Hemant Sri Varma Dantuluri

Performance Prediction (predict performance of the player)

The aim of the project is to predict the performance of the player given his previous matches.

Predicting the outcomes of sporting events and the performances of athletes represents a natural application for machine learning. Major professional sports such as the NBA, NFL, and MLB contain a significant amount of easily accessible data whose outcomes and player performances tend to be randomly distributed and offer attractive data to predict.
Used several algorithms like Logistic Regression, SVM (Support Vector Machine), NN (Neural Network), Naive Bayes, and Random Forest.

• Identified methods and tools to promote student success in project-based learning.
• Supported staff recruitment initiatives for high-quality program delivery.

Deep Learning-Based Illumination Estimation Using Light Source Classification (Deep Learning)

The aim of the project is to illuminate the image by processing and machine learning techniques.

The goal of this paper is to estimate the illumination arriving at a location in an indoor scene based on a selected pixel in a single RGB image. Visual coherence plays an important role in augmented reality (AR) applications. One of the key factors for achieving visual coherence between virtual and real objects is consistent illumination. In order to render virtual objects with consistent lighting, we need to have information about real-world light sources. Therefore, the estimation of real-world illumination is of high importance for AR.

• Used several machine learning algorithms like CNN (Convolutional Neural Network), VGG19 (Visual Geometry Group)

• Built relationships with external stakeholders, community organizations, and donors to increase program scope.