Praveen Radhakrishnan

Graduate Research Assistant at College of Natural Sciences, The University of Texas at Austin
  • Claim this Profile
Contact Information
us****@****om
(386) 825-5501
Location
Austin, Texas, United States, US

Topline Score

Topline score feature will be out soon.

Bio

Generated by
Topline AI

You need to have a working account to view this content.
You need to have a working account to view this content.

Experience

    • United States
    • Higher Education
    • 100 - 200 Employee
    • Graduate Research Assistant
      • Sep 2022 - Present

      Generated insights that help CDC reduce flu transmission by developing Bayesian Hierarchical GLM models to estimate the impact of COVID-19 NPIs(Non-Pharm.Interventions) on Flu cases for U.S 50 states ◦ Improved the reliability of estimation of COVID-19 NPI impacts by identifying optimal lags and parameters using feature engineering, data processing, and statistical tests. Generated insights that help CDC reduce flu transmission by developing Bayesian Hierarchical GLM models to estimate the impact of COVID-19 NPIs(Non-Pharm.Interventions) on Flu cases for U.S 50 states ◦ Improved the reliability of estimation of COVID-19 NPI impacts by identifying optimal lags and parameters using feature engineering, data processing, and statistical tests.

    • Research Assistant
      • Jan 2022 - Present

      ◦ Discovered findings which support Austin Energy to reduce outages in future extreme weather events by optimizing the recall score of anomaly detection pipeline by 35% using ensemble majority voting with Local Outlier Factor, K-means clustering, and LSTM-based Autoencoder with Self-Attention. ◦ Enabled better decision-making for future electricity market planning by enhancing the accuracy of the Random Forest pipeline by 18% through feature importance and nested cross-validation ◦ Discovered findings which support Austin Energy to reduce outages in future extreme weather events by optimizing the recall score of anomaly detection pipeline by 35% using ensemble majority voting with Local Outlier Factor, K-means clustering, and LSTM-based Autoencoder with Self-Attention. ◦ Enabled better decision-making for future electricity market planning by enhancing the accuracy of the Random Forest pipeline by 18% through feature importance and nested cross-validation

    • United States
    • Higher Education
    • 700 & Above Employee
    • Teaching Assistant
      • Jan 2022 - Jan 2023

      1. CE 311K 2. CE 351 1. CE 311K 2. CE 351

Education

  • The University of Texas at Austin
    Masters of Science in Engineering
    2021 - 2023
  • Vellore Institute of Technology
    Bachelor of Technology, Civil Engineering
    2017 - 2021

Community

You need to have a working account to view this content. Click here to join now