Instructor 2024 Jan - Present
Department of Computer Engineering, University of Peradeniya, Sri Lanka
Preparing and conducting lab classes and tutorials for courses: Computer Architecture (CO224), Image Processing (CO543), Operating Systems (CO327)
I am a recent graduate in computer engineering from the Department of Computer Engineering, University of Peradeniya.
My primary research focus is on applying machine learning and computer vision techniques for biomedical applications, with a broader interest in Human-AI collaborative systems. This includes developing low-energy, pervasive sensing systems for real-time, context-aware interactions in embodied AI, utilizing various advanced technologies, including neuromorphic vision sensors, enhancing human-AI collaboration in biomedical and everyday environments.
gaisuridevindi@gmail.com | Resume | Github | LinkedIn | Google Scholar
Group: Isuri Devindi, Sashini Liyanage, Dinura Dissanayake, Achintha Harshamal
Paper published in IEEE Access | Paper published in Oral Oncology Reports | Poster
| Video
2024
A web-based tool to reduce the delay in diagnosing high-risk oral cancer patients by incorporating an automated oral cancer prediction model trained on a white light image database derived from the Sri Lankan population.
Group: Isuri Devindi, Sashini Liyanage
Paper published in Nature Scientific Reports | Project Page
| Repository
| Report
2023
A pre-packaged software solution containing a set of low-complexity algorithms for QRS-peak detection and ECG signal compression addressing the null-power consumption environments, along with a Spiking Neural Network implementation to classify ECG beats based on arrhythmia conditions.
Supervisors: Prof. Archan Misra , Ila Gokarn
Report
2023
Exploration of how compressive sensing techniques such as rate coding, latency coding, delta modulation, event window slicing, time window slicing, and voxel cubes can be applied to efficiently convert event-based data from neuromorphic vision sensors into 2D frames for low-energy spiking neural networks (SNNs). The impact of these input-level compression techniques on the classification and object detection performance of SNNs was also evaluated.
Group: Isuri Devindi, Sashini Liyanage, Aminda Amarasinghe, N. Varnaraj
Repository
| Report
| Video
2022
Demonstration of how traditional
image processing techniques such as Otsu thresholding, morphological transformation,
contouring, spatial and frequency domain filtering,
and degradation modeling can be used to restore highly distorted
images along with the limitations of the traditional
image processing theoretical techniques.
Group: Isuri Devindi, Sashini Liyanage
Repository
2022
The combination of a lexer, parser, semantic analyser, and code generator that can be used to compile programs written in Cool programming language. All components were built using C++. Lexical Analyzer was built using a lexical analyzer generator called "flex" and the Parser using a helper tool called "bison" and a package for manipulating Abstract Syntax Trees.
Group: Isuri Devindi, Sashini Liyanage, Savindu Wannigama
Project Page
| Repository
| Video
2021
A single device which integrates
the hardware and software components needed to conduct
an examination in the currently implemented system,
which will provide a seamless process for the proctors
and students involved in an examination.
Group: Isuri Devindi, Dinura Dissanayake
Repository
2020
An 8-bit single cycle CPU with associated memory hierarchy. The processor includes an ALU, register file, control logic, forwarding unit, data memory, data cache, instruction memory and instruction cache simulated with Verilog HDL.
Department of Computer Engineering, University of Peradeniya, Sri Lanka
Preparing and conducting lab classes and tutorials for courses: Computer Architecture (CO224), Image Processing (CO543), Operating Systems (CO327)
Pervasive Sensing & Systems Lab, School of Computing and Information Systems, Singapore Management University
Supervised by Prof. Archan Misra and Ila Gokarn, explored spatiotemporal compressive sensing techniques for event-based data generated by Neuromorphic Vision Sensors fed into and processed by Spiking Neural Networks.
Writing technical content on computer vision, machine learning, and web development.
Department of Computer Engineering, University of Peradeniya, Sri Lanka
Assisted in lab classes for courses: Embedded Systems (CO321), Data Structures and Algorithms (CO322), Programming and Networking (CO253), Programming Methodology (CO222)
| Type | Course ID | Course Name |
|---|---|---|
| Mathematics | EM502 | Optimization |
| EM527 | Operations Research I | |
| EM211 | Ordinary Differential Equations | |
| EM212 | Calculus II | |
| EM213 | Probability & Statistics | |
| EM214 | Discrete Mathematics | |
| EM215 | Numerical Methods | |
| GP115 | Calculus I | |
| GP116 | Linear Algebra | |
| Computer Engineering | CO521 | Compilers |
| CO542 | Neural Networks & Fuzzy Systems | |
| CO543 | Image Processing | |
| CO544 | Machine Learning & Data Mining | |
| CO321 | Embedded System | |
| CO322 | Data Structures & Algorithms | |
| CO323 | Computer Communication Networks II | |
| CO324 | Network & Web Application Design | |
| CO325 | Computer & Network Security | |
| CO326 | Computer Systems Engineering | |
| CO327 | Operating Systems | |
| CO328 | Software Engineering | |
| CO221 | Digital Design | |
| CO222 | Programming Methodology | |
| CO223 | Computer Communication Networks I | |
| CO224 | Computer Architecture | |
| CO225 | Software Construction | |
| CO226 | Database Systems | |
| Projects & Research | CO227 | Computer Engineering Project |
| CO421 | Final Year Project I | |
| CO425 | Final Year Project II | |
| Electrical & Electronic | EE386 | Electronics II |
| EE387 | Signal Processing | |
| EE282 | Network Analysis for Computer Engineering | |
| EE285 | Electronics I | |
| GP118 | Basic Electrical & Electronic Engineering | |
| Other Technical Courses | GP109 | Materials Science |
| GP110 | Engineering Mechanics | |
| GP111 | Elementary Thermodynamics | |
| GP112 | Engineering Measurements | |
| GP113 | Fundamentals of Manufacture | |
| GP114 | Engineering Drawing | |
| General Courses | GP101 | English I |
| GP102 | English II | |
| EF501 | The Engineer in Society | |
| EF509 | Engineer as an Entrepreneur | |
| EF524 | Business Law | |
| EF528 | Introduction to Digital Art |
Testing practices designed for software systems,
are often inadequate for ML models,
and ML model testing is not yet as mature and well-understood
as traditional testing.
This article will explore the concept of machine learning model testing
and some of the tools specifically designed for testing ML models.
Read More
Developing and deploying
computer vision projects can be
challenging due to the variety of
digital content utilized. This article discusses
five best practices for
building scalable and future-proof
computer vision projects and how to avoid some common mistakes.
Read More
There are a lot of things that can go wrong when you're building a computer vision project. This article explores some of
the common pitfalls of building computer vision projects and show how you can mitigate them.
Read More
In JavaScript,
null and undefined data
types may appear similar
when viewed at an abstract level.
This article will go through
the definitions of null and undefined
along with their similarities,
fundamental differences,
and how you could utilize each
of these values in your program.
Read More
Data scraping is the ultimate method to obtain
such training data from
publicly available resources at scale effortlessly.
This article will explore how data scraping
can be used to collect high-quality training data.
Read More
Amazon DynamoDB and Postgres are two
of the most common database services
used by developers.This article will go through the differences between
the two and give tips on choosing one based on your requirements.
Read More