Optimizing Detection Using Ensemble Learning With Enhanced EfficienNet and Xception Architecture For Beef Quality Classification

Hutomo Kertasanjaya, Wibiyartono and , Diah Priyawati, S.T., M.Eng. (2024) Optimizing Detection Using Ensemble Learning With Enhanced EfficienNet and Xception Architecture For Beef Quality Classification. Skripsi thesis, Universitas Muhammadiyah Surakarta.

	PDF (Naskah Publikasi) Naskah Publikasi.pdf Download (490kB)
	PDF (Halaman Depan) Halaman Depan.pdf Download (701kB)
	PDF (Bab I) Bab I.pdf Download (16kB)
	PDF (Bab II) Bab II.pdf Restricted to Repository staff only Download (340kB)
	PDF (Bab III) Bab III.pdf Restricted to Repository staff only Download (184kB)
	PDF (Bab IV) Bab IV.pdf Restricted to Repository staff only Download (28kB)
	PDF (Bab V) Bab V.pdf Restricted to Repository staff only Download (28kB)
	PDF (Daftar Pustaka) Daftar Pustaka.pdf Download (101kB)
	PDF (Surat Pernyataan Publikasi) Surat Pernyataan Publikasi.pdf Restricted to Repository staff only Download (1MB)

Abstract

In the agriculture industry 4.0 era made of many innovative tools and machines. The aim of production in industry 4.0 is graded by progress development evert year to complete the aim of automation in all parts of the supply chain of agriculture. The automation of good precis is execution by using machine learning techniques. These techniques learn by automatic machine with self-recognizing and self-learning. Automated beef detection will help farmers, customers, traders with high quality standard. The other way it will help farmers to reduce risk of spoilage beef and help a customer to analysis which one is fresh beef. However, in agriculture industry 4.0 era, automated beef detection using machine learning techniques is crucial for maintaining high quality meat standards. The innovation needs to creating more enhance to maintaining the accuracy for image classification. This study utilizes an ensemble model with majority voting and custom weights on the ImageNet dataset to achieve an accuracy of 99.70% in classifying beef images. This research proposes an enhanced image classification method using ensemble learning for efficient and accurate meat detection. The objective is to improve the quality control of meat products by automating the detection process. By combining multiple machines learning models and employing a majority voting strategy with custom weights, the proposed method aims to achieve high accuracy in classifying meat images. This research has the potential to contribute to the food industry by ensuring the quality and safety of meat products.

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Ensemble, Beef detection, Fresh and Spoilage.
Subjects:	T Technology > TZ Technical Information > TA02 Software. Aplication > Pemograman
Divisions:	Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika
Depositing User:	WIBIYARTONO HUTOMO KERTASANJAYA
Date Deposited:	20 Nov 2024 02:02
Last Modified:	20 Nov 2024 02:02
URI:	http://eprints.ums.ac.id/id/eprint/129067

Actions (login required)

View Item