Current technology has been widely applied for development, one of which has an Artificial Intelligence (AI) applied to Smart Farming. AI can give special capabilities to be programmed as needed. In cooperation with agricultural systems, AI is part of improving the quality of agriculture. This technology is no stranger to being applied in basic fields such as agriculture. This smart technology is needed to increase crop yields for various regions by utilizing the current trends paper. This is necessary because less land is available for agriculture, and there is a greater need for food sources. Therefore, this systematic review aims to collect the current trends in AI studies for Smart Farming papers using the latest year features from 2018-2022. This paper is handy for researchers and industry in looking for the latest papers on research to enhance crop yields. The authors utilized Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) of 534 articles from IEEE, ACM, MDPI, IAES, and ScienceDirect. After going through a careful process, 67 papers were found that were judged according to the criteria. After the authors got some of the current trends, the author has discussed several factors regarding the results obtained to enhance crop yields, such as Weather, Soil, Irrigation, Unmanned Aerial Vehicle (UAV), Pest Control, Weed Control, and Disease Control.
Education is one thing that must be arranged as early as conceivable in arrange to realize a quality era. When talking about education today, it cannot be separated from technology. Where we can see that technology has been used in various fields. In the field of education, one of them is the use of the internet network. However, the use of this technology has quite a bad side. Especially for elementary-level students or the age of children. That is the bad impact of exposure to pornography. Exposure to pornography is very dangerous and can damage children both psychologically and mentally. Therefore, it is important to minimize the risk of exposure to pornography. To overcome this, there are many methods that can be used. Like detecting pornographic content automatically and blocking it. One technique that can be developed to detect pornographic content is Artificial Neural Networks. However, so that the image input can be handled effectively, the model of the Artificial Neural Network has been varied into a Convolutional Neural Network (CNN) technique. So it has the ability to recognize objects for image data. The model built in this study was trained using a dataset that has been adapted to the definition of pornography in Indonesia. From the tests that have been carried out on the CNN model that was built, the best accuracy rate is 94.24%. in detecting images that fall into the category of pornographic content.
Collaborative filtering merupakan salah satu teknik yang memanfaatkan informasi preferensi pengguna dalam bentukpenilaian peringkat (rating) yang menghasilkan prediksi berdasarkan kesamaan pola penilaian. Akurasi prediksi selalumenjadi penilaian pada sistem yang dibangun dengan teknik collaborative fitering. Studi ini melibatkan komparasialgoritma similaritas yang digunakan pada collaborative filtering berbasis item untuk memprediksi penilaian (rating)dalam studi kasus data restoran. Pengujian yang dilakukan adalah membangun sistem collaborative filtering berbasisitem dengan menggunakan variansi algoritma similarity antara euclidean distance dan cosine similarity yangbertujuan untuk menganalisis kemampuan keduanya dalam memprediksi item. Hasil studi pada kasus inimenunjukkan bahwa collaborative filtering berbasis item dengan pendekatan euclidean distance memiliki akurasiyang lebih baik daripada cosine similarity.
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.