Search Results

Now showing 1 - 10 of 191
  • Item
    Recreational Motion Simulation: A New Frontier for Virtual Worlds Research
    (The Eurographics Association, 2021) Williams, Benjamin; Headleand, Christopher J.; Xu, Kai and Turner, Martin
    Motion simulation is a developing field which continues to grow with the recent incline in commercial virtual reality. Whilst the majority of motion simulation research focuses on flight simulation and training, its utility in recreational settings is often overlooked. Despite this lack of research, the use of motion simulators for recreational purposes spans decades, and is still today one of the most popular applications of motion simulator devices. Furthermore, with the recent development of low-cost motion simulation platforms, consumers have begun to use these devices in the home. Research regarding motion simulation and its effects in recreational experiences is needed now more than ever, and in this position paper we outline several reasons for its importance.
  • Item
    Real-Time Rendering of Molecular Dynamics Simulation Data: A Tutorial
    (The Eurographics Association, 2017) Alharbi, Naif; Chavent, Matthieu; Laramee, Robert S.; Tao Ruan Wan and Franck Vidal
    Achieving real-time molecular dynamics rendering is a challenge, especially when the rendering requires intensive computation involving a large simulation data-set. The task becomes even more challenging when the size of the data is too large to fit into random access memory (RAM) and the final imagery depends on the input and output (I/O) performance. The large data size and the complex computation processing per frame pose a number of challenges. i.e. the I/O performance bottleneck, the computational processing performance costs, and the fast rendering challenge. Handling these challenges separately consumes a significant portion of the total processing time which may result in low frame rates. We address these challenges by proposing an approach utilizing advanced memory management and bridging the Open Computing Language (OpenCL) and Open Graphics Library (OpenGL) drivers to optimize the final rendering frame rate. We illustrate the concept of the memory mapping technique and the hybrid OpenCL and OpenGL combination through a real molecular dynamics simulation example. The simulation data-set specifies the evolution of 336,260 particles over 1981 time steps occupying 8 Gigabyte of memory. The dynamics of the system including the lipid-protein interactions can be rendered at up to 40 FPS.
  • Item
    Authoring Visualisation of Routinely Collected Data Using LLMs
    (The Eurographics Association, 2024) Hosseini, Amir; Wood, Jo; Elshehaly, Mai; Hunter, David; Slingsby, Aidan
    The integration of routinely collected healthcare data into decision-making processes has the potential to revolutionise patient care and health outcomes. However, the complexity and heterogeneity of these datasets pose significant challenges for effective querying and analysis. Visualisation supports socio-technical processes where data analytics are augmented with human expertise to overcome data complexity. However, the authorship of effective visualisation is a challenging task, especially for users without a technical background, such as commissioners, clinicians and population health experts. This complexity calls for more efforts to develop natural language interfaces (NLIs) to democratise access to and understanding of routine data through visualisation. This short paper presents an innovative approach utilising Large Language Models (LLMs) to facilitate the querying and visualisation of routinely collected healthcare data. We present a preliminary framework for combining natural language queries with visualisation recommendation systems to retrieve and visualise relevant information from electronic health records (EHRs). We propose a human-in-the-loop approach for establishing accurate and efficient LLM-enabled information retrieval. Our preliminary findings suggest that LLMs can significantly streamline the visualisation authoring process, enabling stakeholders and healthcare professionals to access critical information rapidly and accurately. This work underscores the potential of LLM-driven solutions in advancing healthcare data utilisation and paves the way for future research in this promising intersection of artificial intelligence and medical informatics.
  • Item
    Towards Analytical Provenance Visualization for Criminal Intelligence Analysis
    (The Eurographics Association, 2016) Islam, Junayed; Anslow, Craig; Xu, Kai; Wong, William; Zhang, Leishi; Cagatay Turkay and Tao Ruan Wan
    In criminal intelligence analysis to complement the information entailed and to enhance transparency of the operations, it demands logs of the individual processing activities within an automated processing system. Management and tracing of such security sensitive analytical information flow originated from tightly coupled visualizations into visual analytic system for criminal intelligence that triggers huge amount of analytical information on a single click, involves design and development challenges. To lead to a believable story by using scientific methods, reasoning for getting explicit knowledge of series of events, sequences and time surrounding interrelationships with available relevant information by using human perception, cognition, reasoning with database operations and computational methods, an analytic visual judgmental support is obvious for criminal intelligence. Our research outlines the requirements and development challenges of such system as well as proposes a generic way of capturing different complex visual analytical states and processes known as analytic provenance. The proposed technique has been tested into a large heterogeneous event-driven visual analytic modular analyst’'s user interface (AUI) of the project VALCRI (Visual Analytics for Sensemaking in Criminal Intelligence) and evaluated by the police intelligence analysts through it's visual state capturing and retracing interfaces. We have conducted several prototype evaluation sessions with the groups of end-users (police intelligence analysts) and found very positive feedback. Our approach provides a generic support for visual judgmental process into a large complex event-driven AUI system for criminal intelligence analysis.
  • Item
    Automating Visualization Quality Assessment: a Case Study in Higher Education
    (The Eurographics Association, 2021) Holliman, Nicolas S.; Xu, Kai and Turner, Martin
    We present a case study in the use of machine+human mixed intelligence for visualization quality assessment, applying automated visualization quality metrics to support the human assessment of data visualizations produced as coursework by students taking higher education courses. A set of image informatics algorithms including edge congestion, visual saliency and colour analysis generate machine analysis of student visualizations. The insight from the image informatics outputs has proved helpful for the marker in assessing the work and is also provided to the students as part of a written report on their work. Student and external reviewer comments suggest that the addition of the image informatics outputs to the standard feedback document was a positive step. We review the ethical challenges of working with assessment data and of automating assessment processes.
  • Item
    Modelling of Clouds from a Hemispherical Image
    (The Eurographics Association, 2014) Alldieck, Thiemo; Lundtoft, Dennis H.; Montanari, Niels; Nikolov, Ivan; Vlaykov, Iskren G.; Madsen, Claus B.; Rita Borgo and Wen Tang
    This paper presents an image-based method for modelling clouds. Unlike previous image-based approaches, a hemispherical photograph is used as input, enabling to consider an entire sky instead of merely a portion. Our method computes the intensity and opacity of the clouds from the photograph. For this purpose, beforehand, the sun illumination is filtered, the pixels are classified between cloud and sky pixels, and the sky behind the clouds is reconstructed. After having been smoothed, the intensity of the clouds is used to create vertices on a hemisphere, and their radius coordinate is modulated by the intensity value of the corresponding pixel. Finally, the mesh is generated by triangulation of the vertices. Additionally, the use of the opacity of the clouds to simulate their transparency and render them is proposed. The results show that our method can be used to produce a realistic full sky populated with clouds in a very straightforward way for the user.
  • Item
    EBBVH: A Novel Method for Constructing Bounding Volume Hierarchies
    (The Eurographics Association, 2024) Houghton, Matthew; Spoerer, Kristian; Hunter, David; Slingsby, Aidan
    We present an attempt to improve upon the construction of the most prevalent acceleration structure that is used in ray traced rendering techniques, the Bounding Volume Hierarchy. Our improvement is a novel technique for BVH construction called 'Edge-Based Bounding Volume Hierarchy'. This algorithm uses a hybrid top-down & bottom-up approach to improve performance for raytracing in large scenes, by up to 10x in some scenes.
  • Item
    Extended Reality (XR) Immersive Visualisation: Identifying AI project member 'needs' in order to design for a more effective Low-Code Machine Learning Model Development experience
    (The Eurographics Association, 2022) Wheeler, Richard; Carroll, Fiona; Peter Vangorp; Martin J. Turner
    With organisations making machine learning projects more of a priority, issues have been found regarding the presentation of these types of projects and in particular, in explaining how the models that are produced work, not only internally but also to the final user. The following paper discusses the design and development of a novel Extended Reality (XR) solution that enables rapid development, experimentation and clear presentation of complex machine learning models using eXplainable AI (XAI) principles. The paper documents the findings from a short initial feasibility questionnaire study which probed participant's opinions around their current use of XR environments, low-code development platforms, and their experience of working on machine learning model development projects. The findings of that study showed that the proposed solution could be deemed novel especially regarding its use of extended reality, as none of the participants had used this technology for machine learning development productivity or collaboration. The aim of the paper is to highlight the development of a system that uses a low-code development platform for the development of machine learning models and then uses an extended reality environment to not only enable collaboration within development teams but also as a system for presenting a model's output. This paper documents the early phases of the research process (i.e. identifying the need) whilst also sharing ideas on how the issue can be solved.
  • Item
    Sketching for Real-time Control of Crowd Simulations
    (The Eurographics Association, 2017) Gonzalez, Luis Rene Montana; Maddock, Steve; Tao Ruan Wan and Franck Vidal
    Crowd simulations are used in various fields such as entertainment, training systems and city planning. However, controlling the behaviour of the pedestrians typically involves tuning of the system parameters through trial and error, a time-consuming process relying on knowledge of a potentially complex parameter set. This paper presents an interactive graphical approach to control the simulation by sketching in the simulation environment. The user is able to sketch obstacles to block pedestrians and lines to force pedestrians to follow a specific path, as well as define spawn and exit locations for pedestrians. The obstacles and lines modify the underlying navigation representation and pedestrian trajectories are recalculated in real time. The FLAMEGPU framework is used for the simulation and the game engine Unreal is used for visualisation. We demonstrate the effectiveness of the approach using a range of scenarios, producing interactive editing and frame rates for tens of thousands of pedestrians. A comparison with the commercial software MassMotion is also given.
  • Item
    Recognising Specific Foods in MRI Scans Using CNN and Visualisation
    (The Eurographics Association, 2020) Gardner, Joshua; Al-Maliki, Shatha; Lutton, Évelyne; Boué, François; Vidal, Franck; Ritsos, Panagiotis D. and Xu, Kai
    This work is part of an experimental project aiming at understanding the kinetics of human gastric emptying. For this purpose magnetic resonance imaging (MRI) images of the stomach of healthy volunteers have been acquired using a state-of-art scanner with an adapted protocol. The challenge is to follow the stomach content (food) in the data. Frozen garden peas and petits pois have been chosen as experimental proof-of-concept as their shapes are well defined and are not altered in the early stages of digestion. The food recognition is performed as a binary classification implemented using a deep convolutional neural network (CNN). Input hyperparameters, here image size and number of epochs, were exhaustively evaluated to identify the combination of parameters that produces the best classification. The results have been analysed using interactive visualisation. We prove in this paper that advances in computer vision and machine learning can be deployed to automatically label the content of the stomach even when the amount of training data is low and the data imbalanced. Interactive visualisation helps identify the most effective combinations of hyperparameters to maximise accuracy, precision, recall and F1 score, leaving the end-user evaluate the possible trade-off between these metrics. Food recognition in MRI scans through neural network produced an accuracy of 0.97, precision of 0.91, recall of 0.86 and F1 score of 0.89, all close to 1.