Design and Development of an AIoT Architecture for Introducing a Vessel ETA Cognitive Service in a Legacy Port Management Solution
Abstract
:1. Introduction
- RQ1. How to extend an IoT architecture to integrate in it cognitive services?
- RQ2. Is it possible to create and integrate in a commercial legacy system a reliable cognitive service based on ML algorithms that gives an accurate prediction of a vessel’s ETA using IoT data sources?
- RQ3. Which IoT data sources provide the greatest feature importance?
Research Contributions
2. Materials and Methods
2.1. Methodology
2.1.1. Problem Identification and Work Objectives Establishment
2.1.2. Requirements Elicitation
2.1.3. System Architecture Design
2.1.4. Development
2.1.5. Integration
2.1.6. Validation
2.2. System Architecture
- The port service is a real-time vessel activity monitoring system that detects multiple events in the life cycle of a vessel in port and allows us to automate actions and assist a port operator in controlling the vessel’s visit to the port.
- AIS and Weather NGSI adapters have been developed to insert in the system the AIS data gathered by the antenna and the weather conditions.
- Orion Context Broker (OCB) works as an aggregator of context data and, at the same time, is an interface between the components of the architecture. Hence, the other elements of a FIWARE system can publish or consume data without having specific knowledge about the rest of the system.
- A specific context adapter has been developed for this scenario. It is responsible for ensuring that data coming from the port service are transformed to be compliant with the FIWARE NGSI standard. It handles redirected requests (updateContext) and notification requests (notify) sent by the OCB, transforming them into requests to the web interface.
- The cognitive component offers services based on the use of cognitive algorithms. This element retrieves data from a variety of sources and is able to send the results and decisions to other FIWARE components. ML algorithm-based models are embedded in this component to give rise to an AIoT system.
- A complex event processor (CEP) analyzes event data in real-time, detecting patterns in the incoming events. The CEP can receive events from different event producers of the FIWARE platform. In this case, the CEP analyzes the difference between the planned ETA and the calculated ETA. Depending on the degree of deviation between both values, it will send a notification, warning, or alarm to the port service.
2.2.1. Cognitive Component
2.2.2. Message Flow
3. Results and Discussion
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Conflicts of Interest
Appendix A
References
- United Nations. Review of Maritime Transport. 2020. Available online: https://unctad.org/system/files/official-document/rmt2020_en.pdf (accessed on 29 November 2021).
- John, M.; Chandra, L.; Brian, F. Port centric logistics. Int. J. Logist. Manag. 2008, 19, 29–41. [Google Scholar]
- Wen, Y.; Huang, Y.; Zhou, C.; Yang, J.; Xiao, C.; Wu, X. Modelling of marine traffic flow complexity. Ocean Eng. 2015, 104, 500–510. [Google Scholar] [CrossRef]
- Long, A. Port community systems. World Cust. J. 2009, 3, 63–67. [Google Scholar]
- Carlan, V.; Sys, C.; Vanelslander, T. How port community systems can contribute to port competitiveness: Developing a cost–benefit framework. Res. Transp. Bus. Manag. 2016, 19, 51–64. [Google Scholar] [CrossRef]
- Tongzon, J.; Heng, W. Port privatization, efficiency and competitiveness: Some empirical evidence from container ports (terminals). Transp. Res. Part A Policy Pract. 2005, 39, 405–424. [Google Scholar] [CrossRef]
- Rodrigue, J.-P.; Notteboom, T. The terminalization of supply chains: Reassessing the role of terminals in port/hinterland logistical relationships. Marit. Policy Manag. 2009, 36, 165–183. [Google Scholar] [CrossRef]
- Sciomachen, A.; Acciaro, M.; Liu, M. Operations research methods in maritime transport and freight logistics. Marit. Econ. Logist. 2009, 11, 1–6. [Google Scholar] [CrossRef] [Green Version]
- Fancello, G.; Pani, C.; Pisano, M.; Serra, P.; Zuddas, P.; Fadda, P. Prediction of arrival times and human resources allocation for container terminal. Marit. Econ. Logist. 2011, 13, 142–173. [Google Scholar] [CrossRef]
- Werner, M.J., IX. Directive 2002/59/EC establishing a Community vessel traffic monitoring and information system and repealing Council Directive 93/75/EEC. In EU Maritime Transport Law, 1st ed.; Jessen, H., Werner, M.J., Eds.; Nomos Verlagsgesellschaft mbH & Co. KG: Baden-Baden, Germany, 2016; pp. 920–954. [Google Scholar]
- Gómez, R.; Camarero, A.; Molina, R. Development of a vessel-performance forecasting system: Methodological framework and case study. J. Waterw. Port Coast. Ocean Eng. 2016, 142, 4015016. [Google Scholar] [CrossRef]
- Katsilieris, F.; Braca, P.; Coraluppi, S. Detection of malicious AIS position spoofing by exploiting radar information. In Proceedings of the 16th International Conference on Information Fusion, Istanbul, Turkey, 9–12 July 2013; pp. 1196–1203. [Google Scholar]
- Baldauf, M.; Benedict, K. Aspects of Technical Reliability of Navigation Systems and Human Element in Case of Collision Avoidance. In Proceedings of the Navigation Conference & Exhibition, London, UK, 28 October 2008. [Google Scholar]
- Pan, T.; Song, Y.; Chen, S. Wiener model identification using a modified brain storm optimization algorithm. Intell. Autom. Soft Comput. 2020, 26, 934–947. [Google Scholar] [CrossRef]
- Thamotharan, B.; Venkatraman, B.; Chandrasekaran, S. Identification and segmentation of impurities accumulated in a cold-trap device by using radiographic images. Intell. Autom. Soft Comput. 2020, 26, 335–340. [Google Scholar] [CrossRef]
- Pallotta, G.; Vespe, M.; Bryan, K. Vessel Pattern Knowledge Discovery from AIS Data: A Framework for Anomaly Detection and Route Prediction. Entropy 2013, 15, 2218. [Google Scholar] [CrossRef] [Green Version]
- Mao, S.; Tu, E.; Zhang, G.; Rachmawati, L.; Rajabally, E.; Huang, G.-B. An Automatic Identification System (AIS) Database for Maritime Trajectory Prediction and Data Mining BT. In Proceedings of ELM-2016; Springer: Cham, Switzerland, 2018; pp. 241–257. [Google Scholar]
- Meijer, R. Predicting the ETA of a Container Vessel Based on Route Identification Using AIS Data. Master’s Thesis, Delft University of Technology, Delft, The Netherlands, 2017. [Google Scholar]
- Parolas, I. ETA Prediction for Containerships at the Port of Rotterdam Using Machine Learning Techniques. 2016. Available online: http://resolver.tudelft.nl/uuid:9e95d11f-35ba-4a12-8b34-d137c0a4261d (accessed on 29 November 2021).
- Alessandrini, A.; Mazzarella, F.; Vespe, M. Estimated Time of Arrival Using Historical Vessel Tracking Data. IEEE Trans. Intell. Transp. Syst. 2019, 20, 7–15. [Google Scholar] [CrossRef]
- Dobrkovic, A.; Iacob, M.-E.; van Hillegersberg, J.; Mes, M.R.K.; Glandrup, M. Towards an Approach for Long Term AIS-Based Prediction of Vessel Arrival Times BT—Logistics and Supply Chain Innovation: Bridging the Gap between Theory and Practice; Zijm, H., Klumpp, M., Clausen, U., ten Hompel, M., Eds.; Springer International Publishing: Cham, Switzerland, 2016; pp. 281–294. [Google Scholar]
- Pani, C.; Vanelslander, T.; Fancello, G.; Cannas, M. Prediction of Late/Early Arrivals in Container Terminals—A Qualitative Approach. 2015. Available online: https://iris.unica.it/handle/11584/188788 (accessed on 29 November 2021).
- Bodunov, O.; Schmidt, F.; Martin, A.; Brito, A.; Fetzer, C. Real-time destination and eta prediction for maritime traffic. In Proceedings of the 12th ACM International Conference on Distributed and Event-Based Systems, Hamilton, New Zealand, 25–29 June 2018; pp. 198–201. [Google Scholar]
- Watson Studio. Available online: https://www.ibm.com/es-es/cloud/watson-studio/faq (accessed on 29 November 2021).
- Google AI. Available online: https://ai.google/tools/ (accessed on 29 November 2021).
- Azure Machine Learning. Available online: https://azure.microsoft.com/es-es/services/machine-learning/ (accessed on 29 November 2021).
- Azure Cognitive Services. Available online: https://azure.microsoft.com/es-es/services/cognitive-services/ (accessed on 29 November 2021).
- Amazon AWS AI. Available online: https://aws.amazon.com/machine-learning/ (accessed on 29 November 2021).
- Pramanik, P.K.D.; Pal, S.; Choudhury, P. Beyond automation: The cognitive IoT. Artificial intelligence brings sense to the Internet of Things. In Cognitive Computing for Big Data Systems over IoT; Springer: Cham, Switzerland, 2018; pp. 1–37. [Google Scholar]
- Robertson, J.; Robertson, S. Volere. Requirements Specification Templates. 2000. Available online: https://www.cs.uic.edu/~i442/VolereMaterials/templateArchive16/c%20Volere%20template16.pdf (accessed on 29 November 2021).
- Peffers, K.; Tuunanen, T.; Rothenberger, M.A.; Chatterjee, S. A design science research methodology for information systems research. J. Manag. Inf. Syst. 2007, 24, 45–77. [Google Scholar] [CrossRef]
- Hevner, A.R.; March, S.T.; Park, J.; Ram, S. Design science in information systems research. MIS Q. 2004, 28, 75–105. [Google Scholar] [CrossRef] [Green Version]
- Docker. Available online: https://www.docker.com (accessed on 29 November 2021).
- World Weather Online. Available online: https://www.worldweatheronline.com/developer/api/docs/marine-weather-api.aspx (accessed on 29 November 2021).
- Liu, H.; Setiono, R. Incremental feature selection. Appl. Intell. 1998, 9, 217–230. [Google Scholar] [CrossRef]
- Pickle. Available online: https://docs.python.org/3/library/pickle.html (accessed on 29 November 2021).
- Posidonia Operations. Available online: https://www.prodevelop.es/puertos/posidonia/posidonia-operations (accessed on 29 November 2021).
- PortEconomics. Available online: https://www.porteconomics.eu (accessed on 29 November 2021).
Feature | Importance |
---|---|
Distance | 0.188072 |
Longitude | 0.183474 |
Latitude | 0.167127 |
SOG | 0.142248 |
COG | 0.128106 |
Heading | 0.103996 |
Draught | 0.086977 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Valero, C.I.; Ivancos Pla, E.; Vaño, R.; Garro, E.; Boronat, F.; Palau, C.E. Design and Development of an AIoT Architecture for Introducing a Vessel ETA Cognitive Service in a Legacy Port Management Solution. Sensors 2021, 21, 8133. https://doi.org/10.3390/s21238133
Valero CI, Ivancos Pla E, Vaño R, Garro E, Boronat F, Palau CE. Design and Development of an AIoT Architecture for Introducing a Vessel ETA Cognitive Service in a Legacy Port Management Solution. Sensors. 2021; 21(23):8133. https://doi.org/10.3390/s21238133
Chicago/Turabian StyleValero, Clara I., Enrique Ivancos Pla, Rafael Vaño, Eduardo Garro, Fernando Boronat, and Carlos E. Palau. 2021. "Design and Development of an AIoT Architecture for Introducing a Vessel ETA Cognitive Service in a Legacy Port Management Solution" Sensors 21, no. 23: 8133. https://doi.org/10.3390/s21238133
APA StyleValero, C. I., Ivancos Pla, E., Vaño, R., Garro, E., Boronat, F., & Palau, C. E. (2021). Design and Development of an AIoT Architecture for Introducing a Vessel ETA Cognitive Service in a Legacy Port Management Solution. Sensors, 21(23), 8133. https://doi.org/10.3390/s21238133