Analisis perbandingan klasifikasi jenis kacang kering dengan menggunakan metode support vector machine dan linear discriminant analysis

Thames, Justin (2024) Analisis perbandingan klasifikasi jenis kacang kering dengan menggunakan metode support vector machine dan linear discriminant analysis. Bachelor thesis, Universitas Pelita Harapan.

Preview	Text (Title) Title.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (12kB) | Preview
Preview	Text (Abstract) Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (103kB) | Preview
Preview	Text (ToC) ToC.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (212kB) | Preview
Preview	Text (Chapter1) Chapter1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (121kB) | Preview
	Text (Chapter2) Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (958kB)
	Text (Chapter3) Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (300kB)
	Text (Chapter4) Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter5) Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (101kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (290kB) | Preview
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)

Abstract

Kacang merupakan salah satu produk penting dalam industri pertanian dan pangan di seluruh dunia dimana kacang memiliki protein nabati, serat, dan nutrisi penting lainnya untuk proses diet manusia. Setiap jenis kacang memiliki karakteristik masing-masing. Selain itu, klasifikasi secara manual dan menyortir benih kacang tersebut sangat sulit untuk dilakukan. Oleh karena itu, hal ini sangat penting untuk dilakukan klasifikasi dan mengidentifikasi jenis kacang kering tersebut. Metode yang dapat digunakan untuk mengklasifikasikan jenis kacang adalah metode Support Vector Machine dan Linear Discriminant Analysis. Terdapat tujuh jenis kacang kering dengan tujuh tingkat akurasi yang berbeda berdasarkan perhitungan dari per class dengan metode Support Vector Machine (SVM) dan Linear Discriminant Analysis (LDA). Hasil dari akurasi metode SVM yaitu Barbunya sebesar 98%, Bombay sebesar 100%, Cali sebesar 98%, Dermason sebesar 96%, Horoz sebesar 99%, Seker sebesar 98%, Sira sebesar 95% sedangkan hasil dari akurasi metode LDA yaitu Barbunya sebesar 98%, Bombay sebesar 100%, Cali sebesar 98%, Dermason sebesar 95%, Horoz sebesar 98%, Seker sebesar 98%, Sira sebesar 93%. / Nut are an important product in the agricultural and food industry throughout the world where they contain vegetable protein, fiber and other important nutrients for the human diet. Each type of nut has its own characteristics. In addition, manually classifying and sorting the nut seeds is very difficult to do. Therefore, it is very important to classify and identify the type of dry nut. Methods that can be used to classify types of nut are the Support Vector Machine method and Linear Discriminant Analysis. There are seven types of dry nut with seven different levels of accuracy based on calculations per class using the Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) methods. The results of the accuracy of the SVM method are Barbunya at 98%, Bombay at 100%, Cali at 98%, Dermason at 96%, Horoz at 99%, Seker at 98%, Sira at 95% while the results of the accuracy of the LDA method are Barbunya at 98 %, Bombay at 100%, Cali at 98%, Dermason at 95%, Horoz at 98%, Seker at 98%, Sira at 93%.

Actions (login required)

View Item