TY - GEN
T1 - Feature and architecture selection on deep feedforward network for roll motion time series prediction
AU - Suhermi, Novri
AU - Suhartono,
AU - Rahayu, Santi Puteri
AU - Prastyasari, Fadilla Indrayuni
AU - Ali, Baharuddin
AU - Fachruddin, Muhammad Idrus
N1 - Publisher Copyright:
© Springer Nature Singapore Pte Ltd. 2019.
PY - 2019
Y1 - 2019
N2 - The neural architecture and the input features are very substantial in order to build an artificial neural network (ANN) model that is able to perform a good prediction. The architecture is determined by several hyperparameters including the number of hidden layers, the number of nodes in each hidden layer, the series length, and the activation function. In this study, we present a method to perform feature selection and architecture selection of ANN model for time series prediction. Specifically, we explore a deep learning or deep neural network (DNN) model, called deep feedforward network, an ANN model with multiple hidden layers. We use two approaches for selecting the inputs, namely PACF based inputs and ARIMA based inputs. Three activation functions used are logistic sigmoid, tanh, and ReLU. The real dataset used is time series data called roll motion of a Floating Production Unit (FPU). Root mean squared error (RMSE) is used as the model selection criteria. The results show that the ARIMA based 3 hidden layers DNN model with ReLU function outperforms with remarkable prediction accuracy among other models.
AB - The neural architecture and the input features are very substantial in order to build an artificial neural network (ANN) model that is able to perform a good prediction. The architecture is determined by several hyperparameters including the number of hidden layers, the number of nodes in each hidden layer, the series length, and the activation function. In this study, we present a method to perform feature selection and architecture selection of ANN model for time series prediction. Specifically, we explore a deep learning or deep neural network (DNN) model, called deep feedforward network, an ANN model with multiple hidden layers. We use two approaches for selecting the inputs, namely PACF based inputs and ARIMA based inputs. Three activation functions used are logistic sigmoid, tanh, and ReLU. The real dataset used is time series data called roll motion of a Floating Production Unit (FPU). Root mean squared error (RMSE) is used as the model selection criteria. The results show that the ARIMA based 3 hidden layers DNN model with ReLU function outperforms with remarkable prediction accuracy among other models.
KW - ARIMA
KW - Deep feedforward network
KW - PACF
KW - Roll motion
KW - Time series
UR - http://www.scopus.com/inward/record.url?scp=85059053321&partnerID=8YFLogxK
U2 - 10.1007/978-981-13-3441-2_5
DO - 10.1007/978-981-13-3441-2_5
M3 - Conference contribution
AN - SCOPUS:85059053321
SN - 9789811334405
T3 - Communications in Computer and Information Science
SP - 58
EP - 71
BT - Soft Computing in Data Science - 4th International Conference, SCDS 2018, Proceedings
A2 - Yap, Bee Wah
A2 - Mohamed, Azlinah Hj
A2 - Berry, Michael W.
PB - Springer Verlag
T2 - 4th International Conference on Soft Computing in Data Science, SCDS 2018
Y2 - 15 August 2018 through 16 August 2018
ER -