RESEARCH ON VISUAL ANALYSIS TECHNIQUE OF MULTI-DMENSIONAL HEALTH DATA BASED ON PARALLEL COORDINATES

Health data set usually is a huge, complex and multivariate data set. It is difficult for doctors to understand and analyse these large amount of data and the relationships between them without visual techniques. Parallel coordinate is an effective technique to visualize complex multivariate data set. In this paper, we present a visual analysis method on multidimensional health data. With this method, the target properties are first selected from data set. Then the selected data are visualized with parallel coordinate, using coloured subsection property axes and property value marker to solve the disorder problem when there are large amount of data on the screen. And last, the cluster method based on parallel coordinate is provided to help user analysing the data. The method was used in HIMES (Health Information Management and Evaluation System) that can provide relation analysis, trend analysis and cluster analysis etc. The application result of HIMES proved that this method is effect in helping doctor to analyse the complex health data set. The method presented in this paper can also be used in data analysis in other field such as population statistics, market researching and so on.