Nicolas Schneider
ABSTRACT
XCS-GP (Generic Prognosis) is a new process to compute system degradation in industrial prognosis activities field. Our approach is based on XCS core algorithm [6] extended with an auto-diagnosis module and dynamic learning strategies. We've tested our system on a real Airbus use case. We predict the degradation of an A340 system brake wear based on the aircraft mission plan. The underlying idea of our approach is to find implicit links between aircraft data and environmental data which leads to specifics aircraft degradation. Results are promising, furthermore our approach does not need experts knowledge. It is therefore generic and could be easily applied to other systems.
- Jhon Holmes Alwyn Barry and Xavier Llora. Data mining using learning classifier systems. Foundations of Learning Classifier Systems, 2004.Google Scholar
Cross Ref
- Xavier Llor' Ester Bernad and Josep M. Garrell. Xcs and gale: a comparative study of two learning classifier systems with six other learning algorithms on classification tasks. ADVANCES IN LEARNING CLASSIFIER SYSTEMS, 2321/2002:115--132, 2002.Google ScholarCross Ref
- Chris Lokan Hai H. Dam, Hussein A. Abbass. Evolutionary online data mining an investigation in a dynamic environment. The Artificial Life and Adaptive Robotics Laboratory, 2005.Google Scholar
- Martin V. Butz Hussein A. Abbass, Jaume Bacardit and Xavier Llora. Online adaptation in learning classifier systems: Stream data mining. Technical report, IlliGAL, 2004.Google Scholar
- David E Goldberg Lashon B Booker and John H Holland. Classifier systems and genetic algorithms. Artificial Intelligence, 40:235--282, 1989.Google ScholarDigital Library
- Stewart W. Wilson. Classifier fitness based on accuracy. Evolutionary Computation, 3(2):149--175, 1995. Google ScholarDigital Library
- Stewart W. Wilson. Mining oblique data with xcs. Tech report number: 2000028, 2000.Google Scholar
Index Terms
- Generic prognosis with evolutionary approaches
Recommendations
Medical Prognosis Generation from General Blood Test Results Using Knowledge-Based and Machine-Learning-Based Approaches
AI 2016: Advances in Artificial IntelligenceAbstractIn this paper, we present two approaches to generate prognosis from general blood test results. The first approach is a knowledge-based approach using ripple-down rules (RDR). The knowledge-based approach with RDR converts knowledge of ...
MKNK2 as A Prognosis-Related Biomarker for Gastric Cancer
ICBBT '23: Proceedings of the 2023 15th International Conference on Bioinformatics and Biomedical TechnologyGastric cancer is a deadly disease with low survival rates around the world. Even though specific drugs based on molecular biology studies of gastric cancer and improvements in how gastric cancer is treated have been made, the survival rate for people ...
Comments