Introduction of Data Visualization

Some people say that data visualization is not just drawing, and you can't see the value of research. I also naively thought that data visualization is to convert data from icy numbers into graphics. At most, it is rich in colors, which looks cooler and more full.

In fact, a good visualization can bring people not only visual impact, but also reveal the laws and truths contained in the data. The following summarizes the basic concepts of visualization.

The meaning of data visualization
The ultimate goal of visualization is to understand the phenomena and laws contained in the data, which has multiple meanings: discovery, decision-making, interpretation, analysis, exploration and learning.

The simple definition is: to enhance the efficiency of people to complete certain tasks through visual expression. For example, the visualization results of several sets of data with the same statistical characteristics (variance, mean, etc.) are completely different. The significance of visualization is that as an auxiliary tool of the human brain, visualization can retain some of the information for us, and it is not as good as a bad pen. Secondly, graphical symbols can direct the user's attention to important goals.

The goals and roles of  data visualization
Traditional visualization can be roughly divided into exploratory visualization and explanatory visualization. According to the application, visualization has multiple goals:

Effectively present important features
Reveal objective laws
Assist in understanding the concepts and processes of things
Quality monitoring of simulations and measurements
Improve research and development efficiency
Promote communication and cooperation
From a macro perspective, three functions of visualization:

information record
Information reasoning and analysis
Information dissemination and collaboration
Data visualization classification
Data visualization consists of three branches, scientific visualization (Sci Vis, Scientific Visualization) and information visualization (Info Vis, Information Visualization), and later evolved a third branch: visual analysis (VAST, Visual Analytics Science and Technology) from It can be seen in the classification of the IEEE VIS conference.

Scientific visualization is oriented to data in the fields of science and engineering, such as three-dimensional spatial measurement data of spatial coordinates and geometric information, computer simulation data, and medical image data, focusing on exploring how to present the laws contained in the data with geometric, topological, and shape features.

The object of information visualization is unstructured, non-geometric abstract data, such as financial transactions, social networks, and text data. The core challenge is how to reduce the interference of visual confusion on information for large-scale high-dimensional complex data.

In recent years, with the rise of artificial intelligence, people have gradually discovered that some machines can do better things than humans, and also found that some things need to use humans ’300 million years of evolutionary skills. Therefore, the combination of visualization and analysis has produced a new discipline: visual analysis.

Visual analytics is defined as the science of analytical reasoning based on visual interaction interfaces, which integrates graphics, data mining, human-computer interaction and other technologies to form the complementary and mutually reinforcing advantages of human brain intelligence and machine intelligence.