Time series classification based on discrete-space feature extraction
Željko Jagnjić, Nikola Bogunović, Franjo Jović · 2003
In this paper we present time-series classification method based on discrete-space feature extraction. The main characteristics of the method are expansion and coding of quantitative time-series data. Expansion and coding will result in creation of qualitative difference vector. Qualitative difference vector conveys the full information on the variation of the particular time-series and can be seen as a single point in n-dimensional discrete-space. From discrete-space, symbolic and numeric features are extracted and used for the decision tree construction that is later used in time-series classification. The proposed method was tested in the context of Control Chart Pattern data, which are time-series used in Statistical Process Control. Obtained results are compared with other similar methods.