Search

• This paper models the metro system as knowledge graph for passenger flow prediction. • It combines traffic patterns and land-use features for knowledge graph construction. • It proposes a SARGCN model for spatiotemporal prediction on metro knowledge graphs. • It uses an attention mechanism to learn the correlation between inflow and outflow. • Validated on two metro datasets, it outperforms numerous advanced baselines. With the rapid development of intelligent operation and management in metro systems, accurate network-scale passenger flow prediction has become an essential component in real-time metro management. Although numerous novel methods have been applied in this field, critical barriers still exist in integrating travel behaviors and comprehensive spatiotemporal dependencies into prediction. This study constructs the metro system as a knowledge graph and proposes a split-attention relational graph convolutional network (SARGCN) to address these challenges. Breaking the limitations of physical metro networks, we develop a metro topological graph construction method based on the historical origin–destination (OD) matrix to involve travel behaviors. Then, we design a metro knowledge graph construction method to incorporate land-use features. To adapt prior knowledge of metro systems, we subsequently propose the SARGCN model for network-scale metro passenger flow prediction. This model integrates the relational graph convolutional network (R-GCN), split-attention mechanism, and long short-term memory (LSTM) to explore the spatiotemporal correlations and dependence between passenger inflow and outflow. According to the model validation conducted on the metro systems in Shenzhen and Hangzhou, China, the SARGCN model outperforms the advanced baselines. Furthermore, quantitative experiments also reveal the effectiveness of its component and the constructed metro knowledge graph. [ABSTRACT FROM AUTHOR]

• A cascade framework is proposed for automatic lung segmentation in CXRs. • An adaptive closed polyline searching method is used to obtain data sequence. • An improved machine learning model is proposed to express a mathematical model. • The explainability-guided mathematical model is used to denote lung contour. • Performance of the proposed method is evaluated on public multi-site datasets. Large variations in anatomical shape and size, too much overlap between anatomical structures, and inconsistent anatomical shapes make accurate lung segmentation in chest x-rays (CXR) a challenging problem. In this paper, we propose an automatic method called A-LugSeg that consists of two subnetworks for lung segmentation in CXRs. The first is a segmentation subnetwork based on a deep learning model (i.e., Mask-RCNN), which completes a coarse segmentation for each input CXR image. The second is a refinement subnetwork designed to optimize the coarse segmentation result by combining an improved closed principal curve method and an enhanced machine learning, where the lung contour's explainability-guided mathematical model is expressed by the machine learning's parameters. The performance of the proposed method is evaluated on three public datasets, namely the ShenZhen hospital Chest X-ray dataset (SZCX), Japanese Society of Radiological Technology dataset (JSRT), and Montgomery County chest x-ray dataset (MC), which contain the 662 CXRs, 247 CXRs, and 138 CXRs, respectively. We used different datasets for training/validation (SZCX) and testing (SZCX/JSRT/MC). Furthermore, we used six evaluation metrics to evaluate the performance of our proposed method, including Dice Similarity Coefficient (DSC), Jaccard Similarity Coefficient (Ω), Accuracy (ACC), Precision, Sensitivity, and Specificity. The obtained results (DSC = 0.973, Ω = 0.958, ACC = 0.972, and p -value for DSC < 0.001) for JSRT, (DSC = 0.971, Ω = 0.955, ACC = 0.97, and p -value for DSC < 0.001) for MC, (DSC = 0.972, Ω = 0.956, and ACC = 0.97) for hybrid datasets (JSRT + MC), and (Precision, Sensitivity, and Specificity are higher than 0.98) show the superior performance of the proposed dual subnetwork segmentation algorithm compared to the existing state of the art approaches. [ABSTRACT FROM AUTHOR]