Spatiotemporal data mining for movement ecology

GPS tracker technology is revolutionising ecological research. Movement Ecology is the science of using these data to infer behaviours that were not previously known to learn more about the organism, how it interacts with its environment and it sensitivity with the environment. This cross-disciplinary project will take advantage of a long-term collaboration with a movement ecology group to apply the latest data mining techniques to detect places of ecological significance for these animals at appropriate spatial scales.

Objectives

  • Review: Review the state of the art of movement ecology and spatiotemporal data mining
  • Implement: Implement appropriate versions data mining techniques that can be demonstrated to users
  • Test and evaluate: assess the utility of these methods for achieve movement ecology goals

Skills

  • Development: ability to build interactive visualisation interfaces that connect to statistics and data mining libraries/software
  • Statistics: a good understanding of applied statistics
  • User-centred work: open to designing, testing and evaluating these interfaces with analysts from different domains  
  • Other: Handling datasets, working with geographical data

Contact

This topic was suggested by Dr Aidan Slingsby. Please direct further enquiries to the giCentre.

Shelf life of data: a critical look at exploratory data analysis

Exploratory data analysis has significant potential within the analysis of complex, heterogeneous data where analysts are seeking observations that they can answer questions with and can action on within their application domain. As an open-ended process, exploratory analysis sessions can lead to several unexpected findings but with potential for high numbers of false positives and with limited guidance on when to conclude the analysis. This project aims to provide mechanisms and heuristics to increase the likelihood of success and the efficiency of exploratory analysis processes and investigates answers to questions such as, “When to know that the results are stable and actionable?”, “When does a data set stop being useful during exploratory data analysis session?”, “How to action on findings from an exploratory analysis process?” to name a few.

Objectives

  • Review literature within visual analytics and exploratory data analysis for data analysis strategies

  • Develop a theoretical framework to inform and guide users on the progress of an exploratory analysis process towards robust, stable and actionable findings

  • Design, develop, and evaluate interactive visualisations to support the above

Skills/Interests

  • Experience in designing and implement interactive visual representations

  • Good understanding of statistics, exploratory analysis, and related data-science techniques

  • Interest in user-centred design processes

Contact

This topic was suggested by Dr Cagatay Turkay. Please direct further enquiries to the giCentre.

Visualisation as Evidence: On the role and the limits of visualisation as scientific evidence

The tremendously increased availability and volume of data is reshaping how scientific investigation is executed, however, scientists still resort to conventional statistical analysis routines. Data-intensive investigations and analysis requires a new set of tools for the effective and robust generation and testing of hypotheses. Visualisation offers possibilities that can embrace the variety, uncertainty, and the multi-dimensionality within phenomena being investigated. This project aims to investigate the role and limitations of visual representations as scientific evidence to support and provide confidence within hypothesis generation and testing processes.

Objectives

  • Review literature in statistical and visual data analysis to build an understanding on the use of visualisation as an inference methodology

  • Design visual representations to be used as evidence in supporting scientific arguments within data-intensive hypothesis generation and testing settings

  • Design studies to investigate the effectiveness of visualisation designs

  • Develop a framework for the effective use of visualisation as scientific evidence

Skills/Interests

  • Ability to design and implement interactive visual representations

  • Good understanding of Statistical Analysis Techniques

  • Ability to design and execute user studies

Contact

This topic was suggested by Dr Cagatay Turkay. Please direct further enquiries to the giCentre.

Visual analytics for exploring geographical data: incorporating statistical modelling into exploratory data analysis

Design, implement, test and evaluate visual encodings and interactions for supporting explorative geographical data analysis with appropriate statistical and data mining techniques. These techniques should support analysts using domain knowledge to build simple models on-the-fly, gradually refining them using various model fit metrics and summary statistics, with the goal to understand the processes and drivers that led to the original data. Part of this process is maintaining the provenance of which models were built and their characteristics. Restricted to geographic data with features that are generally understood by analysts (i.e. not high dimensional data)

Objectives

  • Review: Exploratory visual interfaces, analytical "goals" in these interfaces, suitable statistical and data mining techniques, their application

  • Design: Based on one or more case studies, design visual encodings and interactions to support exploratory data analysis with appropriate statistical and data mining techniques

  • Implement: Implement versions of this design in order for them to be test and evaluated

  • Test and evaluate: assess the impact this has on the exploratory visualisation process

  • Provenance: Maintaining the provenance of which models were built and their characteristics and make available to support the data exploration process    

Skills

  • Development: ability to build interactive visualisation interfaces that connect to statistics and data mining libraries/software

  • Statistics: a good understanding of applied statistics

  • Statistical graphics: knowledge of the use of statistical graphics

  • User-centred work: open to designing, testing and evaluating these interfaces with analysts from different domains  

  • Other: Handling datasets, working with geographical data

Contact

This topic was suggested by Dr Aidan Slingsby. Please direct further enquiries to the giCentre.

From Personal Data to Personable Visualizations

Explore how by constructing visualizations of their personal data people can create an intimate relationship with their data. This exploration is deeply human-centred. It involves conducting several long-term studies with a group of people already collecting some kind of personal data (e.g., energy bills, bank accounts, fitness, time tracker, medical condition), human-centred iterative approaches to design and qualitative evaluations such as interviews, focus groups, and observations. The space of personal data visualization is ripe for research work, particularly in a dynamic context (with e.g., daily or weekly data updates) as the singularities of this context, such as the relationship that people have with their own personal data, are yet to be explored. This project will particularly look into the role of physical engagement when constructing physical visualizations in order to uncover how cognitive and kinesthetic efforts can enhance learning, memorability, enjoyment, and overall visualization literacy.

Objectives

  • Review the literature in physical visualization, personal visualization, and narrative visualizations; as well as in kinesthetic learning, learning-by-doing, and visualization literacy.

  • Iteratively design (possibly computer-supported) prototypes with people collecting personal data and willing to make better sense of it by themselves.

  • Study through qualitative methods what makes visualizations of personal data personable to people.

Skills/interests

  • Visualization / statistical graphics design

  • Human-centred design

  • Hands-on activities, fabrication

  • Qualitative methods such as interviews and open coding

  • Design and prototyping (computer-supported or not) skills

  • Map out the space of personable visualizations of personal data.

Contact 

This topic was suggested by Dr Charles Perin. Please direct further enquiries to the giCentre.

A quantitative model of visual performance based on principles of visual scanning

Important strides have been made in understanding how people scan visual content for information as a function of the interplay between the fovea and the peripheral view, the interplay between intentional and automatic processes, and the content itself. Such knowledge may be used to predict performance on low-level visual tasks in different visual encodings, and could be used in many cases as an alternative to user experimentation.

The project aims to build on previous models that use an understanding of low-level visual behavior to predict performance on simple HCI tasks (e.g., EPIC architecture), but would innovate by extending it to the much more complex content typical of real-life data visualizations.

Activities

  • Conducting user studies to explore visual scanning patterns for typical data-reading tasks in typical visual data content

  • Relating observed behavior to low-level models of visual scanning

  • Developing a general model of visual scanning as a function of visual content type and data-reading task

  • Conducting experiments to validate the model

Skills/Interests

  • User study design

  • Human factors (e.g., vision, cognition, task analysis)

  • Basic data handling and data analysis

Contact

This topic was suggested by Dr Radu Jianu. Please direct further enquiries to the giCentre.

Gaze-adaptive visualizations: principles, designs, benefits

Eye-tracking can provide real-time insight into the short and long term data preferences and interests of people using visual data analysis systems.  These systems could leverage such information to adapt intelligently in real time, and show data in ways that better support users’ goals and tasks. This project aims to explore principles of gaze-adaptive visual support in real applications.

Activities

  • Design and implement concrete gaze-adaptive interactive responses in established data visualizations or data-analytic systems.
  • Conduct user studies to test the effectiveness of such designs

Skills/Interests

  • User study design

  • Human factors (e.g., vision, cognition, task analysis)

  • Iterative software design and development, rapid prototyping

Contact

This topic was suggested by Dr Radu Jianu. Please direct further enquiries to the giCentre.

Framework for data-of-interest (DOI) eye-tracking experimentation

Eye-tracking allows us to capture where users are looking on a computer screen. DOI, a novel eye-tracking experimentation paradigm, relies on mapping users’ gazes to interactive visual content automatically and dynamically. This allows experimenters to track users’ deep interests in particular content, how these interests change over time, and how they support goals and tasks. This can facilitate unprecedented insight into how people rely on rich visual content and data to understand, learn, analyze, and decide.

The project aims to lay the groundwork for DOI experimentation by exploring the types of insights that can be achieved with it, and by designing novel analytical paradigms and tools necessary to interpret the large and complex data that DOI experiments typically produce. These topics will be pursued by applying DOI experimentation to concrete problems, such as exploring how people use visualization to explore and analyze data, or how students learn from visual content.

Activities

  • Design experiments and collect concrete DOI eye-tracking data, possibly in collaboration with researchers in other domains.

  • Analyze collected DOI data using conventional data science methods (i.e., existing visualization tools and data analysis packages)

  • Design and develop (iteratively) novel visual analytics paradigms and tools to explore DOI data in general

Skills/interests

  • User study design

  • Data handling, analysis, and visualization

  • Human-centred design

  • Iterative software design and development, rapid prototyping

Contact

This topic was suggested by Dr Radu Jianu. Please direct further enquiries to the giCentre.