CHANDRIKA SAHA.
Graduate Student: Computer Science
Western University,
Ontario, Canada.
Hello! I'm Chandrika
I believe, "Learning never exhausts the mind"- learning new things and finding out how they can be applied to the real-world is what I want to dedicate my life to. I am especially passionate in the field of Artificial Intelligence, specifically, Machine Learning; In my free time, I like to paint, and read books.
EXPERIENCE
September 2019 - December 2019
Graduate Trainee
Fujitsu Research Institute
Tokyo, Japan
Thie training was mainly focused on Data Science, Machine Learning and Artificial Intelligence. We also learned about Cyber Security, Internet of Things, Block Chain and Robotic Processing Automation.
EDUCATION
Fall 2021 -
Master of Science (MSc.)
Western University,
Ontario, Canada
Dept.: Computer Science
2014-2019
Bachelor's Degree (BSc.)
The University of Barishal,
Barishal, Bangladesh
Dept.: Computer Science and Engineering
CGPA: 3.95/4.00 (Rank: 1)
2012-2013
Higher Secondary Certificate (HSC)
Barishal Model School and College
Division: Science
GPA: 5.00/5.00
Scholarship: General Grade, The National Board of Education
2010-2011
Secondary School Certificate (SSC)
Barishal Model School and College
Division: Science
GPA: 5.00/5.00
Scholarship: Talent Pool, The National Board of Education
PUBLICATIONS
Bangla Handwritten Basic Character Recognition Using Deep Convolutional Neural Network
A CNN model, namely, BBCNet-15 is proposed for Bangla handwritten basic character recognition; which is evaluated on a benchmark dataset, CMATERdb 3.1.2 which contains 50 character classes including 39 consonants and 11 vowels. The experimental evaluation of BBCNet-15 on the dataset provides a recognition accuracy of 96.40% which outperforms some prominent techniques in existence.
Bangla Handwritten Digit Recognition Using an Improved Deep Convolutional Neural Network Architecture
A Deep Convolutional Neural Network (DCNN) based Bangla handwritten digits recognition scheme. The proposed method applies a seven-layered D-CNN containing three convolution layers, three average pool layers, and one fully connected layer for recognizing Bangla handwritten digits. Rigorous experimentation on a Bangla digit dataset namely, CMATERdb 3.1.1 provides considerable recognition accuracies.
Power Efficient Distant Controlled Smart Irrigation System for AMAN and BORO Rice
This study proposes an Arduino/GSM based remotely controlled power-efficient smart irrigation system for crops that need to be immersed in water during its growing period. It will ensure the proper irrigation of a field by monitoring the water level of the paddy field, providing feedback to farmers, and giving farmers the option to control the water motor via SMS.
Bangla Handwritten Character Recognition Using Local Binary Pattern and Its Variants
A comparative study of different Local Binary Pattern (LBP) based feature descriptors on Bangla basic characters, compound characters, and digits. For classification, Support Vector Machine (SVM) with linear kernel is used. Experiments on CMATERdb 3.1.2, CMATERdb 3.1.3.1, and CMATERdb 3.1.1 datasets have shown reasonable accuracies.
SKILLS
Programming Languages: JAVA, Python, C, C++, C#.
Web Technologies: SQL, SQLite, Firebase, BootStrap, HTML5, CSS3, PHP, ASP.NET.
Deep learning frameworks: Tensorflow, Keras.
Developer Tools: NetBeans, Eclipse, Android Studio, Spyder, Google Colab, Jupyter Notebook, MATLAB, Arduino IDE, Draw.io, Visual Studio, Git, Overleaf.
LANGUAGES
-
BENGALI (NATIVE)
-
ENGLISH (PROFICIENCY: CEFR C1)
-
JAPANESE (ELEMENTARY)
PROJECTS
PROJECTS
"Smart Irrigation"
An electrical water level indicator is planted on the field, which continuously sends the water level to Arduino Uno microcontroller. The microcontroller, after analyzing the data, if finds that the water level is very low, signals the GSM module to send an SMS to farmers' mobile phones. The farmer then sends a specific keyword to the GSM module, which signals the microcontroller to turn the 5V relay on, which then turns the 220V line of the water pump on.
"Barisal Rudder"
This is our 3rd year industrial management project. This web page includes description of places, transportation, restaurants, hotels, and emergency services of Barisal city. It will act as a guideline for the tourists as well as people of Barisal city. ASP.NET is used as server side technology, whereas Bootstrap is used as the front-end framework.
"Tic Tac Toe"
This is a fun project made with Unity3D.... The good old Tic Tac Toe.
MY HOBBIES
"...For the more minutely you describe, the more you will confuse the mind of the reader and the more you will prevent him from a knowledge of the thing described. And so it is necessary to draw and describe...."
MY GALLERY
