“If you have a project to pour your learnings into, you will retain the knowledge.” - Richie Norton
July 2021 - July 2023
Tools : Python, Java, C++, Extreme Multi-label Learning
Description : Designed a supervised machine-learning model to perform classification tasks on large-scale data with more than one label.
February - April 2022
Tools : GAN, Python, Pytorch
Description : Generating maps from satellite images by training a GAN and compared with pre-trained Sat2Map.
September - November 2021
Tools : Python
Description : Comprehensive study done for assessing the suitability of clustering techniques for Micro-array Gene Data.
April – May 2021
Tools : RASA API, Python
Description : An interactive chat bot that can spread awareness about COVID-19 among the society.
October - November 2019
Tools : Python
Description : An audio data is defined by various features sampled at various timestamps. The audio signals are clustered using K-means clustering algorithm while the features are extracted using MFC and Chroma features.
October 2019
Tools : Python
Description : A GUI-based application for tweaking images using subsampling and demonstrating Moire's pattern. The Moire's fringes are prominent in radial patterns.
January 2018 – July 2019
Supervisor : Prof. Atul Gupta (Professor, CSE, IIITDMJ)
Description : The use cases are one of the methods to capture the functional requirements. The main advantage of utilizing UML based use cases is that they are popular in the industry. Moreover, they are slightly more formal as compared to that of textual requirements and equally preferred by the business people and the IT people. Another source of functional requirements are business rules. Since, these business rules are available prior to the requirements elicitation, reusing it in IT backdrop will reduce the effort to an extent. The research is focused on examining and ameliorating the notions of automated test case generation in vogue. The prime accentuation of the dissertation is that assurance regarding the conformance of the final product to that of user requirements can be automated to an extent, without or with minimal human intervention.
January – April 2018
Collaborator : Mr. Shewale Rohan Sanjay
Tools : Python, CNN
Description : User feedback is imperative in improving software quality. Most of the apps or websites now a days have a user feedback system, where users can collaborate with their service/product and make it better by sharing resourceful feedback. These reviews written by the users represent a rich source of information for the app vendors and the developers, as they include information about bugs, ideas for new features, or documentation of released features. The problem is defining different techniques to classify app reviews. A generalized system is proposed which can be used in a similar feedback system, which can classify the reviews in six toxic behaviors, which are: toxic, severe_toxic, obscene, threat, insult, and identity_hate. These classification enable to extract resourceful user feedback.
September – November 2017
Tools: C#, Naive Bayes
Description : Users spend plenty of time on reading news, discussing events and posting messages on social networks. Social spam is unwanted , undesirable content appearing on social networking services and/or any website with user-generated content (comments, chat, etc.). Popularity of social networks attract a significant amount of spammers who continuously expose to malicious behavior; post messages containing commercial URLs; Repetitive Tweets; and so on.
September – December 2015
Tools: C#, .Net (v4.5), MS SQL Server 2014
Description : In this day in age, booking everything from hotels and flights to restaurant reservations all can be done in a commonplace, not to mention convenient. The patients, in current age favor the system that would let them to book the appointments with the doctors throughout the globe and thus, restricting the geographical constraints by providing access to healthcare services. The online booking system is also highly favored by hospitals, doctors, and their staff as it saves them substantial time for scheduling appointments and allows them to allocate resources to other, more pertinent areas. The core goal is to provide a booking process which is easy to use and not time consuming and to build a system that will ease the process of booking appointment of the doctor.
September – November 2013
Tools: C#, .Net (v4.0), MS SQL Server 2008
Description : The people need a space where they can share their own ideas, experiences with others. The platform should provide access throughout the globe anytime. The audience should not be limited due to discrimination on the basis of age, caste, creed, culture, language spoken, field of specialization, marital status, income earned, profession or demographic locations. The surveys or polls are the mirror of society. It is a way of knowing the likes and dislikes of the people. It reflects the views of the layman about the topic raised. The responsibility of conducting such surveys in not limited to publications. The project looks on providing an online platform to serve the aforesaid issues.
January – April 2013
Tools: C#, .Net (v3.5), MS SQL Server 2005
Description : An online auction project that holds online auctions of various products on a website and serves sellers and bidders accordingly. The system is designed to allow users to set up their products for auctions and bidders to register and bid for various products available for bidding.