Stunting adalah malnutrisi yang ditandai dengan tinggi badan, diukur dengan standar deviasi dari WHO. Dinas Kesehatan Provinsi Gorontalo khususnya dibidang Gizi mengenai stunting, selama ini melakukan kegiatan pemantauan tiap-tiap puskesmas dan posyandu. Pemantauan dan pendataan terkait stunting di berbagai puskesmas di wilayah Gorontalo merupakan faktor penting dalam menentukan faktor tumbuh kembang baik dalam kandungan maupun bayi yang dilahirkan. Masalah yang sering muncul adalah data yang dikumpulkan untuk underestimasi selalu tidak akurat setiap bulannya, karena hanya perkiraan yang dihitung berdasarkan kasus Puskesmas. Prediksi yang akurat diperlukan untuk mengatasi permasalahan yang ada. Data mining didefinisikan sebagai ekstraksi informasi berharga atau berguna dari industri pertambangan atau database yang sangat besar. Penelitian ini menggunakan algoritma K-Nearest Neighbor (K-NN) dan Support Vector Machine (SVM) menggunakan feature selection backward elimination. Berdasarkan hasil eksperimen, diprediksi jumlah penderita stunting menggunakan algoritma Support Vector Machine (SVM), dan k-Nearest Neighbor (K-NN) menggunakan Backward Elimination (BE). Tingkat error terkecil hasil RMSE 2,476 pada algoritma k-nearest neighbor. Adapun perbandingan antara hasil prediksi jumlah penderita stunting dibulan januari yaitu 23 orang dengan data aktual jumlah penderita stunting yakni 26 orang. Hasil prediksi menghasilkan nilai keakuratan 88,46%.
Regional retribution as payment for services or granting certain permits specifically granted and/or issued by local governments for personal or business interests. Gorontalo City Government has several public facilities that are used as a source of regional income in the form of taxes or levies. The Dulohupa traditional house levy carried out by the Gorontalo City Youth and Sports Tourism Office often experiences ups and downs because it is caused by uncertainty about rentals or competition. The purpose of this research is to overcome the existing problems by predicting retribution receipts using the backpropagation method, the use of particle swarm optimization (PSO) to increase the accurate value in predicting. The data collected is daily quantitative univariate time series data. This type of data is the Dulohupa Traditional House Retribution Receipt Data. The dataset taken from the levy receipt variable has 211 records. The best model is generated on the backpropagation algorithm using the particle swarm optimization (PSO) selection feature, which can be seen from the smallest error rate of 0.122. Thus the addition of a selection feature can improve the performance of an algorithm. The results of the predictions for the next four months from January to April which have been denormalized with an average number of predictions of Rp. 1,806,789 with an error value of 0.112.
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.