Educational data is important information owned by a university. Large amounts of data can be used to identify specific patterns. This study aims to predict the number of new students by identifying data patterns using an artificial neural network (ANN). ANN is an artificial intelligence that has characteristics such as biological neural networks and works as an information processing system, one of the types is backpropagation model. Backpropagation trains the network to be able to recognize and identify patterns that are given during training and provide a response in the form of predicting similar patterns, therefore backpropagation can be used in the field of forecasting. Data that uses as input for the training is new student data from 2000 to 2020, and the expected output is the number of new students in the following tear, which is 2021. This study tested 4 different ANN architecture models, with MSE 0.0001, learning rate 0.01, with a maximum of 1000 iterations. The training process uses a combination of the tansig-purelin and logsig-purelin as the activation functions, and traingdx, traingda traingdm as the acceleration functions. Result of the training process, it was found that the best network architecture is the 12-8-1 pattern, which means using 12 inputs, 8 hidden neurons, and 1 output. The pattern uses the logsig-purelin activation function, the traingda acceleration function, with the MSE result of 0.0001 after going through 94 iterations. Data mahasiswa merupakan informasi penting yang dimiliki oleh suatu perguruan tinggi. Data dalam jumlah besar dapat digunakan untuk mengidentifikasi suatu pola tertentu. Penelitian ini bertujuan untuk memprediksi jumlah mahasiswa baru yang akan datang dengan mengidentifikasi pola data menggunakan Jaringan Syaraf Tiruan (JST). JST merupakan suatu kecerdasan buatan yang memiliki karakteristik seperti jaringan syaraf biologi dan berfungsi sebagai sistem pemroses informasi, salah satunya adalah model backpropagation. Backpropagation melatih jaringan agar mampu mengenali dan mengidentifikasi pola yang diberikan pada saat pelatihan dan memberikan respon berupa prediksi terhadap pola serupa, oleh karena itu backpropagation dapat digunakan dengan baik dalam bidang peramalan. Data masukan yang digunakan untuk pelatihan adalah data mahasiswa baru pada tahun 2000 sampai 2020, keluaran yang diinginkan adalah jumlah mahasiswa baru pada tahun berikutnya. Penelitian ini menguji 4 model arsitektur JST berbeda, dengan MSE 0.0001, learning rate 0.01, dengan maksimal 1000 iterasi. Proses pelatihan menggunakan kombinasi fungsi aktivasi tansig-purelin dan logsig-purelin, serta fungsi percepatan traingdx, traingda, dan traingdm. Dari pelatihan yang dilakukan, didapatkan bahwa arsitektur jaringan terbaik adalah pola 12-8-1 yang berarti menggunakan 12 masukan, 8 hidden neuron, dan 1 keluaran. Pola tersebut menggunakan fungsi aktivasi logsig-purelin, fungsi percepatan traingda, dengan hasil MSE 0.0001 setelah melalui 94 iterasi.
Due to the TFT LCD (Thin-Film-Transistor Liquid-Crystal-Display) manifestation into many related products, this industry has been growing rapidly along with increasing demand. To satisfy the demand, most companies have increased their production capacity and capability by increasing their number of factories in different places and causing complexity in this industry. This research develops a production and distribution planning model for the multi-stage and multi-site supply chain in the TFT LCD industry. Genetic algorithm proposed in this research to solve the problem. Maximizing capacity utilization and total profit in the supply chain are become the major performance indicator in this model. Regarding the high computational effort of genetic algorithm, then parallel computation performed. Genetic algorithm conducted in multi-processor computation using OpenMP for time efficiency. To compare the computational time, the genetic algorithm conducted in five different number of processors; 1, 2, 4, 8, and 16, to know how many processors are needed to get the optimal computational time. The result is the genetic algorithm using 4 processors has the optimal expected net profit compare to the others. The result shows that a larger number of processors doesn’t mean the computation time will become automatically faster.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.