Honghan Bei

Port State Control (PSC) is critical to maritime safety, yet its efficacy is hindered by limited inspection resources, the challenge of accurately identifying high-risk vessels, underutilized semantic information in unstructured defect texts, and severe class imbalance and label noise in inspection data that degrade predictive performance. To address these issues, this study proposes a semantic-driven risk prediction framework integrating natural language processing and advanced ensemble learning, with tailored AI innovations and targeted engineering applications in maritime regulatory practice.We develop a hybrid architecture of maritime pre-trained language and sentence-level transformer embedding networks to extract and encode defect semantic content and severity, converting unstructured text into informative industrial data analysis risk features..An improved Extreme Gradient Boosting (XGBoost) model is designed by incorporating Focal Loss for hard-sample learning and an Adaptive Semantic Weighting (ASW) mechanism for noise mitigation, enhancing the robustness of ensemble learning for imbalanced and noisy industrial datasets.Semantically Enhanced Adaptive Gradient Boosting(SHAP)-based analysis is further adopted to boost model interpretability and uncover nonlinear feature interactions. Validated on real-world 2021–2023 Paris Memorandum of Understanding PSC inspection data, the framework achieves an Area Under the Curve (AUC) of 0.767, outperforming baseline models relying solely on structured data, and reveals key risk interaction patterns such as the amplification effect between vessel age and engine-room-related deficiencies. As an intelligent decision-support tool for PSC practice, it boosts high-risk vessel identification precision, optimizes port inspection resource allocation, and advances data-driven maritime safety management, offering a scalable AI solution for maritime regulatory engineering demands.

Improving transport efficiency is challenging for multimodal transport participants to improve cost-effectiveness. This paper proposes to select city nodes and establish a multi-objective fuzzy optimization model with mixed time window constraints to consider customer demand and transportation time uncertainty. T-rex Optimization algorithm (TROA) is used to solve the problem, which efficiently lowers transportation costs and carbon emissions and has higher precision and dependability than Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). The efficacy of this method is proven using the example of the multimodal transportation network in China’s central-eastern economic zone. These findings provide potential solutions for multimodal transportation aimed at enhancing transportation efficiency.

To address the imbalanced data problem in classification, the studies of the combination of AdaBoost, short for “Adaptive Boosting,” and cost-sensitive learning have shown convincing results in the literature. The cost-sensitive AdaBoost algorithms are practical since the “boosting” property in AdaBoost can iteratively enhance the small class of the cost-sensitive learning to solve the imbalanced data issue. However, the most available cost-sensitive AdaBoost algorithms are heuristic approaches, which are improved from the standard AdaBoost algorithm by cost-sensitively adjusting the voting weight parameters of weak classifiers or the sample updating weight parameters without strict theoretic proof. The algorithms are appended the cost-sensitive factors to focus on the high-cost and small-class samples, but they have no procedures to show the best place to add the cost factors and the cost factor value set. To complete the cost-sensitive AdaBoost algorithms’ framework, the present article has two main contributions. First, we summarize the popular cost-sensitive boosting algorithms in the literature and propose a generally comprehensive form. We name our specific one, the “AdaImC algorithm,” which is typically appliable to solve the imbalanced data classification problem with theoretic proof. Second, a statistical approach to prove the AdaImC algorithm is proposed to verify the inner relationship between the cost parameters. We show that our proposed algorithm in the machine learning field is identical to the Product of Experts (PoE) model in the statistics field. Besides, a way to determine the cost parameter value by the statistical analysis is introduced. Several numeric studies are listed finally to support our proposed algorithm.

The public transportation system of cities, including subway and public transportation, is becoming more and more perfect. With the rapid development of urban public transport, the path selection considering multiple factors has become a new problem. Based on the optimization model, we take urban public transport operators and travelers as the objects, and use the entroy weight TOPSIS method to comprehensively evaluate the feasible lines and paths between multiple OD pairs. Besides, the optimal path to traverse all nodes was solved by Hamilton cycle problem algorithm, which can also provide reference for both operators and travelers. According to the latest urban public transport data in 2021, we select Beijing, China as the empirical research object. This paper chooses the existing public transport network of Beijing to verify, and selects the optimal path of 5 nodes and 10 paths to traverse all nodes.

As an essential data processing technology, cluster analysis has been widely used in various fields. In clustering, it is necessary to select appropriate measures to evaluate the similarity in the data. In this paper, firstly, a cluster center selection method based on the grey relational degree is proposed to solve the problem of sensitivity in initial cluster center selection. Secondly, combining the advantages of Euclidean distance, DTW distance, and SPDTW distance, a weighted distance measurement based on three kinds of reach is proposed. Then, it is applied to Fuzzy C-MeDOIDS and Fuzzy C-means hybrid clustering technology. Numerical experiments are carried out with the UCI datasets. The experimental results show that the accuracy of the clustering results is significantly improved by using the clustering method proposed in this paper. Besides, the method proposed in this paper is applied to the MUSIC INTO EMOTIONS and YEAST datasets. The clustering results show that the algorithm proposed in this paper can also achieve a better clustering effect when dealing with practical problems.

In this paper, we consider a multistage feedback control strategy for the production of 1, 3-propanediol(1, 3-PD) in microbial fermentation. The feedback control strategy is widely used in industry, and to the best of our knowledge, this is the first time it is applied to 1, 3-PD. The feedback control law is assumed to be linear of the concentrations of biomass and glycerol, and the coefficients in the controller are continuous. A multistage feedback control law is obtained by using the control parameterization method on the coefficient functions. Then, the optimal control problem can be transformed into an optimal parameter selection problem. The time horizon is partitioned adaptively. The corresponding gradients are derived, and finally, our numerical results indicate that the strategy is flexible and efficient.