No abstract

A Neural network is a series of algorithms that endeavours to recognize underlying relationships in a set of data through processes that mimic the way human brains operate. In the case of classification, this method can provide a fit model through various factors, such as the variety of the optimal number of hidden nodes, the variety of relevant input variables, and the selection of optimal connection weights. One popular method to achieve the optimal selection of connection weights is using a Genetic Algorithm (GA), the basic concept is to iterate over Darwin's evolution. This research presents the Neural Network method with the Backpropagation Neural Network (BPNN) and the combined method of BPNN with GA, where GA is used to initialize and optimize the connection weight of BPNN. Based on accuracy value, the BPNN method combined with GA provides better classification, which is 90.51%, in the case of Bidikmisi Scholarship classification in East Java.

No abstract

The implementation of national education must ensure equitable distribution of educational facilities. However, based on data from the Regional Education Balance Sheet (NPD) in 2021, elementary schools in Bojonegoro District still need to meet the criteria for overall equality. It is mainly related to educational capacity and facilities. It is necessary to group elementary schools based on capacity and educational facilities to solve this problem by applying the clustering method. The research aims to conduct a comparative study of three clustering methods to get the best way to be used for clustering elementary schools in Bojonegoro Regency. This study applies three clustering methods, namely K-Means, K-Medoids, and Random Clustering, which are compared to get the best clustering method. The data used is secondary data representing educational capacity and facilities, namely the number of students, teachers, classrooms, and study groups (Rombel) from the Bojonegoro District Education Office. Obtained the resulting comparison of clustering methods with the best way falls on the K-Means method, which forms 5 clusters. It explained that elementary schools with educational capacity and facilities get highly complete 14 schools (cluster_3), complete 236 schools (cluster_2), fairly complete 176 schools (cluster_4), less complete 310 schools (cluster_1), and incomplete 177 schools (cluster_0). The conclusion that comparing Clustering methods obtained grouping of Elementary School data with the best way falls on the K-Means method by getting 5 clusters.

Tuberculosis is a type of infectious disease that is contagious and causes death. In Bojonegoro district, the number of tuberculosis patients is quite high, reaching 3,401 patients in 2019. The DOTS strategy has been used, but it is not optimal in reducing the incidence of tuberculosis. Therefore, research is needed to determine the faktors that significantly cause the incidence of tuberculosis and predict the incidence of tuberculosis for some time to come. The incidence of tuberculosis is not only influenced by the faktors causing tuberculosis but is also influenced by a certain period of time. So that in this study the panel data regression method will be used to model the number of tuberculosis patients in Bojonegoro district in 2018-2020. The variables used are the number of tuberculosis sufferers (Y), the number of stunting cases (X1), the number of trained health workers (X2), the number of proper sanitation (X3), the number of PHBS households (X4), and the number of productive age population ( X5). Based on the analysis results show that the best estimation model is using the Fixed Effect Model (FEM) approach. The variables that significantly affect the number of tuberculosis sufferers in Bojonegoro district in 2018-2020 are the number of stunting cases (X1), the number of proper sanitation (X3) and the number of productive age population (X5) with a coefficient of determination of 71%.