MUHAMMAD ALBIK GHALELA (2022) SISTEM KLASIFIKASI JENIS KENDARAAN BERDASARKAN TEKSTUR MENGGUNAKAN ALGORITMA TRANSFORMASI HAAR WAVELET DAN MACHINE LEARNING. S1 thesis, Universitas Muhammadiyah Yogyakarta.

	Text (Halaman Judul) Halaman Judul.pdf Download (605kB)
	Text (Lembar Pengesahan) Lembar Pengesahan.pdf Restricted to Registered users only Download (426kB)
	Text (Abstrak) Abstrak.pdf Restricted to Registered users only Download (117kB)
	Text (Bab I) Bab I.pdf Download (23kB)
	Text (Bab II) Bab II.pdf Restricted to Registered users only Download (486kB)
	Text (Bab III) Bab III.pdf Restricted to Registered users only Download (750kB)
	Text (Bab IV) Bab IV.pdf Restricted to Registered users only Download (4MB)
	Text (Bab V) Bab V.pdf Restricted to Registered users only Download (14kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf Restricted to Registered users only Download (142kB)
	Text (Naskah Publikasi) Naskah Publikasi.pdf Restricted to Registered users only Download (372kB)
	Text (Full Text) Full Text.pdf Restricted to Repository staff only Download (6MB)

Abstract

Nowadays, various vehicles have developed, which affects the different vehicle shapes. Therefore, the variety of vehicle types' traffic flow needs to be monitored by a classification system built in machine learning. This vehicle classification research uses four classes dataset of the vehicle, which is class 3 “Audi TL Acure Sedan 2012”, class 14 “Audi TTS Coupe 2012”, class 106 “Ford F-450 Super Duty Crew Cab”, and class 134 “Hyundai Sonata Hybrid 2012”. This research aims to evaluate the result of vehicle type classification using the transforms Haar wavelet algorithm as a feature extracted method. The result of the featured form transforms Haar wavelet algorithm decomposition levels 1 and 2, subsequently used as a training data model for classification on support vector machine and k-nearest neighbor. The highest classification result on training data model level 1 is in the Weighted KNN model with 0.33% and medium SVM with 0.33%. While decomposition level 2 is in the Weighted KNN model with 0.66%. At the same time, the training merge data model between levels 1 and 2 is in WeightedKNN with 0.75%.

Dosen Pembimbing:	YESSI JUSMAN, S.T., M.SC., PH.D. and MUHAMAD YUSVIN MUSTAR, S.T., M.ENG. | NIDN1007058408, NIDN0508058801
Item Type:	Thesis (S1)
Uncontrolled Keywords:	HAAR WAVELET, SUPPORT VECTOR MACHINE, K-NEAREST NEIGHBOR, MACHINE LEARNING, CLASSIFICATION SYSTEM.
Divisions:	Fakultas Teknik > S1 Teknik Elektro
Depositing User:	M. Erdiansyah
Date Deposited:	20 Apr 2022 02:34
Last Modified:	20 Apr 2022 02:34
URI:	https://etd.umy.ac.id/id/eprint/29547

Actions (login required)

View Item