Search Results

Now showing 1 - 4 of 4
  • Item
    Comparing Distance Metrics in Space-time Clustering to Provide Visual Summaries of Traffic Congestion
    (The Eurographics Association, 2024) Baudains, Peter; Holliman, Nicolas S.; Hunter, David; Slingsby, Aidan
    Smart Cities are characterised by their ability to collect and process large volumes of sensor data. Visual analytics is then often required to make this data actionable and to allow decisions to be made in support of the well-being of inhabitants. In this study, using Bus Open Data, we consider how space-time clustering can be used to generate visual summaries of traffic congestion. Using a space-time extension of DBSCAN, our clustering procedure is evaluated with respect to both Euclidean distance and street network distance. Results show that network-based distance metrics improve the clustering procedure by generating clusters with less uncertainty. Moreover, congestion clusters derived from network-based distances are also more likely to last longer and to precede future congestion appearing nearby. We suggest that network-based distances might provide greater opportunity for more impactful traffic control room decision-making and we discuss steps towards a near real-time system design that can be used in support of operational decision-making.
  • Item
    Visual Interpretation of Tagging: Advancing Understanding in Task-Oriented Dialogue Systems
    (The Eurographics Association, 2024) Zhou, Yazhuo; Xing, Yiwen; Abdul-Rahman, Alfie; Borgo, Rita; Hunter, David; Slingsby, Aidan
    In task-oriented dialogue systems, tagging tasks leverage Large Language Models (LLMs) to understand dialogue semantics. The specifics of how these models capture and utilize dialogue semantics for decision-making remain unclear. Unlike binary or multi-classification, tagging involves complex multi-to-multi relationships between features and predictions, complicating attribution analyses. To address these challenges, we introduce a novel interactive visualization system that enhances understanding of dialogue semantics through attribution analysis. Our system offers a multi-level and layer-wise visualization framework, revealing the evolution of attributions across layers and allowing users to interactively probe attributions. With a dual-view for streamlined comparisons, users can effectively compare different LLMs. We demonstrate our system's effectiveness with a common task-oriented dialogue task: slot filling. This tool aids NLP experts in understanding attributions, diagnosing models, and advancing dialogue understanding development by identifying potential sources of model hallucinations.
  • Item
    LLM-Assisted Visual Analytics: Opportunities and Challenges
    (The Eurographics Association, 2024) Hutchinson, Maeve; Jianu, Radu; Slingsby, Aidan; Madhyastha, Pranava; Hunter, David; Slingsby, Aidan
    We explore the integration of large language models (LLMs) into visual analytics (VA) systems to transform their capabilities through intuitive natural language interactions. We survey current research directions in this emerging field, examining how LLMs are integrated into data management, language interaction, visualisation generation, and language generation processes. We highlight the new possibilities that LLMs bring to VA, especially how they can change VA processes beyond the usual use cases. We especially highlight building new visualisation-language models, allowing access of a breadth of domain knowledge, multimodal interaction, and opportunities with guidance. Finally, we carefully consider the prominent challenges of using current LLMs in VA tasks. Our discussions in this paper aim to guide future researchers working on LLM-assisted VA systems and help them navigate common obstacles when developing these systems.
  • Item
    Multi-fidelity Multi-disciplinary Optimisation of Propeller Design by Visual Analytics
    (The Eurographics Association, 2024) Shubham, Shubham; Spinelli, Andrea; Kipouros, Timoleon; Hunter, David; Slingsby, Aidan
    This paper introduces a comprehensive framework for multi-fidelity, multi-disciplinary optimization of propeller design using visual analytics. The proposed methodology integrates advanced data visualization techniques, surrogate modelling and optimisation methodologies to handle high-dimensional data across various disciplines, including aerodynamics, aeroacoustics, and structures. By leveraging multi-fidelity simulations, the framework balances accuracy with computational efficiency, enabling detailed exploration and optimization of propeller designs. Interactive visualization tools in the framework facilitate the identification of optimal design parameters and trade-offs, highlighting its potential to improve decision-making in engineering design processes in terms of confidence and knowledge creation.