Implementation of artificial neural network algorithm for classification of normal and crackles respiratory sounds for lung cancer screening /
The mortality rate of lung cancer is increasing year by year. As reported by the International Agency for Research on Cancer (IARC) in 2014, lung cancer is the primary death cause worldwide and ranked 3rd in Malaysia as the most common type of cancer. Methods used for lung cancer screening are expen...
Saved in:
Main Author: | |
---|---|
Format: | Thesis |
Language: | English |
Published: |
Kuala Lumpur :
Kulliyyah of Engineering, International Islamic University Malaysia,
2019
|
Subjects: | |
Online Access: | http://studentrepo.iium.edu.my/handle/123456789/4875 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
LEADER | 028310000a22002890004500 | ||
---|---|---|---|
008 | 190515s2019 my a f m 000 0 eng d | ||
040 | |a UIAM |b eng |e rda | ||
041 | |a eng | ||
043 | |a a-my--- | ||
100 | 0 | |a Nurfatihah binti Shafian, |e author | |
245 | 1 | 0 | |a Implementation of artificial neural network algorithm for classification of normal and crackles respiratory sounds for lung cancer screening / |c by Nurfatihah binti Shafian |
264 | 1 | |a Kuala Lumpur : |b Kulliyyah of Engineering, International Islamic University Malaysia, |c 2019 | |
300 | |a xiv, 67 leaves : |b colour illustrations ; |c 30cm. | ||
336 | |2 rdacontent |a text | ||
347 | |2 rdaft |a text file |b PDF | ||
502 | |a Thesis (MSCIE)--International Islamic University Malaysia, 2019. | ||
504 | |a Includes bibliographical references (leaves 56-59). | ||
520 | |a The mortality rate of lung cancer is increasing year by year. As reported by the International Agency for Research on Cancer (IARC) in 2014, lung cancer is the primary death cause worldwide and ranked 3rd in Malaysia as the most common type of cancer. Methods used for lung cancer screening are expensive, contain radiation exposure or invasive. Thus, this study proposed an implementation of Artificial Neural Network (ANN) algorithm for classification of normal and crackles respiratory sounds in lung cancer patients. This method is safe and non-invasive. A total of 23 healthy subjects and 23 lung cancer patients were recruited in this study. The data collected was extracted via a Discrete Wavelet Transform that is based on two different mother-wavelets which are Daubechies 7 (db7) and Symlet 7 (sym7) and Fast Fourier Transform (FFT). Seven statistical features which are mean, variance, minimum amplitude, maximum amplitude, minimum energy, maximum energy and mean of energy were extracted. ANN was used to classify respiratory sound signals as normal and crackle sounds. The results displayed that db7 and sym7 have achieved classification accuracies of 99.0%, while FFT achieved 85.0% classification accuracy. This shows that db7, sym7, and FFT features and ANN algorithm can be used in classifying respiratory sound signals in lung cancer patients. | ||
596 | |a 1 | ||
655 | 7 | |a Theses, IIUM local | |
690 | |a Dissertations, Academic |x Department of Electrical and Computer Engineering |z IIUM | ||
710 | 2 | |a International Islamic University Malaysia. |b Department of Electrical and Computer Engineering | |
856 | 4 | |u http://studentrepo.iium.edu.my/handle/123456789/4875 | |
900 | |a sbh to aaz | ||
999 | |c 441832 |d 472424 | ||
952 | |0 0 |6 XX(556077.1) |7 0 |8 THESES |9 763065 |a IIUM |b IIUM |c MULTIMEDIA |g 0.00 |o XX(556077.1) |p 11100408724 |r 1900-01-02 |t 1 |v 0.00 |y THESIS | ||
952 | |0 0 |6 XX(556077.1) CD |7 5 |8 THESES |9 858245 |a IIUM |b IIUM |c MULTIMEDIA |g 0.00 |o XX(556077.1) CD |p 11100408725 |r 1900-01-02 |t 1 |v 0.00 |y THESISDIG |