Visual Analytics - Process

Process

The input for the data sets used in the visual analytics process are heterogeneous data sources (i.e., the internet, newspapers, books, scientific experiments, expert systems). From these rich sources, the data sets S = S₁, ..., S_m are chosen, whereas each S_i, i ∈ (1, ..., m) consists of attributes A_i1, ..., A_ik. The goal or output of the process is insight I. Insight is either directly obtained from the set of created visualizations V or through confirmation of hypotheses H as the results of automated analysis methods. This formalization of the visual analytics process is illustrated in the following figure. Arrows represent the transitions from one set to another one.

More formal the visual analytics process is a transformation F: S → I, whereas F is a concatenation of functions f ∈ {D_W, V_X, H_Y, U_Z} defined as follows:

D_W describes the basic data pre-processing functionality with D_W : S → S and W ∈ {T, C, SL, I} including data transformation functions D_T, data cleaning functions D_C, data selection functions D_SL and data integration functions D_I that are needed to make analysis functions applicable to the data set.

V_W, W ∈ {S, H} symbolizes the visualization functions, which are either functions visualizing data V_S : S → V or functions visualizing hypotheses V_H : H → V.

H_Y, Y ∈ {S, V} represents the hypotheses generation process. We distinguish between functions that generate hyphotheses from data H_S : S → H and functions that generate hypotheses from visualizations H_V : V → H.

Moreover, user interactions U_Z, Z ∈ {V, H, CV, CH} are an integral part of the visual analytics process. User interactions can either effect only visualizations U_V : V → V (i.e., selecting or zooming), or can effect only hypotheses U_H : H → H by generating a new hypotheses from given ones. Furthermore, insight can be concluded from visualizations U_CV : V → I or from hypotheses U_CH : H → I.

The typical data pre-processing applying data cleaning, data integration and data transformation functions is defined as D_P = D_T(D_I(D_C(S₁, ..., S_n))). After the pre-processing step either automated analysis methods H_S = {f_s1, ..., f_sq} (i.e., statistics, data mining, etc.) or visualization methods V_S : S → V, V_S = {f_v1, ..., f_vs} are applied to the data, in order to reveal patterns as shown in the figure above.

In general the following paradigm is used to process the data:

Analyse First – Show the Important – Zoom, Filter and Analyse Further – Details on Demand