How to identify anomalies?
In this section, the best explainable visualisations to identify anomalies are displayed. Anomalies are deviations or irregularities in data patterns that stand out from the expected or normal behavior. This section will help you to early detect irregularities by minimising their impact before they escalate. Anomalies can manifest in diverse ways, including outliers, spikes, unexpected trends, and instances of missing data.
Heatmap
Description
Example from XMANAI
A heatmap is a visual representation of data in the form of a colored matrix, where colors indicate numerical values in the matrix cells. Typically, more intense colors represent higher or lower values depending on the context. Heatmaps are used to highlight patterns and relationships in data, making it easier to understand trends. They are often employed to visualize the correlation between variables in a dataset or to represent the distribution of values in a matrix.
A 3D heatmap representation has been used in XMANAI to highlight the predicted measurement error on a spherical surface. The 3 axys (x, y, z) constitute the 3d space – expressed in mm – in which each error point is represented. The points are represented in a specific point of the space using a gradient color scale to identify the intensity of the error.
