Please use this identifier to cite or link to this item:
http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/5505
Title: | Convolutional Neural Network as an Image Processing Technique for Classification of Bacilli Tuberculosis Extra Pulmonary (TBEP) Disease |
Authors: | Bob Subhan, Riza |
Keywords: | Tuberculosis Extra Pulmonary, Otsu Thresholding, Hue Saturation Value (HSV), feature extraction, feature selection, Convolutional Neural Network |
Issue Date: | 29-Aug-2022 |
Publisher: | TEM Journal |
Series/Report no.: | Volume 11, Issue 3;pages 1331‐1340 |
Abstract: | Tuberculosis Extra Pulmonary (TBEP) is an infectious disease caused by the bacterium Mycobacterium tuberculosis and can cause death. Patients suffering from this disease must be treated quickly without waiting for a long time. Biopsy is one of the techniques used to take the patient's lung fluid and given Ziehl Neelsen chemical dye and then observed using a microscope to determine this TBEP disease. In this research, the TBEP detection process was developed using a classification method, namely CNN with feature extraction and feature selection. The feature uses 5 features where these features are a combination of shape features and texture features with the highest information gain value. From the results of research conducted through the training and testing stages of the classification method using feature selection, the accuracy rate is higher than not using feature selection with a comparison of the feature selection stage increasing 0.6536% for the training process, and 0.8942% for the testing process. |
Description: | Tuberculosis is a life-threatening infectious disease worldwide caused by the bacterium Mycobacterium tuberculosis. These bacteria are in the form of AcidFast Bacilli (AFB). These bacilli are 1-4 m long and 0.3-0.56 m wide as shown in Figure 1., are nonspore-forming, non-motile, and facultative. Bacterial cell walls contain long chain glycolipids that are mycolic, rich in acids and phosphopoglycans [1], [2]. Tuberculosis (TB) is a chronic and infectious disease that affects the world's human population and requires complex treatment. It is a public health problem with more than 9 million estimated new cases and 1.5 million deaths annually worldwide [3]. Of the estimated 9 million people who contracted TB in 2013, more than 80% were in Southeast Asia, the Western Pacific and Africa. Most of the infected population comes from poor and marginalized communities with weak health services infrastructure |
URI: | http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/5505 |
ISSN: | 2217-8309 |
Appears in Collections: | Untitled |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2. Q3_Convolutional Neural Network as an Image Processing Technique for Classification of Bacilli Tuberculosis.pdf | 675.52 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.