Algoritma Random Forest untuk klasifikasi ambitus pada Paduan Suara

Ma'rup, Muhamad Nurul (2023) Algoritma Random Forest untuk klasifikasi ambitus pada Paduan Suara. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

Preview	Text (COVER) 1_cover.pdf Download (118kB) | Preview
Preview	Text (ABSTRAK) 2_abstrak.pdf Download (208kB) | Preview
Preview	Text (DAFTAR ISI) 3_daftarisi.pdf Download (68kB) | Preview
Preview	Text (BAB I) 4_bab1.pdf Download (216kB) | Preview
	Text (BAB II) 5_bab2.pdf Restricted to Registered users only Download (443kB) | Request a copy
	Text (BAB III) 6_bab3.pdf Restricted to Registered users only Download (256kB) | Request a copy
	Text (BAB IV) 7_bab4.pdf Restricted to Registered users only Download (559kB) | Request a copy
	Text (BAB V) 8_bab5.pdf Restricted to Registered users only Download (22kB) | Request a copy
	Text (DAFTAR PUSTAKA) 9_daftarpustaka.pdf Restricted to Registered users only Download (175kB) | Request a copy

Abstract

Human voices can achieve a certain number of notes, referred to as ambitus, or the range of notes used to compose a chorus, which corresponds to the range of frequencies that musical instruments or human vocals can produce. Today's technology allows us to apply similar concepts to sound analysis. Generally, signal processing algorithms are frequently employed to classify ambitus using audio. One of the utilized methods is the Random Forest algorithm. This study aims to develop a sound classification system utilizing the Random Forest algorithm to identify ambitus and assess the accuracy of the classification. The study achieved an accuracy of approximately 96.08% when using a training data and data testing ratio of 7:3. When altering the ratio to 8:2, the accuracy increased to around 96.27%, and with a ratio of 6:4, the accuracy reached approximately 96.31%. This study demonstrates that a sound classification system based on the Random Forest algorithm can effectively identify ambitus with a high degree of accuracy, making a significant contribution to sound analysis across various applications, including music and audio engineering.

Actions (login required)

View Item