Abstract
In this paper the author tests and compares the use of multiple regression algorithms like Artificial Neural Network (ANN), Decision Tree Regressor (DTRs), Random Forest Regressor (RFR), K-Nearest Neighbor (kNN), Linear Regression and AdaBoost, on the prediction of ships main engine required power. This data driven approach is based on real values that are collected from a ship’s onboard Automated Data Logging & Monitoring (ADLM) system in a period of six months. Two separated set of Algorithm benchmark tests are caried out and compared: one with the use of the above complete data set and the second with the use of a preprocessed one that is constructed from the original, with the use of a combination of statistical inference methods as well as the knowledge of the physical principles. The study shows that with the use of Artificial intelligence (through Machine Learning) and proper data preprocessing we can achieve prediction results that are below an 3% error percentage in 99.31% of the respective values.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
