Roshan Ragel

Roshan Ragel
University of Peradeniya | UOP · Department of Computer Engineering

BSc Eng Hons (Peradeniya), PhD (UNSW)

About

188
Publications
55,850
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
932
Citations
Additional affiliations
October 2015 - December 2015
UNSW Sydney
Position
  • Visiting Fellow (Research)
December 2007 - present
University of Peradeniya
Position
  • Professor (Associate)
December 2007 - present
University of Peradeniya
Position
  • Professor (Associate)
Education
February 2003 - August 2006
UNSW Sydney
Field of study
  • Embedded Systems
November 1997 - November 2001
University of Peradeniya
Field of study
  • Computer Engineering

Publications

Publications (188)
Conference Paper
Full-text available
Computer vision-based security surveillance with automated CCTV cameras helps identify criminals and reduce the crime rate. It has been widely used in defence, transportation, and public places like airports, harbours, and bus terminals. The tiny object detection is essential for providing complete real-time surveillance in high-security zones. In...
Conference Paper
Entity linking (EL) is a process of extracting entity mentions in documents and linking them to their corresponding actual entities in a Knowledge Base (KB) such as Wikipedia or Wikidata. This task is challenging due to name variations, incompleteness of the KB and high ambiguity of entity mentions. News articles generally contain mentions of entit...
Article
Side channel analysis attacks employ the emanated side channel information to deduce the secret keys from cryptographic implementations by analyzing the power traces during execution or scrutinizing faulty outputs. To be effective, a countermeasure must remove or conceal as many as possible side channels. However, many of the countermeasures agains...
Preprint
Intrinsic Image Decomposition is an open problem of generating the constituents of an image. Generating reflectance and shading from a single image is a challenging task specifically when there is no ground truth. There is a lack of un-supervised learning approaches for decomposing an image into reflectance and shading using a single image. We prop...
Preprint
Recently, researchers in the field of interactive computer gaming have introduced two technologies that can be integrated into game engines to provide a better user experience: dynamic difficulty adjustment (DDA); affect-based difficulty adjustment (Affect-DA). DDAsystems monitor the performance of the user to dynamically adjust the difficulty leve...
Article
Application-specific instruction-set processors (ASIPs) utilize customized instructions to speedup a specific application or a set of applications. Thus, ASIPs execute the application(s) faster and are energy efficient compared to general-purpose processors. State-of-the-art custom instruction design methods typically target small applications or k...
Article
Full-text available
The advent of portable nanopore sequencing devices has enabled DNA and RNA sequencing to be performed in the field or the clinic. However, advances in in situ genomics require parallel development of portable, offline solutions for the computational analysis of sequencing data. Here we introduce Genopo , a mobile toolkit for nanopore sequencing ana...
Preprint
Full-text available
Low light image enhancement is an important challenge for the development of robust computer vision algorithms. The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset. This paper presents a novel deep learning pipeline that can learn from both paired and unpa...
Preprint
Full-text available
Low light image enhancement is an important challenge for the development of robust computer vision algorithms. The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset. This paper presents a novel deep learning pipeline that can learn from both paired and unpa...
Conference Paper
Online news reading has become general among people and suggesting relevant news articles to readers is a non-trivial task. News recommender systems (NRS) are built to provide appropriate stories to readers based on their interest. News articles usually contain mentions of persons, locations and other named entities which are excellent resources fo...
Preprint
Full-text available
F5N is the first ever Android application for nanopore sequence analysis on a mobile phone, comprised of popular tools for read alignment ( Minimap2 ), sequence data manipulation ( Samtools ) and methylation calling ( F5C/Nanopolish ). On NA12878 nanopore data, F5N can perform a complete methylation calling pipeline on a mobile phone in ∼15 minutes...
Article
Multiprocessor System-on-Chip (MPSoC) has become necessary due to the the billions of transistors available to the designer, the need for fast design turnaround times, and the power wall. Thus, present embedded systems are designed with MPSoCs, and one possible way MPSoCs can be realized is through Pipelined MPSoC (PMPSoC) architectures, which are...
Article
Full-text available
Small unmanned aerial systems (UASs) now have advanced waypoint-based navigation capabilities, which enable them to collect surveillance, wildlife ecology and air quality data in new ways. The ability to remotely sense and find a set of targets and descend and hover close to each target for an action is desirable in many applications, including ins...
Conference Paper
Full-text available
Optical Character Recognition (OCR) is reproducing the text as a digital format that has been produced by the non-computerized system. The translation is an essential part because people have barriers in languages. Especially when people read articles and books in their native language, they can understand more clearly and can get more ideas about...
Article
Full-text available
Recently, researchers in the area of biosensor based human emotion recognition have used different types of machine learning models for recognizing human emotions. However, most of them still lack the ability to recognize human emotions with higher classification accuracy incorporating a limited number of bio-sensors. In the domain of machine learn...
Preprint
Full-text available
Sleep apnea is a breathing disorder where a person repeatedly stops breathing in sleep. Early detection is crucial for infants because it might bring long term adversities. The existing accurate detection mechanism (pulse oximetry) is a skin contact measurement. The existing non-contact mechanisms (acoustics, video processing) are not accurate enou...
Thesis
Optical character recognition is reproducing the text as a digital format that has been produced by the non-computerized system. The translation is an essential part because people have barriers in languages. Especially when people read articles and books in their native language, they can understand more clearly and can get more ideas about the co...
Chapter
Full-text available
Recognizing sEMG (Surface Electromyography) signals belonging to a particular action (e.g., lateral arm raise) automatically is a challenging task as EMG signals themselves have a lot of variations even for the same action due to several factors. To overcome this issue, there should be a proper separation which indicates similar patterns repetitive...
Conference Paper
Full-text available
The aim of this paper is to implement an entity linking system for news recommendation. Which can automatically recognize Person entities (humans) from input English text (news article), and link them to the best-matched entities in Wikidata knowledge base. That is, for each specific mention of a person entity found in a text, the developed Named E...
Conference Paper
Full-text available
The advancement in DNA microarray dataset technology has become an area of interest among many scholars. Application of this technology can be a great success for cancer data classification. However, DNA microarray data usually contains thousands of irrelevant and redundant gene information which need to be eliminated to improve the accuracy of cla...
Article
Full-text available
Recognizing sEMG (Surface Electromyogra-phy) signals belonging to a particular action (e.g., lateral arm raise) automatically is a challenging task as EMG signals themselves have a lot of variation even for the same action due to several factors. To overcome this issue, there should be a proper separation which indicates similar patterns repetitive...
Conference Paper
Full-text available
The improvement in DNA microarray technology is an important area of interest among many researchers and medical scholars to investigate the expression levels of enormous number of genes in a DNA simultaneously. It has been shown that the use of this technology is beneficial for cancer data classification. However, the DNA microarray data usually c...
Preprint
Present Field Programmable Gate Array (FPGA) manufacturers incorporate multi-millions of logic resources which enables hardware designers to design applications extending to enormous scales. However, handling such applications by existing FPGA Computer Aided Design (CAD) flow requires more improvement in terms of compilation time, performance and p...
Conference Paper
Full-text available
In a normal environment, it is difficult to achieve the optimum conditions needed for plant growth and yield. Therefore, proper environment monitoring and controlling of the environment is needed to provide the optimum conditions necessary for a plant. Greenhouses are used to control the environmental factors and provide such ideal conditions for p...
Article
Full-text available
This is an empirical study based on correlation power analysis for extracting the secret key from a Speck based embedded cryptosystem. Speck was recently introduced by the National Security Agency, USA as a lightweight softwarebased block cipher targetting embedded systems. The pervasive nature of embedded devices makes it crucial to perform this a...
Conference Paper
Full-text available
Reproducing printed documents with their existing format is becoming an important task when we need to reprint or republish existing printed documents with the latest updates of contents. Text, images, charts, graphs, tables, logos and signatures are some of the prominent components of a printed document. When reproducing the text of a printed docu...
Conference Paper
Full-text available
This research is intended to identify the association between the Learning Style (LS) and the learners’ access biasness over e-learning activities using Data Mining (DM). Such associations can be used for proposing guidelines to develop learner based dynamic online learning environments.
Presentation
Full-text available
Experimental results of Cache Optimization Techniques for General Purpose Graphics Processing Units
Conference Paper
Hardware Trojans are a major concern due to the damage caused by their stealth. One popular utilization of Multiprocessor System on Chips (MPSoCs) is the Pipelined MPSoC (PMPSoC) architectures. They are used in applications from video surveillance to consumer electronics. We present a method that detects the presence of Trojans in third party IP co...
Article
Full-text available
Digitisation is a process of representing real world objects in digital format. The rapid conversion of material available in printed form to editable digital form requires a significant amount of work if we are to maintain the format and the style of the electronic documents similar to their printed counterparts. Most of the existing digitisation...
Conference Paper
Full-text available
Optical Character Recognition (OCR) is a well-researched topic. Feature selection plays a vital role in a functional OCR system. The right feature selection process would make an OCR system faster, accurate and complete. The Sinhala language suffers from complete OCR systems. In this paper, we introduce a quantifiable and systematic feature selecti...
Conference Paper
Full-text available
k-Nearest Neighbor (k-NN) is a well-known classification algorithm used in many machine learning applications. When the input data size of k-NN algorithm increases, the execution time of the algorithm increases significantly. Therefore, this becomes a bottleneck for practical usage. Since k-NN algorithm is using searching, sorting and other paralle...
Conference Paper
Full-text available
General Purpose Graphic Processing Unit(GPGPU) is used widely for achieving high performance or high throughput in parallel programming. This capability of GPGPUs is very famous in the new era and mostly used for scientific computing which requires more processing power than normal personal computers. Therefore, most of the programmers, researchers...
Conference Paper
Full-text available
This paper discusses load balancing methods available in the Apache2 server. The Apache2 server runs on Raspberry-Pi2 model B+ clustered web server which consisting of three Raspberry-Pi boards one functions as the load balancer and two as worker nodes. As a part of this research, we developed a web application called the “Student Information Syste...
Conference Paper
Full-text available
The Aho-Corasick algorithm is multiple patterns searching algorithm running sequentially in various applications like network intrusion detection and bioinformatics for finding several input strings within a given large input string. The parallel version of the Aho-Corasick algorithm is called as Parallel Failure-less Aho-Corasick algorithm because...
Article
Digitisation is a process of representing real world objects in digital format. The rapid conversion of material available in printed form to editable digital form requires a significant amount of work if we are to maintain the format and the style of the electronic documents similar to their printed counterparts. Most of the existing digitisation...
Article
Today, soft errors are one of the major design technology challenges at and beyond the 22nm technology nodes. This article introduces the soft error problem from the perspective of processor design. This article also provides a survey of the existing soft error mitigation methods across different levels of design abstraction involved in processor d...
Conference Paper
Compression is desirable for network applications as it saves bandwidth. Differently, when data is compressed before being encrypted, the amount of compression leaks information about the amount of redundancy in the plaintext. This side channel has led to the “Browser Reconnaissance and Exfiltration via Adaptive Compression of Hypertext (BREACH)” a...
Conference Paper
Greenhouse has been the best alternative solution to get a better crop production compared to the traditional agricultural industry. Greenhouses are used to increase harvest by controlling key factors which will aect the planet growth. Real-time monitoring of the greenhouse environment and taking necessary control decisions will result in improveme...
Conference Paper
Smart Parking Sensor Network project aims to develop a low cost sensor based parking system to map the usage of parking areas. This system consists of sensor nodes which can detect the occupancy of parking space; relay nodes to communicate between sensor nodes and the server; server application to get data from the relay nodes and send data to mobi...
Conference Paper
Full-text available
With the increasing amount of data used for various purposes, maintaining the efficiency of storing and transmitting them are proving to be a challenge. Data compression brings forward a solution to this issue. We perform a lossless compression of data on Graphic Processor Units (GPU) for NVIDIAs CUDA Framework, using a parallelized Lempel-Ziv-Stor...