Özet:

A classification scheme for disturbance signals using the Partitioned Feature-based Classifier (PFC) model is proposed in this paper. PFC model does not use the entire feature vectors extracted from the original data in a concatenated form to classify each datum, but rather uses groups of features related to each feature vector separately. In order to find proper features for disturbance signals, Fourier transform and wavelet transform are utilized. To validate the proposed scheme and feature extraction methods, experiments are performed with several types of disturbances in signals. The results show that the proposed classifier scheme with CNN (Centroid Neural Network) as its local classifier can improve its training speed and classification accuracy over conventional classification algorithms.

Anahtar Kelimeler: