Analisis Pengaruh Fungsi Aktivasi, Learning Rate Dan Momentum Dalam Menentukan Mean Square Error (MSE) Pada Jaringan Saraf Restricted Boltzmann Machines (RBM)

Susilawati, Susilawati; Muhathir, Muhathir

doi:10.31289/jite.v2i2.2162

Cited by 7 publications

(7 citation statements)

References 2 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Kode program 1 menggambarkan pembuatan model LSTM ini. Dalam proses ini, optimisasi menggunakan algoritma ADAM, sementara loss function dievaluasi menggunakan mean square error (MSE) [17], [18], [19], yang mengukur sejauh mana perkiraan model mendekati nilai sebenarnya. Proses pelatihan LSTM dimulai dengan menggunakan perintah pada kode program.…”

Section: Pembuatan Model Lstmunclassified

Prediksi Radiasi Surya Menggunakan Metode Long Short-Term Memory

Rezza,

Ismail Yusuf,

Yacoub

2024

ilkomnika

View full text Add to dashboard Cite

Penelitian ini memfokuskan pada optimalisasi pemanfaatan energi matahari di Kalimantan Barat, sebuah wilayah yang kaya akan sumber daya matahari, dengan total pembangkit listrik tenaga surya (PLTS) mencapai 1.58 MW. Untuk memprediksi potensi energi matahari, penelitian menggunakan metode jaringan syaraf tiruan Long Short-Term Memory (LSTM) dengan data yang diperoleh dari data logger yang merekam tegangan, arus, dan daya keluaran panel surya selama 57 hari dengan interval 1-2 detik, menghasilkan 4.294.273 data. Dalam pengolahan data, 80% digunakan untuk pelatihan dan sisanya untuk pengujian model LSTM. Model LSTM yang digunakan terdiri dari 2 layer LSTM, masing-masing dengan 50 node LSTM. Penggunaan Google Colaboratory sebagai platform komputasi memungkinkan pelatihan model LSTM dalam dua skenario, yaitu dengan epoch sebesar 1 dan 10. Evaluasi model dilakukan menggunakan metrik Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), dan R-squared (R2). Hasil pengujian menunjukkan bahwa model dengan epoch 10 memiliki nilai evaluasi yang lebih baik, dengan MSE sebesar 0.04444, RMSE sebesar 0.00456, MAE sebesar 0.06753, dan R2 sebesar 0.99961, menunjukkan performa prediksi energi matahari yang sangat akurat dan efisien.

show abstract

Section: Pembuatan Model Lstmunclassified

Prediksi Radiasi Surya Menggunakan Metode Long Short-Term Memory

Rezza,

Ismail Yusuf,

Yacoub

2024

ilkomnika

View full text Add to dashboard Cite

show abstract

“…If the desired value (convergence) has been achieved by obtaining good weights during the process, the RBM algorithm will stop learning. When the cycle of learning patterns occurs, each weight changes, and it is expected to obtain an accurate value with a stable weight [6].…”

Section: Negative Phasementioning

confidence: 99%

“…Susilawati & Muhathir research was conducted to analyze the results of the mean square error (MSE) in the restricted Boltzmann machine algorithm [6]. The best percentage value in this study was 93.42%, with a binary sigmoid activation function and a learning rate of 0.05, and a momentum of 0.7.…”

Section: Introductionmentioning

confidence: 96%

Comparison of Performance Metrics Level of Restricted Boltzmann Machine and Backpropagation Algorithms in Detecting Diabetes Mellitus Disease

Anggoro

Hajiati²

2023

Iraqi Journal of Science

View full text Add to dashboard Cite

Diabetes is a disease caused by high sugar levels. Currently, diabetes is one of the most common diseases in the number of people with diabetes worldwide. The increase in diabetes is caused by the delay in establishing the diagnosis of the disease. Therefore, an initial action is needed as a solution that requires the most appropriate and accurate data mining to manage diabetes mellitus. The algorithms used are artificial neural network algorithms, namely Restricted Boltzmann Machine and Backpropagation. This research aims to compare the two algorithms to find which algorithm can produce high accuracy, and determine which algorithm is more accurate in detecting diabetes mellitus. Several stages were involved in this research, including data collection, data pre-processing, data processing, and evaluation models. This research shows that the Restricted Boltzmann Machine algorithm achieved accuracy of 82.02% while the Backpropagation algorithm reached87.01% when using the normalization method. Thus, the diabetes mellitus dataset used can be said to have a better value for the backpropagation algorithm than the restricted Boltzmann machine algorithm.

show abstract

“…Selanjutnya dilakukan perhitungan Mean Square Error (MSE) yang bertujuan untuk mengetahui rata-rata selisih kuadrat antara nilai yang diramalkan dan diamati (Hodson, 2022;Susilawati & Muhathir, 2019). Sedangkan Mean Absolute Percentage Error (MAPE) adalah pengukuran kesalahan yang menghitung ukuran presentase penyimpangan antara data aktual dengan data peramalan (Almeida et al, 2018;Nicolson & Paliwal, 2019;Shin et al, 2018) menggunakan persamaan 3.…”

Section: Metodeunclassified

Sistem Peramalan Permintaan Darah dengan Metode Simple Moving Average

Muttaqin¹,

Ramdhan²,

Kifti³

2022

Edumatic

View full text Add to dashboard Cite

Simple Moving Average (SMA) is a method used to forecast a state of affairs in the next period. This method is applied to determine the number of blood requests in PMI in the Asahan Regency area. Blood stock is an important factor to support activities in this PMI organization by paying attention to the condition of this month /period and predicting the next period. The purpose of this study is to build a blood demand forecasting system with the SMA method. The model used to build this system is a waterfall with stages of analysis, design, implementation and testing. The data we use for this forecasting is the demand for blood from July 2021 to June 2022. Data analysis used the SMA method to determine the rate of prediction errors in this system, while testing this system used a black box. The results of our products are in the form of a web consisting of the login menu, the main menu, the calculation results. The calculation results using the SMA method in our system are appropriate, and can display the number of blood demand stocks in each period. The results of testing the system using black box show that this system is running properly without any errors, and it is working properly. Therefore, the existence of this system can help pmi to determine the number of requests based on blood type.

show abstract

Analisis Pengaruh Fungsi Aktivasi, Learning Rate Dan Momentum Dalam Menentukan Mean Square Error (MSE) Pada Jaringan Saraf Restricted Boltzmann Machines (RBM)

Cited by 7 publications

References 2 publications

Prediksi Radiasi Surya Menggunakan Metode Long Short-Term Memory

Prediksi Radiasi Surya Menggunakan Metode Long Short-Term Memory

Comparison of Performance Metrics Level of Restricted Boltzmann Machine and Backpropagation Algorithms in Detecting Diabetes Mellitus Disease

Sistem Peramalan Permintaan Darah dengan Metode Simple Moving Average

Contact Info

Product

Resources

About