Comparative Study On Different Features And Classifiers For Emboli Signal Identification

DZATI, ATHIAR RAMLI and HARYATI, JAAFAR and NAJAH, GHAZALI (2016) Comparative Study On Different Features And Classifiers For Emboli Signal Identification. In: Fourth International Conference on Advances in Bio-Informatics and Environmental Engineering - ICABEE 2016, 18-19 August 2016, Rome, Italy.

20160908_064204.pdf - Published Version

Download (672kB) | Preview
Official URL:


Occurrence of embolism from patients who suffer from carotid artery stenosis may bring to the onset of stroke if it became severe. In clinical practice, Doppler ultrasound technique is commonly used to detect the emboli in the cerebral circulation. Instead of depending on human observer as a gold standard to detect the emboli, this study proposes an automated embolic identification system based on ultrasound signal analysis. Experimental studies on 1,400 samples from five independent data sets are employed in this study. Two feature extraction methods based on spectral feature i.e. Linear Prediction Coefficient (LPC) and statistical features i.e. combination of Measured Embolus-to-Blood Ratio (MEBR), Peak Embolus-to-Blood Ratio (PEBR), entropy, standard deviation and maximum peak are used to extract the signal. Subsequently, four classifiers based on nearest neighbor approach i.e. k Nearest Neighbor (kNN), Fuzzy k-Nearest neighbor (FkNN), k Nearest Centroid Neighbor (kNCN), and Fuzzy-Based k-Nearest Centroid Neighbor (FkNCN) are used to evaluate the performance of the identification system. The experimental results show that FkNCN with statistical feature outperforms the other classifiers with the performance of 92.45±2.12% is achieved.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Embolus detection; Transcranial Doppler Ultrasound; Feature extraction; Classification.
Depositing User: Mr. John Steve
Date Deposited: 22 Mar 2019 10:24
Last Modified: 22 Mar 2019 10:24

Actions (login required)

View Item View Item