Open AccessA Hybrid Deep Neural Network Model for Time Series Forecasting
Publication year - 2022
Publication title -
international journal of advanced trends in computer science and engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3091
DOI - 10.30534/ijatcse/2022/051112022
Subject(s) - computer science , recurrent neural network , convolutional neural network , deep learning , artificial intelligence , robustness (evolution) , artificial neural network , feature (linguistics) , time series , long short term memory , feature extraction , feature engineering , hybrid neural network , pattern recognition (psychology) , machine learning , biochemistry , chemistry , linguistics , philosophy , gene
Deep neural networks have proven to perform optimal forecasts even with the presence of noisyand non-linear nature of time series data. In thispaper, a hybrid deep neural network consisting of Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) architecture have been proposed. The model combines the convolutional layer’s capability of feature extraction along with the LSTM’s feature of learning long term sequential dependencies. The experiments were performed on two datasets and compared with four other approaches: Recurrent Neural Network (RNN), LSTM, Gated Recurrent Unit (GRU) and Bidirectional LSTM. All five models are evaluated and compared with one step ahead forecasting. The proposed hybrid CNN-LSTM outperformed other modelsfor both datasets showing robustness against error.