Wind Speed Prediction Using Hybrid 1D CNN and BLSTM Network

Lawal, Abdulmajid; Rehman, Shafiqur; Alhems, Luai M.; Alam, Md. Mahbub

doi:10.1109/access.2021.3129883

Cited by 41 publications

(14 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A typical LSTM network consists of three gates, respectively input, output, and forget gate. The gates are used to both manage and protect the states of the cells that are passed to the subsequent cell, including the hidden state and the cell state (Lawal et al, 2021).…”

Section: Methodsmentioning

confidence: 99%

A Performance-Driven Economic Analysis of a LSTM Neural Network Used for Predicting Building Energy Consumption

Bălăcian

Stancu

2023

Proceedings of the International Conference on Business Excellence

View full text Add to dashboard Cite

The energy sector occupies a central role in European policy regarding the sustainability and climate change ambitions. This economic sector gained even more importance in the context of a growing energy demand and the threat to energy security and stability in Eastern Europe. The administrative changes from the past years and the shift towards renewable energy sources created the momentum for a general transformation of the energy sector. The research in this field is much needed in order to find the best solutions to predict the energy demand and how to efficiently satisfy it. The purpose of this paper is to assess the economic impact of using artificial neural networks on a dataset that captures information from one building about the energy consumption. The network follows a Long – Short Term Memory architecture and it is characterized by a Root Mean Squared Propagation function for optimization. The analysis consists in the comparison of the performance of three activation functions: Rectified Linear Unit, Sigmoid and Tanh. The results complement the existing research in the field by focusing on the prediction of energy consumption at building level. The case study indicates that the Rectified Linear Unit and Tanh functions are more appropriate than Sigmoid to be used in an LSTM network applied on energy consumption data. The former performs better in terms of accuracy, measured by the Mean Absolute Value, and has similar computational costs to Tanh, with a slightly larger value for training time.

show abstract

Section: Methodsmentioning

confidence: 99%

A Performance-Driven Economic Analysis of a LSTM Neural Network Used for Predicting Building Energy Consumption

Bălăcian

Stancu

2023

Proceedings of the International Conference on Business Excellence

View full text Add to dashboard Cite

show abstract

“…Following that, the flattening process takes place, and then it proceeds to the dense layer, ultimately producing the output. For a detailed design of the modeling architecture using 1D-CNN, refer to Figure 6 [46]. In Table 4 presents details regarding the parameters or characteristics of each layer.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…This evaluation process employs the root mean square error (RMSE), mean absolute error (MAE), mean squared error (MSE), and mean absolute percentage error (MAPE) techniques. The mathematical calculations for each evaluation technique, such as RMSE, MAE, MSE, and MAPE, can be seen in Formulas 3 to 6 [46]- [48].…”

Section: Evaluation Modelmentioning

confidence: 99%

IoT-enhanced infant incubator monitoring system with 1D-CNN temperature prediction model

Ady Aryanto,

Maneetham,

Crisnapati

2024

IJEECS

View full text Add to dashboard Cite

This research aims to develop a monitoring system and temperature prediction model in neonatal premature infant incubators by applying the internet of things (IoT) concept and the 1-dimensional convolutional neural network (1D-CNN) method. The system is designed by integrating sensors, actuators, and microcontrollers connected through Wi-Fi network with message queue telemetry transport (MQTT) protocol. Sensor data in the incubator is stored in a database and displayed in real-time on a web application. The data in the database is also used for creating a temperature prediction model in the incubator. Test results indicate that the best model configuration consists of 5 neurons in the first layer, 20 neurons in the second layer, and a dense layer with 100. The evaluation of this model yields a high level of accuracy with an root mean square error (RMSE) of 0.200 °C, MSE of 0.004 °C, mean absolute error (MAE) of 0.152 °C, and mean absolute percentage error (MAPE) of 0.4%. Based on the error values obtained between the predicted and actual values from each evaluation technique in the model, it can be concluded that the range between the real and predicted values is approximately 0.2 °C. Overall, this research contributes to improving the quality of care for premature infants.

show abstract

“…As redes CNNs são utilizadas, com muito sucesso, em classificação de imagens. Sua versão 1D é aplicada para tratar sequências de dados, tais como séries temporais, gravações de áudio e processamento de linguagem natural (Lawal, 2021).…”

Section: Redes Cnn-blstmunclassified

Previsão do preço do café arábica: uma aplicação de redes neurais CNN-BLSTM

Santos

2022

RSD

View full text Add to dashboard Cite

Este trabalho propõe a utilização da rede neural CNN-BLSTM como ferramenta de previsão do preço do café arábica. A base de dados disponibilizada pelo CEPEA (Centro de Estudos Avançados em Economia Aplicada) apresenta uma série histórica, do preço do café arábica, no período entre janeiro de 1997 e dezembro de 2021. Modelos de previsão baseados em redes neurais LSTM, BLSTM, CNN e CNN-BLSTM foram implementados, na linguagem Python, utilizando o framework Keras. Resultados obtidos, dos quatro modelos, foram comparados por meio das métricas MAE, RMSE e MAPE. Verificou-se, para um horizonte de 6 meses, que o modelo CNN-BLSTM apresentou melhor desempenho.

show abstract

Wind Speed Prediction Using Hybrid 1D CNN and BLSTM Network

Cited by 41 publications

References 54 publications

A Performance-Driven Economic Analysis of a LSTM Neural Network Used for Predicting Building Energy Consumption

A Performance-Driven Economic Analysis of a LSTM Neural Network Used for Predicting Building Energy Consumption

IoT-enhanced infant incubator monitoring system with 1D-CNN temperature prediction model

Previsão do preço do café arábica: uma aplicação de redes neurais CNN-BLSTM

Contact Info

Product

Resources

About