Cahyaningrum, Dwi, - (2021) Deteksi Penyakit Tuberkulosis (TB) Menggunakan Kombinasi Self Organizing Map (SOM)-Radial Basis Function (RBF). Skripsi thesis, UNIVERSITAS AIRLANGGA.

	Text (HALAMAN JUDUL) 1. HALAMAN JUDUL.pdf Download (651kB)
	Text (ABSTRAK) 2. ABSTRAK.pdf Download (197kB)
	Text (DAFTAR ISI) 3. DAFTAR ISI.pdf Download (333kB)
	Text (BAB I) 4. BAB I PENDAHULUAN.pdf Download (160kB)
	Text (BAB II) 5. BAB II TINJAUAN PUSTAKA.pdf Restricted to Registered users only until 14 October 2024. Download (389kB) | Request a copy
	Text (BAB III) 6. BAB III METODE PENELITIAN.pdf Restricted to Registered users only until 14 October 2024. Download (157kB) | Request a copy
	Text (BAB IV) 7. BAB IV PEMBAHASAN.pdf Restricted to Registered users only until 14 October 2024. Download (916kB) | Request a copy
	Text (BAB V) 8. BAB V KESIMPULAN DAN SARAN.pdf Restricted to Registered users only until 14 October 2024. Download (146kB) | Request a copy
	Text (DAFTAR PUSTAKA) 9. DAFTAR PUSTAKA.pdf Download (198kB)
	Text (LAMPIRAN) 10. Lampiran.pdf Restricted to Registered users only until 14 October 2024. Download (1MB) | Request a copy
	Text (PERMOHONAN EMBARGO) 11. PERMOHONAN EMBARGO.pdf Restricted to Registered users only Download (268kB) | Request a copy

Abstract

Tuberculosis (TB) is an airborne disease caused by Mycobacterium Tuberculosis (MTB) that usually attacks the lungs causing severe coughing, fever, and chest pain. With relatively easy transmission, so there needs to be a system that can help for early detection of tuberculosis disease so that treatment can be done early and the death rate can be lowered. The thesis aims to detect tuberculosis using a combination of Self Organizing Map (SOM) and Radial Base Function (RBF). The stages of this study are preprocessing to convert original medical record data to numerical data, data normalization, data sharing, parameter initialization, SOM-RBF training procedures to find optimal weights and biases to be used in validation tests, validation test procedures, and calculating the accuracy of classification results on the system. The data used in this thesis is data on patients who contract tuberculosis and who are not infected or other lung patients as much as 70 data on the training process and 30 data on the validation test process. Based on the test results that have been done with variations in the value of learning rate parameters, minimum error = 0.01, and maximum iteration = 1000 obtained the best classification result accuracy of 100%.

Actions (login required)

View Item