Rudiono, Rudiono (2019) Klasifikasi Jenis Tanah Berbasis Website Menggunakan Ekstraksi Ciri Histogram dan Algoritma K-Nearest Neighbor (KNN). Tugas Akhir thesis, University of Technology Yogyakarta.
|
Text
Naskah Publikasi-Rudiono-5140411235.pdf Download (663kB) | Preview |
Abstract
Soil is a part of the earth's crust which is composed of minerals and organic matter. Soil is very supportive of the life of plants by providing nutrients and water on the earth. To find out the quality of soil in an area, we must know the characteristics of the soil in the area. The easiest way to do this is to observe the color and texture of the soil. Langensari is a region with very diverse topography. Some of the Langensari region has a height of less than 25 meters above sea level, making it suitable for agriculture and plantation areas. The level of soil fertility in the Langensari region is relatively good with a subtle soil texture with various types of soil. The lack of public knowledge about the types of land, resulting in the use of land to be less than optimal because the type of plant planted does not fit the type of soil. In addition, many soil color variations make it difficult for researchers to determine the type of soil, because the only method currently used by researchers is to manually compare samples one by one with the default colors in the Munsell Soil Color Chart book, which makes researchers need a long time and accuracy in determining the type of soil. Based on the problems in this study, the writer conducted research on classification of soil types with soil images as input data. The method used in the extraction process is feature extraction of the histogram, while the soil type classification process uses the K-Nearest Neighbor (KNN) algorithm. The features extracted are the value of intensity, standard deviation, skewness, energy, entropy and smoothness. The system accuracy results obtained are 60% with parameter values, namely K = 3. Keywords : Classification of Soil Types, Histogram Feature Extraction, K-Nearest Neighbor, Website.
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 01 Apr 2019 00:07 |
| Last Modified: | 01 Apr 2019 00:07 |
| URI: | http://eprints.uty.ac.id/id/eprint/2632 |
Actions (login required)
 |
View Item |
