Data mining has been widely used to diagnose diseases from medical data. Classification is a data mining technique that can be used to predict disease. In previous studies, a support vector machine was widely used to obtain high accuracy in predicting hepatitis. In this study, the principal component analysis was applied to the support vector machine. A principal component analysis is used to extract features and reduce the number of features or attributes. Principal component analysis can reduce data dimensions without removing important information from the dataset. The extracted and reduced data are then used to classify the support vector machine. Classification performance measurement is done by using a confusion matrix. Hepatitis prediction accuracy achieved was 93.55%. This result is better than the support vector machine classification results without the application of principal component analysis.
Banks try to get profit from society in various ways. One way is to use long-term deposit investment offers. If the product offering process for potential investors is not carefully considered, it will waste resources. Therefore, this study analyzes the accuracy of the predictions of consumers who have a high chance of participating in this program. The dataset used is historical bank data provided by Kaggle. In previous research, accuracy prediction has been carried out, but the accuracy is still low because it does not use a method to balance the class. Better accuracy can be improved using LightGBM and SMOTE methods. The test results with the number of testing data as much as 6590 and training data as many as 32950 show the highest accuracy of 90.63%.
Sorghum seeds form some varieties are range from 2 to 4 mm in size and containing the outer skin/husk about 30 percent. Parallel with tampering of cortex/husk sorghum seeds, also needs exfoliation process. In order of husk exfoliation process can be done equally, it’s required grading/sorting of sorghum seeds and tampering process be spread evenly. Tampering purposes to remove sorghum’s pericarp and tesla coating that contains tannin on endosperm section. This section able to reduce protein digestibility inside the human body and causes constipation. Center for Agricultural Engineering Research and Development (BBP Mektan) developed Sorghum grading machine with pneumatic type with work capacity 400 kg/hour. The aims of this study were : (i) to sorting sorghum seeds evenly (ii) to produce clean sorghum seeds. The testing of grading machine performance, includes: preparation, fabrication and modification, functional and performance test, and reporting. Sorting/grading machine use diesel motor driving force 6.5 HP and the dimension of the machine are 1610 x 1280 x 1820 mm. The capacity of sorting/grading machine able to achieve 400 kg/hour with the efficiency of sorghum’s seed uniformity around 86.25%.
Evaluasi pendidikan di Sekolah Menengah Kejuruan Negeri 2 Depok seperti Ulangan Harian, Ulangan Tengah Semester, Ulangan Akhir Semester, dan Ujian Sekolah Berstandar Nasional belum terkomputerisasi. Evaluasi pendidikan yang belum terkomputerisasi ini mengakibatkan perlunya biaya untuk penggandaan soal dan waktu untuk proses koreksi jawaban. Oleh karena itu, solusi untuk menjawab masalah tersebut adalah pembuatan sebuah sistem terkomputerisasi untuk melakukan evaluasi pendidikan atau sering disebut sebagai computer-based test (CBT). Penelitian ini bertujuan untuk membuat sistem CBT di SMKN 2 Depok, sesuai dengan rencana pihak sekolah yang ingin merapkan sistem CBT pada evaluasi pendidikan. Penelitian ini menggunakan metode Fisher-Yates shuffle (FYS) untuk melakukan pengacakan soal. Metode pengembangan sistem yang digunakan adalah Waterfall. Alat yang digunakan dalam pembuatan CBT yaitu PHP, JavaScript, Bootstrap dan MySQL. Percobaan pada sistem CBT dilakukan dengan mengacak soal ujian yang terdiri atas 30 soal. Pengacakan soal dilakukan sebanyak 40 kali. Pengacakan soal yang dilakukan berhasil dengan baik, karena tidak terdapat urutan soal yang sama. Pengujian sistem dilakukan menggunakan metode black box. Hasil pengujian sistem menunjukan bahwa fungsional sistem sudah 100% berjalan dengan baik.
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.