A pattern recognition framework for detecting dynamic changes on cyclic time series

作者：

Highlights：

• We present a novel framework for classifying cyclic stochastic time series.

• The framework suggests a novel hybrid HMM–SVM model.

• Cyclic contents of the time series are learned by in the preprocessing phase.

• Considerations for “one versus C classes” classification is taken into account.

• The performance is improved by the model in a demanding clinical study.

摘要

Highlights•We present a novel framework for classifying cyclic stochastic time series.•The framework suggests a novel hybrid HMM–SVM model.•Cyclic contents of the time series are learned by in the preprocessing phase.•Considerations for “one versus C classes” classification is taken into account.•The performance is improved by the model in a demanding clinical study.

论文关键词：Hybrid model,Cyclic time series,Time series,Phonocardiogram,Systolic murmurs

论文评审过程：Received 14 December 2013, Revised 6 August 2014, Accepted 18 August 2014, Available online 28 August 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.08.017