Komparasi Fungsi Aktivasi Relu Dan Tanh Pada Multilayer Perceptron

Firmansyah, Ichsan; Hayadi, B. Herawan

doi:10.26798/jiko.v6i2.600

Cited by 8 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The study uses two types of activation functions, namely Rectified Linear Unit (ReLU) and Adaptive Moment Estimation (ADAM). According to a study, the model using the ReLu activation function with 4 hidden layers and 50 neurons in each hidden layer had the highest accuracy score [10]. This shows that ReLu is able to do a good job as an activation function.…”

Section: Deep Learning Neural Networkmentioning

confidence: 99%

“…It is commonly used in research methods involving forecasting, including those related to rainfall forecasting. The RMSSE is a scaled version of the RMSE (Root Mean Squared Error) that takes into account the seasonality and the actual variability in the data, the equation of RMSSE can be written as in Equation ( 9) [16]: (10) Where 𝑦 𝑡 is the actual future value of the examined time series at point t, 𝑦 ̂𝑡 is the forecast by the method under evaluation, 𝑛 is the length of the training sample (number of historical observation), and ℎ is the forecasting horizon.…”

Section: Metric Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Rainfall Forecasting With an Intermittent Approach Using Hybrid Exponential Smoothing Neural Network

Permata,

Muhaimin,

Hidayati

2024

BAREKENG: J. Math. & App.

View full text Add to dashboard Cite

Rainfall forecasting is crucial in agriculture, water resource management, urban planning, and disaster preparation. Traditional approaches fail to capture complicated and intermittent rainfall patterns. The “Hybrid Exponential Smoothing Neural Network” is introduced in this study to handle intermittent rainfall forecasting issues. Exponential Smoothing, an established approach for discovering underlying patterns and seasonal fluctuations in time series data, is combined with Neural Networks, which are good at capturing complex linkages and nonlinearities. Using these two methods, this model hopes to deliver a complete rainfall forecasting solution that accounts for short-term changes and long-term patterns. This research uses residuals from the exponential smoothing model and is modeled using a Neural Network. The residual input is transformed using rolling mean. The results show that the hybrid model is able to capture patterns well, but there are still patterns that experience time lag. Experimental results obtained reveal that the hybrid methodology performs better than the model exponential smoothing, implying that the proposed model hybrid synergy approach can be used as an alternative solution to the rainfall time series forecasting. The results show that the Hybrid method can form patterns better than individual exponential smoothing models or neural networks. The RMSSE values for all areas are 1.0185, 1.55092, 1.0872.

show abstract

Section: Deep Learning Neural Networkmentioning

confidence: 99%

Section: Metric Evaluationmentioning

confidence: 99%

Rainfall Forecasting With an Intermittent Approach Using Hybrid Exponential Smoothing Neural Network

Permata,

Muhaimin,

Hidayati

2024

BAREKENG: J. Math. & App.

View full text Add to dashboard Cite

show abstract

“…The ReLU activation function is used on hidden layers, while the Sigmoid activation function is used on the model output. The use of this activation function requires all data to have a positive value because the ReLU function returns a value of 0 for a negative input [15]. Sigmoid is used to convert the original range of values into a range between 0 and 1 [16].…”

Section: Ann Modelmentioning

confidence: 99%

“…One of the most well-known and proven methods useful in modeling complex hydrological processes or nonlinear systems such as sediment transport is the Artificial Neural Network (ANN) [8]. Neural Network has an effective performance in transforming data so that it can be processed more easily [9]. ANN is a data-driven method that uses experience learned from historical data to estimate desired outputs.…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network to Classify Seabed Sediment Using MBES Multifrequency

Khomsin,

Hadicahyo

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

This study investigates the classification of sediment distribution and types in inland waters using Artificial Neural Network (ANN) models based on multibeam echosounder data. Multibeam Echosounder Technology (MBES) is an acoustic instrument that emits high-speed sound pulses to map the bottom of water bodies. Valuable information about sediment characteristics can be obtained by analyzing the backscattering phenomenon, which measures the acoustic intensity reflected from the water bottom. The angular response curve (ARC) method, developed by Fonseca and Calder, is employed to analyze the relationship between backscatter intensity and the angle of reflection. The ANN models in this study are trained and tested using intensity values and angular response curves obtained from multibeam echo sounders. The ANN model architecture consists of an input layer, three hidden layers, and an output layer. The sigmoid activation function is utilized in the output layer, while the ReLU activation function is applied to the input and hidden layers. Performance evaluation demonstrates that the ANN model using uncorrected data achieves remarkable accuracy, with 100% accuracy obtained in both the training and testing stages. The model exhibits a training loss value of 0.059443 and a testing loss value of 0.110030, indicating its effectiveness in capturing patterns and reducing errors. Visualizing the sediment distribution in Waduk Selorejo reveals a relatively balanced presence of Clavey sand and Sandy silt sediment types. However, noticeable differences arise between the corrected and uncorrected data, which can be attributed to the alterations made during the data correction process. The best-performing ANN model achieves a testing accuracy of 0.75, indicating that it does not perfectly predict the given data. Acknowledging the potential for prediction errors when using corrected data is important.

show abstract

“…The Multilayer Perceptron (MLP) algorithm, characterized by an input layer, two or more hidden layers, and an output layer, exhibits resilience to data noise and is capable of solving complex data problems effectively due to its architecture with multiple hidden layers (Pardede & Hayadi, 2023). This algorithm utilizes activation functions, such as ReLu, in the hidden layer to minimize the error values of the output produced by each neuron (Firmansyah & Hayadi, 2022). When dealing with complex data, MLPs are susceptible to overfitting, where the model excessively learns details from the training data and fails to generalize well to test or new data (Dovbnych & Plechawska-Wójcik, 2021).…”

Section: Introductionmentioning

confidence: 99%

Enhancing Multi-Layer Perceptron Performance with K-Means Clustering

Pardede,

Ichsan,

Riyadi

2024

CNAHPC

View full text Add to dashboard Cite

Machine learning plays a crucial role in identifying patterns within data, with classification being a prominent application. This study investigates the use of Multilayer Perceptron (MLP) classification models and explores preprocessing techniques, particularly K-Means clustering, to enhance model performance. Overfitting, a common challenge in MLP models, is addressed through the application of K-Means clustering to streamline data preparation and improve classification accuracy. The study begins with an overview of overfitting in MLP models, highlighting the significance of mitigating this issue. Various techniques for addressing overfitting are reviewed, including regularization, dropout, early stopping, data augmentation, and ensemble methods. Additionally, the complementary role of K-Means clustering in enhancing model performance is emphasized. Preprocessing using K-Means clustering aims to reduce data complexity and prevent overfitting in MLP models. Three datasets - Iris, Wine, and Breast Cancer Wisconsin - are employed to evaluate the performance of K-Means as a preprocessing technique. Results from cross-validation demonstrate significant improvements in accuracy, precision, recall, and F1 scores when employing K-Means clustering compared to models without preprocessing. The findings highlight the efficacy of K-Means clustering in enhancing the discriminative power of MLP classification models by organizing data into clusters based on similarity. These results have practical implications, underlining the importance of appropriate preprocessing techniques in improving classification performance. Future research could explore additional preprocessing methods and their impact on classification accuracy across diverse datasets, advancing the field of machine learning and its applications

show abstract

Komparasi Fungsi Aktivasi Relu Dan Tanh Pada Multilayer Perceptron

Cited by 8 publications

References 8 publications

Rainfall Forecasting With an Intermittent Approach Using Hybrid Exponential Smoothing Neural Network

Rainfall Forecasting With an Intermittent Approach Using Hybrid Exponential Smoothing Neural Network

Deep Neural Network to Classify Seabed Sediment Using MBES Multifrequency

Enhancing Multi-Layer Perceptron Performance with K-Means Clustering

Contact Info

Product

Resources

About