dani-amirtharaj Goto Github PK
Name: Daniel Amirtharaj
Type: User
Company: University at Buffalo
Bio: Grad Student
Location: Buffalo, NY
Name: Daniel Amirtharaj
Type: User
Company: University at Buffalo
Bio: Grad Student
Location: Buffalo, NY
Augmented Reality Authentication Mechanism that allows users to authenticate themselves by interacting with a virtual keypad (involving no touch and only by moving the phone).
Aggregated data from Twitter, New York Times and Common Crawl, applied a big data analytic method (Hadoop MapReduce) on data obtained, and built a data visualization product with Tableu.
A program to train an agent on a simple tile based environment using deep Q-networks (Neural Networks and Q-learning) and a program to train an agent to play the Breakout ATARI game.
Programs to detect edges in Images using the Sobel filter, detect points using the Laplacian kernel, detect lines and circles using the Hough transform and detect cursors using template matching.
Programs to recognize MNIST, USPS digits using Neural Networks, SVM and Random forests, and to compare handwriting samples to determine if it were written by the same person on the CEDAR datasets.
Programs to detect clusters in data using GMM and compressed images (Color Quantization) using k-means clustering methods, detect bone fragments in an X-ray image using Segmentation and de-noise binary images using Morphological Image Processing.
Programs to detect keyPoints in Images using SIFT, compute Homography and stitch images to create a Panorama and compute epilines and depth map between stereo images.
Implemented a multicast protocol that allows users to multicast messages to other devices on a network, in an ordered fashion ( FIFO and total orderings), with failure handling on Android.
Improved Multi-threading capabilities (with priority scheduling) and User Program execution in the PintOS kernel.
Sceneform SDK for Android
Python wrapper for Twitter Premium and Enterprise Search APIs
Android Augmented Reality application that uses Google's ARCore to display documents (using pre-generated markers) based on User credentials and permission levels.
Implemented a Dynamo-style key-value storage with Partitioning, Replication, and Failure handling, that provides Availability and Linearizability at the same time across multiple Android devices.
Developed a location based predictive model to forecast occurrences of riots and protests in various Indian cities, (with a minimum lead time of 2 days) using data mined from Twitter and News sources.
A program to show differences between Software 1.0 and 2.0 programming approaches using Neural Networks and a data-driven ranking program (LeToR) with Linear regression and Radial Basis Functions.
Actively maintained, pure Python wrapper for the Twitter API. Supports both normal and streaming Twitter APIs.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.