Aulia Dwi Maharani (2015) Penggunaan Regression Tree (Rf Klasifikasi Periodontitis Kronis Pada Pasien Rumah Sakit Gigi Dan Mulut Universitas Hang Tuah Surabaya. Thesis thesis, UNIVERSITAS AIRLANGGA.

	Text (HALAMAN JUDUL) 1. HALAMAN JUDUL.pdf Download (1MB)
	Text (ABSTRAK) 2. ABSTRAK.pdf Download (700kB)
	Text (DAFTAR ISI) 3. DAFTAR ISI.pdf Download (749kB)
	Text (BAB I) 4. BAB I PENDAHULUAN.pdf Download (753kB)
	Text (BAB II) 5. BAB II TINJAUAN PUSTAKA.pdf Restricted to Registered users only until 24 May 2023. Download (896kB) | Request a copy
	Text (BAB III) 6. BAB III KERANGKA KONSEPTUAL.pdf Restricted to Registered users only until 24 May 2023. Download (740kB) | Request a copy
	Text (BAB IV) 7. BAB IV METODE PENELITIAN.pdf Restricted to Registered users only until 24 May 2023. Download (770kB) | Request a copy
	Text (BAB V) 8. BAB V HASIL DAN ANALISIS DATA.pdf Restricted to Registered users only until 24 May 2023. Download (1MB) | Request a copy
	Text (BAB VI) 9. BAB VI PEMBAHASAN.pdf Restricted to Registered users only until 24 May 2023. Download (755kB) | Request a copy
	Text (BAB VII) 10. BAB VII PENUTUP.pdf Restricted to Registered users only until 24 May 2023. Download (735kB) | Request a copy
	Text (DAFTAR PUSTAKA) 11. DAFTAR PUSTAKA.pdf Download (741kB)
	Text (LAMPIRAN) 12. LAMPIRAN.pdf Restricted to Registered users only until 24 May 2023. Download (892kB) | Request a copy

Abstract

Classification tree method now commonly used method of Classification and Regression Tree (CART). The advantage of this method is the method CART is not bound by assumptions - assumptions and effectively used on data that has a large dimension or having many independent variables. However, CART method has drawbacks where such methods are less stable on learning data changes that cause changes in the results of the prediction. To overcome this problem, developed a method to improve the accuracy of prediction ensemble. This study used random forest method ensemble because in previous research studies yhe used of random forest method known to increase the accuracy of the classification of CART. The random forest-CART method use in the study of Chronic Perodontitis in RSGM Hang Tuah University Surabaya . the gingival resesion and the smoking habit are factors that classified the mild type of chronic periodontitis. The gingival resesion, smoking habit, gingival hiperplation, tooth movement, malocclusion, and tooth migration are factors that classified chronic periodontitis into moderate type of chronic periodontitis. The gingival resesion, smoking habit, gingival hiperplation, tooth movement, malocclusion, tooth migration, malpotition, and calculus are factors that classified chronic periodontitis into heavy type of chronic periodontitis. The criteria used to compare the accuracy of the classification CART and RFCART is 1-APER of each learning data and testing. RF-CART classification method has a 1-APER greater than the CART method. There was an increase of 3,5% accuracy for data learning and by 1% for data testing.

Actions (login required)

View Item