Hi, I'am Danujan
Computer Engineering Undergraduate
I have a passion for Software Development, Machine Learning, DevOps. Eager to apply my skills to real-world projects and push the boundaries of technology.
Contact MeAbout Me
My Introduction
I'm a Computer Engineering undergraduate at the University of Peradeniya with a strong passion for Software Development, Machine Learning, DevOps. My academic journey has equipped me with the skills and knowledge to excel in these areas, and I'm eager to apply them in real-world projects and challenges. Whether it's training machine learning models, building robust back-end systems, or creating dynamic web applications with React, I'm always enthusiastic about pushing the boundaries of technology.
experience
certifications
Finished
Technical Skills
My technical expertiseProgramming Languages
Java
Python
C
JavaScript
Web Development
HTML5
CSS
React.js
Spring Boot
Libraries
NumPy
Pandas
Matplotlib
scikit-learn
OpenCV
Database & Cloud
MySQL
PostgreSQL
AWS
EC2, RDS, S3Google Cloud
Qualification
My personal journeyGCE Ordinary Level
J/Chavakachcheri Hindu College9A
GCE Advance Level
J/Chavakachcheri Hindu College3A
Engineering Undergraduate
University of Peradeniya Current GPA: 3.30/4.00Blog Writer
MediumExecutive Committee Member
ACES, University of PeradeniyaWeb Development Team Member
Hacker's Club, University of PeradeniyaSoftware Engineer Intern
GTN Technologies (Pvt) Ltd Colombo, Sri LankaProjects
Most recent worksPublications
Research WorkPredicting Inpatient Bed Demand Using Machine Learning
Group Project | October 2023 - June 2024- Implemented a hybrid machine learning solution to address hospital overcrowding by forecasting inpatient bed demand, reducing patient waiting times and optimizing resource allocation across Emergency Department and Post-Anesthesia Care units.
- Engineered an ensemble model architecture combining LSTM networks and CNNs with time series decomposition techniques, achieving significant performance improvements with MAE of 2.45 ± 0.27, MSE of 9.43 ± 1.77, and R² of 0.63 ± 0.06.
- Developed and evaluated multiple prediction approaches including K-Means clustering for patient segmentation, Support Vector Regression for trend analysis, and ARIMA for baseline comparison.