Refine
Year of publication
- 2017 (17) (remove)
Document Type
- Working Paper (8)
- Report (3)
- Book (2)
- Conference Proceeding (2)
- Article (1)
- Preprint (1)
Has Fulltext
- yes (17)
Keywords
- Forschungsbericht (2)
- Krisenmanagement (2)
- Optimization (2)
- Risikomanagement (2)
- Solvency II (2)
- 3D Printing (1)
- Algorithm Tuning (1)
- Alternativer Risikotransfer (1)
- Barwert (1)
- Basisrisiko (1)
- Bewertete Markov-Kette (1)
- Bewertung (1)
- Bewertungsportale (1)
- Big Data (1)
- Charakteristische Funktion (1)
- Collateralized Reinsurance (1)
- Combined simulation (1)
- Computational fluid dynamics (1)
- Conditional inference tree (1)
- Consumer Information (1)
- Decision tree (1)
- Design of Experiments (1)
- Digitalisierung (1)
- Disaster Risk Reduction (1)
- Embedded Value (1)
- Event Detection (1)
- Evolutionary Robotics (1)
- Faserverbundwerkstoffe (1)
- Forschung (1)
- Forschungsstelle FaRis (1)
- Forschungsstelle Versicherungsmarkt (1)
- Forschungsstelle Versicherungsrecht (1)
- Health condition monitoring (1)
- Hochschule (1)
- Institut für Versicherungswesen (1)
- Insurance Linked Securities (ILS) (1)
- Knowledge extraction (1)
- Konsumenteninformation (1)
- Kölner Forschungsstelle Rückversicherung (1)
- Lessons learned (1)
- Machine Learning (1)
- Machine learning (1)
- Markov-Kette (1)
- Massendaten (1)
- Metamodel (1)
- Modeling (1)
- Neural Networks (1)
- Online Information Review (1)
- Parameter Tuning (1)
- Predictive Analytics (1)
- Present Value (1)
- Priced Markov Chain (1)
- R (1)
- Research Report (1)
- Rückversicherung (1)
- SPOT (1)
- Signalanalyse (1)
- Simulation (1)
- Social Learning (1)
- Stacking (1)
- Structural Health Monitoring (1)
- Surrogate Models (1)
- Test function generator (1)
- Trinkwasser (1)
- Versicherung (1)
- Versicherungswesen (1)
- Versicherungswirtschaft (1)
- Wirtschaftswissenschaften (1)
- Word-of-Mouth (1)
- Ökonomisches Kapital (1)
As the amount of data gathered by monitoring systems increases, using computational tools to analyze it becomes a necessity.
Machine learning algorithms can be used in both regression and classification problems, providing useful insights while avoiding the bias and proneness to errors of humans. In this paper, a specific kind of decision tree algorithm, called conditional inference tree, is used to extract relevant knowledge from data that pertains to electrical motors. The model is chosen due to its flexibility, strong statistical foundation, as well as great capabilities to generalize and cope with problems in the data. The obtained knowledge is organized in a structured way and then analyzed in the context of health condition monitoring. The final
results illustrate how the approach can be used to gain insight into the system and present the results in an understandable, user-friendly manner