
Port and vessel networks increasingly operate on IP/Ethernet backbones with high-noise, high-dimensional traffic. We present a lightweight hybrid intrusion-detection model that couples a variational autoencoder (VAE) with a multilayer perceptron (MLP) and augments training with a boundary-oriented latent-space mixup strategy. The VAE models the distribution of normal traffic and identifies anomalies through reconstruction errors. Subsequently, it generates robust latent vectors, enabling the MLP to perform highly accurate supervised classification. On the UNSW-NB15 dataset, the proposed pipeline attains >= 97% accuracy and an outstanding recall of 99.56% in binary intrusion detection, and visualization of the latent-space (PCA) together with reconstruction-error analyses and the confusion matrix corroborates clear anomaly separation. The model uses a compact design. The VAE produces latent representations, and an MLP classifies them. With latent-space mixup, it detects new anomalies and reliably classifies known threats, making it suitable for smart-port monitoring and ship-communication security at the edge.
Maritime ship detection is of great significance for both military security and civilian applications. Synthetic Aperture Radar (SAR), with its all-weather and all-day imaging capability, plays a vital role in maritime surveillance. Nevertheless, SAR ship targets typically appear small in scale, embedded in complex backgrounds, blurred at boundaries, and easily confused with near-shore features, which pose substantial challenges for accurate detection. To address these issues, we propose a SAR ship detection network that integrates dual enhancements of small-object representation and edge information. The network introduces two key components: the Small Target Refine Pyramid (STRP) to strengthen shallow feature representation for small targets, and the Edge Information Enhancement and Propagation Mechanism (EIEP) to refine and transmit boundary cues. Additionally, a customized bounding box regression loss, Focaler-MPDIoU, is designed to improve localization accuracy and robustness to complex object morphologies. Experiments on benchmark SAR ship detection datasets (HRSID, SSDD, and LS-SSDD) demonstrate that the proposed method achieves superior performance compared with both classical and state-of-the-art detection models.
The shipboard safety management system (SMS) is designed to enhance safe operations, risk management, and emergency response to improve overall ship safety and efficiency. This paper demonstrates the use of an engine room simulator (ERS) for collecting failure modes and applies it to a comprehensive failure analysis of the stern tube lubricating oil system. A new risk closeness coefficient method was developed, integrating expert background knowledge and weighted risk assessments. The analysis, based on multiple expert evaluations, covered five subsystems, eight main components, 23 failure modes, and 112 failure causes. This study presents 26 recommendations for maritime practitioners and onboard operators to prevent and mitigate risks. A comparative analysis highlights the differences between the AHP-EMM and traditional FMEA methods.
We developed a two-scale time series framework using monthly container throughput (20-foot equivalent units, TEU) as a port activity indicator. Applied to Kaohsiung, Taiwan (2017-2024), we related TEU to near-port NO2 and PM2.5 (monthly) and air quality to outpatient respiratory diagnoses (weekly) across the 2019-2020 sulfur rules and the COVID-19 pandemic. Transfer-function models indicate TEU tends to lead near-port NO2 by 6-9 months. Structural break tests at policy dates indicate nonsignificant changes in levels and slopes, suggesting gradual rather than abrupt shifts in the activity-pollution linkage. Weekly two-pollutant distributed-lag Poisson models estimated relative risks (lags 0-8) per interquartile range (IQR) increase. For acute upper respiratory infection, NO(2)was associated with higher risk (RR, 1.184; 95% CI, 1.032-1.358), whereas PM2.5 estimates were null (RR, 1.032; 95% CI, 0.917-1.161). Pre-specified negative-control endpoints yielded mixed-sign associations, which were interpreted as residual design noise rather than a coherent nonrespiratory signal. Combining TEU statistics with meteorology-adjusted NO2 helps screen whether maritime policies and operational changes coincide with air-quality shifts and respiratory risk. This approach requires only publicly reported TEU statistics, routine air-quality monitoring, and syndromic outpatient counts, and is therefore feasible in settings where AIS-based ship-activity metrics or detailed emissions inventories are unavailable.
Following the COVID-19 pandemic, the global tourism industry has steadily recovered since 2022. Island-hopping cruises have gained increasing attention for enhancing regional connectivity and diversifying marine travel experiences; however, their development in Asia remains limited compared with that in Europe and the Caribbean due to fragmented policy coordination, inadequate port infrastructure, and uneven technological readiness. Although Taiwan possesses a geographic advantage and can serve as a strategic hub linking Asian island destinations, systematic planning and stakeholder coordination remain insufficient, resulting in unclear mechanisms that drive or constrain island-hopping cruise tourism. Existing studies mainly focus on market demand or passenger behavior, while limited attention has been paid to the system-level causal structure and critical driving factors. To address this research gap and corresponding industrial challenges, this study identifies the key influencing factors and their interrelations from Taiwan's perspective using a hybrid multi-criteria decision-making approach integrating the Fuzzy Decision-Making Trial and Evaluation Laboratory (FDEMATEL) and an FDEMATEL-based Analytic Network Process (FDANP). The framework was established through political, economic, social, technological, environmental, and legal (PESTEL) analysis and validated using a modified Delphi method. The results indicate that political and technological dimensions are core causal drivers, while government-driven policies for cruise industry development represent the most critical criterion. This study elucidates the causal structure among factors and provides actionable implications for policymakers to strengthen policy integration, enhance technological innovation, and promote sustainable island-hopping cruise tourism in Asia, with Taiwan serving as a strategic reference context rather than representing the entire Asia-Pacific region.