Browsing by Author "Jayarathna, S"

Filter results by typing the first few letters
Now showing 1 - 4 of 4
  • Thumbnail Image
    item: Conference-Abstract
    Change detection optimization in frequently changing web pages
    (2017) Meegahapola, LB; Alwis, PKDRM; Nimalarathna, LBEH; Mallawaarachchi, VG; Meedeniya, DA; Jayarathna, S
    Web pages at present have become dynamic and frequently changing, compared to the past where web pages contained static content which did not change often. People have the need to keep track of web pages which are of interest to them, using bookmarks in the web browser and continuously keep track of them in order to get the updates. Tracking changes which occur in these bookmarked web pages and getting updates has become a significant challenge in the current context. Hence there is a need for better and convenient methods to keep track of web pages. Many researches and implementations have been carried out in order to increase the efficiency of change detection of web pages and related algorithms. In this paper, we discuss the architectural aspects of change detection systems and introduce an optimized change detection solution including a web service, browser plugin and an email notification service. Consequently, this research will pave the way for a novel research area to explore.
  • Thumbnail Image
    item: Conference-Abstract
    An EEG based channel optimized classification approach for autism spectrum disorder
    Haputhanthri, D; Brihadiswaran, G; Gunathilaka, S; Meedeniya, D; Jayawardena, Y; Jayarathna, S; Jaime, M
    Autism Spectrum Disorder (ASD) is a neurodevelopmental condition which affects a person’s cognition and behaviour. It is a lifelong condition which cannot be cured completely using any intervention to date. However, early diagnosis and follow-up treatments have a major impact on autistic people. Unfortunately, the current diagnostic practices, which are subjective and behaviour dependent, delay the diagnosis at an early age and makes it harder to distinguish autism from other developmental disorders. Several works of literature explore the possible behaviour-independent measures to diagnose ASD. Abnormalities in EEG can be used as reliable biomarkers to diagnose ASD. This work presents a low-cost and straightforward diagnostic approach to classify ASD based on EEG signal processing and learning models. Possibilities to use a minimum number of EEG channels have been explored. Statistical features are extracted from noise filtered EEG data before and after Discrete Wavelet Transform. Relevant features and EEG channels were selected using correlation-based feature selection. Several learning models and feature vectors have been studied and possibilities to use the minimum number of EEG channels have also been explored. Using Random Forest and Correlation-based Feature Selection, an accuracy level of 93% was obtained.
  • Thumbnail Image
    item: Article-Full-text
    Eye gaze estimation: A survey on deep learning-based approaches
    (Elsevier, 2022) Pathirana, P; Senarath, S; Meedeniya, D; Jayarathna, S
    Human gaze estimation plays a major role in many applications in human-computer interaction and computer vision by identifying the users’ point-of-interest. The revolutionary developments of deep learning have captured significant attention in the gaze estimation literature. Gaze estimation techniques have progressed from single-user constrained environments to multiuser unconstrained environments with the applicability of deep learning techniques in complex unconstrained environments with extensive variations. This paper presents a comprehensive survey of the single-user and multi-user gaze estimation approaches with deep learning. The state-of-the-art approaches are analyzed based on deep learning model architectures, coordinate systems, environmental constraints, datasets and performance evaluation metrics.Akey outcome from this survey realizes the limitations, challenges, and future directions of multi-user gaze estimation techniques. Furthermore, this paper serves as a reference point and a guideline for future multi-user gaze estimation research.
  • Thumbnail Image
    item: Conference-Abstract
    A Rule-based system for adhd identification using eye movement data
    De Silva, S; Dayarathna, S; Ariyarathne, G; Meedeniya, D; Jayarathna, S; Michalek, AMP; Jayawardena, G
    Attention Deficit Hyperactivity Disorder (ADHD) is one of the common psychiatric disorder in childhood, which can continue to adulthood. The ADHD diagnosed population has been increasing, causing a negative impact on their families and society. This paper addresses the effective identification of ADHD in early stages. We have used a rulebased approach to analyse the accuracies of decision tree classifiers in identifying ADHD subjects. The dataset consists of eye movements and eye positions of different gaze event types. The feature extraction process considers fixations, saccades, gaze positions, and pupil diameters. The decision tree-based algorithms have shown a maximum accuracy of 84% and classification rule algorithms have shown an accuracy of 82% using eye movement measurements. Thus, both algorithms have shown high accuracy with the rule-based component.