29 results
Search Results
Now showing 1 - 10 of 29
Item Authoring Visualisation of Routinely Collected Data Using LLMs(The Eurographics Association, 2024) Hosseini, Amir; Wood, Jo; Elshehaly, Mai; Hunter, David; Slingsby, AidanThe 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 EBBVH: A Novel Method for Constructing Bounding Volume Hierarchies(The Eurographics Association, 2024) Houghton, Matthew; Spoerer, Kristian; Hunter, David; Slingsby, AidanWe 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 Map Augmentation and Sketching for Cycling Experience Elicitation(The Eurographics Association, 2024) Reljan-Delaney, Mirela; Wood, Jo D.; Taylor, Alex S.; Hunter, David; Slingsby, AidanThis work examines the use of maps for knowledge elicitation in the sphere of urban cycling. The study involved running 14 distinct workshops, each serving as a unique data collection session for a particular individual. In each workshop, the participant was provided with 12 different renditions of the geographical areas as well as drawing materials. The geographical area renditions contained regions specified by the participant as cycling locations during the preparatory correspondence. The outputs were analysed for patterns in map augmentations and thematic content in the sketches. We have found that participants engaged deeply with the map augmentation process expressing their preferences and giving new insights. Themes such as connectivity, scenic beauty, and temporality emerged prominently from the analysed data, shedding light on the subjective experiences and preferences of urban cyclists.Item Skipping Spheres: SDF Scaling & Early Ray Termination for Fast Sphere Tracing(The Eurographics Association, 2024) Polychronakis, Andreas; Koulieris, George Alex; Mania, Katerina; Hunter, David; Slingsby, AidanThis paper presents a rapid rendering pipeline for sphere tracing Signed Distance Functions (SDFs), showcasing a notable boost in performance compared to the current state-of-the-art. Existing methods endeavor to reduce the ray step count by adjusting step size using heuristics or by rendering multiple intermediate lower-resolution buffers to pre-calculate non-salient pixels at reduced quality. However, the accelerated performance with low-resolution buffers often introduces artifacts compared to fully sphere-traced scenes, especially for smaller features, which might go unnoticed altogether. Our approach significantly reduces steps compared to prior work while minimising artifacts. We accomplish this based on two key observations and by employing a single low-resolution buffer: Firstly, we perform SDF scaling in the low-resolution buffer, effectively enlarging the footprint of the implicit surfaces when rendered in low resolution, ensuring visibility of all SDFs. Secondly, leveraging the low-resolution buffer rendering, we detect when a ray converges to high-cost surface edges and can terminate sphere tracing earlier than usual, further reducing step count. Our method achieves a substantial performance improvement (exceeding 3× in certain scenes) compared to previous approaches, while minimizing artifacts, as demonstrated in our visual fidelity evaluation.Item Real-time Data-Oriented Virtual Forestry Simulation for Games(The Eurographics Association, 2024) Williams, Benjamin; Oliver, Tom; Ward, Davin; Headleand, Chris; Hunter, David; Slingsby, AidanThe current frontier of virtual forestry algorithms remain largely unoptimised and ultimately unsuitable for real-time applications. Providing an optimisation strategy for the real-time simulation of virtual forestry would find particular utility in some areas, for example, in video games. With this motivation in mind, this paper presents a novel optimisation strategy for asymmetric plant competition models. In our approach, we utilise a data-oriented methodology with spatial hashing to enable the real-time simulation of virtual forests. Our approach also provides a significant improvement in performance when contrasted with existing serial implementations. Furthermore, we find that the introduction of our optimisation strategy can be used to simulate hundreds of thousands of virtual trees, in real-time, on a typical desktop machine.Item Creating Data Art: Authentic Learning and Visualisation Exhibition(The Eurographics Association, 2024) Roberts, Jonathan C.; Hunter, David; Slingsby, AidanWe present an authentic learning task designed for computing students, centred on the creation of data-art visualisations from chosen datasets for a public exhibition. This exhibition was showcased in the cinema foyer for two weeks in June, providing a real-world platform for students to display their work. Over the course of two years, we implemented this active learning task with two different cohorts of students. In this paper, we share our experiences and insights from these activities, highlighting the impact on student engagement and learning outcomes. We also provide a detailed description of the seven individual tasks that learners must perform: topic and data selection and analysis, research and art inspiration, design conceptualisation, proposed solution, visualisation creation, exhibition curation, and reflection. By integrating these tasks, students not only develop technical skills but also gain practical experience in presenting their work to a public audience, bridging the gap between academic learning and professional practice.Item Computer Graphics and Visual Computing (CGVC): Frontmatter(The Eurographics Association, 2024) Slingsby, Aidan; Hunter, David; Slingsby, Aidan; Hunter, DavidItem The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Others(The Eurographics Association, 2024) Sikar, Daniel; Garcez, Artur d'Avila; Bloomfield, Robin; Weyde, Tillman; Peeroo, Kaleem; Singh, Naman; Hutchinson, Maeve; Laksono, Dany; Reljan-Delaney, Mirela; Hunter, David; Slingsby, AidanThis study introduces the Misclassification Likelihood Matrix (MLM) as a novel tool for quantifying the reliability of neural network predictions under distribution shifts. The MLM is obtained by leveraging softmax outputs and clustering techniques to measure the distances between the predictions of a trained neural network and class centroids. By analyzing these distances, the MLM provides a comprehensive view of the model's misclassification tendencies, enabling decision-makers to identify the most common and critical sources of errors. The MLM allows for the prioritization of model improvements and the establishment of decision thresholds based on acceptable risk levels. The approach is evaluated on the MNIST dataset using a Convolutional Neural Network (CNN) and a perturbed version of the dataset to simulate distribution shifts. The results demonstrate the effectiveness of the MLM in assessing the reliability of predictions and highlight its potential in enhancing the interpretability and risk mitigation capabilities of neural networks. The implications of this work extend beyond image classification, with ongoing applications in autonomous systems, such as self-driving cars, to improve the safety and reliability of decision-making in complex, real-world environments.Item A Stereo-Integrated Novel View Synthesis Pipeline for the Enhancement of Road Surface Reconstruction Dataset(The Eurographics Association, 2024) Zhan, Mochuan; Morley, Terence; Turner, Martin; Hunter, David; Slingsby, AidanThis proposal outlines a novel view synthesis pipeline designed for road reconstruction in autonomous driving scenarios that leverages virtual camera technology to synthesise images from unvisited camera poses, thereby enhancing and expanding current datasets. It consists of three main steps: data acquisition, data preprocessing and fusion, and then importantly interacting with new 3D view synthesis with geometric priors. The modular design allows each component to be independently optimised and upgraded, ensuring flexibility and adaptability to various datasets and task requirements. The proposed approach aims to improve the robustness, realism, and photometric consistency of novel view synthesis, effectively handling dynamic scenes and varying lighting conditions. Additionally, this research plans to open-source a low-cost stereo camera hardware solution with the included software implementation.Item DeFT-Net: Dual-Window Extended Frequency Transformer for Rhythmic Motion Prediction(The Eurographics Association, 2024) Ademola, Adeyemi; Sinclair, David; Koniaris, Babis; Hannah, Samantha; Mitchell, Kenny; Hunter, David; Slingsby, AidanEnabling online virtual reality (VR) users to dance and move in a way that mirrors the real-world necessitates improvements in the accuracy of predicting human motion sequences paving way for an immersive and connected experience. However, the drawbacks of latency in networked motion tracking present a critical detriment in creating a sense of complete engagement, requiring prediction for online synchronization of remote motions. To address this challenge, we propose a novel approach that leverages a synthetically generated dataset based on supervised foot anchor placement timings of rhythmic motions to ensure periodicity resulting in reduced prediction error. Specifically, our model compromises a discrete cosine transform (DCT) to encode motion, refine high frequencies and smooth motion sequences and prevent jittery motions. We introduce a feed-forward attention mechanism to learn based on dual-window pairs of 3D key points pose histories to predict future motions. Quantitative and qualitative experiments validating on the Human3.6m dataset result in observed improvements in the MPJPE evaluation metrics protocol compared with prior state-of-the-art.
- «
- 1 (current)
- 2
- 3
- »