2018<BR>Research Assistant - Predicting Primary Crop Footprint from Satellite Images.<BR>• Developed a ResNet (Convolutional Neural Network) based feature extractor and recorded a<BR>prediction accuracy of 97.43%. This model can also be adapted to novel satellite scenes.<BR>Kohli Center on Intelligent Systems, India<BR>May 2017 - July 2017<BR>Research Intern - Dynamic Winner Prediction in Twenty20 cricket<BR>• Investigated this problem using supervised learning techniques (KNN, SVM, RF, XGBoost).<BR>• Random Forest Classification yielded the highest prediction accuracy of 75.68%.<BR>TECHNICAL STRENGTHS<BR>Programming/ Scripting Languages<BR>Python, Java, C, MATLAB, JavaScript, Bash<BR>Technologies<BR>Tensorflow, PyTorch, Spark, MySQL, AWS, Hadoop, D3.js<BR>Projects<BR>Data Visualization Dashboard: Visual Analysis of Security Incidents<BR>Data visualization, Time Series analysis - (D3.js, Flask)<BR>• Built a web framework to analyze and visualize various attributes of security incidents.<BR>• ARMA based time-series forecasting also informs the possible trend of future incidents.<BR>Crop Yield Prediction - Using Deep Learning<BR>Big Data Analytics, Machine Learning - (Spark, Tensorflow)<BR>• Developed a data pipeline to estimate future crop yield from satellite data (dataset size: 62 GB).<BR>• Data pre-processing to extract histogram features from satellite data was performed using Spark.<BR>• A stacked-two layer LSTM network was used for predicting crop yield from the histogram features.<BR>Publication<BR>1. Sasank Viswanadha, Kaustubh Sivalenka, Madan Gopal Jhawar, Vikram Pudi. ”Dynamic Winner<BR>Prediction in Twenty20 Cricket: Based on Relative Team Strengths.” Workshop of Machine Learning in<BR>Sports Analytics 2017 at the European Conference for Machine Learning.<BR>Achievements<BR>• Recipient: Platinum and Team Leader Award - Apollo AI and IEEE Scholarship for Machine Learning

How We Protect Your Privacy

0

Following

0

Followers

452

Profile Views

© 2026 RezScore. Use of our site is governed by terms and conditions.

Privacy Policy
Terms of Use
API