Numerical Time-Series Pattern Extraction Reflecting User's Interest

抄録

In this paper, we propose a method for extracting interesting patterns from numerical time-series data which takes account of user subjectivity. The proposed method irregularly samples the data preserving the subjectively noteworthy features using a user specified gradient. It also irregularly quantizes the data preserving the intrinsically objective characteristics of the data using statistical distributions. It then extracts representative patterns from the discretized data using group average clustering. We conducted the two experiments to evaluate the extraction performance of the proposed method. It is indicated that the proposed method does not destroy the intrinsically objective features by the experimental results using benchmark datasets. It is also indicated that the proposed method has the possibility to extract interesting patterns for a medical expert by the experimental results using a real clinical dataset on hepatitis.