Tuberculosis is a disease caused by the mycobacterium tuberculosis virus. Tuberculosis is very dangerous and it is included in the top 10 causes of the death in the world. In its detection, errors often occur because it is similar to other diffuse lungs. The challenge is how to better detect using DNA sequence data from mycobacterium tuberculosis. Therefore, preprocessing data is necessary. Preprocessing method is used for feature extraction, it is k-Mer which is then processed again with TF-IDF. The use of dimensional reduction is needed because the data is very large. The used method is LDA. The overall result of this study is the best k value is k = 4 based on the experiment. With performance evaluation accuracy = 0.927, precision = 0.930, recall = 0.927, F score = 0.924, and MCC = 0.875 which obtained from extraction using TF-IDF and dimension reduction using LDA.
Corona Virus Disease (Covid-19) telah menjadi bencana dunia karena menyerang banyak korban di seluruh dunia dan mengakibatkan kematian. Karena virus tersebut menyerang di beberapa negara termasuk Indonesia, pemerintah Indonesia membuat keputusan untuk menutup hotel dan restaurant sebagai pencegahan Covid-19. Pada penelitian ini, metode prediksi akan dilakukan menggunakan Backpropagation dan Adaptive Neuro Fuzzy. Pada prediksi jumlah hotel dan restaurant yang tutup menggunakan Backpropagation dan Adaptive Neuro Fuzzy, dibutuhkan beberapa input seperti jumlah korban di Jakarta, jumlah korban di Indonesia, dan jumlah korban di dunia. Backpropagation dan Adaptive Neuro Fuzzy dapat menghasilkan prediksi jumlah hotel dan restaurant yang tutup mendekati nilai target. Simulasi diterapkan dengan membagi dataset ke dalam data training (80%) dan data testing (20%). Dari simulasi Backpropagation, Backpropagation dapat menghasilkan prediksi jumlah hotel dan restaurant yang tutup pada data training dengan optimal RMSE adalah 9,2422 dan data testing dengan optimal RMSE adalah 8,9419. Dari simulasi Adaptive Neuro Fuzzy, Adaptive Neuro Fuzzy dapat membuat prediksi jumlah hotel dan restaurant yang tutup pada data training dengan optimal RMSE adalah 0,5324 dan testing data dengan optimal RMSE adalah 5,3198.
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.