Intelligent Engineering Systems through Artificial Neural Networks, Volume 16
48 Modeling and Classification for Uterine EMG Signals Using Autoregressive Model
Download citation file:
- Ris (Zotero)
- Reference Manager
This article proposes a method for modeling and classification apply on the uterine contractions in the electromyogram (EMG) signal for the detection of preterm birth. The frequency content of the contraction changes from one woman to another and during pregnancy. Firstly we apply an AR model on the Uterine EMG signal for the calculation of the ai parameters. Wavelet decomposition is used to extract the parameters of each simulated contraction, and an unsupervised statistical classification method based on Fisher test is used to classify the signals. A principal component analysis projection is then used to evidence the groups resulting from this classification. Results show that uterine contractions may be classified into independent groups according to their frequency content and according to term (at the recording, or at delivery).