Neural Network Analysis With Backpropogation In Predicting Human Development Index (HDI) Component by Regency/City In North Sumatera

Siregar, Muhammad Noor Hasan

doi:10.30645/ijistech.v1i1.3

Cited by 5 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pada penelitian kali ini, obyek permasalahan yang digunakan adalah Exclusi Or, dimana nilai On "1" dan Off "0" diset atau dinormalisasi mengikuti pada persamaan (12), (Siregar, 2017). ( 12)…”

Section: Pengolahan Data Inputunclassified

Meningkatkan Kinerja Backpropagation Neural Network Menggunakan Algoritma Adaptif

Bohari¹

2022

imtech

View full text Add to dashboard Cite

The application of Artificial Neural Networks in various fields of human life is getting wider, especially in the industrial sector. One of the artificial neural network structures that are quite often used is the Feedforward Neural Network with its well-known learning algorithm, namely Backpropagation. However, as reported by several researchers, Backpropagation has several weaknesses such as it takes a long time to converge in the training process, it is quite sensitive to initial weight conditions and is relatively often trapped in a local minima which can thwart the training process. In this study, the Adaptive algorithm is proposed as an alternative to the Backpropagation learning algorithm. The proposed algorithm provides hope in overcoming the weaknesses faced by Bakpropagation. As reported in the test results, compared to Backpropagation, the Adaptive algorithm is much stronger in dealing with variations in the initial weight conditions. From 100 tests in this study for each Backpropagation and Adaptive algorithm, with random variations for the initial weight value, the success rate of the Adaptive algorithm training process reaches 100% compared to Backpropagation which is at the level of 77%. In terms of speed, the Adaptive algorithm has successfully carried out the training process with an average number of iterations of 37 times compared to Backpropagation which requires an average of 162 iterations.

show abstract

Section: Pengolahan Data Inputunclassified

Meningkatkan Kinerja Backpropagation Neural Network Menggunakan Algoritma Adaptif

Bohari¹

2022

imtech

View full text Add to dashboard Cite

show abstract

“…Dalam hal ini peneliti menggunakan teknik wawancara dan angket/kuisioner dalam melakukan penilaian terhadap toko terbaik di kota Pematangsiantar. [8], bidang jaringan saraf tiruan [9]- [11] [12], bidang sistem pendukung keputusan [13]- [17] [18]. Berdasarkan penjelasan tersebut, peneliti menggunakan sistem pendukung keputusan untuk dapat menyelesaikan masalah diatas [19], [20].…”

Section: Pendahuluanunclassified

Penerapan Sistem Pendukung Keputusan Dengan Metode Simple Multi Attribute Rating Technique Pada Pemilihan Toko Roti

et al. 2019

View full text Add to dashboard Cite

Bakery is a place frequented by people as a place to buy bread to be given as a gift or food. The number of bakeries that are open in Pematangsiantar city makes consumers confused and need accurate information to decide to visit a bakery that suits their needs. Moreover, every bakery provides and offers their best products to consumers. The method used in decision making is the SMART method (Simple Multi Attribute Rating Technique) because SMART is a method in making multi-attribute decisions. This system can provide recommendations for bakeries that are in accordance with the expectations of consumers to be considered in choosing the right bakery, especially in pematangsiantar city where there are 5 bakeries namely: Double (A1), Aroma (A2), Francebakery (A3), Valetine ( A4) and My darling (A5). In this study there are 5 criteria that support the research objectives, namely: service (C1), texture (C2), taste (C3), price (C4) and location (C5). The research data was obtained by interviewing and giving questionnaires / questionnaires to 250 consumers. The results of the questionnaire were processed and calculated using the SMART method. Based on the results of the study, it is obtained double (A1) first rank with the final value of 0.8835, francebakery (A3) second rank with the final value of 0.5530 and my dear (A5) ranked third with the final value of 0.45. It is hoped that this research can provide input to consumers in recommending and choosing the best bakery in Pematangsiantar.

show abstract

“…Hal ini terbukti dari penelitian terdahulu peneliti dalam menyelesaikan permasalahan bidang Datamining [4], [5], bidang Jaringan Saraf Tiruan (JST) [6]- [8] dan bidang Sistem Pendukung Keputusan [9]- [13]. Berdasarkan alasan tersebut, peneliti menggunakan jaringan saraf tiruan backpropagation [14] [15] dalam memprediksi indikator terpenting pada perusahaan listrik. Penelitian terdahulu terkait penyelesaian menggunakan prediksi JST backpropagation adalah [7].…”

Section: Pendahuluanunclassified

Penerapan Backpropagation dan Analisis Sensitivitas pada Prediksi Indikator Terpenting Perusahaan Listrik

Fachri¹,

Windarto²,

Parinduri³

2019

JEPIN

View full text Add to dashboard Cite

Listrik merupakan kebutuhan bagi kehidupan masyarakat yang sangat penting. Penelitian ini bertujuan untuk mengetahui indikator terpenting pada perusahaan listrik dengan menggunakan metode backpropagation dan analisis sensitivitas. Data bersumber dari Badan Pusat Statistik (BPS) dengan sampel data tahun 2001-2015. Variabel input terdiri dari 6 indikator terpenting perusahaan listrik antara lain: jumlah tenaga kerja (X1); daya terpasang (X2); produksi listrik (X3); tenaga listrik yang terjual (X4); biaya input (X5) dan biaya output (X6). Berdasarkan hasil pelatihan dan pengujian dari 5 model JST (6-10-1; 6-45-1; 6-45-10-1; 6-75-10-1 dan 6-100-75-1) diperoleh model JST terbaik adalah 6-100-75-1 dengan tingkat akurasi 83%. Hasil dari pemilihan model JST terbaik dianalisis dengan analisa sensitivitas, sehingga menghasilkan dua variabel yang paling berpengaruh pada indikator terpenting perusahaan listrik yakni: biaya output (X6) sebagai peringkat pertama dengan nilai error rata-rata 0,13670 dan daya terpasang (X2) nilai error rata-rata 0,08778.

show abstract

Neural Network Analysis With Backpropogation In Predicting Human Development Index (HDI) Component by Regency/City In North Sumatera

Abstract: Human Development Index (HDI)

Cited by 5 publications

References 17 publications

Meningkatkan Kinerja Backpropagation Neural Network Menggunakan Algoritma Adaptif

Meningkatkan Kinerja Backpropagation Neural Network Menggunakan Algoritma Adaptif

Penerapan Sistem Pendukung Keputusan Dengan Metode Simple Multi Attribute Rating Technique Pada Pemilihan Toko Roti

Penerapan Backpropagation dan Analisis Sensitivitas pada Prediksi Indikator Terpenting Perusahaan Listrik

Contact Info

Product

Resources

About