The State of the Art in Integrating Machine Learning into Visual Analytics (Endert et al. 2017)

The vision

• Visual analytics systems combine machine learning or other analytic techniques with interactive data visualization to promote sensemaking and analytical reasoning.

• People can make sense of large, complex data.

• Synergy between machine learning and visual analytics for impactful future research directions.

The State of the Art in Integrating Machine Learning into Visual Analytics (Endert et al. 2017)

The vision

The State of the Art in Integrating Machine Learning into Visual Analytics (Endert et al. 2017)

The vision

The State of the Art in Integrating Machine Learning into Visual Analytics (Endert et al. 2017)

The vision

The State of the Art in Integrating Machine Learning into Visual Analytics (Endert et al. 2017)

The vision

Interpretability and visualization in machine learning (Vellido 2019)

Problem of ML

• Data overabundance and new methodologies for data management and analysis pose some serious challenges. One of them is model interpretability and explainability, especially for complex nonlinear models.
• In some areas such as medicine and health care, not addressing such challenge might seriously limit the chances of adoption, in real practice, of computer-based systems that rely on machine learning and computational intelligence methods for data analysis.

Interpretability and visualization in machine learning (Vellido 2019)

Interpretability and visualization in machine learning (Vellido 2019)

Interpretability and visualization in machine learning (Vellido 2019)

ML techniques to achieve a better design, development, and evaluation of visualizations (Wang et al 2022).

ML4VIS

Two questions:

• What visualization processes can be assisted by ML?
• How ML techniques can be used to solve visualization problems?

Three big areas and seven Main Visualization Processes Employing ML:

ML4VIS

Source: Wang, Qianwen, Zhutian Chen, Yong Wang, and Huamin Qu. 2022. “A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization.” IEEE Transactions on Visualization and Computer Graphics 28(12): 5134–53.

Seven Main Visualization Processes Employing ML:

ML4VIS

ML4VIS

• Rule # 1: Never use default

• Grammar of Graphics

• Cognitive elements + Functionalism

• Science of Color (Palette use)

• Font and theme use

• Message in Data

• R Graphics (Murrell and others)

• R ggplot2 (Wickham and associates)

  • GGAlly

  • gganimate (if you want animation)

• Shiny

• Interactive elements (Dash, D3, bokeh, Plotly)

• Dashboard

• Note on data: time series, spatial and models

• Website

What more skills I should learn?

What's next?

• Markdown language (MD): Quarto, Bookdown, Blogdown, dashboards

• Notebook-based development: Colab, Jupyter notebook, RStudio cloud (bilingual)

• Dashboard with live data

• Language: R, Python, SQL and Julia

• AI: GPT for coding and visualization (?)

• EPPS 6323 Knowledge Mining

  • Data Mining

  • Text Analytics

  • Machine Learning

• EPPS 6354 Information Management

  • SQL
  • Database server: PostgreSQL
  • Web/application server: Shiny and Django