Self-labelling of tugboat operation using unsupervised machine learning and intensity indicator
The actual operational data, such as a time sequence of fuel consumption and speed, is usually unlabeled or not associated with a specific activity like tugging or cruising. The operation type is critical for further analysis, as tugging and cruising operations require different fuel and navigation...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-06-01
|
| Series: | Maritime Transport Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666822X23000011 |
| _version_ | 1797798544652894208 |
|---|---|
| author | Januwar Hadi Dimitrios Konovessis Zhi Yung Tay |
| author_facet | Januwar Hadi Dimitrios Konovessis Zhi Yung Tay |
| author_sort | Januwar Hadi |
| collection | DOAJ |
| description | The actual operational data, such as a time sequence of fuel consumption and speed, is usually unlabeled or not associated with a specific activity like tugging or cruising. The operation type is critical for further analysis, as tugging and cruising operations require different fuel and navigation profiles. This paper aims to develop a self-labelling framework for tugboat operation by using unsupervised machine learning and a proposed intensity indicator. The framework considers two sets of data: the positional data and the fuel consumption rate data. The fuel consumption data is obtained from mass flowmeters installed on tugboats, while the positional data are navigational data purchased from marine data aggregators. The developed self-labelling enables ship operators in identifying operations and locations that require heavy fuel consumption andcan be used for further big data analytics and machine learning for fuel consumption prediction when vessel speeds are known. |
| first_indexed | 2024-03-13T04:06:22Z |
| format | Article |
| id | doaj.art-79c1f2255f85448e877528ab95cedbe5 |
| institution | Directory Open Access Journal |
| issn | 2666-822X |
| language | English |
| last_indexed | 2024-03-13T04:06:22Z |
| publishDate | 2023-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Maritime Transport Research |
| spelling | doaj.art-79c1f2255f85448e877528ab95cedbe52023-06-21T07:01:02ZengElsevierMaritime Transport Research2666-822X2023-06-014100082Self-labelling of tugboat operation using unsupervised machine learning and intensity indicatorJanuwar Hadi0Dimitrios Konovessis1Zhi Yung Tay2Engineering Cluster, Singapore Institute of Technology, 10 Dover Drive, Singapore 534038, SingaporeDepartment of Naval Architecture, Ocean and Marine Engineering, University of Strathclyde, 100 Montrose St, Glasgow G4 0LZ, United KingdomEngineering Cluster, Singapore Institute of Technology, 10 Dover Drive, Singapore 534038, Singapore; Corresponding author.The actual operational data, such as a time sequence of fuel consumption and speed, is usually unlabeled or not associated with a specific activity like tugging or cruising. The operation type is critical for further analysis, as tugging and cruising operations require different fuel and navigation profiles. This paper aims to develop a self-labelling framework for tugboat operation by using unsupervised machine learning and a proposed intensity indicator. The framework considers two sets of data: the positional data and the fuel consumption rate data. The fuel consumption data is obtained from mass flowmeters installed on tugboats, while the positional data are navigational data purchased from marine data aggregators. The developed self-labelling enables ship operators in identifying operations and locations that require heavy fuel consumption andcan be used for further big data analytics and machine learning for fuel consumption prediction when vessel speeds are known.http://www.sciencedirect.com/science/article/pii/S2666822X23000011Machine learningSelf-labellingIntensity indicatorsK-means clusteringFuel prediction |
| spellingShingle | Januwar Hadi Dimitrios Konovessis Zhi Yung Tay Self-labelling of tugboat operation using unsupervised machine learning and intensity indicator Maritime Transport Research Machine learning Self-labelling Intensity indicators K-means clustering Fuel prediction |
| title | Self-labelling of tugboat operation using unsupervised machine learning and intensity indicator |
| title_full | Self-labelling of tugboat operation using unsupervised machine learning and intensity indicator |
| title_fullStr | Self-labelling of tugboat operation using unsupervised machine learning and intensity indicator |
| title_full_unstemmed | Self-labelling of tugboat operation using unsupervised machine learning and intensity indicator |
| title_short | Self-labelling of tugboat operation using unsupervised machine learning and intensity indicator |
| title_sort | self labelling of tugboat operation using unsupervised machine learning and intensity indicator |
| topic | Machine learning Self-labelling Intensity indicators K-means clustering Fuel prediction |
| url | http://www.sciencedirect.com/science/article/pii/S2666822X23000011 |
| work_keys_str_mv | AT januwarhadi selflabellingoftugboatoperationusingunsupervisedmachinelearningandintensityindicator AT dimitrioskonovessis selflabellingoftugboatoperationusingunsupervisedmachinelearningandintensityindicator AT zhiyungtay selflabellingoftugboatoperationusingunsupervisedmachinelearningandintensityindicator |