Text
PREDIKSI PANEN PERIKANAN DENGAN ALGORITMA GATED RECURRENT UNIT YANG DIOPTIMASIKAN DENGAN ALGORITMA GENETIKA
Indonesia is a maritime country with most of the population living near on water areas and water products are a common commodity that is often consumed cheaply and food is therefore one of the primary human needs, so fishery harvest predictions are needed in order to control prices, prepare seeds, so that sales remain stable, consumption is not problematic, etc. The reason for choosing GRU for this prediction is that previously it was common to use classical methods that have been used in econometrics or time series analysis in general, and GRU has fewer operations than LSTM. Instead of training with an optimization algorithm that relies on backpropagation and gradients such as gradient descent, by using metaheuristic optimization in the form of a genetic algorithm on the grounds that the GA does not require gradient information and is expected to avoid local optima, the total average MSE obtained is 9.55%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407001742 | T141439 | T1414392024 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available