Viscovery® Data Mining: Improving rockets, race cars and more
[News Viscovery]
Vienna / Austria, 23 October 2018 The Viscovery team has compiled a selection of scientific articles covering diverse applications in explorative data mining, clustering, and predictive analytics. With this collection, data analysts can leverage a wealth of experience that Viscovery users have gained through the use of self-organizing maps in a variety of application areas.
Out of several hundred publications, a representative selection of more than 180 articles has been listed on the Viscovery website. Each citation is supplemented by a brief description of the objective and a download link to the corresponding article.
Analytical application areas range from drug design, healthcare and nutrition to social development, customer analytics, crime and security, banking and economics to sensor data analysis and industrial engineering. In aerodynamic design engineering alone, you can read how Viscovery was used to optimize the design parameters of airliners, helicopters and drones, supersonic aircrafts, rockets and race cars.
The full list of publications is available at viscovery.net/scientific-articles.
Viscovery characterizes the respiratory physiome
[News Viscovery]
Horn (NL) / Vienna (AT), 12 September 2018 Together with Ingrid Augustin and her colleagues from our long term customer CIRO+, we published the article The respiratory physiome: clustering based on a comprehensive lung function assessment in patients with COPD in PLOS ONE.
The aim of this paper is to provide a comprehensive description of lung function for patients with chronic obstructive pulmonary disease (COPD) and study its connection to functional performance and health status. The Viscovery SOMine cluster model shows that lung-function impairment is a multidimensional problem, which cannot be characterized by a single measurement. In addition, it is shown that the lung-function profile alone is a poor predictor for functional performance, highlighting the necessity of additional performance tests and questionnaires to provide optimal treatment for patients.
Find the full open access article at journals.plos.org
New Viscovery® SOMine® data mining suite raises the bar for Big Data preprocessing and visual model interpretation
[News Viscovery]
Vienna / Austria, 29 June 2018 Viscovery has launched version 7.2 of its Viscovery® SOMine® visual data mining suite. The new version offers a set of features for improved performance in Big Data preprocessing, as well as for advanced annotation and interpretation of explorative models on multiple semantic levels.
Viscovery® SOMine® v7.2 comes with considerable performance improvements for preprocessing of Big Data. By using single-instance caching in data and model processing, the runtime for applying bulky definitions of nominal variables has been significantly reduced.
Annotation of the map with textual labels has been extended to allow thumbnails. For example, an associated image document, such as a photo, can be displayed at the location in the Viscovery map to which a patient has been classified. Another new feature allows users to manage labels, group them hierarchically, and hide or show these groupings. This helps users annotate and interpret the Viscovery map on different semantic levels.
The complete list of innovations is available at viscovery.net/data-sheets.
Viscovery powers COPD decision support system
[News Viscovery]
Marburg (DE) / Trondheim (NO) / Maastricht (NL) / Horn (NL) / Vienna (AT), 1 July 2018 Viscovery and our transnational group of scientific and clinical collaborators just started the interdisciplinary project ERACo SysMed-COPD.
The main aim of this project is to develop a clinical decision support system for chronic obstructive pulmonary disease (COPD), which will help doctors and medical staff to find the best therapeutic option for the individual patient. Data about several thousand patients from different patient cohorts at different clinics will be used to build a model for identifying possible risk factors and expectable outcomes to respiratory therapy.
The project is part of the EU framework ERACoSysMed for Systems Medicine to address clinical needs and is co-funded by the national funding institutions
- Bundesministerium für Bildung und Forschung (BMBF), Germany,
- The Austrian Science Fund (FWF), Austria,
- The Research Council of Norway (RCN), Norway,
- Zorgonderzoek Nederland (ZON), Netherlands.
Read more about the project at www.uni-marburg.de.