Mohammad Yazid Bastomi (2020) Deteksi Tuberkulosis Menggunakan Citra X-Ray Berbasis Gray Level Cooccurance Matrices (GLCM) Dan K-Nearest Neighbor (KNN). Skripsi thesis, UNIVERSITAS AIRLANGGA.

	Text (HALAMAN JUDUL) 1. HALAMAN JUDUL.pdf Download (345kB)
	Text (ABSTRAK) 2. ABSTRAK.pdf Download (202kB)
	Text (DAFTAR ISI) 3. DAFTAR ISI.pdf Download (207kB)
	Text (BAB 1) 4. BAB 1 PENDAHULUAN.pdf Download (203kB)
	Text (BAB II) 5. BAB II TINJAUAN PUSTAKA.pdf Restricted to Registered users only until 7 January 2024. Download (502kB) | Request a copy
	Text (BAB III) 6. BAB III METODE PENELITIAN.pdf Restricted to Registered users only until 7 January 2024. Download (569kB) | Request a copy
	Text (BAB IV) 7. BAB IV HASIL DAN PEMBAHASAN.pdf Restricted to Registered users only until 7 January 2024. Download (1MB) | Request a copy
	Text (BAB V) 8. BAB V KESIMPULAN DAN SARAN.pdf Restricted to Registered users only until 7 January 2024. Download (189kB) | Request a copy
	Text (DAFTAR PUSTAKA) 9. DAFTAR PUSTAKA.pdf Download (162kB)
	Text (LAMPIRAN) 10. Lampiran.pdf Restricted to Registered users only until 7 January 2024. Download (2MB) | Request a copy
	Text (PERMOHONAN EMBARGO) 11. PERMOHONAN EMBARGO.pdf Restricted to Registered users only Download (277kB) | Request a copy

Abstract

Tuberculosis is an infectious disease caused by a bacterium called bacillus mycobacterium tuberculosis. Tuberculosis is spread through coughing and sneezing which affects the lungs of people infected with pulmonary tuberculosis. One of the method is using the thorax image. However, the accuracy without standard is the problem in this topic. It’s caused by the analysis result depen on the ability of the medical experts only. In this study, a Tuberculosis detection program was designed using the k-nearest neighbor classification method and GLCM features as classification input. So that the detection program was expected to be a tool for medical experts who had standardized accuracy. The GLCM features were to input the k-nearest neighbor classification those are contrast, correlation, energy, entropy, and homogeneity. The program output was divided into 2 classes namely abnormal (tuberculosis) and normal. The combination of entropy-correlation and entropy-energy-correlation features by optimal level of accuracy, sensitivity and specificity showed a value of k=1 that is 92%, 92%, 92%.

Actions (login required)

View Item