Benchmarking feed-forward randomized neural networks for vessel trajectory prediction
The burgeoning scale and speed of maritime vessels present escalating challenges to navigational safety. Perceiving the motions of vessels, identifying anomalies, and risk warnings are crucial. Central to addressing these challenges is the analysis of vessel trajectories, which are pivotal for anoma...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/180801 |
| _version_ | 1824455450732527616 |
|---|---|
| author | Cheng, Ruke Liang, Maohan Li, Huanhuan Yuen, Kum Fai |
| author2 | School of Civil and Environmental Engineering |
| author_facet | School of Civil and Environmental Engineering Cheng, Ruke Liang, Maohan Li, Huanhuan Yuen, Kum Fai |
| author_sort | Cheng, Ruke |
| collection | NTU |
| description | The burgeoning scale and speed of maritime vessels present escalating challenges to navigational safety. Perceiving the motions of vessels, identifying anomalies, and risk warnings are crucial. Central to addressing these challenges is the analysis of vessel trajectories, which are pivotal for anomaly detection and risk mitigation. This study introduces an innovative approach to time series vessel trajectories, focusing on the Chengshantou waters. We implement and rigorously compare seven feed-forward neural network models, including random vector functional link neural network without direct links (RVFLwoDL), deep RVFLwoDL (DRVFLwoDL), ensemble deep RVFLwoDL (edRVFLwoDL), random vector functional link neural network (RVFL), deep RVFL (DRVFL), ensemble deep RVFL (edRVFL), and broad learning system (BLS). Our evaluation, utilizing diverse error metrics and datasets from various waterways, reveals the superior performance of the RVFL-based models with direct links in trajectory prediction. The findings underscore the critical role of direct links in enhancing the representational and generalization capabilities of RVFL models, thus offering robust and reliable prediction solutions. |
| first_indexed | 2025-02-19T03:38:24Z |
| format | Journal Article |
| id | ntu-10356/180801 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:38:24Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1808012024-10-28T02:42:44Z Benchmarking feed-forward randomized neural networks for vessel trajectory prediction Cheng, Ruke Liang, Maohan Li, Huanhuan Yuen, Kum Fai School of Civil and Environmental Engineering Engineering Trajectory prediction Random vector functional link The burgeoning scale and speed of maritime vessels present escalating challenges to navigational safety. Perceiving the motions of vessels, identifying anomalies, and risk warnings are crucial. Central to addressing these challenges is the analysis of vessel trajectories, which are pivotal for anomaly detection and risk mitigation. This study introduces an innovative approach to time series vessel trajectories, focusing on the Chengshantou waters. We implement and rigorously compare seven feed-forward neural network models, including random vector functional link neural network without direct links (RVFLwoDL), deep RVFLwoDL (DRVFLwoDL), ensemble deep RVFLwoDL (edRVFLwoDL), random vector functional link neural network (RVFL), deep RVFL (DRVFL), ensemble deep RVFL (edRVFL), and broad learning system (BLS). Our evaluation, utilizing diverse error metrics and datasets from various waterways, reveals the superior performance of the RVFL-based models with direct links in trajectory prediction. The findings underscore the critical role of direct links in enhancing the representational and generalization capabilities of RVFL models, thus offering robust and reliable prediction solutions. 2024-10-28T02:42:43Z 2024-10-28T02:42:43Z 2024 Journal Article Cheng, R., Liang, M., Li, H. & Yuen, K. F. (2024). Benchmarking feed-forward randomized neural networks for vessel trajectory prediction. Computers and Electrical Engineering, 119, 109499-. https://dx.doi.org/10.1016/j.compeleceng.2024.109499 0045-7906 https://hdl.handle.net/10356/180801 10.1016/j.compeleceng.2024.109499 2-s2.0-85199873503 119 109499 en Computers and Electrical Engineering © 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. |
| spellingShingle | Engineering Trajectory prediction Random vector functional link Cheng, Ruke Liang, Maohan Li, Huanhuan Yuen, Kum Fai Benchmarking feed-forward randomized neural networks for vessel trajectory prediction |
| title | Benchmarking feed-forward randomized neural networks for vessel trajectory prediction |
| title_full | Benchmarking feed-forward randomized neural networks for vessel trajectory prediction |
| title_fullStr | Benchmarking feed-forward randomized neural networks for vessel trajectory prediction |
| title_full_unstemmed | Benchmarking feed-forward randomized neural networks for vessel trajectory prediction |
| title_short | Benchmarking feed-forward randomized neural networks for vessel trajectory prediction |
| title_sort | benchmarking feed forward randomized neural networks for vessel trajectory prediction |
| topic | Engineering Trajectory prediction Random vector functional link |
| url | https://hdl.handle.net/10356/180801 |
| work_keys_str_mv | AT chengruke benchmarkingfeedforwardrandomizedneuralnetworksforvesseltrajectoryprediction AT liangmaohan benchmarkingfeedforwardrandomizedneuralnetworksforvesseltrajectoryprediction AT lihuanhuan benchmarkingfeedforwardrandomizedneuralnetworksforvesseltrajectoryprediction AT yuenkumfai benchmarkingfeedforwardrandomizedneuralnetworksforvesseltrajectoryprediction |