An automated feature extraction and emboli detection system based on the PCA and fuzzy sets
An automated feature extraction and emboli detection system based on the PCA and fuzzy sets
marzieyeh banaie shotorbaan1
1) Computer engineering graduate student in artificial intelligence orientation, Islamic Azad University, Tehran, Iran -
IOI Code
:
XYBD-ZKEEK
Publication :
4th International Conference On Research Science And Technology(4rstconf.com)
Abstract :
The Doppler ultrasound technique is commonly used to detect emboli in the cerebral circulation. Here an automated feature extraction and emboli detection system is proposed based on the principal components analysis (PCA) and fuzzy sets. In the system, two features, Rry and k, are extracted by the PCA method. Meanwhile, MMR and min are obtained with the traditional temporal processing and spectrogram analysis, respectively. Normal blood flow signals are firstly distinguished from abnormal signals by MMR. Then signals containing emboli and disturbance noises are further differentiated by other features based on fuzzy sets. From experiments with computer-simulated and clinical Doppler ultrasound signals, it is shown that features extracted from the PCA method achieve better classification performance than those of traditional methods. The fuzzy-based detection system not only obtains high classification accuracy but is more applicable in clinical diagnosis.
Keywords : emboli detection system doppler ultrasound signal feature extraction pca fuzzy sets