Kunal Jani
Male
Scottsdale, Arizona, United States
Research Intern Dhirubhai Ambani Institute of Information and Communication Technology
da-iict
Recent badges
Python language Badge
math - Math - 1 Star badge
Amateur Badge
basic programming - Basic Programming - 3 Stars badge
C++ language Badge
Connected Accounts
Amateur Badge
Level
Amateur
Points
780
Contest ratings
1081
Problem solved
83
Solutions submitted
186
19 submissions in the last year
JulAugSepOctNovDecJanFebMarAprMayJun
Practice badges
Basic Programming - Basic Programming - 3 Stars Badge
Basic Programming
10725 480
+2 more badges
90 Points
30 Points
Data Structure - Data Structures - 3 Stars Badge
Data Structure
3409 270
+2 more badges
90 Points
30 Points
Math - Math - 1 Star Badge
Math
17615 30
Badges earned
Python language Badge
C++ language Badge
Contest Rating
#
Challenge name
Rank
Language
Education
da-iict
Bachelor of Technology (B.Tech.) , kunaljani18@gmail.com
2016 - 2020
CGPA : 3.6
Work experience
Research Intern
Dhirubhai Ambani Institute of Information and Communication Technology , Gandhinagar, Gujarat, India
Jan 2020 - May 2020 - (5 months)
A comparison between two face recognition algorithms, namely, Principal Component based face recognition algorithm and the Discrete Cosine Transform based face recognition algorithm, comparing accuracy and execution time. Gaussian noise, quantization noise and salt and pepper noise were taken to analyze the performance in terms of accuracy and the ROC curves representing the variation of the false positive rate with the true positive rate. MPI was used for parallelization so that the execution time reduced for both algorithms.
Research Intern
Dhirubhai Ambani Institute if Information and Communication Technology , Gandhinagar, Gujarat, India
May 2019 - Jul 2019 - (3 months)
Principal Component Analysis of Dimensionality Reduction was used to compare a new face image with a set of face images in a data store. When the face recognition system was parallelized, a super linear speedup was observed without the accuracy of the being affected. The research paper written for this project was accepted by HiPC student research symposium.
Projects
Jack Thief Simulation
Jun 2019 - Jun 2019 - (1 months)
A python script was written to simulate the game of jack thief. Two graphs were plotted which showed the variation of the length of the game with the number of players and the variation of the length of the game with number of cards.
Human Expression Recognition Using Deep Learning
May 2020 - Jun 2020 - (2 months)
Using Convolutional Neural Networks, a human expression recognition system was developed that could identify emotions based on the poses of the different parts of the face such as the eyes and mouth. The training an testing databases consisted of images representing various such as anger, disgust, fear, happy, sad neutral and surprise. Training the neural network with 2800 images and 700 testing images, it was possible to achieve a validation accuracy of 86.2%.
Handwritten Digit Recognition Using Machine Learning Algorithms
May 2020 - May 2020 - (1 months)
For this project, the MNIST database was used for the purpose of handwritten digit recognition. All the images were read from the MNIST database. Since there was a large number of pixels in each image, the number of computations involved in the implementation of machine learning algorithms would be large. Therefore a dimensional reduction operation was performed on the database. Once the dimensional reduction operation was performed, six machine learning classification algorithms were K Nearest Neighbors, Support Vector Classification, Logistic Regression, Naive Bayes, Decision Tree, and Random Forest.
Hpcfolder
May 2019 - May 2019 - (1 months)
A folder was created for high performance computing which would analyze the performance(execution time) of the serial and parallel algorithm and generate a csv file, which would be read by a python script to generate graphs for the speedup, execution time and the efficiency
Railway Ticket Booking System
Mar 2020 - Apr 2020 - (2 months)
The front end client side design of a railway reservation system was developed and implemented using HTML and BootStrap. This application can frequent railway users to register themselves and create an account with the website by registering their details such as their username, real name, gender, age, aadhar number, age, mobile phone number and address. For enhanced security, the password for the user account is encrypted using the Argon2 encryption algorithm which is inbuilt in the Django framework. The purpose of the encryption is that the administrator who accesses the user data does not have access to the real password since it is encrypted. Once the user has created his or her account, he or she can login with his or her username and password and book tickets for other passengers online by providing the passenger name, the train number, the station code of the location of departure and the station code of the location of arrival. Once the booking is done, the details of the booking are securely stored in the Django database which can be accessed only by a website administrator.
Modelling of Spread of a Typical Viral Disease in a Small Population
Mar 2020 - Mar 2020 - (1 months)
In a small population of initially healthy people, a computer simulation was developed which considered the random movement from one place to another within the small village with multiple points of entry or exit, the entry of healthy people, the entry of people who caught the virus but were not infected, the entry of people who were infected and the exiting of people. The infected people who have entered the small village come in close contact with people and spread the virus to other people. A graphical visualization displays how the people move around and get infected by other people.
Analysis of the Brusselator Model
Mar 2019 - Mar 2019 - (1 months)
Given a system of two differential equations for the Brusselator model, the videos of the bifurcation diagrams were created for this model which represented how the Brusselator model would behave for different initial conditions.
Legend Map Plotting of Yes Bank Customers Around the World
Mar 2019 - Apr 2019 - (2 months)
Given a dataset of 10 million entries, 200k entries were read from the dataset which has the list of yes bank customers around the world. Based on the location of yes bank customers around the world, a legend map was plotted showing the approximate number of yes bank customers located in each city.
Game of Hearts
Feb 2020 - Feb 2020 - (1 months)
A game of hearts between 4 players was developed which simulated the random assignment of cards to each player, selection of cards which are to be passed on to the other player, the playing of the game of hearts with values of each and every card. Each and every heart card had a value of one point and the queen of spades was given a value of 13 points. After one round was finished, the total score of each of the players was calculated.

Skills

Django
CSS
mpi
openmp
Machine Learning
bootstrap 3
C++14
Java
Python
HTML
jupyter notebook
C
Java 8
C++
Python 3
Publications
Machine Learning in Films: An Approach Towards Automation in Film Censoring
5 Dec, 2019
Publisher: Journal of Data, Information and Management