RNN_ts {TSdeeplearning}

Recurrent neural network Model

Description

The RNN function computes forecasted value with different forecasting evaluation criteria for recurrent neural network model.

Usage

RNN_ts(xt, xtlag = 4, uRNN = 2, Drate = 0, nEpochs = 10,
Loss = "mse", AccMetrics = "mae",ActFn = "tanh",
Split = 0.8, Valid = 0.1)

Arguments

xt

Input univariate time series (ts) data.

xtlag

Lag of time series data.

uRNN

Number of unit in RNN layer.

Drate

Dropout rate.

nEpochs

Number of epochs.

Loss

Loss function.

AccMetrics

Metrics.

ActFn

Activation function.

Split

Index of the split point and separates the data into the training and testing datasets.

Valid

Validation set.

Details

Recurrent neural networks (RNNs) (Rumelhart 1986) add the explicit handling of order between observations when learning a mapping function from inputs to outputs. RNNs actually process single elements of any input sequence at a particular time, and maintain a ‘state vector’ in their hidden units. Nevertheless, when the interval of data dependencies increases, the standard RNNs tend to suffer increasingly heavily from the problem of either vanishing gradient or exploding gradient (Bengio et al. 1994; Lin et al. 1996).

Value

TrainFittedValue

Training Fitted value for given time series data.

TestPredictedValue

Final forecasted value of the RNN model.

fcast_criteria

Different Forecasting evaluation criteria for RNN model.

References

Bengio et al. 1994; Lin Sagheer A, Kotb M (2019) Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing 323: 203–213.

Rumelhart DE (1986) Learning internal representations by error propagation. In: Parallel distributed processing: Explorations in the microstructure of cognition. pp 318–362.

Jha, G. K. and Sinha, K. (2014). Time-delay neural networks for time series prediction: An application to the monthly wholesale price of oilseeds in India. Neural Computing and Applications, 24(3–4), 563–571. Jaiswal, R., Jha, G. K., Kumar, R. R. and Choudhary, K. (2022). Deep long short-term memory based model for agricultural price forecasting. Neural Computing and Applications, 34(6), 4661–4676.

See Also

LSTM, GRU

Examples

data("Data_Maize")
RNN_ts(Data_Maize)