Graduate student studying Masters in computer science at UT Arlington with focus on Data Mining, Spatio-temporal Databases and Software Testing. Skilled in python and Java with hands on experience using scikit-learn, Tensorflow and pandas for Data analysis. Excited about opportunities to utilize machine learning in real world context.
| Programming Languages | Python, Java, SQL, BASH, C++, HTML, CSS, Javascript |
|---|---|
| Machine Learning and statistics | Scikit-Learn, TensorFlow, pandas |
| Databases and Visualization | Oracle, MySQL, QGIS |
| Focus | Machine Learning, Data Mining, Spatio-Temporal Databases |
Implemented various machine learning algorithms from scratch just using NumPy including regression, classification, and clustering algorithms like KNN, Gaussian Naïve Bayes, Logistic Regression, Adaboost, Decision Trees, Hierarchical Clustering, K-means, locally weighted linear regression, stochastic gradient descent etc.
Evaluated performance of various algorithms on synthetic datasets using K-fold cross validation, Leave-one-out cross validation.
Programming Language: Python
Performed PCA-based image recognition to classify volcanoes on venus: using PCA-based features and a k-Nearest Neighbour classifier to classify the certainty that there is a volcano in the picture from the Volcanoes on UCI Venus image dataset.
Used ensemble methods like bagging to increase performance.
Evaluated performance of the models using k-fold cross validation.
Programming Language: Python
Analysed and visualized traffic conditions like delays, accidents, and traffic jams in various counties in Dallas Fort Worth Metroplex using WAZE event dataset, Counties Maps and road maps using SpatiaLite and QGIS tools.
Computed and visualized various geometric locations and spatial attributes like area,distance etc using spatial functions.
Analysed temporal events like traffic flow throughout the day in various locations across DFW Metroplex.
Programming Language: SQL
Visualization Tool: QGIS
Implemented an end-to-end streaming content management system with user interface where users can interact with the database to obtain information regarding region and age-group specific user preferences, streaming demand based on time and region.
Programming Language: SQL and Javascript
Implemented various sorting algorithms from scratch using Python including Selection sort, Bubble sort, Insertion sort, Merge sort, Quick sort, Quick sort with Median and Heap sort
Evaluated the run time complexity of various sorting algorithms and identified best sorting algorithm with large set of data.
Programming Language: Python
Implemented web page for Portfolio using github pages.
Programming language: HTML5 and CSS
