Pemilihan Model Arsitektur Terbaik Dengan Mengoptimasi Learning Rate Pada Neural Network Backpropagation

Astria, Cici; Windarto, Agus Perdana; Damanik, Irfan Sudahri

doi:10.30865/jurikom.v9i1.3834

“…Based on the four indices, the class is determined in the classification results as shown in Table 2. Architectural optimization is carried out on the architectural model to obtain the model with the most efficient time and the best accuracy (Astria et al, 2022).…”

Section: Results and Discussion Land Parameters For Urban Environment...mentioning

confidence: 99%

“…Optimization of the artificial neural network architecture, one of which has been developed with a neural architecture optimization (NAO) design automation algorithm (Luo, Tian, Qin, Chen, & Liu, 2018). Determination of the best neural network architecture model also needs to be done by optimizing the learning rate and momentum rate on the neural network with the backpropagation learning system (Astria, Windarto, & Damanik, 2022;Kushardono, 2017).…”

Section: Introductionmentioning

confidence: 99%

Optimized Artificial Neural Network for the Classification of Urban Environment Comfort using Landsat-8 Remote Sensing Data in Greater Jakarta Area, Indonesia

Sari

¹

,

Kushardono

²

,

Mukhoriyah

³

et al. 2023

JAETS

2

0

View full text Add to dashboard Cite

The development of computer vision technology as a type of artificial intelligence is increasing rapidly in various fields. This method uses deep learning methods based on artificial neural networks, a well-performed algorithm in multi-parameter analysis. One of the development of computer vision models and algorithms is for a thematic digital image classification, such as environmental analysis. Remote sensing based digital image classification is one of the reliable tools for environmental quality analysis. This study aims to perform neural network optimization for the analysis of the urban environment comfort based on satellite data. The input data used are 4 types of geobiophysical indexes as urban environmental comfort parameters derived from cloud-free annual mosaics Landsat-8 remote sensing satellite data. The results obtained in this study indicate that the 1 hidden layer neural network architecture with 16 neurons for the classification of urban environmental comfort and 10 other land cover classes is quite good. The result of the classification using this optimized artificial neural network shows that the distribution of classes is very uncomfortable which dominates the Greater Jakarta area and its surroundings. For other classes in the study area, some are uncomfortable and rather comfortable. By using this method, we obtained a fast classification training time of 18 seconds for 145 iterations to achieve an RMS Error of 0.01, and has a fairly high classification accuracy overall 89% with a Kappa coefficient of 0.88, while the 2 hidden layer neural network architecture does not succeed in achieving convergence

show abstract

“…Neural Network ditentukan oleh tiga factor yaitu arsitektur jaringan, algoritma pembelajaran, dan fungsi aktivasi pernyataan tersebut diungkapkan oleh Fauset pada tahun 1994 [18]. Sebagai sekelompok elemen pemrosesan dalam kelompok tertentu, jaringan melakukan perhitungannya sendiri dan meneruskan hasilnya ke kelompok berikutnya [19]. Data non-numerik harus diubah menjadi data numerik dikarenakan algoritma JST bekerja langsung dengan angka [20].…”

Section: Jaringan Saraf Tiruan (Jst)unclassified

Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing Di Indonesia

Rika Setiana,

Siregar,

Fahry Husaini

et al. 2023

comforch

0

View full text Add to dashboard Cite

A science that has always developed rapidly until now is artificial neural networks. A computational science that works like the human nervous system is an artificial neural network. Artificial neural networks with the backpropagation method can make a prediction on data. In this article, a prediction will be made on the amount of goat production in Indonesia. Goats are one of the livestock that can produce nutritious meat. The lack of goat meat will cause the price of goat meat to rise. Producing enough goat meat helps stabilize the price of meat, but if goat meat production is less than demand, it will lead to price increases. Therefore, looking at the problems above, this study aims to predict goat meat so that in the future it can know how much goat meat must be predicted by processing data first and then being used as input in predicting the amount of goat meat production. Prediction is one way to estimate future demand. Avoiding the lack of meat availability, by predicting the amount of goat meat produced in such a way that there is no scarcity of goat meat and fluctuations in the price of goat meat in the market. Basic methods and data are required to make predictions. In this study, data was obtained from BPS Indonesia in the livestock section using data from 2001-2021 as training data and 2002-2022 as test data. The method applied in this article is the backpropagation algorithm. This article applies 5 network architectures implemented in the mathlab application. The architecture used in this article is 20-25-1 with a Mean Squred Error testing 0.00447765, in 20-30-1 architecture produces Mean Squred Error 0.00300466, in 20-35-1 architecture produces 0.00426823, in 20-37-1 architecture produces 0.00357757. Based on the best architecture produced in this study, the 20-15-1 architecture with 90% accuracy with a Mean Squared Error testing 0.00262384 at epoch 27915 Iterations. Thus it can be concluded that the backpropagation algorithm can provide good accuracy in the prediction process. With this research, the livestock industry can utilize it as one of the materials to predict goat meat in the future

show abstract

“…Neural Network ditentukan oleh tiga factor yaitu arsitektur jaringan, algoritma pembelajaran, dan fungsi aktivasi pernyataan tersebut diungkapkan oleh Fauset pada tahun 1994 [15]. Sebagai sekelompok elemen pemrosesan dalam kelompok tertentu, jaringan melakukan perhitungannya sendiri dan meneruskan hasilnya ke kelompok berikutnya [16]. Data non-numerik harus diubah menjadi data numerik dikarenakan algoritma JST bekerja langsung dengan angka [17].…”

Section: Gambar 2 Alur Kerja Penelitianunclassified

Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing di Indonesia

Rika Setiana,

Razalfa Aindi Siregar,

Fahry Husaini

et al. 2023

jieee

0

View full text Add to dashboard Cite

A science that has always developed rapidly until now is artificial neural networks. A computational science that works like the human nervous system is an artificial neural network. Artificial neural networks with the backpropagation method can make a prediction on data. In this article, a prediction will be made on the amount of goat production in Indonesia. Goats are one of the livestock that can produce nutritious meat. The lack of goat meat will cause the price of goat meat to rise. Producing enough goat meat helps stabilize the price of meat, but if goat meat production is less than demand, it will lead to price increases. Therefore, looking at the problems above, this study aims to predict goat meat so that in the future it can know how much goat meat must be predicted by processing data first and then being used as input in predicting the amount of goat meat production. Prediction is one way to estimate future demand. Avoiding the lack of meat availability, by predicting the amount of goat meat produced in such a way that there is no scarcity of goat meat and fluctuations in the price of goat meat in the market. Basic methods and data are required to make predictions. In this study, data was obtained from BPS Indonesia in the livestock section using data from 2001-2021 as training data and 2002-2022 as test data. The method applied in this article is the backpropagation algorithm. This article applies 5 network architectures implemented in the mathlab application. The architecture used in this article is 20-25-1 with a Mean Squred Error testing 0.00447765, in 20-30-1 architecture produces Mean Squred Error 0.00300466, in 20-35-1 architecture produces 0.00426823, in 20-37-1 architecture produces 0.00357757. Based on the best architecture produced in this study, the 20-15-1 architecture with 90% accuracy with a Mean Squared Error testing 0.00262384 at epoch 27915 Iterations. Thus it can be concluded that the backpropagation algorithm can provide good accuracy in the prediction process. With this research, the livestock industry can utilize it as one of the materials to predict goat meat in the future

show abstract

Pemilihan Model Arsitektur Terbaik Dengan Mengoptimasi Learning Rate Pada Neural Network Backpropagation

Cited by 4 publications

References 3 publications

Optimized Artificial Neural Network for the Classification of Urban Environment Comfort using Landsat-8 Remote Sensing Data in Greater Jakarta Area, Indonesia

Optimized Artificial Neural Network for the Classification of Urban Environment Comfort using Landsat-8 Remote Sensing Data in Greater Jakarta Area, Indonesia

Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing Di Indonesia

Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing di Indonesia

Contact Info

Product

Resources

About