Every year, more than 150 million people, primarily children under five, develop pneumonia. Various articles present various methods for detecting pneumonia. However, to accurately analyze chest X-ray images, radiologists need expertise field. The traditional techniques remain shortcomings, including the availability of experts, maintenance costs, and expensive tools. Thus, we present a new intelligence method to detect pneumonia images quickly and accurately using the Faster Region Convolutional Neural Network (Faster R-CNN) algorithm. To build our detection model, we collect data, process it first, train it with various parameters to get the best accuracy, and then test it with new data. Based on the experimental results, it was found that this model can accurately detect pneumonia x-ray images marked with bounding boxes. In this model, it is possible to predict the bounding box that is more than what it should be, so NMS is applied to eliminate the prediction of the bounding box that is less precise to increase accuracy
Pada zaman sekarang perkembangan teknologi begitu pesat yang memungkinkan semua hal dapat dilakukan dengan mudah dengan bantuan teknologi, terutama dalam mendeteksi jenis pisang. Di Indonesia terdapat berbagai jenis pisang yag memiliki bentuk dan tekstur yang hampir sama yang menyebabkan masyarakat masih sulit untuk membedakannya. Kesulitan yang dihadapi masyarakat dapat dibantu dengan perkembangan teknologi yang ada saat ini. Berdasarkan masalah di atas peneliti mengusulkan sebuah aplikasi klasifikasi jenis pisang menggunakan Convolutional Neural Network untuk mengklasifikasikan tiga jenis pisang seperti pisang nangka, pisang barangan dan pisang cavendish dengan melakukan proses pada model Training dan Testing kemudian diimplementasikan ke dalam bentuk aplikasi menggunakan Android Studio. Hasil penelitian ini berupa aplikasi klasifikasi jenis pisang menggunakan algoritma Convolutional Neural Network. Aplikasi mendapatkan hasil akurasi di kisaran angka 60% - 70% dari tiga jenis pisang. Adapun hasil akurasi yang dihasilkan dari model training diperoleh 99,94% dan untuk testing diperoleh 86,56% akurasi.
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.