Claim Missing Document
Check
Articles

Found 8 Documents
Search

Analysis of Weight Product (WP) Algorithms in the best Go Car Driver Recommendations at PT. Maranatha Putri Bersaudara Roni Kurniawan; Agus Perdana Windarto; M Fauzan; Solikhun Solikhun; Irfan Sudahri Damanik
IJISTECH (International Journal of Information System and Technology) Vol 3, No 1 (2019): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v3i1.28

Abstract

This study aims to rank the best Go Car Driver. The problem arises because of the inaccuracy in giving value to the driver which results in the decision being given incorrectly so that the assessment tends to be subjective. This research was conducted at PT. Maranatha Putri Bersaudara. Sources of data obtained by observing, interviewing. The settlement method used is a decision support system with the Weight Producted method. The assessment criteria used are Performance (C1), Number of orders (C2), Rating (C3), Attitude (C4), Rating (C5) and Appearance (C6) where the alternatives used are 4 samples. The results obtained using the Weighted Product method are Alternative1 and Alternative4 which are recommended as the best go car driver with the assessment results of 0.0307 and 0.0272. It is expected that research results can be input to the relevant parties in recommending the best go car driver so as to minimize subjective judgment.
Improving Adaptive Learning Rate With Backpropogation on Retail Rice Price Prediction in Traditional Markets Erwin Binsar Hamonangan Ompusunggu; Solikhun Solikhun; Iin Parlina; Sumarno Sumarno; Indra Gunawan
IJISTECH (International Journal of Information System and Technology) Vol 3, No 1 (2019): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v3i1.26

Abstract

Rice is the most important staple food and carbohydrate food in the world especially people in Indonesia. This study aims to predict the retail price of rice in traditional markets using backpropogation by improvising Adaptive Learning Rate to increase the value of accuracy. Data sources were obtained from the Central Statistics Agency (BPS) in 33 provinces in Indonesia for the retail price of rice in the traditional market (Rupiah / kg) for the past 6 years (2011-2016). The results of the study state that the improvised learning rate uses 2 models: 2-10-1 and 2-15-1 (LR= 0,1; 0,5; 0,9) that the best architectural models are 4-15-1 (LR= 0.9) with an accuracy of 82%, Training MSE 0,000999936, Testing MSE 0.016051433 and Epoch 20515. The results of this study are expected to provide input to the government in providing input on predictions of retail rice prices that have an impact on the stability of rice prices in Indonesia.
MODEL JARINGAN SYARAF TIRUAN DALAM MEMPREDIKSI PENDAPATAN PERKAPITA MASYARAKAT PERKOTAAN PADA GARIS KEMISKINAN BERDASARKAN PROPINSI Solikhun Solikhun; Ahmad Revi; Syahrul Ramadan; Rina Novita Sari
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 5, No 2 (2018)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v5i2.136

Abstract

The problem of poverty is one of the fundamental issues that becomes the center of attention of the Government in any country. In an effort to realize the provisions as stipulated in Article 28A of the 1945 Constitution of the State of the Republic of Indonesia which affirms that every person has the right to live and has the right to maintain his life and life, the GOI has established a poverty reduction program as a priority program. The primary target of poverty is mostly in urban areas, because the large number of residents who do transmigration to improve the economy but failed to get results. This study contributes to the government to predict the per capita opinion of urban communities according to the poverty line based on the province in the future. The data used is data from the National Statistics Agency through the website www.bps.go.id. The data is data on per capita income of urban communities on poverty line by province in 2013 semester 2 until 2016 semester 2. Algorithm used in this research is Artificial Neural Network with Backpropogation method. The input variables are data of year 2014 semester (X1), data of 2014 semester 1 (X2), data of 2014 semester 2 (X3), data of 2015 semester 1 (X4), data of 2015 semester 2 ( X5) and data of 2016 semester 1 (X6) with architectural model of training and testing as much as 4 architecture that is 6-2-1, 6-6-1, 6-3-2-1 and 6-2-3-1. The output generated is the best pattern of the ANN architecture. The best architectural model is 6-3-2-1 with epoch 1190, MSE 0,0102524619 and 100% accuracy rate. From this model, the prediction of per capita income of urban community on the poverty line is based on the provinces of each province in Indonesia.Keywords: Income Per Capita, ANN, Backpropogation and PredictionMasalah kemiskinan merupakan salah satu persoalan mendasar yang menjadi pusat perhatian Pemerintah di negara manapun. Dalam Upaya mewujudkan ketentuan sebagaimana ditetapkan Pasal 28A Undang-Undang Dasar Negara Republik Indonesia Tahun 1945 yang menegaskan bahwa setiap orang berhak untuk hidup serta berhak mempertahankan hidup dan kehidupannya, maka Pemerintah Indonesia telah menetapkan program penanggulangan kemiskinan sebagai program prioritas. Sasaran primer kemiskinan mayoritas lebih banyak terdapat di perkotaan, sebab banyaknya para penduduk yang melakukan transmigrasi guna memperbaiki perekonomian namun malah gagal mendapatkan hasil. Penelitian ini memberikan kontribusi bagi pemerintah untuk dapat memprediksi pendapat perkapita masyarakat perkotaan menurut garis kemiskinan berdasarkan propinsi ke depan. Data yang digunakan adalah data dari Badan Statistik Nasional melalui website www.bps.go.id. Data tersebut adalah data pendapatan perkapita masyarakat perkotaan pada garis kemiskinan berdasarkan propinsi tahun 2013 semster 2 sampai dengan tahun 2016 semester 2. Algoritma yang digunakan pada penelitian ini adalah Jaringan Saraf Tiruan dengan metode Backpropogation. Variabel masukan (input) yang digunakan adalah data tahun 2013 semester 2(X1), data tahun 2014 semester 1(X2), data tahun 2014 semester 2(X3), data tahun 2015 semester 1(X4), data tahun 2015 semester 2(X5) dan data tahun 2016 semester 1(X6) dengan model arsitektur pelatihan dan pengujian sebanyak 4 arsitektur yakni 6-2-1, 6-6-1, 6-3-2-1 dan 6-2-3-1. Data target diambil dari data tahun 2016 semster 2. Keluaran yang dihasilkan adalah pola terbaik dari arsitektur JST. Model arsitektur terbaik adalah 6-3-2-1 dengan epoch 1190, MSE 0,0102524619 dan tingkat akurasi 100%. Dari model ini maka dihasilkan prediksi pendapatan perkapita masyarakat perkotaan pada garis kemisikinan berdasarkan propinsi dari masing-masing propinsi di Indonesia.Kata Kunci: Pendapata Perkapita, JST, Backpropogation dan Prediksi
Implementasi Jaringan Syaraf Tiruan Resilient Backpropagation dalam Memprediksi Angka Harapan Hidup Masyarakat Sumatera Utara Samuel Palentino Sinaga; Anjar Wanto; Solikhun Solikhun
Jurnal Infomedia:Teknik Informatika, Multimedia & Jaringan Vol 4, No 2 (2019): Jurnal Infomedia
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (361.331 KB) | DOI: 10.30811/jim.v4i2.1573

Abstract

Angka Harapan Hidup merupakan indikator dan alat untuk mengevaluasi kinerja pemerintah dalam meningkatkan kesejahteraan penduduk pada umumnya, dan meningkatkan derajat kesehatan pada khususnya. Adapun penulisan ini dilakukan untuk mengimplementasikan dan membuktikan bahwa Algoritma Resilient Backpropagation dapat digunakan untuk memprediksi angka harapan hidup masyarakat di Sumatera Utara. Data penelitian adalah data angka harapan hidup di Sumatera Utara yang terdiri dari 33 kabupaten/Kota, yang diperoleh dari Badan Pusat Statistik Sumatera Utara dari tahun 2013 sampai tahun 2017.  Penelitian ini menggunakan 5 model arsitektur yaitu 4-10-1, 4-11-1, 4-12-1, 4-13-1 dan 4-14-1. Dari kelima model arsitektur yang digunakan di peroleh satu model arsitektur terbaik 4-10-1 dengan tingkat keakurasian 88 %, epoch 22 iterasi dalam waktu 4 detik dan MSE 0,00100006. Berdasarkan model arsitektur terbaik ini akan digunakan untuk memprediksi angka harapan hidup masyarakat Sumatera Utara untuk 5 tahun yang akan datang, yakni tahun 2018 hingga tahun 2022
MODEL JARINGAN SYARAF TIRUAN MEMPREDIKSI EKSPOR MINYAK SAWIT MENURUT NEGARA TUJUAN UTAMA Saifullah Saifullah; Nani Hidayati; Solikhun Solikhun
Jurnal Teknovasi : Jurnal Teknik dan Inovasi Vol 6, No 2 (2019): TEKNOVASI OKTOBER 2019
Publisher : LPPM Politeknik LP3I Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55445/teknovasi.v6i2.306

Abstract

This study aims to find the best architectural model in predicting palm oil exports according to the main destination countries. The role of the agricultural sector in the national economy is very important and strategic. Oil Palm is an industrial plant producing cooking oil, industrial oil, and bio-diesel fuel. Indonesia is the largest producer and exporter of palm oil in the world. In addition to the increasingly open export opportunities, the domestic market for palm oil and palm kernel oil is still quite large. Prediction is a process for estimating how many needs in the future. State revenues in the export sector must be able to be predicted to help set the state's financial regulations specifically on palm oil exports. By using Artificial Neural Networks and backpropagation algorithms, architectural models will be sought to predict the amount of palm oil exports according to the main destination country. This study uses 12 input variables, and 1 hidden layer. Using 4 architectural models to test the data to be used for prediction, namely models 12-4-1, 12-8-1, 12-16-1 and 12-32-1. The results of the best architectural model are architectural models 12-16-1 with 100% accuracy accuracy.
Analisis Sistem Pendukung Keputusan Penyeleksian Siswa Calon Peserta Olimpiade Dengan Metode MOORA Sri Wardani; Solikhun Solikhun; Ahmad Revi
Jurnal Teknovasi : Jurnal Teknik dan Inovasi Vol 5, No 1 (2018): Teknovasi April 2018
Publisher : LPPM Politeknik LP3I Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55445/teknovasi.v5i1.203

Abstract

Olimpiade Sains Nasional adalah ajang berkompetisi dalam bidang sains bagi para siswa pada jenjang SD, SMP, dan SMA di Indonesia. Siswa yang mengikuti Olimpiade Sains Nasional adalah siswa yang telah lolos seleksi tingkat kabupaten dan provinsi dan adalah siswa-siswa terbaik dari provinsinya masing-masing. SMA Negeri 2 Bandar merupakan salah satu sekolah Negeri yang selalu mengirim siswanya untuk mengikuti olimpiade pada tingkat kabupaten, adapun permasalahan yang muncul dalam pemilihan siswa peserta olimpiade di SMA Negeri 2 Bandar ini dimana guru atau kepala sekolah dalam memilih siswa hanya berdasarkan nilai pelajaran yang di peroleh, Karena permasalahan tersebut maka perlu dirancang suatu sistem pendukung keputusan yang dapat membantu mengambil suatu keputusan dalam mendapatkan informasi untuk menentukan siswa yang tepat dalam mengikuti olimpiade sains baik pada tingkat kabupaten propinsi maupun nasional. Berdasarkan perhitungan menggunakan metode MOORA terhadap 6 alternatif, didapatkan A6 sebagai peringkat pertama kemudian diikuti oleh A2 dan A3.
Improving Adaptive Learning Rate With Backpropogation on Retail Rice Price Prediction in Traditional Markets Erwin Binsar Hamonangan Ompusunggu; Solikhun Solikhun; Iin Parlina; Sumarno Sumarno; Indra Gunawan
IJISTECH (International Journal of Information System and Technology) Vol 3, No 1 (2019): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (463.23 KB) | DOI: 10.30645/ijistech.v3i1.26

Abstract

Rice is the most important staple food and carbohydrate food in the world especially people in Indonesia. This study aims to predict the retail price of rice in traditional markets using backpropogation by improvising Adaptive Learning Rate to increase the value of accuracy. Data sources were obtained from the Central Statistics Agency (BPS) in 33 provinces in Indonesia for the retail price of rice in the traditional market (Rupiah / kg) for the past 6 years (2011-2016). The results of the study state that the improvised learning rate uses 2 models: 2-10-1 and 2-15-1 (LR= 0,1; 0,5; 0,9) that the best architectural models are 4-15-1 (LR= 0.9) with an accuracy of 82%, Training MSE 0,000999936, Testing MSE 0.016051433 and Epoch 20515. The results of this study are expected to provide input to the government in providing input on predictions of retail rice prices that have an impact on the stability of rice prices in Indonesia.
Analysis of Weight Product (WP) Algorithms in the best Go Car Driver Recommendations at PT. Maranatha Putri Bersaudara Roni Kurniawan; Agus Perdana Windarto; M Fauzan; Solikhun Solikhun; Irfan Sudahri Damanik
IJISTECH (International Journal of Information System and Technology) Vol 3, No 1 (2019): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (285.5 KB) | DOI: 10.30645/ijistech.v3i1.28

Abstract

This study aims to rank the best Go Car Driver. The problem arises because of the inaccuracy in giving value to the driver which results in the decision being given incorrectly so that the assessment tends to be subjective. This research was conducted at PT. Maranatha Putri Bersaudara. Sources of data obtained by observing, interviewing. The settlement method used is a decision support system with the Weight Producted method. The assessment criteria used are Performance (C1), Number of orders (C2), Rating (C3), Attitude (C4), Rating (C5) and Appearance (C6) where the alternatives used are 4 samples. The results obtained using the Weighted Product method are Alternative1 and Alternative4 which are recommended as the best go car driver with the assessment results of 0.0307 and 0.0272. It is expected that research results can be input to the relevant parties in recommending the best go car driver so as to minimize subjective judgment.