Avocado seeds have been studied for use as corrosion inhibitors of mild steel in a solution of 0.75 M sulfuric acid. Corrosion inhibition efficiency at a concentration of 10 g / L avocado seed extract (ASE) was obtained at 74.56% with weight loss method and 68.38% with potentiometric polarization method. Corrosion inhibition efficiency was found to be greater with increasing ASE concentration. Polarization studies show that the avocado seed extract is a mixed corrosion inhibitor. SEM images on mild steel with the addition of ASE showed the formation of a thin layer on the mild steel surface. OH and CN functional groups appear on the FT-IR spectrum of ASE. These functional groups interact with iron on the steel surface to form a thin layer that can inhibit corrosive ion attacks from sulfuric acid solutions.
Setiap tanaman memiliki daun dengan bentuk dan ukuran yang berbeda. Meskipun demikian, matamanusia memiliki kesulitan untuk mengidentifikasi dengan tepat jenis tanaman hanya berdasarkan daridaunnya saja. Pada penelitian ini digunakan "Supervised Learning?¢â?¬? untuk membantu mengenali jenistanaman berdasarkan daunnya. Pertama-tama sejumlah daun akan difoto, lalu foto tersebut akan diresizemenjadi citra baru dengan ukuran tertentu, kemudian dimasukkan ke dalam dataset. Lalu citraakan dikonversi menjadi matriks dimana matriks ini akan dimasukkan ke dalam algoritma CNN(Convolutional Neural Network). Pada algoritma CNN, matriks tersebut akan digunakan untukmengekstraksi fitur yang ada pada citra menggunakan beberapa filter yang sebelumnya telahditentukan menggunakan metode konvolusi. Lalu hasil konvolusi tersebut akan digunakan untukpelatihan menggunakan algoritma feedforward dan backpropagation untuk mendapatkan data weightdan bias yang optimal. Setelah itu dilakukan proses test dimana citra uji akan melalui proses konvolusi.Hasil konvolusi akan diklasifikasi menggunakan algoritma feedforward berdasarkan data weight danbias yang sudah didapatkan dari proses training sebelumnya. Pengujian dilakukan dengan 375 gambardaun: 250 citra sebagai data training (latih), dan 125 citra sebagai data test (uji). Hasil pengujianmenunjukkan algoritma CNN memiliki tingkat akurasi yang baik dalam pengidentifikasian piksel dandapat mengenali setiap jenis daun yang ada. Pengujian ini menghasilkan tingkat akurasi 76%. Darihasil pengujian dapat dinyatakan bahwa pada penelitian ini CNN adalah classifier terbaik.
One of the problems in data mining classification is class imbalance, where the number of instances in the majority class is more than the minority class. In the classification process, minority classes are often misclassified, because machine learning prioritizes the majority class and ignores the minority class so that this can cause the classification performance to be not optimal. The purpose of this study is to provide a solution to overcome class imbalances so as to optimize classification performance using chi-square and adaboost on one of the classification algorithms, namely C5.0. In this study, the majority class in the dataset used is dominated by the negative class, so the performance appraisal should focus more on the positive class. Therefore, a more suitable assessment is recall/sensitivity/TPR because the resulting value only depends on the positive class. The results showed that both methods were able to increase the recall/sensitivity/TPR value, meaning that the application of chi-square and adaboost was able to improve the classification performance of the minority 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.