A Novel Method for Imputing Missing Values in Ship Static Data Based on Generative Adversarial Networks
Open Access
- 10 April 2023
- journal article
- research article
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 11 (4) , 806
Abstract
Ship data obtained through the maritime sector will inevitably have missing values and outliers, which will adversely affect the subsequent study. Many existing methods for missing data imputation cannot meet the requirements of ship data quality, especially in cases of high missing rates. In this paper, a missing data imputation method based on generative adversarial networks (GANs) is proposed. The generative adversarial imputation network (GAIN) is improved using the Wasserstein distance and gradient penalty to handle missing values. Meanwhile, the data preprocessing process is optimized by combining knowledge from the ship domain, such as using isolation forests for anomaly detection. Statistical analysis of ship data is also conducted, including correlation analysis of ship design parameters, analysis of outliers, and analysis of missing data types. These analyses provide the basis for the proposed model. In a case study of 8167 bulk carriers, the proposed model outperformed the missing forest (MF) and polynomial fitting (PF) models, with an average error reduction of 2.4% and 6.3%, respectively. The proposed model also showed stable performance in cases of high missing rates. This study provides a new approach for estimating or imputing critical parameters of ships.Keywords
Funding Information
- Innovation Program of the Shanghai Municipal Education Commission (2021-01-07-00-10-E00121)
This publication has 30 references indexed in Scilit:
- Maritime pattern extraction and route reconstruction from incomplete AIS dataInternational Journal of Data Science and Analytics, 2018
- Prediction of main particulars of a chemical tanker at preliminary ship design using artificial neural networkShips and Offshore Structures, 2018
- High-spatiotemporal-resolution ship emission inventory of China based on AIS data in 2014Science of The Total Environment, 2017
- Design of inferential sensors in the process industry: A review of Bayesian methodsJournal of Process Control, 2013
- Inference of Single Vessel Behaviour with Incomplete Satellite-based AIS DataJournal of Navigation, 2013
- Predictions of oil/chemical tanker main design parameters using computational intelligence techniquesApplied Soft Computing, 2011
- Treatment of missing values in process data analysisThe Canadian Journal of Chemical Engineering, 2008
- Random ForestsMachine Learning, 2001
- A Test of Missing Completely at Random for Multivariate Data with Missing ValuesJournal of the American Statistical Association, 1988
- Inference and missing dataBiometrika, 1976