Corn is a plant that is widely grown in developing countries such as Indonesia. To increase maize yields, researchers are always innovating on the current state of technology for classifying maize plant diseases. Three kinds of diseases attack corn leaves, namely Gray leaf Spot, Blight, and Common Rush. The amount of data that we use is 3500 data consisting of 500 Gray Leaf Spots, 1000 Blights, 1000 Common Rushes, and 1000 healthy leaves. This study aims to develop an artificial intelligence model. The artificial intelligence model that we developed uses LBP feature extraction combined with k-NN for the classifier. In addition to using the k-NN method, our tests were carried out using several classification methods such as Naïve Bayes and Adaboost. The result of our test is that the k-NN method has the highest value compared to the Naïve Bayes and Adaboost methods. The results of the performance using k-NN with k=5 resulted in a value of 81.1%, the AUC value of 94.1%, the F1-Score of 80.9%, Precision of 81.8%, and Recall of 81.1%.
The final goal of restoration is image improvement. In general, restoration to degradation modeling and implementation of invers process to get real image. Hopefield method in neural network restoration of image is done by parameters approximation in neural network modeling and reconstruction of degradation image to get real image. In this paper, this method is used image restoration which combines with Gaussian Blur, Uniform Blur and Gaussian Noise. The restoration process using this method take place really fast and suitable to defects restoration of recorder device which recognize the cause of defects and high process speed is needed.
Digital Image processing implementation can be applied to identify medicinal leaves, because it can help the elderly and people with color-blindness in identifying medicinal leave to be consumed and in avoiding reading errors, since some leaves have similar shape and color . In this discussion, the feature-extractions are using color and shape features, and using Levenberg-Marquardt for pattern recognition algorithm. The success of this medicinal plant identification system resulted in fairly good accuracy. The backpropagation network architecture used two hidden layers with 10 and 5 neurons. Data training is using 60 training leaf images with 15 images each of 5 types: green betel leaf, red betel, soursop, castor and aloe vera. Then, offline testing is using 20 test images for each of 4 images from 5 types with the accuracy of 85%. Meanwhile the online (realtime) test is using 20 times for each leaf types so the accuracy is 88%.
Pandemik Covid-19 yang dialami seluruh dunia saat ini termasuk Indonesia, memaksa pembelajaran dilakukan secara daring atau e-learning termasuk pada Politeknik Negeri Padang. Dengan kendala yang ada pada mahasiswa sebagai peserta didik dalam sistem pembelajaran ini yaitu kendala dalam mengakses sistem melalui jaringan internet dan belum semua mahasiswa memiliki perangkat komputer yang dibutuhkan dalam mengaplikasikan matakuliah berbasis pemrograman. Agar capaian pembelajaran tetap bisa dicapai secara optimal maka dalam penelitian ini dibuat web untuk sistem pembelajaran daring atau e-learning. Dari hasil penggunaan web ini 82,9 % mahasiswa memahami materi yang ditayangkan dalam web tersebut dan sebagain besar mahasiswa menginginkan materi dalam bentuk video offline sehingga dapat digunakan setiap saat.
Sistem pintar banyak digunakan dalam smart building, smart home, smart car, smart class, dan lainnya. Sistem pintar dalam artikel ini yang merupakan hasil penelitian, memanfaatkan modul mikrokontroller Intel Galileo dan teknologi Internet of Things (IoT) sebagai pengendali, dimana perangkat yang dikendalikan terhubung dengan sistem pengendali jarak jauh berbasis web yang diakses melalui smart devices (smart phone, tablet, dan laptop). Intel galileo merupakan modul mikrokontroller yang menggabungkan mini komputer dan arduino yang open source serta mendukung teknologi IoT dan web. Pemilihan web sebagai pengendali jarak jauh dalam penelitian ini untuk mempermudah pengguna sistem agar dapat mengendalikan sistem dari jarak jauh dengan memanfaatkan browser yang ada pada smart devices walaupun sistem operasi berbeda. Perangkat yang dikontrol dalam sistem ini adalah lampu LED (on-off otomatis dan pengaturan intensitas cahaya lampu), AC (on-off otomatis, pengaturan suhu), proyektor (on-off) dan IP camera (digerakkan ke atas, bawah, kiri, dan kanan) untuk memonitor ruangan. Semua perangkat dikontrol secara embedded untuk memudahkan dalam pengendalian dan efektif dalam penggunaan sehingga menghasilkan sistem pintar pengendali terpusat untuk multi perangkat dalam kelas dalam upaya mewujudkan smart class.
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.