Several problems related to determining the quality of dragon fruit quality are: fruit disease, harvest time selection, sorting process and post-harvest grading. Determination sorting dragon fruit quality by observing the appearance of fruit, fruit smoothness, presence or absence of defects and fruit size. However, this quality determination has disadvantages such as longer sorting time and different perceptions of farmers about the quality of dragon fruit. To solve this problem, we need a sorting system that is able to determine the quality of dragon fruit effectively and efficiently without damaging the dragon fruit. In this study, determining the quality of white dragon fruit using digital image processing techniques and intelligent systems. The output of the digital image processing technique is five morphological features such as area, perimeter, length, diameter and metric. This feature is the input of the backpropagation method so that the quality of white dragon fruit is divided into 3 classes such as class A, class B and class C. The results showed the best network architecture model was 5,8,5,3 with the best testing accuracy rate of 86.67%.
The demand for cayenne pepper in Indonesia tends to increase annually, but the productivity of cayenne pepper continues to decline and depends on the changing seasons. One of the factors that must be considered in the harvest of cayenne pepper is the level of maturity. This research aims to classify the maturity level of cayenne pepper using the extraction of color and texture features. The extraction of features based on the color is taken from the mean saturation value, while the extraction of feature-based textures uses the value of the Gray Level Co-Occurrence Matrix (GLCM) feature ASM (Angular Second Moment), contrast, IDM (Inverse Difference (Entropy) and correlation (Correlation) then using angles of 0 ° and 45 °. These features become input in the classification process using the Backpropagation method. The results of the system training are able to classify the level of maturity of cayenne pepper with an accuracy of 81.4% and an accuracy of the testing process of 74.2%. Permintaan cabai rawit di Indonesia cenderung meningkat setiap tahunnya, namun produktivitas cabai rawit terus menurun dan bergantung pada pergantian musim. Salah satu faktor yang harus diperhatikan dalam panen cabai rawit adalah tingkat kematangan. Penelitian ini bertujuan untuk melakukan klasifikasi tingkat kematangan cabai rawit menggunakan ekstraksi fitur warna dan tekstur. Ekstraksi fitur berdasarkan warna diambil dari nilai mean saturasi, sedangkan ekstraksi fitur berdasarkan tekstur menggunakan nilai fitur Gray Level Co-occurrence Matrix (GLCM) yaitu ASM (Angular Second Moment), Kontras (Contrast), IDM (Inverse Difference Momentum), Entropi (Entropy) dan Korelasi (Correlation) dan menggunakan sudut 0° dan 45°. Fitur-fitur tersebut menjadi masukan pada proses klasifikasi menggunakan metode Backpropagation. Hasil pelatihan sistem mampu mengklasifikasi tingkat kematangan cabai rawit dengan akurasi sebesar 81,4% dan akurasi proses pengujian cabai rawit sebesar 74,2%.
Penurunan mutu dan produktivitas tomat diakibatkan oleh curah hujan tinggi, cuaca dan budidaya yang tidak baik sehingga tomat menjadi busuk, retak, dan timbul bercak. Pemerintah berupaya memberikan pelatihan untuk meningkatkan mutu tomat pada para petani. Namun pelatihan tersebut tidak efektif sehingga para peneliti membantu membuat sebuah sistem yang mampu mengedukasi para petani dalam klasifikasi kerusakan mutu tomat. Sistem ini berfungsi untuk mempermudah petani dalam mengenali kerusakan tomat sehingga mengurangi risiko gagal panen. Pada penelitian ini, metode klasifikasi yang digunakan yaitu backpropagasi dengan 7 parameter input. Input tersebut terdiri dari fitur morfologi dan tekstur. Output dari sistem klasifikasi ini terdiri dari 3 kelas adalah busuk buah, retak buah dan bercak buah yang diakibatkan oleh bacterial speck. Tingkat akurasi terbaik dari sistem dalam mengklasifikasi kerusakan mutu tomat pada proses pelatihan sebesar 89,04% dan pengujian sebesar 81,11%.
Jeruk siam adalah salah satu jeruk local yang mempunyai nilai jual yang tinggi di Indonesia. Tahun 2020, tingkat produksi jeruk siam mengalami penurunan menjadi 712.585 ton di Jawa Timur. Salah satu faktor utama yang menyebabkan menurunnya tingkat produksi jeruk siam yaitu serangan penyakit pada daun jeruk siam. Dua penyakit yang sering menyerang daun jeruk siam adalah penyakit kanker yang disebabkan oleh patogen Xanthomonas axonopodis pv.citri dan penyakit ulat peliang. Selama ini, pengamatan pada penyakit daun jeruk siam dilakukan secara manual menggunakan mata sehingga penentuan penyakit tersebut bersifat subyektif. Untuk mengatasi masalah tersebut dibuatlah sistem otomatis identifikasi daun jeruk siam sehat dan daun jeruk siam terserang penyakit dengan bantuan teknik computer vision. Tahapan penelitian yaitu pengumpulan citra daun jeruk, konversi warna, ekstraksi fitur warna dan tekstur serta klasifikasi K-Nearest Neighbor (KNN). Parameter fitur yang digunakan yaitu fitur warna GB, fitur tekstur (ASM, entropi dan kontras). Metode KNN mampu mengklasifikasi dan mengidentifikasi penyakit daun jeruk siam dengan akurasi sebesar 70% dengan variasi nilai K = 21.
Tidal lowland is one of the potential lands for agriculture that is found very widely in coastal areas of South Sumatra. There are about 400,000 hectares (ha) was reclaimed for agriculture purpose. However, in many parts, the rice production is still low (<3 ton/ha), mainly in the high part of hydrotopography class (Type C) that the tidewater could not possibly irrigate the land. This study aimed to evaluate the level of actual and potential suitability of tidal swamps for rice plants. This research has been carried out in Bandar Jaya Village, Air Sugihan Subdistrict, Ogan Komering Ilir Regency. This research used a survey level method with very detailed (intensive) with a scale of 1:6,000 covering a research area of 16 ha. The results showed that actual suitability for rice plants in the study site is N-n with an area of 5 ha and N-f, n with an area of 11 ha with limiting factors of soil pH and P nutrient. The potential land suitability class for rice plants in the study location is S3-n with an area of 5 ha and S3-f, n with an area of 11 ha. Land quality improvement was done by using the lime application and control water table at a depth of at least 10 cm from the soil surface during rice growth. Rainwater should be retained in the tertiary block as much as possible to fulfill crop water requirements. Setting the planting time (November-January) and balanced fertilization will be able to increase the land suitability class to S1 (highly suitable).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.