In knowledge graph construction, a challenging issue is how to extract complex (e.g., overlapping) entities and relationships from a small amount of unstructured historical data. The traditional pipeline methods are to divide the extraction into two separate subtasks, which misses the potential interactio between the two subtasks and may lead to error propagation. In this work, we propose an effective cascade dual-decoder method to extract overlapping relational triples, which includes a text-specific relation decoder and a relation-corresponded entity decoder. Our approach is straightforward and it includes a text-specific relation decoder and a relation-corresponded entity decoder. The text-specific relation decoder detects relations from a sentence at the text level. That is, it does this according to the semantic information of the whole sentence. For each extracted relation, which is with trainable embedding, the relation-corresponded entity decoder detects the corresponding head and tail entities using a span-based tagging scheme. In this way, the overlapping triple problem can be tackled naturally. We conducted experiments on a real-world open-pit mine dataset and two public datasets to verify the method's generalizability. The experimental results demonstrate the effectiveness and competitiveness of our proposed method and achieve better F1 scores under strict evaluation metrics.

In complex marine environments, intelligent vessels require a high level of dynamic perception to process multiple types of information for mitigating collision risks. To ensure the safety of maritime traffic and enhance the efficiency of navigation information, vessel trajectory prediction is crucial for Automatic Identification Systems (AIS). This study introduces a Graph Convolutional Mamba Network (GC-MT) utilizing AIS data for predicting vessel trajectories. To capture motion interaction characteristics, we employed a Graph Convolutional Network (GCN) to construct a spatiotemporal graph that reflects the interaction relationships among various vessels within the maritime information flow. Furthermore, high-level spatiotemporal features were extracted using a Mamba Neural Network (MNN) to incorporate time-related dynamics. Validation against real-world historical AIS data demonstrates that the proposed model achieved improvements of approximately 35% and 28% in the Average Displacement Error (ADE) and Final Displacement Error (FDE), respectively, compared to the leading baseline model. The predictive capability of the proposed method demonstrates its effectiveness in improving maritime navigation safety in a shipping environment with multiple information sources.

In this paper, we introduce PortLaneNet, an optimized lane detection model specifically designed for the unique challenges of enclosed container terminal environments. Unlike conventional lane detection scenarios, this model addresses complexities such as intricate ground markings, tire crane lane lines, and various types of regional lines that significantly complicate detection tasks. Our approach includes the novel Scene Prior Perception Module, which leverages pre-training to provide essential prior information for more accurate lane detection. This module capitalizes on the enclosed nature of container terminals, where images from similar area scenes offer effective prior knowledge to enhance detection accuracy. Additionally, our model significantly improves understanding by integrating both high- and low-level image features through attention mechanisms, focusing on the critical components of lane detection. Through rigorous experimentation, PortLaneNet has demonstrated superior performance in port environments, outperforming traditional lane detection methods. The results confirm the effectiveness and superiority of our model in addressing the complex challenges of lane detection in such specific settings. Our work provides a valuable reference for solving lane detection issues in specialized environments and proposes new ideas and directions for future research.

In port environments, container stacking at significant heights obstructs satellite signal reception by terminal equipment on container trucks, leading to inaccurate positional tracking data. To address this, it is necessary to predict container truck trajectories to fill in the inaccurate positioning signals. In this study, we collected port container truck trajectory data and compared the predictive performance of long short-term memory (LSTM) networks and transformer models, revealing performance turning points at different prediction steps. Based on these findings, we propose a hybrid model named CT-HybridNet, which integrates the LSTM-based DeepPBM-M model with the transformer-based PatchTST model. Given the independence of the prediction errors of the two models, we assume both errors follow a Gaussian distribution. By performing an affine transformation, the proposed hybrid method’s output also follows a Gaussian distribution. Additionally, an adaptive parameter adjustment mechanism optimises performance, enabling CT-HybridNet to achieve dual improvements in trajectory prediction accuracy and stability, with 15% improvement in short-term accuracy and 20% in long-term performance. This study provides a more accurate and stable technical solution for port container truck trajectory prediction, overcoming issues related to positioning inaccuracies and signal obstructions.