Ankush Jain's Projects
GitHub.io
An implementation of canny edge detector from scratch.
A Dining Concierge chatbot built on Amazon Web Services (AWS). It sends restaurant suggestions for given a set of preferences via SMS.
A benchmark of the different word embedding techniques on fairness and bias in AI models
FairPrep is a design and evaluation framework for fairness-enhancing interventions that treats data as a first-class citizen.
A minimal FARM stack boilerplate / template project to get you started with a Python FastAPI backend, React frontend, MongoDB, and JWT user authentication (via FastAPIUsers).
Join the GitHub Graduation Yearbook and "walk the stage" on June 5.
A low-resource unsupervised image captioning solution by using autoencoder for image feature extraction and NLP for determining the best caption from the pre captioned similar images
An implementation of K-Means clustering algorithm along with the K-Means++ seeding technique from scratch using NumPy.
An explainable and interpretable binary classification project to clean data, vectorize data, K-Fold cross validate and apply classification models. The model is made explainable by using LIME Explainers.
An application to store bookmarks, share them on social media platforms and gather a brief description of the webpage by web crawling. Developed using Laravel web application framework for PHP and Bootstrap 3.2.0.
Implemented a question and answering model for multi-hop questions that requires logical inference or aggregation of information from various parts of the information text (like referring multiple wikis to answer a question)
A generic and semantic profiling of 1159 New York City open datasets using Apache Spark. The generic profiling has been performed using the Spark RDDs and Dataframes. Semantic profiling has been performed using Named Entity Recognition, Soundex, Regex, Ontologies and Clustering.
An analysis of NYC parking violation datasets using PySpark, SparkSQL and MapReduce with Hadoop Streaming
Securodrive is a driving assistant platform built on Amazon Web Services (AWS). It is built to avoid road accidents due to sleepy drivers. This app assists the drivers by applying AI techniques to the live video stream of the driver and generating alerts when the driver appears to be yawning excessively or going in a drowsy state.
A Smart Door Authentication system built on Amazon Web Services (AWS). It performs face recognition on a live streaming video of the doorway and issues an alert to the house owner (via SMS and Email) when a new or old visitor arrives.
An exploratory data analysis of the Stack Overflow 2018 Survey data set with informative data visualizations.
Testing travis-ci
The exploratory data analysis for the road traffic data-sets used in the Traffic Congestion project.
Built a time-series forecasting model for predicting the traffic congestion condition at the road intersections with ARIMA model
A Photo Search Gallery that utilizes AI for speech-to-text transcription and object detection for tagging objects within the images.