Review of visual analytics methods for food safety risks

Area of Science:

• Food Safety Science
• Data Science
• Information Visualization

Background:

• Big data is increasingly utilized in food safety for risk analysis and prewarning (RAPW).
• Visual analytics offers interactive, human-machine integrated approaches for large-scale data insights.
• There is a growing need for advanced methods to address complex food safety challenges.

Purpose of the Study:

• To review the developments in visual analytics for food safety RAPW over the past decade.
• To summarize data sources, characteristics, and analysis tasks in food safety.
• To identify future opportunities and challenges in the field.

Main Methods:

• Review of data analysis methods for association analysis, risk assessment, risk prediction, and fraud identification.
• Review of visualization and interaction techniques for multidimensional, hierarchical, associative, and spatial-temporal data.
• Synthesis of current research trends and future directions in visual analytics for food safety.

Main Results:

• Data sources, characteristics, and analysis tasks in food safety are summarized.
• Data analysis methods for key RAPW tasks are reviewed.
• Visualization and interaction techniques for various data types are assessed.

Conclusions:

• Visual analytics provides novel solutions for food safety RAPW.
• Future opportunities include multimodal data analysis and AI integration.
• Addressing challenges is crucial for advancing visual analytics in food safety.