Thaqifullah, Muchamad (2025) Pengaruh Preprocessing Kontras dan Pencahayaan pada Kinerja Model VGG16 dalam Deteksi Sel Malaria. Undergraduate thesis, Universitas Muhammadiyah Malang.
PENDAHULUAN .pdf
Download (963kB) | Preview
BAB 1.pdf
Download (118kB) | Preview
BAB 2.pdf
Download (157kB) | Preview
![[thumbnail of BAB 3.pdf]](https://eprints.umm.ac.id/style/images/fileicons/text.png)
BAB 3.pdf
Restricted to Registered users only
Download (297kB) | Request a copy
![[thumbnail of BAB 4.pdf]](https://eprints.umm.ac.id/style/images/fileicons/text.png)
BAB 4.pdf
Restricted to Registered users only
Download (476kB) | Request a copy
![[thumbnail of BAB 5.pdf]](https://eprints.umm.ac.id/style/images/fileicons/text.png)
BAB 5.pdf
Restricted to Registered users only
Download (115kB) | Request a copy
![[thumbnail of poster.pdf]](https://eprints.umm.ac.id/style/images/fileicons/text.png)
poster.pdf
Restricted to Registered users only
Download (302kB) | Request a copy
Abstract
Malariaaissa serioussdiseaseecauseddbyytheePlasmodium parasite and transmitted through the bite of the Anophelessmosquito, with millions of cases occurring each year and a major impact in developing countries. Rapid and accurate diagnosis is critical to controlling the disease, but conventional methodsssuchhas microscopy and rapid diagnostic tests have limitations, including the dependence on skilled personnel and high costs. This study utilized a Convolutional Neural Network (CNN) baseddon the VGG-16 architecture optimized using a transfer learning approach to detect malaria in red blood cell images. The Contrast Limited Adaptive Histogram Equalization (CLAHE) technique was used in the image processing stage to improve image quality before classification. The results showed that the application of CLAHE was able to produce the highest accuracy of 96% by increasing image contrast without significantly increasing noise, so that important patterns in the image became easier to recognize. This approach proves that the combination of VGG-16 and CLAHE is effective in supporting rapid and accurate malaria diagnosis, and has the potential to strengthen efforts to control this disease.
Item Type: | Thesis (Undergraduate) |
---|---|
Student ID: | 202010370311183 |
Keywords: | Malaria, Convolutional Neural Network (CNN), VGG-16, Contrast Limited Adaptive Histogram Equalization (CLAHE). |
Subjects: | R Medicine > RC Internal medicine R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer) R Medicine > RZ Other systems of medicine |
Divisions: | Faculty of Engineering > Department of Informatics (55201) |
Depositing User: | 202010370311183 thaqifullah1 |
Date Deposited: | 31 Jan 2025 03:36 |
Last Modified: | 31 Jan 2025 03:36 |
URI: | https://eprints.umm.ac.id/id/eprint/14351 |