Yulianti, Titin and Telaumbanua, Mareli and Septama, Hery Dian and Fitriawan, Helmy and Yudamson, Afri (2021) Pengaruh Seleksi Fitur Citra Terhadap Klasifikasi Tingkat Kesegaran Daging Sapi Lokal. Jurnal Teknik Pertanian Lampung, 10 (1). pp. 85-95. ISSN 2302-559X

[img]
Preview
Text
1. Jurnal_TY_Seleksi fitur.pdf

Download (232kB) | Preview

Abstract

Identifying beef manually has some drawbacks because human visual has limitations and there are differences of human perception in assessing object quality. Several researches developed beef quality assessment methods based on image feature extraction. However, not all features support for obtaining the classification results that have high accuracy. The efficiency will be achieved if the classification analyzes only the relevant features. Therefore, a feature selection process is required to select relevant features and to eliminate irrelevant features to obtain more accurate and faster classification results. One of the feature selection algorithms is the F-Score which is a simple technique that measures the discrimination of two sets of real numbers. The features with the lowest ranking from the F-Score will be eliminated one by one until the most relevant features are obtained. The test is carried out by analyzing the classification results in the form of sensitivity, specificity, and accuracy values. The results of this research showed that by using the F-Score feature, the most relevant features for the classification of freshness level of local beef are obtained using the K-Nearest Neighbor (KNN) method. These features include the average color intensity R and standard deviation with a sensitivity of 0.8, a specificity of 0.93, and an accuracy of 86%.

Item Type: Article
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Teknik (FT) > Prodi Teknik Informatika
Depositing User: titin yulianti
Date Deposited: 08 Jun 2021 16:15
Last Modified: 08 Jun 2021 16:15
URI: http://repository.lppm.unila.ac.id/id/eprint/32278

Actions (login required)

View Item View Item