The aim of this study is to apply a collision warning algorithm for a small fishing vessel in a fishing waterway to verify its alarm operation and to validate its feasibility. For this purpose, a scenario-based real ship test was conducted, and cases extracted from real sea data (Vpass data) were applied. Moreover, zones with frequent alarms and high-risk waters were compared. First, we installed millimeter-wave communication terminals in three small fishing vessels and applied our algorithm based on two scenarios. Furthermore, we applied the collision warning algorithm by extracting two cases encountered by multiple ships from the Vpass data. The results show that the algorithm triggered alarms continuously under risky situations. This study also compares waterway risk levels as assessed by maritime risk-assessment tools (potential assessment of risk model, environment stress model, and International Association of Marine Aids to Navigation and Lighthouse Authorities Waterway Risk Assessment Program MkII) and the locations having frequent alarms based on Vpass data collected for 7 days. Not only did the eastern sea of Yeongheung Island indicate that more alarms were triggered, but we found high-risk results from the risk-level assessment, indicating that the risky zones and the frequent alarm zones were identical. Additional research is necessary to develop an algorithm based on qualitative evaluation by actual ship operators. In addition, since fishing vessels navigate differently from general navigation methods during fishing, it is necessary to develop additional algorithms for this.

Maritime collisions pose significant risks, prompting the need for robust risk assessment models to enhance safety measures. This study endeavors to develop a comprehensive ship collision risk model reflecting the intricate marine traffic environment in South Korea. Through a survey of experienced maritime personnel and a random forest model analysis, an evaluation model integrating internal and external factors was devised. Internal factors were determined through conjoint analysis, emphasizing encounter relationships, separation distance, and vessel speed. External risk factors were established using a random forest model based on historical collision data. The model’s efficacy was then applied to and validated in the vicinity of Busan Port, a region with complex marine traffic. The resulting risk map highlighted high‐risk areas, offering valuable insights for risk management and policy formulation. This model provides a foundational framework for maritime safety policy decisions, representing a significant contribution to collision risk assessment methodologies.

Marine pilot occupational accidents during transfer to/from ships are the primary concern of the International Marine Pilots’ Association (IMPA) and industry professionals. There are multiple transfer methods for marine pilots, with the most common being the pilot boat. To reach the mother ship bridge, the following stages must be safely completed: car transfer, walking on the pier, pier to pilot boat, pilot transfer by boat, cutter to pilot ladder, mother ship freeboard climbing, and ship deck to the bridge. Each stage has its own risk. Previous accident records and expert opinions are commonly used to conduct a risk analysis and take preventive actions. However, the reports vary in scope and are often complex, making qualitative analysis a timeintensive task. To overcome this challenge, this study aggregates 500 reports to create a multi-source dataset describing instances of undesired events. A ML(machine learning) approach is used to predict and explain marine pilot occupational accidents. Analyzing the importance of factors distinguishing between accidents, incidents, and non-compliance, we conclude that workplace factors are more dangerous than environmental factors. The findings of this study provide a foundation for developing a unified accident reporting system for predicting accidents on a wider scale.

As a method of reviewing the design of new fairways and the redesign of existing fairways, we proposed a fairway design plan based on the collision and grounding probability, considering vessel traffic. A case study was conducted on the four traffic separation schemes (TSS) on the southern coast, which is the most complex coast among Korean coastal waters. The evaluation items of Korea’s Maritime Traffic Safety Assessment Scheme, the PIANC Guide, and the Port and Fishing Port Design Standards were all satisfied; however, some fairways had very high ship congestion at specific times, exceeding the fairway capacity. For each target fairway, the collision risk using the environmental stress (ES) model and the grounding risk using the IWRAP Mk II Model were analyzed. The grounding risk was found to be equally good, but the aggregation environmental stress ($E{S}_A$) value, according to the ES model, was high in three fairways. The widths of the three fairways with high risk were partially expanded, and, thus, were re-evaluated. The overall $E{S}_A$ was reduced, and the psychological burden of operators due to the marine environment, such as the fairways, was significantly eased. Based on the results of this study, it would be beneficial to apply a design scheme using collision and stranded risk models when designing new fairways or reviewing existing fairways. An appropriate fairway design plan is prepared that, through further research using various evaluation models and techniques, could be useful in coastal waters in the future.

This work quantitatively analyses vessel traffic service (VTS) communications in ports and suggests improvements for more efficient control of the service. For this purpose, analysis of VTS communications was performed on VHF channel 12 in Busan North Port, South Korea. This communications service follows the queue of M/G/1 (the arrivals have a Poisson distribution, the service time is characterized by a general distribution, and with a single server). The degree of congestion of the communication channel was shown as the utilisation rate of the queue, which was 67·7% at peak times and 29·6% at non-peak times. To reduce congestion in the communication channel, we propose to separate the peak time control channel, exclude passing reporting, and decrease the reporting time. With separation of the peak time control channel, the utilisation rate decreased by 41·1%. The utilisation rate decreased by 5·7% when passing reporting was omitted, and by 8·3% when reporting time was reduced by 60%. The results of this study can be used as basic policy data to improve VTS, including reinforcement of the VTS officer's role and adjustment of the control report contents.