TY  - CONF
N2  - This paper proposed a technique named Recurrent Neural Network-Gated Recurrent Unit (RNN-GRU) to predict the condition of machines by using time series data generated by oil and gas company. The problem raised due to limited research of RNN-GRU in improving the accuracy through hyperparameter tuning. Hence, this paper will provide an optimization method that can improve the accuracy of RNN-GRU in forecasting time series data. The preliminary findings of the experiment conducted shows that RNN-GRU can utilize time series data to predict machine failure with improved high accuracy. © 2019 IEEE.
N1  - cited By 1; Conference of 1st International Conference on Artificial Intelligence and Data Sciences, AiDAS 2019 ; Conference Date: 19 September 2019; Conference Code:157266
TI  - Predictive analytics for machine failure using optimized recurrent neural network-gated recurrent unit (GRU)
ID  - scholars11331
SP  - 88
KW  - Forecasting; Gas industry; Genetic algorithms; Predictive analytics; Public utilities; Time series
KW  -  Forecasting time series; High-accuracy; Hyper-parameter; Machine failure; Oil and gas companies; Optimization method; Time-series data
KW  -  Recurrent neural networks
AV  - none
A1  - Zainuddin, Z.
A1  - P Akhir, E.A.
A1  - Aziz, N.
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85079346213&doi=10.1109%2fAiDAS47888.2019.8970725&partnerID=40&md5=ac076132c400990b24e1c17a4bc8214c
EP  - 93
Y1  - 2019///
PB  - Institute of Electrical and Electronics Engineers Inc.
SN  - 9781728130415
ER  -