HELLO, I'M
Harshinee Sriram
Undergraduate Artificial Intelligence Researcher and Author
Harshinee Sriram
Computer Science and Engineering student at SRM Institute of Science and Technology, Kattankulathur
About
MY BACKGROUND
If there is something that is consistent with nature and life, it is pattern, symmetry, and the fluidic passing of infinite moments. Ever since I was a little girl, I was drawn to creating something that resonates with all that life is about. Be it music, dance, art, or advancement. My music and writing taught me to be observant, tactile, and to dream. My dance helped me understand vulnerabilities, touch, and confidence. And, my Computer Science education taught me to believe in the seemingly impossible and to create something that is beautiful, helpful, and in harmony with the picturesque series of fleeting moments that we call the Human Life.
Do contact me if you would like to discuss the abstract, the unique, and the revolutionary over a cup of cranberry tea and the Marvel Cinematic Universe (read: definitely the Guardians of the Galaxy).
Education
WHAT I’VE LEARNED
2020 - 2022 (Expected)
The University of British Columbia, Vancouver
Master of Science (MSc) in Computer Science [Thesis]
​
2016 - 2020 (Expected)
SRM Institute of Science and Technology, Kattankulathur
Bachelor of Technology, Computer Science and Engineering
CGPA: 8.89/10 | SGPA (6th): 9.121/10
2014 - 2016
Delhi Public School, Nerul West, Mumbai (CBSE)
Science (Physics, Chemistry, and Mathematics) with Computer Science (Data Structures and C++ with SQL concentration)​
2013 - 2014
Ryan International School, Kharghar, Navi Mumbai (ICSE)
Social and theoretical sciences with Computer Science (JAVA)​
Clubs
WHERE I’VE CONTRIBUTED
February 2019 - Present
Association for Computing Machinery (ACM) - SRM Chapter
Technical domain revolving around Artificial Intelligence
August 2016 - January 2019
Aakash Research Labs (IIT Bombay) - SRM Branch
Android Application Developer
August 2017 - April 2018
SRM Spectrum Official Magazine
Reporter and Journalist
Internships
WHERE I’VE WORKED
December 2019 - March 2020
The University of Auckland, New Zealand
Visiting Research Scholar working under Professor Helen Sword with a stipend of NZD $500/week.
October 2019 - December 2019
Indian Institute of Science (IISc), Bangalore
AI Intern in the field of Real-time Reinforcement Learning for the NeurIPS Challenge 2019.
June 2019 - July 2019
Artificial Intelligence Intern in the field of Automation
December 2018 - January 2019
The National University of Singapore (NUS)
Intern for Big Data Analytics using Artificial Neural Networks
Skills & Languages
WHAT I BRING TO THE TABLE
C & C++
Python
Traditional JAVA
R Programming
Data Science
Human-Computer Interaction
Machine Learning
Neural Networks and Deep Learning
Creative and Report Writing
August 2017 - April 2018
SRMByAG News Broad Casting system
Android Application Developer
Projects
WORK I HAVE DONE TILL DATE
Distracted Driver Detection [December 2018]
This is a Computer Vision project that has been solved via various machine learning frameworks in order to identify the most efficient among them. The input comprises images taken from a camera in a car that captures the movements of the driver. It then determines if the driver is distracted and also specifies the class of distraction (such as Drinking, Talking on the phone, and Reaching behind).
The preprocessing for some of the frameworks was done using R (to convert the background pixels to black using filters, and then using dplyr and EBImage to create filters for detecting a wide array of human skin tones).
The models we utilized to process the images are:
-
K Nearest Neighbour classifier
-
Support Vector Classifier
-
CNN from Scratch
-
CNN from VGG16 (Transfer Learning)
-
LSTM Model
Project TunnelEnd [August 2018]
This project is based on the data inferred from surveys conducted from the year 2005 to the year 2011, which contains information regarding state-wise statistics of civilian and veteran suicides based on gender, along with their probabilities. Using the assimilated data, we helped create machine learning models to identify places of high alert and growth rates in each of those states.
We compared the following learning models:
-
Random Forest
-
SVR
-
Linear Regression
-
K Neighbours
-
XGBoost
-
Boosted Random Forest
-
Bagging Regressors
Since the accuracy of Linear Regression is the highest (off by the lowest value of suicides), it helped us infer that with each year, the rate of US veteran suicides increases. This led to the unfortunate inference that the rate of suicides has progressively increased with each year for both civilians, and US veterans, although the rate has increased faster for the latter.
Eunoia - Mental Health Awareness in the Workplace Environment [August 2018]
[Top 15 Technical Projects in Southern India - IET Project Exhibition 2018]
With an increase in technology, social network, and efficiency, human beings have been forced to become more efficient than ever. And with exceedingly intensive expectations comes feelings of social resentment, depression, and lack of vigour. Mental illness in the workplace environment is still something that is known but not quite acted upon on a global scale and hence is a universally-erupting meltdown.
This project uses Artificial Intelligence to act upon a 2014 Mental Health Survey in order to produce results regarding detection and requirement of treatment. I compare efficiency rates among:
-
Logistic Regression,
-
K Neighbours Classifier, and
-
Tree Classifier
To obtain the best method and store the computed results to a CSV file. I have been able to achieve a success rate of 81% (based on the dataset alone).
Personalized News Recommendation based on Click Behavior - Implementation [August 2018]
We devised a working model for the research paper with the same title, where we determine the interests of the user towards an array of news topics, and recorded any and all fluctuations and alterations that may have occurred, in order to compute the genuine interest of the user towards each of the news topics and generate a personalized feed of news articles.​
The various concepts that we utilized (and have been mentioned in the paper) were:
-
Click distribution
-
Changes in the user's interests over time
-
Predicting user's genuine news interests
-
Combining predictions of past time periods
-
Predicting user's current news interests
-
Deriving absolute interests​
Breath of Life [August 2018 - Recreational Project]
Breath of Life is a simple Deep Learning project that converts an image in black-and-white format (greyscale) to coloured.
It utilizes an API that creates a pixel processing neural network to determine gradients and possible combinations of them.
SRMIST Intra College Messenger [June 2017 - December 2017]
The major issues that we found in the online study group creation method via WhatsApp were:
-
Minimum or no filter to remove and/or prevent spamming and unnecessary message exchange(s) in the group
-
A new member is unable to access documents/PDFs/other study materials that were sent prior to his/her inclusion
-
Important announcements by the subject faculty member and/or class representative were easily clouded by future series of messages
Hence, we designed an intra-college messenger to address all of these issues as efficiently as possible. Some of the unique features were: a global server to retrieve all documents sent/received, text moderations, and categorization.​
A comprehensive list of my activities included the following:
-
Created an inter-campus android application to facilitate easy transmission of exam and lecture related materials and question papers
-
Stored all provided materials on a server in order to make document-retrieval more efficient
WebLearn 1.0 (Version 2017) [June 2016 - July 2016]
I helped create an Android Application aimed at educating school students on the basics of Web Development with HTML and CSS bases. The APK was installed in all the Aakash Tablets (Make-In-India Android Tablets developed in association with IIT Bombay Department of Computer Science and Engineering) for use in TEKMUX 1.0 - a one-of-a-kind Tri-Hackathon and Educational event held at SRM Institute of Science and Technology during the month of September 2017.
Based on the hands-on educational event, we also conducted seminars and quizzes to deepen their knowledge of the fundamentals and increase their interests in Computer Programming.
A comprehensive list of my activities included the following:
-
Illustrated the core principles required in attaining knowledge on Web Development
-
Incorporated lesson-oriented quizzes for performance tracking
-
Developed an easy to use application with progress tracking​​
Interests and undertaken courses
WHAT AM I CURRENTLY LEARNING?
Completed
-
Data structures, analysis, and design of algorithms
Currently Learning
-
Multi-Agent Systems
-
NetLogo Programming
-
Dual Diagnosis
Books & Scientific Articles
CURRENTLY AVAILABLE WORKS
Author of "The Horrors of Happiness"
Ranked #81 in the list of "Best Horror Books on Amazon" in the opening week
Life, as you subconsciously know, is built up of an infinite number of moments. Moments which change us, moments which improve us, moments which define us. Therefore, with this principle in mind, this book was created. There is no specific category for this book, although most would classify it as horror.
It is, and not, about Love. It is, and not, about Fear. It is, and not, about Dreams.
And maybe, it is that very uncertainty that appeals to us. The "What if" in life. What would have happened if I had said yes to him? What would have happened if I had accepted the offer that night? What would have happened if nobody intervened to save me?
This book is a collection of short stories and poems that celebrate all that the human race is about: uncertainty, hope, hatred, and creating an infinitely large collection of infinitesimal moments.
Co-author of "Horn OK Please - Pandora's Box"
Written by authors from around the world, Pandora's Box is an aspiration to release hope in the world today. This Anthology marks the 10th book in the book series titled 'Horn OK Please'.
Pandora's box is an artefact in Greek mythology, taken from the myth of Pandora's creation in Hesiod's Works and Days. The "box" was actually a large jar given to Pandora. It contained all the evils of the world. Pandora was actually sent as a curse to Zeus’ men and was given the jar upon her marriage. It was never meant to be opened and yet she did. Just the way the forbidden fruit was never meant to be eaten. Upon opening the box, she unleashed eight demons unto the world. The first ones being the seven deadly sins and the last one which she managed to capture back was of course - hope. And hope forms the basis of our very existence in the world we live in today. The only thing we need is hope. We cling on to it. It makes life awesome.
In a world devoid of hope, humanity cannot survive. For opening Pandora's box refers to getting into a situation over which one has very little control over. The very essence of this book is hope for as you will flip through the pages, you will release hope unto this world.
Wrote the articles:
"The 4th ICONN - The Future is smaller than you think"
"World Space Week 2017 - Exploring New Possibilities Around Us"
"Are We Actually Here? - A Brief Study on the Simulation Hypothesis"
