<span lang="EN-US">Plant disease is a challenge in the agricultural sector, especially for rice production. Identifying diseases in rice leaves is the first step to wipe out and treat diseases to reduce crop failure. With the rapid development of the convolutional neural network (CNN), rice leaf disease can be recognized well without the help of an expert. In this research, the performance evaluation of CNN architecture will be carried out to analyze the classification of rice leaf disease images by classifying 5932 image data which are divided into 4 disease classes. The comparison of training data, validation, and testing are 60:20:20. Adam optimization with a learning rate of 0.0009 and softmax activation was used in this study. From the experimental results, the InceptionV3 and InceptionResnetV2 architectures got the best accuracy, namely 100%, ResNet50 and DenseNet201 got 99.83%, MobileNet 99.33%, and EfficientNetB3 90.14% accuracy.</span>
AbstrakKehadiran guru sangat berpengaruh terhadap proses belajar mengajar di sekolah maka dari itu seorang guru haruslah disiplin dalam melakukan kehadiran setiap harinya. Presensi merupakan salah satu cara untuk mencatat kehadiran guru. Berdasarkan hasil dari observasi dan wawancara di sekolah proses presensi masih dilakukan dengan cara melakukan tanda tangan diatas kertas. Cara ini masih kurang efektif dilakukan karena masih ditemui beberapa kelemahan seperti menitip tanda tangan, hadir terlambat dan lupa tanda tangan. Proses pelaporan presensi ke Disdik Kabupaten Bengkalis juga masih dilakukan dengan cara mengirim hasil rekap dalam bentuk laporan. Maka dibutuhkan aplikasi presensi dengan menggunakan mesin sidik jari untuk memudahkan proses presensi. Data presensi akan dikirim ke dalam sebuah server raspberry pi menggunakan web service SOAP dan disimpan kedalam database MySql. Data presensi juga akan dikirim ke Disdik menggunakan web service REST. Hal ini sangat bermanfaat untuk meminimalisir terjadinya kecurangan dalam melakukan presensi, mudah dalam memonitoring kehadiran dan rekap data presensi guru. Disdik Kabupaten Bengkalis juga lebih mudah dalam memonitoring kehadiran guru karena sistem presensi guru di sekolah sudah terintegrasi dengan sistem yang dimiliki oleh Disdik. AbstractThe presence of teachers is very influential on the teaching and learning process in schools so a teacher must be disciplined in making attendance every day. Presence is one way of record teacher attendance. Based on the results of observations and interviews in schools the attendance process is still done by doing a signature on paper. This method is still less effective because there are still some weaknesses such as signing autographs, being late and forgetting signatures. The process of reporting attendance to Bengkalis District Education Office is also still done by sending the recap results in the form of reports. Then the presence application is needed by using a fingerprint machine to facilitate the presence process. Presence data will be sent to a raspberry pi server using the SOAP web service and stored in the MySql database. Presence data will also be sent to Disdik using the REST web service. This is handy to minimize the occurrence of fraud in presence, easy to monitor the presence and recap of teacher attendance data. The District Education Office of Bengkalis District is also easier to monitor teacher attendance because the teacher attendance system in schools have been integrated with the system owned by Disdik. 1. PendahuluanMenurut pusat bahasa Departemen Pendidikan Nasional menjelaskan bahwa pendidikan adalah proses pengubahan sikap dan tatalaku seseorang atau kelompok orang dalam usaha mendewasakan manusia melalui upaya pengajaran, pelatihan, dan perbuatan mendidik [1]. Dengan adanya pengubahan tingkah laku tersebut tidak luput dari peran seorang guru selaku tenaga pengajar. Guru menjadi faktor penting dalam dunia pendidikan karena guru yang akan melaksanakan proses pembelajaran, menilai hasil pembelajaran, mel...
Penyakit tanaman merupakan sebuah tantangan pada sektor pertanian terutama bagi petani padi. Mengidentifikasi penyakit pada daun padi merupakan langkah awal untuk memberantas dan mengobati penyakit, sehingga dapat meminimalisir terjadinya gagal panen. Dengan perkembangan cepat dari convolutional neural network (CNN), penyakit daun padi dapat dikenali dengan baik tanpa bantuan seorang ahli. Arsitektur MobileNet-V2 digunakan untuk mengklasifikasi penyakit daun padi karena yang memiliki ukuran yang kecil namun dengan peforma yang baik. Untuk meningkatkan peforma dari model CNN, akan dilakukan optimasi hyperparameter yang terdiri epoch, batch size, learning rate dan optimizer. Penelitian ini bertujuan untuk untuk mendapatkan hyperparameter yang optimal sehingga memberikan peforma yang baik pada model CNN. Dataset yang digunakan terdiri dari 3 kelas penyakit yang menyerang daun tanaman padi antara lain blast, blight dan tungro. Berdasarkan percobaan yang sudah dilakukan, penentuan hyperparameter sangat berpengaruh terhadap peforma model. Hyperparameter dengan jumlah epoch 100, batch size 32, learning rate 0,001 dan optimizer RMSProp memberikan hasil yang paling optimal dengan nilai accuracy 97,56%, precission 97,64%, recall 97,57% dan f1-score 97,57%.
Database design is a data design process that is used to support the operational activities and goals of organizations and agencies. The use of databases on the geographic information system of residents' lands makes it possible to store, change, and display all data quickly and easily. One of the factors that become a problem in database design is the point of view of seeing data that varies between designers, programmers, and end-users. Therefore we need a methodology in good database design by applying procedures, techniques, tools, and documentation. The method used in this study used the Research and Development (R&D) method, while the database design method used the Database Life Cycle (DBLC) method. The research variables were database design for the geographic information system of resident land with a relational data model. Research aspects include conceptual design, logical design, and physical design. The final result of this research is to produce 10 types of conceptual entities, produce a relationship diagram of the ten logical entities, and produce a physical design consisting of user_admin, user_pengguna, data_desa, data_kecamatan, data_kabupaten, jenis_tanah, data_penduduk, data_buku_c, data_mutasi, and data_sppt tables.
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.