BACKGROUND: Research confirms that physical activity (PA) is irreplaceable in a healthy and physically active lifestyle. One of the key research questions is what the optimal level of everyday PA for health is and how it should be quantified and interpreted. Formal concept analysis is one possible way of how to assess and describe the level of PA as related to personal data. OBJECTIVE: The main goal of this study was to introduce the method of Formal Concept Analysis (FCA) using data from the ANEWS questionnaire and data from the objective monitoring of a number of steps using the YAMAX SW-701 pedometer. A further aim was to adopt the most appropriate method within the FCA. METHODS: A random sample of 273 males aged 18-69 from selected regional centers participated in the study. RESULTS: The example of daily steps allows for the demonstration of how important it is to select a scale in FCA data analysis. It is better to use an ordinal scale for the daily number of steps (in our example); because, in so doing, we create the attributes that can be ordered (a lower number of steps is also insufficient). CONCLUSIONS: A rough scale produces easier lattice with the general scope of the observed attributes. The smoothing of the scale produces more difficult lattice and makes for more difficult analyses, but gives more detailed results. FCA requires more expertise from a researcher than do "classical" testing statistics, but gives us deeper insight into the examination of the problem.
In this research a combined Semantic Web, Web Services and Web 2.0 approach is adopted in order to semi-automate social media Web sites for Museum Collections. The framework described has been applied in two Web-information system applications, the Virtual Museum of the Pacific and the Art Collection Ecosystem. Our paper highlights the generality of CollectionWeb by way of these two case studies.
T. Hanika, und J. Hirth. Accepted for Publication in Annals of Mathematics and Artificial Intelligence, (2022)cite arxiv:2002.11776Comment: 13 pages, 10 figures.
G. Stumme. Conceptual Structures: Knowledge Representation as Interlingua Proc. ICCS'96, Volume 1115 von LNAI, Seite 308-320. Heidelberg, Springer, (1996)
S. Prediger, und G. Stumme. Proc. 6th Intl. Workshop Knowledge Representation Meets Databases (KRDB'99), CEUR Workshop Proc. 21, (1999)Also in: P. Lambrix et al (Eds.): Proc. Intl. Workshop on Description Logics (DL'99). CEUR Workshop Proc. 22, 1999 http://ceur-ws.org/Vol-21.
B. Ganter, und S. Kuznetsov. Conceptual Structures: Broadening the Base, Volume 2120 von Lecture Notes in Computer Science, Springer Berlin Heidelberg, (2001)
S. Kuznetsov, und S. Obiedkov. Principles of Data Mining and Knowledge Discovery, Seite 289--300. Berlin, Heidelberg, Springer Berlin Heidelberg, (2001)
S. Doerfel, R. Jäschke, und G. Stumme. ICFCA 2012, Volume 7278 von Lecture Notes in Artificial Intelligence, Seite 77--95. Berlin/Heidelberg, Springer, (2012 (forthcoming))