Please use this identifier to cite or link to this item:
https://repositori.uma.ac.id/handle/123456789/22248
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Khairina, Nurul | - |
dc.contributor.author | Marpaung, Febriady | - |
dc.date.accessioned | 2023-12-06T02:53:32Z | - |
dc.date.available | 2023-12-06T02:53:32Z | - |
dc.date.issued | 2023-08-04 | - |
dc.identifier.uri | https://repositori.uma.ac.id/handle/123456789/22248 | - |
dc.description | 109 Halaman | en_US |
dc.description.abstract | Penentuan daun teh siap panen merupakan faktor penting dalam menentukan kualitas dan nilai jual dari produk teh. Klasifikasi daun teh siap panen dapat membantu para petani teh dan produsen teh dalam menentukan waktu yang tepat untuk memetik daun teh sehingga dapat menghasilkan teh dengan kualitas terbaik. Oleh karena itu diperlukan ada pendekatan digital agar dapat mengenali daun teh siap panen dengan cepat dan akurat. Penelitian ini menggunakan metode Convolutional Neural Network (CNN) dengan arsitektur MobileNetV2 dalam melakukan klasifikasi tingkat daun teh siap panen daun teh. Berdasarkan hasil training pada 6 skenario model yang diuji, diperoleh tingkat akurasi tertinggi pada pengujian skenario model 2 sebesar 100% menggunakan hyperparameter epoch 50, input shape : 224x224x3 (RGB channel), batch size : 32, dan optimizer : Adam. Hasil akurasi dari model setelah diuji menggunakan data testing (100 citra per class) didapatkan hasil akurasi sebesar 100% dengan nilai presisi (precision) sebesar 100%, recall 100%, dan f1-score 100%. The determination of ready-to-harvest tea leaves is a crucial factor in determining the quality and market value of tea products. Classifying ready-to-harvest tea leaves can assist tea farmers and tea producers in identifying the right time to pluck tea leaves to produce the highest-quality tea. Therefore, a digital approach is needed to quickly and accurately recognize ready-to-harvest tea leaves. This research utilizes the Convolutional Neural Network (CNN) method with the MobileNetV2 architecture to classify the readiness level of tea leaves. Based on the training results of six tested model scenarios, the highest accuracy was obtained in scenario model 2 at 100% using hyperparameters: 50 epochs, input shape: 224x224x3 (RGB channel), batch size: 32, and optimizer: Adam. The accuracy of the model after testing with testing data (100 images per class) yielded an accuracy of 100%, with precision, recall, and f1-score all at 100%. | en_US |
dc.language.iso | id | en_US |
dc.publisher | Universitas Medan Area | en_US |
dc.relation.ispartofseries | NPM;188160032 | - |
dc.subject | Classification | en_US |
dc.subject | Ready-to-harvest tea leaves | en_US |
dc.subject | Tea Leaves | en_US |
dc.subject | Convolutional Neural Network | en_US |
dc.subject | MobileNetV2 | en_US |
dc.subject | Daun teh siap panen | en_US |
dc.subject | Daun Teh | en_US |
dc.title | Klasifikasi Daun Teh Siap Panen Menggunakan Cnn Dengan Arsitektur Mobilenetv2 | en_US |
dc.title.alternative | Classification of Tea Leaves Ready to Harvest Using CNN with Mobilenetv2 Architecture | en_US |
dc.type | Thesis | en_US |
Appears in Collections: | SP - Informatic Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
188160032 - Febriady Marpaung - Chapter IV.pdf Restricted Access | Chapter IV | 1.2 MB | Adobe PDF | View/Open Request a copy |
188160032 - Febriady Marpaung - Fulltext.pdf | Cover, Abstract, Chapter I, II, III, V, Bibliography | 2.82 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.