Fuzzy c-Means Clustering in the Presence of Noise Cluster for Time Series Analysis
Cluster analysis for time series is becoming increasingly important in many real applications. Clustering plays an important role in extracting information from the noise in economic and financial time series. In this paper we consider the use of fuzzy c-means clustering method in the context of econometric analysis of time-series data. We discuss and demonstrate a methodology for model identification and estimation that is based on the fuzzy c-means algorithm in the presence of noise cluster that is widely used in the context of pattern recognition. The effect of noise on time-series prediction is important to quantify for accurate forecasting. The noise clustering approach is based on the concept of first defining a noise cluster and then defining a similarity or dissimilarity measure for the noise cluster.
Unable to display preview. Download preview PDF.
- 6.Barnet, V., Lewis, T.: Outliers in statistical data, 3rd edn. John Wiley, Chichester (1994)Google Scholar
- 8.Miyagishi, K., Yasutomi, Y., Ichihashi, H., Honda, K.: Fuzzy Clustering with regularization by K-L information. In: 16th Fuzzy System Symposium, Akita, September 6-8, pp. 549–550 (2000) (in Japanese)Google Scholar
- 10.Kaiser, R., Maravall, A.: Seasonal outliers in time series, Banco de Espana - Servicio de Estudios paper number 9915 (1999) Google Scholar