Analysys of the impact of disturbance on the arteriovenous fistula state classification

• Autorzy: Grochowina Marcin , Leniowska Lucyna

Identyfikatory

DOI

10.15439/2017F305

• Konferencja: Communication Papers of the 2017 Federated Conference on Computer Science and Information Systems
• Języki publikacji: EN

Abstrakty

EN

The quality of data sets used in the classification process has a significant impact on the outcome. The noise contained in the input data depending on the nature and intensity may have a different effect on the classification result. This paper presents the results of research on the quality and reliability of arterio-venous fistula classification based on the signal recorded under controlled disturbance conditions and in the model of artificial disturbations. Typical environmental noise that may occur when the acoustic signal produced by the fistula was recorded and it is used as a disturbance. Its influence on the features extraction process and on the result of the fistula assessment was determined. Finally, a relationship between the intensity of the disturbances and the degree of shifting of the classification result to the pathological state of the fistula was demonstrated

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2017
• Tom: Vol. 13
• Strony: 51--55
• Opis fizyczny: Bibliogr. 15 poz., tab., wykr.

Twórcy

autor

Grochowina Marcin

• University of Rzeszów, al. Rejtana 16, 35-310 Rzeszów, Poland

autor

Leniowska Lucyna

• University of Rzeszów, al. Rejtana 16, 35-310 Rzeszów, Poland

Bibliografia

• 1. Marcin Grochowina, Lucyna Leniowska and Piotr Dulkiewicz, “Application of Artificial Neural Networks for the Diagnosis of the Condition of the Arterio-venous Fistula on the Basis of Acoustic Signals,” Brain Informatics and Health, Springer, 2014, pp. 400-411.
• 2. Marcin Grochowina and Lucyna Leniowska, “Comparison of SVM and k-NN classifiers in the estimation of the state of the arteriovenous fistula problem,” Proceedings of the 2015 Federated Conference on Computer Science and Information Systems (FedCSIS), IEEE, 2015, pp. 249-254.
• 3. Grochowina Marcin and Lucyna Leniowska, “The new method of the selection of features for the k-NN classifier in the arteriovenous fistula state estimation,” Proceedings of the 2016 Computer Science and Information Systems (FedCSIS), IEEE, 2016, pp. 281-285.
• 4. Grochowina Marcin and Lucyna Leniowska, “Analysis of the head prototype acoustic parameters for the acquisition of arteriovenous fistula signal,” Mechanics in Medicine 12 (2014), University of Rzeszow, 2014, pp. 64-73. (in Polish).
• 5. Mikkel Grama , Jens Tranholm Olesena, Hans Christian Riisa, Maiuri Selvaratnama and Michalina Urbaniaka, “Stenosis detection algorithm for screening of arteriovenous fistulae,” 15th Nordic-Baltic Conference on Biomedical Engineering and Medical Physics (NBC 2011), Springer, 2011, pp. 241-244.
• 6. Duda Richard and Hart Peter and Stork David G “Pattern classification”, John Wiley & Sons 2012.
• 7. Aha David and Kibler Dennis “Noise-Tolerant Instance-Based Learning Algorithms”, IJCAI 1989, Citeseer, 1989, pp. 794-799,
• 8. Jain Anil and Ross Arun “Learning user-specific parameters in a multibiometric system”, Image Processing. 2002. Proceedings. 2002 International Conference on, IEEE, 2002, pp. I-I.
• 9. Grochowina Marcin and Lucyna Leniowska, “The selection of features for the svm classifier in the arteriovenous fistula state estimation on the basis of acoustic signal”, Acta Bio-Optica et Informatica Medica. Inżynieria Biomedyczna, vol.22(4), pp. 207-212. (in Polish).
• 10. Domeniconi Carlotta and Peng Jing and Gunopulos Dimitrios “Locally adaptive metric nearest-neighbor classification”, IEEE Transactions on Pattern Analysis and Machine Intelligence vol.1, IEEE, 2002, pp. 1281-1285.
• 11. Aleksander Cisłak and Szymon Grabowski, “Experimental evaluation of selected tree structures for exact and approximate k-nearest neighbor classification,” Proceedings of the 2014 Federated Conference on Computer Science and Information Systems, IEEE, 2014, pp. 93-100.
• 12. Przemysław Wiktor Pardel and Jan G. Bazan and Jacek Zarychta and Stanisława Bazan-Socha, “A two-level classifier for automatic medical objects classification,” Proceedings of the 2015 Federated Conference on Computer Science and Information Systems, IEEE, 2015, pp. 139-143.
• 13. “WEKA documentation,” http://www.cs.waikato.ac.nz/ml/weka/documentation.html
• 14. “Audacity manual,” http://manual.audacityteam.org/#tutorials
• 15. “Digital Sound Level Meter AZ8921,” http://www.az-instrument.com.tw/az-instrument/en/productsinfo/147.html