ANALISIS JARINGAN SYARAF TIRUAN METODE BACKPROPOGATION DALAM MEMPREDIKSI KETERSEDIAAN KOMODITAS BERAS BERDASARKAN PROVINSI DI INDONESIA

Food is a major human need that must be completed at any time. This right is one of human rights, stated in article 27 of the 1945 Constitution and in the Rome Declaration (1996). These considerations underlie the issuance of Law No. 7/1996 concerning Food. With these considerations, the Government always considers increasing food security related to increasing domestic production. This research is expected to contribute to the government in order to predict the contribution of rice by province in Indonesia. The data used is data from the National Statistics Agency through the website www.bps.go.id. The data is data on rice / rice production based on provinces in Indonesia in the period of 2010 to 2015. The algorithm used in this study is Artificial Neural Networks with the Backpropagation method. The input (input) variables used are data for 2010 (X1), data for 2011 (X2), data for 2012 (X3), data for 2013 (X4), data for 2014 (X5) and data for 2015 as targets with models training and testing architecture of 4 architectures namely 4-4-1, 4-8-1, 4-16-1, 4-32-1. The resulting output is the best pattern of ANN architecture. The best architectural model is 4-4-1 with 218 days, MSE 0.012728078 and an accuracy rate of 97%. From this model obtained from estimates obtained from provinces in Indonesia.

Download Full-text

ANALISIS JARINGAN SYARAF TIRUAN METODE BACKPROPOGATION DALAM MEMPREDIKSI KETERSEDIAAN KOMODITAS BERAS BERDASARKAN PROVINSI DI INDONESIA

Jurnal RESISTOR (Rekayasa Sistem Komputer) ◽

10.31598/jurnalresistor.v2i1.348 ◽

2019 ◽

Vol 2 (1) ◽

pp. 48-60

Author(s):

Abdullah Ahmad ◽

Pipit Mutiara Putri ◽

Winanda Alifah ◽

Indra Gunawan ◽

Solikhun .

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Food Security ◽

Accuracy Rate ◽

National Statistics ◽

Architectural Model ◽

Human Need ◽

Backpropagation Method ◽

Input Variables ◽

The Government

Download Full-text

ALGORITMA BACKPROPAGATION DALAM MEMPREDIKSI JUMLAH KENDARAAN BERMOTOR YANG MEMBAYAR PAJAK MENURUT JENIS KENDARAAN DI KABUPATEN BATUBARA

Jurnal RESISTOR (Rekayasa Sistem Komputer) ◽

10.31598/jurnalresistor.v2i1.357 ◽

2019 ◽

Vol 2 (1) ◽

pp. 24-33

Author(s):

Enjelica Rumapea ◽

Bintang Bestari ◽

Joose Andar Laidin Manurung ◽

Handrizal Handrizal ◽

Solikhun Solikhun

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Social Problems ◽

Motor Vehicle ◽

The State ◽

Architectural Model ◽

Backpropagation Method ◽

Artificial Neural ◽

Input Variables ◽

Motorized Vehicles

Tax is a source of funds for the state to overcome various problems such as social problems, improving welfare, prosperity of its people. In the Batubara district itself, the number of receipts of Motor Vehicle Taxes and the development of the number of motorized vehicles have increased but not offset by awareness of taxpayers, this is reflected in the amount of arrears and considerable fines at the Coal Samsat Office. Looking at these problems, a method that is effective in estimating the number of vehicles paying taxes in the Batubara district is needed. The data used is data from the Regency Statistics Agency. Coal through the website www.batubarakab.bps.go.id. The data is the number of motorized vehicles that pay taxes in the Coal district in the period of 2012 to 2017. The algorithm used in this study is Artificial Neural Networks with the Backpropagation method. Input variables used are 2012 data (X1), 2013 data (X2), 2014 data (X3), 2015 data (X4), 2016 data (X5) and 2017 data as targets with models training and testing architecture of 4 architectures namely 4-4-1, 4-8-1, 4-16-1, 4-32-1. The resulting output is the best pattern of ANN architecture. The best architectural model is 4-8-1 with epoch 3681, MSE 0.009744 and 100% accuracy. So that the prediction of the number of motorized vehicles that pay taxes is obtained in Batubara district.

Download Full-text

MODEL JARINGAN SYARAF TIRUAN MEMPREDIKSI PRODUKSI EKSPOR BATU BARA MENURUT NEGARA TUJUAN UTAMA DALAM MENDORONG LAJU PERTUMBUHAN EKONOMI

KLIK - KUMPULAN JURNAL ILMU KOMPUTER ◽

10.20527/klik.v6i2.227 ◽

2019 ◽

Vol 6 (2) ◽

pp. 184

Author(s):

Rafiqa Dewi ◽

Sundari Retno Andani ◽

Solikhun Solikhun

Keyword(s):

Economic Growth ◽

Neural Networks ◽

Artificial Neural Networks ◽

Fossil Fuels ◽

Agricultural Sector ◽

General Definition ◽

Architectural Models ◽

Artificial Neural ◽

Input Variables ◽

The Government

Prediction is a process for estimating how many needs in the future. This study aims to predict the amount of coal exports according to the country the main goal in driving the pace of economic growth. The role of the agricultural sector in the national economy is very important and strategic. Coal is one of the fossil fuels. The general definition is a sedimentary rock that can burn, formed from organic deposits, mainly the remains of plants and formed through the process of pembatubaraan. The main elements consist of carbon, hydrogen and oxygen. Domestic production makes the government continue to implement coal export policies according to the state's main goal in driving the pace of economic growth in Indonesia. By using Artificial Neural Networks and backpropagation algorithms, architectural models will be sought to predict the amount of coal exports according to the state's main goal in driving the pace of economic growth to determine steps to assist the government in exporting coal based on the main destination country. This study uses 12 input variables with 1 target. Using 4 architectural models to test the data to be used for prediction, namely models 12-8-1, 12-16-1, 12-32-1 and 12-64-1. The best architectural model results obtained are 12-16-1 architectural models with 100% truth accuracy, the number of epoch 2602 and MSE is 0.0032. By using this model, predictions of coal exports are in accordance with the main destination countries with 100% accuracy.Keywords: Coal, Exports, predictions, backpropagation, Artificial Neural Networks Prediksi adalah proses untuk memperkirakan berapa banyak kebutuhan di masa depan. Studi ini bertujuan untuk memprediksi jumlah ekspor batubara menurut negara tujuan utama dalam mendorong laju pertumbuhan ekonomi. Peran sektor pertanian dalam ekonomi nasional sangat penting dan strategis. Batubara adalah salah satu bahan bakar fosil. Definisi umum adalah batuan sedimen yang dapat terbakar, terbentuk dari endapan organik, terutama sisa-sisa tanaman dan terbentuk melalui proses pembatubaraan. Unsur utama terdiri dari karbon, hidrogen, dan oksigen. Produksi dalam negeri membuat pemerintah terus menerapkan kebijakan ekspor batubara sesuai dengan tujuan utama negara dalam mendorong laju pertumbuhan ekonomi di Indonesia. Dengan menggunakan Jaringan Saraf Tiruan dan algoritma backpropagation, model arsitektur akan dicari untuk memprediksi jumlah ekspor batubara sesuai dengan tujuan utama negara dalam mendorong laju pertumbuhan ekonomi untuk menentukan langkah-langkah untuk membantu pemerintah dalam mengekspor batubara berdasarkan negara tujuan utama . Penelitian ini menggunakan 12 variabel input dengan 1 target. Menggunakan 4 model arsitektur untuk menguji data yang akan digunakan untuk prediksi, yaitu model 12-8-1, 12-16-1, 12-32-1 dan 12-64-1. Hasil model arsitektur terbaik yang diperoleh adalah model arsitektur 12-16-1 dengan akurasi 100%, jumlah zaman 2602 dan MSE adalah 0,0032. Dengan menggunakan model ini, prediksi ekspor batubara sesuai dengan negara tujuan utama dengan akurasi 100%.Kata kunci: Batubara, Ekspor, prediksi, backpropagation, Jaringan Syaraf Tiruan

Download Full-text

JARINGAN SARAF TIRUAN DALAM MEMPREDIKSI SUKUK NEGARA RITEL BERDASARKAN KELOMPOK PROFESI DENGAN BACKPROPOGATION DALAM MENDORONG LAJU PERTUMBUHAN EKONOMI

KLIK - KUMPULAN JURNAL ILMU KOMPUTER ◽

10.20527/klik.v4i2.90 ◽

2017 ◽

Vol 4 (2) ◽

pp. 184

Author(s):

Agus Perdana Windarto ◽

Solikhun Solikhun ◽

Handrizal Handrizal ◽

M Fauzan

Keyword(s):

Neural Network ◽

Sensitivity Analysis ◽

Accuracy Rate ◽

Financial Products ◽

Community Benefits ◽

Architectural Model ◽

Ministry Of Finance ◽

Input Variables ◽

The Government ◽

Age Category

State Retail Sukuk is a Sharia Securities issued and its sale is regulated by the State, namely the Ministry of Finance (Depkeu). Where the government will choose the seller agent and consulting retail sukuk law. Selling agents must be obliged to have a commitment to the government in the development of the sukuk market and experience in selling Islamic financial products. The publication of this instrument is likened to a "mutualist symbiosis" between the Government and Society, both of which benefit equally. The government as the publisher benefits from the use of funds from the community, while the community benefits from investments made. This research contributes to the government and the Bank to be able to promote maximally for the next sukuk issuer. The data used is data from kemenkeu through website www.djppr.kemenkeu.go.id. The data are sukuk sales data with series 001 - 007 which are grouped into several categories namely geography, profession and age category. Algorithm used in this research is Artificial Neural Network with Backpropogation method. The input variables used are PNS (X1), Private Officer (X2), IRT (X3), Entrepreneur (X4), TNI / Polri (X5) and Others (X6) with architectural model of training and testing of 6 architectures 6-2-1, 6-5-1, 6-2-5-1 and 6-5-2-1. The output (output) generated is the best pattern of the ANN architecture. The best architectural model is 6-5-2-1 with epoch 37535, MSE 0.0009997295 and 100% accuracy rate. From this model will be conducted sensitivity analysis to see the variable that has the best performance and obtained variable Private Employees (X2) with a score of 0.3268. So obtained the results of the most investors predicted on the purchase of sukuk for the next 008 series based on the profession category is Private Employees. Keywords: Sukuk, JST, Backpropogation, Sensitivity Analysis and PredictionSukuk Ritel Negara adalah Surat berharga Syariah yang diterbitkan dan penjualannya diatur oleh Negara, yaitu Departemen Keuangan (depkeu). Dimana pemerintah akan memilih agen penjual dan konsultasi hukum sukuk ritel. Agen penjual haruslah wajib memiliki komitmen terhadap pemerintah dalam pengembangan pasar sukuk dan berpengalaman dalam menjual produk keuangan syariah. Penerbitan instrumen ini diibaratkan sebuah “simbiosis mutualis” antara Pemerintah dan Masyarakat, dimana keduanya sama-sama memperoleh keuntungan. Pemerintah selaku penerbit memperoleh keuntungan berupa penggunaan dana dari masyarakat, sedangkan masyarakat memperoleh keuntungan dari investasi yang dilakukan. Penelitian ini memberikan kontribusi bagi pemerintah dan Bank untuk dapat melakukan promosi secara maksimal untuk penerbitat sukuk berikutnya. Data yang digunakan adalah data dari kemenkeu melalui website www.djppr.kemenkeu.go.id. Data tersebut adalah data penjualan sukuk dengan seri 001 – 007 yang dikelompokkan dalam beberapa kategori yakni geografis, profesi dan kategori umur. Algoritma yang digunakan pada penelitian ini adalah Jaringan Saraf Tiruan dengan metode Backpropogation. Variabel masukan (input) yang digunakan adalah PNS (X1), Pegawai Swasta (X2), IRT (X3), Wiraswasta (X4), TNI/Polri (X5) dan Lainnya (X6) dengan model arsitektur pelatihan dan pengujian sebanyak 6 arsitektur yakni 6-2-1, 6-5-1, 6-2-5-1 dan 6-5-2-1. Keluaran (output) yang dihasilkan adalah pola terbaik dari arsitektur JST. Model arsitektur terbaik adalah 6-5-2-1 dengan epoch 37535, MSE 0,0009997295 dan tingkat akurasi 100%. Dari model ini akan dilakukan analisis sensivitas untuk melihat variabel yang memiliki performa terbaik dan diperoleh variabel Pegawai Swasta (X2) dengan skor 0,3268. Sehingga didapat hasil prediksi investor terbanyak pada pembelian sukuk untuk seri 008 berikutnya berdasarkan kategori profesi adalah Pegawai Swasta.Kata Kunci: Sukuk, JST, Backpropogation, Analisis Sensivitas dan Prediksi

Download Full-text

Analisis dalam Melihat Perkembangan Indeks Harga Perdagangan Besar Menurut Sektor di Indonesia Menggunakan Algoritma Backpropagation

Prosiding Seminar Nasional Riset Information Science (SENARIS) ◽

10.30645/senaris.v1i0.41 ◽

2019 ◽

Vol 1 ◽

pp. 359

Author(s):

Zulfikar Zulfikar ◽

Anjar Wanto ◽

Zulaini Masruro Nasution

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Secondary Data ◽

Training Data ◽

Accuracy Rate ◽

Price Indexes ◽

Testing Data ◽

Backpropagation Method ◽

Architectural Models ◽

Artificial Neural

The Large Trade Price Index (IHPB) is one of the economic indicators that contains index numbers and shows changes in the price of goods purchased by traders from consumers. This study uses Artificial Neural Networks (ANN) with the Backpropagation method. Artificial neural networks are branches of artificial intelligence that mimic or imitate the workings of the human brain. The data of this study are secondary data sourced from the Central Statistics Agency (BPS) from 2000 to 2017. The data is divided into 2 parts, namely training data and testing data. There are 5 architectural models used in this study. 8-15-1, 8-25-1, 8-26-1, 8-30-1 and 8-40-1. From the 5 architectural models used 1 best model was obtained, namely 8-25-1 with an accuracy rate of 85%, MSE 0.00100074 and 10000 iterations. So this model is good for predicting large trade price indexes according to sectors in Indonesia in the future.

Download Full-text

Jaringan Syaraf Tiruan dalam Memprediksi Jumlah Pelanggan PT.Telkom Akses Area Sumbagut Menggunakan Metode Backpropagation

Prosiding Seminar Nasional Riset Information Science (SENARIS) ◽

10.30645/senaris.v1i0.87 ◽

2019 ◽

Vol 1 ◽

pp. 804

Author(s):

Reza Muhammad Riansah ◽

Rahmat W. Sembiring ◽

Zulaini Masruro

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Service Company ◽

Architectural Model ◽

Backpropagation Method ◽

Artificial Neural ◽

Number Of Customers

The number of customers of a service company greatly affects the development and progress of the company. Likewise with the number of customers of PT. Telkom Access (PTTA) Sumbagut Area which has an increase in the number of customers every year. In this study, the author will make predictions aimed at knowing the number of customers at PT. Telkom Access (PTTA) Sumbagut Area using the backpropagation method. Backpropagation is one method of artificial neural networks that mimics the workings of human nerves. Research uses data obtained from the database of PT. Telkom Access Pematangsiantar. This study produced the best architectural model, namely 3-14-1 which will be used to predict the number of customers of PT. Telkom Access (PTTA) Sumbagut Area with 85% accuracy.

Download Full-text

Prediction Modeling of PM-10 in Chiangmai City Moat by Using Artificial Neural Networks

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.781.628 ◽

2015 ◽

Vol 781 ◽

pp. 628-631 ◽

Cited By ~ 1

Author(s):

Rati Wongsathan ◽

Issaravuth Seedadan ◽

Metawat Kavilkrue

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Prediction Model ◽

Chiang Mai ◽

Adverse Health Effects ◽

High Pollution ◽

Artificial Neural ◽

Input Variables ◽

Pm 10 ◽

Respiratory Conditions

A mathematical prediction model has been developed in order to detect particles with a diameter of 10 micrometers or less (PM-10) that are responsible for adverse health effects because of their ability to cause serious respiratory conditions in areas of high pollution such as Chiang Mai City moat area. The prediction model is based on 3 types of Artificial Neural Networks (ANNs), including Multi-layer perceptron (MLP-NN), Radial basis function (RBF-NN), and hybrid of RBF and Genetic algorithm (RBF-NN-GA). The model uses 8 input variables to predict PM-10, consisting of 4 air pollution substances ( CO, O3, NO2 and SO2) and 4 meteorological variables related PM-10 (wind speed, temperature, atmospheric pressure and relative humidity). These 3 types of ANN have proved efficient instrument in predicting the PM-10. However, the performance of RBF-NN was superior in comparison with MLP-NN and RBF-NN-GA respectively.

Download Full-text

Modelling and Prediction of Monthly Global Irradiation Using Different Prediction Models

Energies ◽

10.3390/en14082332 ◽

2021 ◽

Vol 14 (8) ◽

pp. 2332

Author(s):

Cecilia Martinez-Castillo ◽

Gonzalo Astray ◽

Juan Carlos Mejuto

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Random Forests ◽

Prediction Models ◽

Meteorological Station ◽

Ann Model ◽

Global Irradiation ◽

Artificial Neural ◽

Input Variables ◽

Using Data

Different prediction models (multiple linear regression, vector support machines, artificial neural networks and random forests) are applied to model the monthly global irradiation (MGI) from different input variables (latitude, longitude and altitude of meteorological station, month, average temperatures, among others) of different areas of Galicia (Spain). The models were trained, validated and queried using data from three stations, and each best model was checked in two independent stations. The results obtained confirmed that the best methodology is the ANN model which presents the lowest RMSE value in the validation and querying phases 1226 kJ/(m2∙day) and 1136 kJ/(m2∙day), respectively, and predict conveniently for independent stations, 2013 kJ/(m2∙day) and 2094 kJ/(m2∙day), respectively. Given the good results obtained, it is convenient to continue with the design of artificial neural networks applied to the analysis of monthly global irradiation.

Download Full-text

Generalization of Patterns by Identification with Polynomial Neural Network

Journal of Electrical Engineering ◽

10.2478/v10187-010-0017-4 ◽

2010 ◽

Vol 61 (2) ◽

pp. 120-124 ◽

Cited By ~ 3

Author(s):

Ladislav Zjavka

Keyword(s):

Neural Network ◽

Neural Networks ◽

Artificial Neural Networks ◽

Functional Dependence ◽

Polynomial Neural Network ◽

New Type ◽

Input Variables ◽

The Brain ◽

Functional Output ◽

Simplified Form

Generalization of Patterns by Identification with Polynomial Neural Network Artificial neural networks (ANN) in general classify patterns according to their relationship, they are responding to related patterns with a similar output. Polynomial neural networks (PNN) are capable of organizing themselves in response to some features (relations) of the data. Polynomial neural network for dependence of variables identification (D-PNN) describes a functional dependence of input variables (not entire patterns). It approximates a hyper-surface of this function with multi-parametric particular polynomials forming its functional output as a generalization of input patterns. This new type of neural network is based on GMDH polynomial neural network and was designed by author. D-PNN operates in a way closer to the brain learning as the ANN does. The ANN is in principle a simplified form of the PNN, where the combinations of input variables are missing.

Download Full-text

Artificial Neural Networks, Sequence-to-Sequence LSTMs, and Exogenous Variables as Analytical Tools for NO2 (Air Pollution) Forecasting: A Case Study in the Bay of Algeciras (Spain)

Sensors ◽

10.3390/s21051770 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1770

Author(s):

Javier González-Enrique ◽

Juan Jesús Ruiz-Aguilar ◽

José Antonio Moscoso-López ◽

Daniel Urda ◽

Lipika Deka ◽

...

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Short Term Memory ◽

Prediction Method ◽

Monitoring Network ◽

Exogenous Variables ◽

Prediction Horizon ◽

Artificial Neural ◽

Input Variables ◽

Analytical Tools

This study aims to produce accurate predictions of the NO2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the forecasting models. Additionally, a new prediction method was proposed combining LSTMs using a rolling window scheme with a cross-validation procedure for time series (LSTM-CVT). Two different strategies were followed regarding the input variables: using NO2 from the station or employing NO2 and other pollutants data from any station of the network plus meteorological variables. The ANN and LSTM-CVT exogenous models used lagged datasets of different window sizes. Several feature ranking methods were used to select the top lagged variables and include them in the final exogenous datasets. Prediction horizons of t + 1, t + 4 and t + 8 were employed. The exogenous variables inclusion enhanced the model’s performance, especially for t + 4 (ρ ≈ 0.68 to ρ ≈ 0.74) and t + 8 (ρ ≈ 0.59 to ρ ≈ 0.66). The proposed LSTM-CVT method delivered promising results as the best performing models per prediction horizon employed this new methodology. Additionally, per each parameter combination, it obtained lower error values than ANNs in 85% of the cases.

Download Full-text