Browsing by Author "Welivita, A"

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • Thumbnail Image
    item: Conference-Abstract
    A Framework for adaptive user interface generation based on user behavioural patterns
    Rathnayake, NM; Meedeniya, DA; Perera, I; Welivita, A
    The concept of adaptivity is crucial in enterprise software systems with a large user base. Adaptive user interfaces (AUI) is an emerging research area that enables customized user experience based on user activities. Most of the existing studies that are in the conceptual level do not provide production level adaptivity for mainstream user interaction. This paper presents a generic software platform for automatic AUI generation by analyzing user behaviour patterns and customizing web user interfaces using machine learning. AdaBoost classifier showed 100% accuracy for large UI components and user scenarios (n=800). The AUI generator supports the configuration and automation of capturing user behaviour, data storage, processing, querying analysis results and dynamic rendering of the user interface. AUI platform had SUS value of 80.75. The SUS scores for the UIs without AUI was 57.3 and with AUI scored 64.35 on average. The proposed AUI platform provides production level UI design means to meet dynamic adaptability on user traits.
  • Thumbnail Image
    item: Article-Full-text
    Managing complex workflows in bioinformatics: an interactive toolkit with GPU acceleration
    (2018) Welivita, A; Perera, I; Meedeniya, D; Wickramarachchi, A; Mallawaarachchi, V
    Bioinformatics research continues to advance at an increasing scale with the help of techniques such as next-generation sequencing and the availability of tool support to automate bioinformatics processes. With this growth, a large amount of biological data gets accumulated at an unprecedented rate, demanding high-performance and high-throughput computing technologies for processing such datasets. Use of hardware accelerators, such as graphics processing units (GPUs) and distributed computing, accelerates the processing of big data in highperformance computing environments. They enable higher degrees of parallelism to be achieved, thereby increasing the throughput. In this paper, we introduce BioWorkflow, an interactive workflow management system to automate the bioinformatics analyses with the capability of scheduling parallel tasks with the use of GPU-accelerated and distributed computing. This paper describes a case study carried out to evaluate the performance of a complex workflow with branching executed by BioWorkflow. The results indicate the gains of ×2.89 magnitude by utilizing GPUs and gains in speed by average ×2.832 magnitude (over n =5 scenarios) by parallel execution of graph nodes during multiple sequence alignment calculations. Combined speed-ups are achieved ×1.71 times for complex workflows. This confirms the expected higher speed-ups when having parallelism through GPU-acceleration and concurrent execution of workflow nodes than the mainstream sequential workflow execution. The tool also provides a comprehensive user interface with better interactivity for managing complex workflows; a system usability scale score of 82.9 is confirmed high usability for the system.
  • Thumbnail Image
    item: Conference-Abstract
    Quantitative evaluation of face detection and tracking algorithms for head pose estimation in mobile platforms
    (2017) Welivita, A; Nimalsiri, N; Wickramasinghe, R; Pathirana, U; Gamage, C
    Face detection, face tracking and head pose estimation are commonly utilized in many computer vision applications related to face recognition, expression analysis, augmented reality and human computer interaction. Many different types of face detection and face tracking algorithms have been proposed by different research groups and based on the target platforms and applications, these algorithms have their own strengths and imitations. Yet a comprehensive intra and inter approach evaluation against a single data set is not available in the literature. In this paper, we present a comprehensive evaluation carried out on a set of selected face detection and tracking algorithms with respect to their accuracy, performance and robustness on both PC and mobile platforms.