Visual analytics has been important for many data-driven applications in modern industries.However, there has been limited research of semantic technologies for visual analytics, which hamstrings its transparency and reusability. To this end, we propose a semantic system that encodes visual analytical solutions in reusable knowledge graphs, which can be translated to executable scripts. Further more, our approach incorporates domain knowledge such as feature type information by linking domain ontologies and visual ontology. This poster paper presents preliminary evaluation of our approach with a Bosch use case with promising results.
Visual analytics has been essential for data analysis in a wide range of applications in modern
industries, such as in exploratory data analysis for gaining understanding and first insights for
the data [
Moreover, existing ontologies [
System Overview. We now walk through our system (Figure 1a). From the bottom left, the
Non-KG Data can be e.g., relational tables (csv), json files. For simplicity, we focus on relational
tables. These data are mapped to the domain ontology via Data-to-Domain (Data2Domain)
Mapping. The Data2Domain Mapping maps tables and table columns to classes in the .
Through Data Integration, domain KGs are generated. The Visual Ontology contains
axioms that describe the knowledge for visual analytics. The Visual KG Construction follows
the schema defined by and generates Visual KG [
The Data2Domain Mapping is provided by domain experts in the form of rules as sql() → , where sql() is an SQL query on table R that returns table columns and A is a class in the ontologies. We choose OWL 2 QL for becasue it is optimised for eficient query answering over relational databases. We choose OWL 2 EL for because of its expressivity and it is still polynomial for query answering. Between Data2Domain Mapping and there exist class links, since Data2Domain Mapping maps the Non-KG Data to classes in . All classes in that represent features in data are linked to classes in via the subclass axioms. Example 1. CurrentCurve is a column in the relational tables Current that stores the data of current sensors measured every millisecond. This column is mapped to the class OperationCurveCurrent in the : SELECT CurrentCurve AS cc FROM Current → do:OperationCurveCurrent(cc), which describes the current curve corresponding to a welding operation. The class OperationCurveCurrent is linked to the class TimeSeries via the subclass axiom: do:OperationCurveCurrent ⊑ visu:TimeSeries.
Data Integration. With the Data2Domain Mapping and the , data from diferent sources 1.6 1.4 e1.2 u l a V -Q 1 0.8 0.6
Prog1
Prog2 and formats are integrated into KGs with unified formats and feature names. This is done via the ETL (extract-transform-load) process.
Example 2. A series of columns in diferent data sources, such as CurrentCurve, Strom, CurrentAmp are all mapped to the class OperationCurveCurrent in the . They all are renamed to OperationCurveCurrent in the resulting Domain KG.
Visual KG Construction. To construct Visual KGs, our approach takes a KG template (Figure 1b), and extends the template with more entities of the PlotTask and fills in the properties. We ofer two ways of Visual KG construction. One is the manual way done by the users via a GUI (Example 3), or semi-automated via a set of rules with open world assumption (Example 4). Example 3. Take Fig. 2 as an example. Once the users choose to create a visual KG, the GUI will use the template in Figure 1b, which contains several owl:NamedIndividuals of the types VisualPipeline, CanvasTask, PlotTask, and DescriptionTask. Next, the users will need to select the input data, and add several entities of PlotTasks from available tasks based on . For each PlotTask, the input data, the method and some parameters are mandatory to be given. The users need to configure the PlotTasks by specifying e.g., the inputs, line colour, line width. After that, they can also configure the CanvasTask and the DescriptionTask by giving the x label, y label, legend, etc. Example 4. Our approach first identifies there exists three input features with the labels: target, estimated training and estimated test. Then it generates a KG from the template in Figure 1b with three entities of PlotTasks between the CanvasTask and DescriptionTask. All of them are subclasses of TimeSeries. For TimeSeries, our approach uses the rule that adopts LinePlotMethod as the recommended plot method and adds its typing information: ∃hasMethod−.(Task ⊓ ∃hasInput.TimeSeries) ⊑ LinePlotMethod Visual KG Execution. The execution of visual KGs is language-dependent. Here we use Python for discussion: each individual of PlotMethod is a Python script for plotting, whose mandatory inputs/outputs and parameters are clearly defined. Each Visual KG contains an entity of VisualPipeline and a series of Tasks connected with hasNextTask. Thus, the execution of a Visual KG invokes the Python function scripts with the inputs/outputs and parameters given by Data and datatype properties of KGs, according to the order defined by hasNextTask.
Industrial Use Case. We tested our approach in an industrial scenario of machine learning based quality monitoring for automated resistance spot welding at Bosch, which is an impactful welding process accounting for the production of over 50 million cars globally every year. We invited industrial users from Bosch, including non-data-scientists to workshops for evaluation. The visual KGs ran on a sample welding production dataset collected from a factory in Germany, contains 4585 welding operation records.
Visual Analytical Tasks and Reusability. The tasks in the use case can be categorised into two types: I. Data inspection (Figure 2a and Example 3), and II. Results visualisation. Type I tasks are to inspect various data in exploratory data analysis for understanding the data, and Type II tasks are to visualise results of statistical/ML analytics for discussing and interpreting the statistical/ML models for decision-making.
Example 5. For a new task of Type II and a new dataset in Figure 3a, the users can reuse the
VisualPipeline in Figure 2a by simply modifying the input data entities (1), the plot methods (2),
and properties of the plotting tasks (3, e.g., colour, marker size, labels, legend). This demonstrates
the good reusability of our approach.
Transparency and Coverage. Category Plot types # KGs Coverage
W2K4Ge2 KCpGraostgaalrnoadgmuumes.aettihcaiWsllyaes tgoheregnaVenriasistueeaddl iDnastpaection LPHiieneaecthmpalaorptt, scatter plot, bar chart 538647 1880550%%%
extensive workshops and collected Results Line plot, scatter plot, bar chart 48 100%
24 reports from Bosch welding visualisation Heatmap 17 85%
experts, engineers, semantic experts, data scientists. They answered questions such as “I
found the semantic system helps to improve the transparency of visual analytics compared to the
case without the approach”, and gave scores ranging 1-5 (from disagree, fairly agree, neural,
fairly agree, to agree) which aggregated to 4.28 ± 0.47 (mean ± standard deviation) for the
transparency. After discussion, we categorised most tasks of visual encountered in our project
in groups (Table 1), and give the coverage percentage according to our empirical cases. We
can see that most of categories can be covered (above 80%)
Conclusion and Outlook. This poster presents our system of domain knowledge supported
KG construction for visual analytics, which ofers good reusablity, transparency and coverage
for the visual analytic tasks. We evaluated the system on a Bosch welding use case with
promising results. As future work we plan to study hierarchical topic modelling to better
organise our visual KG catalogue and push the deployment further. We also plan to further
improve the system and organise demonstrations to a broader audience [
References