Sign in

Engineering Data

Syracuse, NY
March 19, 2019

Contact this candidate



*** ********* ******, ********, *** York 13210

+1-315-***-**** EDUCATION

Masters of Science, Syracuse University May 2019

Department of Computer Engineering GPA: 3.33/4

IBM Data Science Professional, CourseEra Mar 2019

Bachelors of Science, Vidyavardhaka college of Engineering May 2017 Department of Electronics & Communication Engineering GPA: 3.8/4 TECHNICAL SKILLS

Programming Languages: Python, C++, C, SQL, MATLAB, Verilog Frameworks/Models: Numpy, Pandas, Matplotlib, NLTK, Keras, Scikitlearn, Random Forest, Logistic Regression, Convolutional Neural Networks, K means clustering, Ca e, Tensor

ow, Pytorch, Deep Neural Networks, K Nearest Neighbors EXPERIENCE

Madog Co - Hardware Engineering Intern - Syracuse, NY Jun 2018- Aug 2018

Assisted in building a 3D printer for ceramic printing based on Ytech-3D design

Successfully programmed the Arduino using C++ to print 3D ceramic objects ACADEMIC PROJECTS

Quality Product Recommendation Mar 2019

Employed implicit collaborative ltering on retail-rocket data set of size (2,756,101) obtained from Kaggle

Applied matrix factorization model using keras and obtained MSE of 0.56

Increased the accuracy by further implementing Neural Network Model using fully connected Dense layers, ReLu activation function and obtained an MSE as low as 0.05. Eye Gaze Tracking Dec 2018

Analyzed the facial data of over 1400 people, collected from Gaze Capture

Python library, Pytorch was incorporated for training Convolutional Neural Network called iTracker

Tracked the performance and accuracy with and without ne tuning and augmentation

Achieved an accuracy of 74% in detecting eye gaze Activity recognition using Smart Phone Mar 2019

Collected sensor reading data set of size (7653, 563) from Kaggle

Performed feature engineering using principal component analysis to nd the most contributing features

Converted the time series data into a DataFrame and fed the Classi ers for comparing Four Machine Learning Models

(SVC, LR, KNN, Random Forest)

Logistic Regression resulted in delivering highest Accuracy of 83.5% Using Machine Learning to predict Exoplanets in outer space Mar 2019

Incorporated TensorFlow’s BoostedTressClassi er on Kepler dataset of (5680,3198) from kaggle

Created 100 trees by bucketizing the features and achieved an acurracy of 96% in detecting Exoplantes RELEVANT COURSES AND PROJECTS

Projects Courses

Poppy Humanoid Robot Introduction to Arti cial Intelligence Implementation of Dijkstra’s Algorithm in O(nlogn) Advanced Data Structures using C++ Automatic Street Parking Assist Digital Electronic Circuits Median Housing Price Prediction for California Machine Learning Engineer

Contact this candidate