This study forecasts pangasius export volumes in the Mekong Delta for the period 2026-2035 to provide a basis for planning and developing the logistics service chain. Based on quarterly time series data from 2014 to 2025, a time series linear regression model is first employed to establish the underlying growth trend; however, it fails to capture the seasonal characteristics of the data. Therefore, the Holt-Winters model is applied to simultaneously account for both trend and seasonality, indicating that export volumes may reach approximately 938 thousand tons by 2035. Nevertheless, this approach is limited in long-term forecasting due to its assumption of structural continuity from the past. To address this limitation, the study incorporates an uncertainty forecasting approach based on Uncertainty Theory, integrating expert judgment to reflect the potential range of market fluctuations. The results suggest that the expected export volume in 2035 is approximately 917 thousand tons. The study contributes by proposing an integrated approach combining statistical models and uncertainty-based methods, providing a reference for the development of logistics service systems supporting pangasius exports in the Mekong Delta.

Conventional amplitude-based indicators may be insufficient to characterise the effects of varying crack elevation in offshore wind turbine towers. To address this limitation, a bidirectional multi-feature sensitivity analysis was conducted using a finite element model based on the NREL 5 MW reference wind turbine. Transient dynamic analyses were performed in ANSYS under combined stochastic wind–wave loading. One intact case and five cracked cases with identical crack dimensions but different elevations were considered. Acceleration responses in the X and Y directions were extracted at eight measurement points. The root-mean-square value, peak absolute acceleration, dominant frequency, and frequency-band energy indices were calculated, and their sensitivities to variations in crack elevation were quantified using the absolute relative change with respect to the intact case. Under the adopted loading conditions, the X-direction response exhibited a larger overall amplitude. However, the RMS and frequency-band energy indices exhibited higher relative sensitivities in the Y direction, whereas the peak-value sensitivity was higher in the X direction. No detectable change in dominant frequency was observed at the adopted frequency resolution. Among the investigated features, the frequency-band energy in the 0–0.05 Hz band exhibited the highest sensitivity in both directions. Among the eight candidate measurement points, P1 showed the highest sensitivity under the considered loading and crack cases, and the sensitivity generally decreased with increasing measurement height. These findings provide a basis for damage-sensitive feature selection and sensor-layout optimisation in crack monitoring of offshore wind turbine towers.

This study proposes a systematic cargo securing method for non-standard cargoes loaded on general cargo ships in Incheon Port. Despite the increasing transportation of non-standard cargoes with different shapes and characteristics, there are insufficient detailed securing standards, which frequently causes cargo damage and disputes among ship operators, shipping companies, and stevedores. In this study, international regulations including SOLAS and the CSS Code, as well as cargo securing manuals, were analyzed to establish systematic securing criteria for non-standard cargoes. In addition, external force calculations and safety factor criteria were applied to evaluate the securing safety according to vehicle weight categories. Based on the analysis, securing arrangements including the number and placement of lashing devices were proposed for each cargo weight range. The proposed securing methods were verified by comparing external forces and calculated securing strengths. The results confirm that the proposed methods can provide safe and practical securing standards for non-standard cargoes. Furthermore, the proposed approach is expected to contribute to the standardization of field operations, reduction of cargo damage, and prevention of disputes related to cargo securing.

Recent advances in Maritime Autonomous Surface Ships (MASS) and e-Navigation technologies have increased the demand for decision support systems based on real-time maritime environmental information. In rough weather conditions, navigators are required to comprehensively assess wave conditions, atmospheric pressure, and wind variations. However, such decisions are still highly dependent on the experience and judgment of individual navigators. Therefore, quantitative decision support techniques are required for autonomous and remotely operated ships. This study proposes a rough weather navigation decision support system based on real-time wave observation data. The proposed system utilizes an X-band radar-based wave observation system to estimate significant wave height and employs a fuzzy inference engine with atmospheric pressure information to calculate heavy weather risk. In addition, a ship-tonnage compensation module is introduced to reflect the different impacts of rough weather according to vessel size. The calculated risk is used as an input to the Enhanced Recommend System under Rough Weather (RRW) algorithm. Based on the relative position of the vessel to a typhoon, the system recommends either Heave-to maneuvering in the dangerous semicircle or Scudding maneuvering in the navigable semicircle. Simulation results show that the proposed system appropriately estimates heavy weather risk according to wave height and atmospheric pressure conditions. Furthermore, the Enhanced RRW algorithm is activated only when the estimated risk exceeds a predefined threshold, thereby reducing unnecessary maneuvering actions. The proposed system can support safe navigation of conventional merchant ships and is expected to be applicable to decision support systems for MASS and remote ship operation environments.

Printed circuit board (PCB) defect inspection is a key task in industrial automatic optical inspection (AOI). Its deployment in low-label scenarios remains difficult because PCB defects are often small, weakly contrasted, and unevenly distributed across categories and scales. Semi-supervised object detection can reduce annotation demand by using unlabelled images, but its performance depends strongly on the reliability of pseudo labels. In PCB inspection, confidence scores are shaped not only by defect category but also by object scale, which makes fixed or class-only filtering insufficient for small-defect supervision. This paper proposes dual-granularity pseudo-label calibration (DGPC) for semi-supervised PCB surface defect detection. DGPC first fuses weak-view and strongview teacher predictions into a unified candidate pool. It then estimates pseudo-label thresholds from both classlevel and class–scale statistics, and applies a scale-dependent lower-bound relaxation to retain informative smalldefect candidates. The method is applied only during training and leaves the detector architecture and inference procedure unchanged. Experiments on Deep PCB at 5%, 10%, and 20%labeled ratios show that DGPC improves pseudo-label-based training under low-label settings. The gains are most consistent when the teacher provides a sufficiently informative candidate pool, especially at 10% and 20% labelled ratios. Ablation, stability, crossdetector, pseudo-label statistics, scale-wise, qualitative, and sensitivity analyses show that class–scale-aware calibration improves pseudo-label selection for annotation-efficient PCB inspection.