Similarity Search in Time Series of Dynamical Model-based Systems

摘要: Similarity search in time series is usually based on an assessment of the geometric similarity curves. In bioinformatics, dynamical model-based analysis and processing used, where curve itself not meaningful. However, some internal features a model extracted from are Therefore, explaining observation instead being merely superficial observation. There currently exist no methods for meaningful such data emerging bioinformatics. this paper, we introduce new method features, called perturbation method.