Please use this identifier to cite or link to this item:
https://repositori.uma.ac.id/handle/123456789/24220
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Syah, Rahmad | - |
dc.contributor.author | Siregar, Martua Andri | - |
dc.date.accessioned | 2024-06-06T03:35:26Z | - |
dc.date.available | 2024-06-06T03:35:26Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | https://repositori.uma.ac.id/handle/123456789/24220 | - |
dc.description | 59 Halaman | en_US |
dc.description.abstract | Penelitian ini bertujuan meningkatkan akurasi klasifikasi biji kopi melalui pemanfaatan ekstraksi Local Binary Pattern (LBP) dengan menggunakan Modular Neural Network (MNN). Kopi, sebagai salah satu komoditas unggulan di Indonesia, memainkan peran vital dalam perekonomian negara. Produksi kopi, terutama jenis arabika dan robusta, mengalami fluktuasi dari tahun 2018 hingga 2020, memotivasi penelitian ini untuk mengeksplorasi teknologi terkini dalam meningkatkan ketepatan klasifikasi jenis kopi. Penelitian ini memfokuskan pada tiga jenis kopi utama di Indonesia, yaitu arabika, robusta, dan liberika. Meskipun arabika dan robusta lebih umum dijumpai, kopi liberika juga mendapat perhatian dalam industri kopi Indonesia. Melalui ekstraksi LBP, sebuah teknik fitur penting dalam pengolahan citra dan pengenalan pola, penelitian ini menggambarkan langkahlangkah menggunakan diagram alur untuk memudahkan proses. Hasil pengujian dengan metode Confusion Matrix pada MNN menunjukkan akurasi sebesar 87.25% dalam mengklasifikasikan 2000 citra biji kopi, mengindikasikan efektivitas ekstraksi LBP dalam meningkatkan kualitas klasifikasi. Dengan demikian, penelitian ini memberikan kontribusi penting pada pengembangan teknologi dalam konteks perkebunan kopi di Indonesia. Penggunaan LBP pada MNN tidak hanya meningkatkan akurasi klasifikasi biji kopi tetapi juga membuka peluang pengembangan lebih lanjut dalam penerapan teknologi di sektor perkebunan dan pengolahan hasil pertanian. This research aims to improve the accuracy of coffee bean classification through utilization of Local Binary Pattern (LBP) extraction using Modular Neural Network (MNN). Coffee, as one of the leading commodities in Indonesia, plays a vital role in the country's economy. Coffee production, especially types arabica and robusta, experienced fluctuations from 2018 to 2020, motivating This research is to explore the latest technology in improving accuracy of coffee type classification. This research focuses on three types of coffee The main types in Indonesia are Arabica, Robusta and Liberica. Although arabica and robusta is more common, liberica coffee is also gaining attention in the industry Indonesian coffee. Through LBP extraction, an important feature technique in image processing and pattern recognition, this research describes the steps Use flowcharts to make the process easier. Test result with the Confusion Matrix method on MNN shows an accuracy of 87.25% in classifying 2000 coffee bean images, indicating effectiveness LBP extraction in improving classification quality. Therefore, This research makes an important contribution to the development of deep technology context of coffee plantations in Indonesia. The use of LBP in MNN is not only improve the accuracy of coffee bean classification but also open up opportunities further development in the application of technology in the plantation sector and processing of agricultural products. | en_US |
dc.language.iso | id | en_US |
dc.publisher | Universitas Medan Area | en_US |
dc.relation.ispartofseries | NPM;198160012 | - |
dc.subject | ekstraksi biji kopi | en_US |
dc.subject | klasifikasi kopi | en_US |
dc.subject | local binary pattern (lbp) | en_US |
dc.subject | modular neural network (mnn) | en_US |
dc.subject | coffee bean extraction | en_US |
dc.subject | coffee classification | en_US |
dc.title | Ekstraksi Local Binary Pattern terhadap Klasifikasi Kopi Menggunakan Modular Neural Network (MNN) | en_US |
dc.title.alternative | Local Binary Pattern Extraction for Coffee Classification Using Modular Neural Network (MNN) | en_US |
dc.type | Skripsi Sarjana | en_US |
Appears in Collections: | SP - Informatic Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
198160012 - Martua Andri Siregar - Fulltext.pdf | Cover, Abstract, Chapter I, II, III, V, Bibliography | 873.09 kB | Adobe PDF | View/Open |
198160012 - Martua Andri Siregar - Chapter IV.pdf Restricted Access | Chapter IV | 128.15 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.