One of the biggest problems facing the marine industry globally is properly navigating ships during bad weather. Ensuring ship safety in inclement weather circumstances becomes crucial in today's interconnected world, which is defined by the globalization of trade and the reliance on maritime transportation for the flow of goods and commodities. To reduce risks and improve maritime safety, sophisticated monitoring and prediction systems must be developed and put into use. To ensure the timely passage of ships through hazardous waters with a particular focus on contrasting the performance of the k-Nearest Neighbors (KNN) algorithm with the Random Forest algorithm, this study investigates the efficacy of machine learning techniques in enhancing ship safety during inclement weather. The KNN algorithm demonstrated superior performance, achieving an accuracy of 96.63%, compared to Random Forest accuracy of 91.63%. Thus, the findings of this study advocate for the adoption of KNN is the preferred predictive modelling technique for ensuring ship safety in tumultuous maritime environments, paving the way for more effective risk management strategies and enhanced maritime operations.
Enhancing Ship Navigation Safety Through K-Nearest Neighbor on Monitoring of Adverse Weather Conditions
22.11.2024
625635 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Ship propulsion under adverse weather conditions
Engineering Index Backfile | 1937
|Ship propulsion under adverse weather conditions
Engineering Index Backfile | 1936
|Ship propulsion under adverse weather conditions
Engineering Index Backfile | 1936
|Ship propulsion under adverse weather conditions
Engineering Index Backfile | 1937
|British Library Online Contents | 2015
|