ORGANIZING THE COUNTRY'S DREDGING VESSELS BASED ON DATA MINING TECHNIQUES BASED ON ARTIFICIAL NEURAL NETWORKS AND BAYESIAN NETWORKS IN IBM MODELER SOFTWARE
Dredging is often done by a special floating device called a dredger. The important goals in dredging are usually obtaining more water depth or extracting materials that have special value or use. Consideration of risk management is based on data mining techniques in the IBM Modeler environment. The method used in this research is the quantitative analysis method based on data mining techniques in the IBM Modeler environment. This research is of an exploratory type, and for this reason we do not hypothesize. The information required for this research is obtained by using field techniques, library, Observations and interviews and technical meetings held with experts have been obtained. The main findings of the research for organizing the country’s dredging vessels, considering risk management, are as follows: By implementing the results of this study in the Ports and Maritime Organization, the performance of “reducing dredging operation time in various ports (I1)” equals 0.07; “risk control aimed at enhancing security in ports (I2)” equals 0.10; “improving maritime traffic conditions index (I3)” equals 0.06; “allocation based on the number of existing dredgers and their capacity (I4)” equals 0.17; “allocation based on the environmental conditions of the region (I5)” equals 0.07, and “allocation based on reducing the costs of dredging projects in ports (I6)” equals 0.13. These contribute to a 25% improvement in the organization of the country’s dredging vessels with risk management considered. Dredging is a relatively costly technique. However, employing suitable and efficient equipment can reduce these costs. Among the main challenges are the allocation of dredgers, the release of toxic substances, and environmental damage.
Data Mining Techniques, Artificial Neural Networks, Bayesian Networks, Dredging Vessels, IBM Modeler Software.