Projects

This page includes some of my personal projects. I have skipped my work related projects, you can find those in my resume.

The Society Fair

A website for events of societies under CSED, TIET along with attendance, details and media for each event. Also, an interface for students to contact society admins.

User Section: Home User Section: Society View User Section: Events_View User Section: Open Event User Section: Poster View User Section: Event attendance User Section: Event attendance_2 User Section: Event Images Admin Section: Coordinator Login Admin Section: Problem Dashboard Admin Section: Adding new event Admin Section: Adding new event_2 User/Admin Section: Contact
Visit website: sf.thapar.edu

Detection of Atrial Fibrillation of heart from a Single Lead ECG recording

The goal of this project was to implement a deep-learning algorithm that classifies electrocardiogram (ECG) recordings from a single-channel handheld ECG device into four distinct categories: normal sinus rhythm (N), atrial fibrillation (A), other rhythm (O), or too noisy to be classified (~). This model was guided by the paper Convolutional Recurrent Neural Networks for Electrocardiogram Classification by Zihlmann et al. which was published following the authors’ contribution to the 2017 PhysioNet/Computing in Cardiology (CinC) Challenge. I followed Andreas Werdich’s implementation of the above paper. I improved the results of this model by penalizing weights that apply to higher frequency classes inorder to balance all the classes and reduce prominent peaks in validation accuracy.

Fallingrain.com Data Scraper

A web scraper written in python that scrapes fallingrain.com and dumps a CSV file containing State, City, Latitude, Longitude, Elevation and Estimated Population for every place in India.

View Github Repository

User Attendance & Activity Monitoring System

A website that monitors a visitor’s activity, prints exit slips for day scholars and links this data with student IDs. This website is currently live in Nava Nalanda Central Library, TIET.

Smart Car Parking System

Focused on making the process of finding a parking spot, a breeze. An array of sensors to detect the car, a machine learning algorithm for finding an optimal parking slot in real time, Google Maps API integration and Digital Image Processing for car recognition. This project is under development.