Data mining usage in emboli detection

Adem Karahoca; Turkalp Kucur; Nizamettin Aydin

doi:10.1109/BLISS.2007.20

Data mining usage in emboli detection

Adem Karahoca^*
, Turkalp Kucur
, Nizamettin Aydin

^*Corresponding author for this work

Bahcesehir University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Citations (Scopus)

Abstract

Asymptomatic circulating cerebral emboli, which are particles bigger than blood cells, can be detected by transcranial Doppler ultrasound. In certain conditions asymptomatic embolic signals (ES) appear to be markers of increased stroke risk. ES, reflected by an embolus, have usually larger amplitude than the signals from normal blood flow and show a transient characteristic. A number of methods to detect cerebral emboli have been studied in the literature. In this study, data mining techniques have been used in order to increase sensitivity and specificity of an embolic signal detection system. The classification results of different methods have been compared by using a data set including 100 ES, 100 speckle and 100 artifact. The ROC analysis results show that adaptive neuro fuzzy inference (ANFIS) system method appears to give better results.

Original language	English
Title of host publication	Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007
Pages	159-162
Number of pages	4
DOIs	https://doi.org/10.1109/BLISS.2007.20
Publication status	Published - 2007
Externally published	Yes
Event	2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007 - Edinburgh, United Kingdom Duration: 9 Aug 2007 → 10 Aug 2007

Publication series

Name	Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007

Conference

Conference	2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007
Country/Territory	United Kingdom
City	Edinburgh
Period	9/08/07 → 10/08/07

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1109/BLISS.2007.20

Cite this

Karahoca, A., Kucur, T., & Aydin, N. (2007). Data mining usage in emboli detection. In Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007 (pp. 159-162). Article 4290960 (Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007). https://doi.org/10.1109/BLISS.2007.20

@inproceedings{67a59da2152740709b478c312d5a528c,

title = "Data mining usage in emboli detection",

abstract = "Asymptomatic circulating cerebral emboli, which are particles bigger than blood cells, can be detected by transcranial Doppler ultrasound. In certain conditions asymptomatic embolic signals (ES) appear to be markers of increased stroke risk. ES, reflected by an embolus, have usually larger amplitude than the signals from normal blood flow and show a transient characteristic. A number of methods to detect cerebral emboli have been studied in the literature. In this study, data mining techniques have been used in order to increase sensitivity and specificity of an embolic signal detection system. The classification results of different methods have been compared by using a data set including 100 ES, 100 speckle and 100 artifact. The ROC analysis results show that adaptive neuro fuzzy inference (ANFIS) system method appears to give better results.",

author = "Adem Karahoca and Turkalp Kucur and Nizamettin Aydin",

year = "2007",

doi = "10.1109/BLISS.2007.20",

language = "English",

isbn = "0769529194",

series = "Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007",

pages = "159--162",

booktitle = "Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007",

note = "2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007 ; Conference date: 09-08-2007 Through 10-08-2007",

}

Karahoca, A, Kucur, T & Aydin, N 2007, Data mining usage in emboli detection. in Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007., 4290960, Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007, pp. 159-162, 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007, Edinburgh, United Kingdom, 9/08/07. https://doi.org/10.1109/BLISS.2007.20

Data mining usage in emboli detection. / Karahoca, Adem; Kucur, Turkalp; Aydin, Nizamettin.
Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007. 2007. p. 159-162 4290960 (Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Data mining usage in emboli detection

AU - Karahoca, Adem

AU - Kucur, Turkalp

AU - Aydin, Nizamettin

PY - 2007

Y1 - 2007

N2 - Asymptomatic circulating cerebral emboli, which are particles bigger than blood cells, can be detected by transcranial Doppler ultrasound. In certain conditions asymptomatic embolic signals (ES) appear to be markers of increased stroke risk. ES, reflected by an embolus, have usually larger amplitude than the signals from normal blood flow and show a transient characteristic. A number of methods to detect cerebral emboli have been studied in the literature. In this study, data mining techniques have been used in order to increase sensitivity and specificity of an embolic signal detection system. The classification results of different methods have been compared by using a data set including 100 ES, 100 speckle and 100 artifact. The ROC analysis results show that adaptive neuro fuzzy inference (ANFIS) system method appears to give better results.

AB - Asymptomatic circulating cerebral emboli, which are particles bigger than blood cells, can be detected by transcranial Doppler ultrasound. In certain conditions asymptomatic embolic signals (ES) appear to be markers of increased stroke risk. ES, reflected by an embolus, have usually larger amplitude than the signals from normal blood flow and show a transient characteristic. A number of methods to detect cerebral emboli have been studied in the literature. In this study, data mining techniques have been used in order to increase sensitivity and specificity of an embolic signal detection system. The classification results of different methods have been compared by using a data set including 100 ES, 100 speckle and 100 artifact. The ROC analysis results show that adaptive neuro fuzzy inference (ANFIS) system method appears to give better results.

UR - https://www.scopus.com/pages/publications/46449121524

U2 - 10.1109/BLISS.2007.20

DO - 10.1109/BLISS.2007.20

M3 - Conference contribution

AN - SCOPUS:46449121524

SN - 0769529194

SN - 9780769529196

T3 - Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007

SP - 159

EP - 162

BT - Proceedings - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007

T2 - 2007 ECSIS Symposium on Bio-inspired, Learning, and Intelligent Systems for Security, BLISS 2007

Y2 - 9 August 2007 through 10 August 2007

ER -

Data mining usage in emboli detection

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this