Prediksi Kuantitas Penggunaan Obat pada Layanan Kesehatan Menggunakan Algoritma Backpropagation Neural Network

Abstract

Prediction of the amount of drug use at public health centers is needed to ensure the availability of drugs for patients in service quality management. A good prediction of the amount of medicine needed helps the quality of development planning in the health sector. Scientific developments in the field of Artificial Intelligence (AI) deliver a variety of the best techniques for making predictions. By adopting the workings of neural networks (neurons) in the human brain or Artificial Neural Network (ANN), the Backpropagation Neural Network (BPNN) algorithm is one of the best algorithms in making predictions, including predicting drug use in health services. The problem of this research is how to design the best architectural model such as the number of neurons in the input layer, hidden layer and other parameters so as to produce predictions with optimal accuracy. This study aims to develop an ANN architectural design with the Backpropagation algorithm to predict the need for drug use. The data used is data on drug use reports from 2015 to 2021 at the Andalas Community Health Center (Puskesmas) Padang City. The steps taken to predict are; collect data, pre-process data and perform analysis, design ANN architecture, make predictions. Learning using the backpropagation algorithm through the initial weight initialization process, activation stage, weight training (weight change) and iteration stage. The proportion of the amount of data used for training is 70% data and 30% for testing data. The results of this study indicate that the best ANN architecture is 12-12-1 with an accuracy of predicting the quantity of drug use reaching 97.87% for paracetamol with a Mean Absolute Percentage Error (MAPE) of 2.13%. The prediction results become a reference for the Puskesmas and the Health Office for service planning and development.

Penerapan Metode Neural Network Dengan Struktur Backpropagation Untuk Memprediksi Kebutuhan Stok Pada Toko Umkm Perlengkapan Bayi Babyqu

“…Artificial Neural Network (ANN) atau disebut juga jaringan saraf buatan adalah sebuah model komputasi yang meniru cara kerja jaringan saraf dalam sistem saraf pada hewan maupun manusia. Jaringan saraf buatan terdiri dari banyak unit yang disebut neuron atau unit pengolah [9] [10]. Neuronneuron tersebut terhubung satu sama lain melalui sinaps, dan mampu memproses serta menyimpan informasi.…”

Penerapan Neural Network dengan Menggunakan Algoritma Backpropagation pada Prediksi Putusan Perceraian

“…Salah satu metode yang baik dalam melakukan prediksi adalah backpropagation [12]. Backpropagation adalah salah satu metode pembelajaran dari jaringan suaraf tiruan untuk mengatasi masalah menarik yang ditemukan, salah satunya peramalan [13]. Kelebihan dari metode backpropagation yaitu yang bersifat adaptive dan fault tolerance [14].…”