Journal article
Prediction of Engine Demand with a Data-driven Approach
Procedia computer science, Vol.103, pp.28-35
2017
DOI: 10.1016/j.procs.2017.01.005
Abstract
Models predicting volume of engine demand from historical data are developed. To accommodate seasonal effects, neural networks and autoregressive integrated moving average (ARIMA) approaches are considered. Previous research on the effectiveness of neural networks to model phenomena with seasonality and trend using raw data has been inconclusive. In this paper, four predictive models for a linear time series with seasonality are developed and their accuracy is studied. Performance of a dummy variable linear regression model, a seasonal ARIMA model, a neural network model using raw historical data, and a hybrid linear model is compared. The seasonal ARIMA and linear regression models are found to perform better than the neural network model. The hybrid linear model is found to outperform the three individual models.
Details
- Title: Subtitle
- Prediction of Engine Demand with a Data-driven Approach
- Creators
- Hudson Francis - University of IowaAndrew Kusiak - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Procedia computer science, Vol.103, pp.28-35
- DOI
- 10.1016/j.procs.2017.01.005
- ISSN
- 1877-0509
- eISSN
- 1877-0509
- Publisher
- Elsevier B.V
- Language
- English
- Date published
- 2017
- Academic Unit
- Industrial and Systems Engineering; Nursing
- Record Identifier
- 9984187080602771
Metrics
19 Record Views