A comparison of feed-forward and recurrent neural networks in time series forecasting

Brezak, Danko; Baček, Tomislav; Majetić, Dubravko; Kasač, Josip; Novaković, Branko

doi:10.1109/cifer.2012.6327793

Cited by 47 publications

(26 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[33] compares the feedforward model with the radial basis neural network. [34] compares the feedforward model with the recurrent neural network. This is not sufficient to recognize ….…”

Section: Introductionmentioning

confidence: 99%

Short-term load forecasting algorithm and optimization in smart grid operations and planning

Skolthanarat

Lewlomphaisarl

Tungpimolrut

2014

2014 IEEE Conference on Technologies for Sustainability (SusTech)

View full text Add to dashboard Cite

Electrical load forecasting is one of the important parts for smart grid system. The reliable prediction of the load demand contributes to the efficient and economical operations and planning. The artificial neural network is used extensively in load demand forecasting. The nonlinear nature of the electrical load demand conforms to the ability of the artificial neural network in calculating the nonlinear relationship of inputs and outputs. Among many models of neural networks, radial basis neural networks yield superior performance in small error and fast simulation time.However, it is challenge to design the radial basis neural networks. The excessive numbers of hidden neurons lead to lacking of generalization or so called overfitting problems. This paper proposes an approach to design the radial basis neural networks that use as least numbers of hidden neurons as possible. The error criterion is optimized based on modified genetic algorithm as the numbers of hidden neurons are incrementally increased. Simulation results of short term load forecasting are calculated in Matlab, and compared to the orthogonal least square error method. The proposed approach gives better results with the same numbers of hidden neurons.

show abstract

“…[33] compares the feedforward model with the radial basis neural network. [34] compares the feedforward model with the recurrent neural network. This is not sufficient to recognize ….…”

Section: Introductionmentioning

confidence: 99%

Short-term load forecasting algorithm and optimization in smart grid operations and planning

Skolthanarat

Lewlomphaisarl

Tungpimolrut

2014

2014 IEEE Conference on Technologies for Sustainability (SusTech)

View full text Add to dashboard Cite

show abstract

“…Thus, previous input and output values may be used for current output calculation. Analysis of several independent papers [15][16][17] showed that amongst various architectures of networks such as focused time delay, distributed time delays, Jordan, Elman, Hopfield, Hamming, the most suitable architecture for time-serious processing is non-linear autoregressive model with exogenous inputs (NARX). Basically it is multilayer perceptron with shortterm memory.…”

Section: Methodsmentioning

confidence: 99%

Blind Separation of Abdominal Electrocardiogram Sources through Dynamic Neural Network

Devyatykh¹,

Gerget²

2016

Proceedings of the 2016 Conference on Information Technologies in Science, Management, Social Sphere and Medicine

View full text Add to dashboard Cite

Abstract-Cardiovascular system of the fetus is biological critical infrastructure. Fetal electrocardiogram and its characteristics such as heart ratio, waveform and dynamic behavior overall include vital information about health state, development and possible deviations from normal fetation. Thus fetal heart ratio monitoring is mandatory during pregnancy. Widespread Doppler ultrasound diagnostics can guarantee obtaining accurate results but is not suitable for long-term monitoring. Non-invasive fetal electrocardiography proposes to extract fetal signal from maternal abdominal electrocardiogram. This approach is applicable for long-term monitoring, but because of amplitude of maternal R-peaks is significantly larger than fetal it is a challenge to extract fetal signal. In this paper we propose using dynamic neural networks for extracting fetal components and demonstrate its advantages compared to blind source separation though independent component analysis. The training algorithm is a combination of backpropagation through time and resilient propagation. The proposed approach accuracy of R-peak detection is 97%. Statistical analysis proved that developed algorithm can process even non-stationary signals with loss of accuracy and no additional training is required.

show abstract

“…An NN method is applied in this study for predicting the soil moisture dynamics because of their ability to produce robust functions approximating complex processes [ 45 ]. However, traditional feedforward neural networks (FFNNs) have limited ability to model dynamic data because they are unable to preserve previous information, resulting in suboptimal predictions when they are applied in modelling highly causal systems [ 46 ]. The learning capability of FFNNs can be improved through additional pre-processing of dynamic data and combining the FFNN with other methods including genetic algorithms [ 47 ] and fuzzy logic [ 36 ].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Neural Network Modelling of Soil Moisture Content for Predictive Irrigation Scheduling

Adeyemi

Grove

Peets

et al. 2018

Sensors

155

View full text Add to dashboard Cite

Sustainable freshwater management is underpinned by technologies which improve the efficiency of agricultural irrigation systems. Irrigation scheduling has the potential to incorporate real-time feedback from soil moisture and climatic sensors. However, for robust closed-loop decision support, models of the soil moisture dynamics are essential in order to predict crop water needs while adapting to external perturbation and disturbances. This paper presents a Dynamic Neural Network approach for modelling of the temporal soil moisture fluxes. The models are trained to generate a one-day-ahead prediction of the volumetric soil moisture content based on past soil moisture, precipitation, and climatic measurements. Using field data from three sites, a R2 value above 0.94 was obtained during model evaluation in all sites. The models were also able to generate robust soil moisture predictions for independent sites which were not used in training the models. The application of the Dynamic Neural Network models in a predictive irrigation scheduling system was demonstrated using AQUACROP simulations of the potato-growing season. The predictive irrigation scheduling system was evaluated against a rule-based system that applies irrigation based on predefined thresholds. Results indicate that the predictive system achieves a water saving ranging between 20 and 46% while realizing a yield and water use efficiency similar to that of the rule-based system.

show abstract

A comparison of feed-forward and recurrent neural networks in time series forecasting

Cited by 47 publications

References 8 publications

Short-term load forecasting algorithm and optimization in smart grid operations and planning

Short-term load forecasting algorithm and optimization in smart grid operations and planning

Blind Separation of Abdominal Electrocardiogram Sources through Dynamic Neural Network

Dynamic Neural Network Modelling of Soil Moisture Content for Predictive Irrigation Scheduling

Contact Info

Product

Resources

About