Used Infrastructure management tooks like Terraform, Ansible to automate the Infrastructure.
Configure and maintain Amazon Web Services (AWS) Cloud Computing environments.
Setting up alerts, handling overloads on server, performing release engineering.
Machine Learning internship
Generally financial institutions receive different documents
like Pan Cards, Aadhar Cards, Driving Licenses etc. as
identity proofs for their reference. As of now the
information in these documents is being entered manually
into their applications. So, we tried to solve the ongoing
manual entry of fields from physical documents in several
online application portals. Automatic field entry process is
much more reliable than manual entry because humans
generally tend to make mistakes in laborious tasks.
Application developed automatically identifies the type of
document and retrieves the necessary fields in JSON format,
which in turn can be used by clients and can be easily
integrated with their applications.
Summer Research Internship
This project involves the employment of machine learning to
represent satellite imagery and discriminate different
satellites, based on their reflectance signatures. The
objective of discriminating satellites arises from the need
to identify and classify space debris, which essentially
comprises parts of satellites and is a major threat to space
operations. To achieve this, we used pattern recognition
which is, broadly speaking, a basis for machine learning
used to detect patterns in datasets. We developed a pattern
recognition algorithm to identify the probable satellite
IDs. The results we achieved were very satisfactory, as we
were able to develop a method of classifying
satellites/satellite parts using a Tabular Nearest Neighbor
Encoding (TNE) classifier. We completed the project in its
entirety, although there is ample scope for future
modifications.
Information Science Internship
The objective was to modify certain sections and add new
features to the T-Hub website. My internship started by
looking at the data of the general questions people ask in
the contact section of T-hub website and after careful
analysis, my team divided the questions into user groups and
so we thought of automating the replies by implementing
chatbot to the website. Initial weeks were spent in
understanding what are the chatbot frameworks exist in the
present market and what is suitable for our website to give
end user better experience. After that, a custom bot is
chosen and modified according to our needs. Dev team were
impressed with the functionality of the bot and currently
working on the content so that it will be implemented to the
existing website in the upcoming sprints. After chatbot
implementation, I moved on analyzing the backend of the
website. I started working on adding events module to the
website. First software requirements are properly drafted
and planned the functionalities into sprint goals. After
that my team went to them with different options, we went on
to work on the full-scale production of the events page. The
team was impressed with my work. The framework which I used
throughout my internship is Django.
Research and Development Internship
I worked on developing a virtual surveillance monitoring
system using Open CV.
Project Link
Research internship
The goal of the project was to predict the survival of
passengers based on a set of data. We used Kaggle
competition "Titanic: Machine Learning from Disaster" (see
https://www.kaggle.com/c/titanic/data) to retrieve necessary
data and evaluate the accuracy of our predictions. The
historical data has been split into two groups, a 'training
set' and a 'test set'. For the training set, we are provided
with the outcome (whether or not a passenger survived). We
used this set to build our model to generate predictions for
the test set. For each passenger in the test set, we had to
predict whether or not they survived the sinking. Our score
was the percentage of correct predictions.
