Zhuo Liu

Multimodal public transport network (MPTN) plays an important role in relieving road traffic pressure for metropolitan area. Nevertheless, the impact of an accident happened in an individual station may not only disrupt the station itself or the single lines that go through the station but also spread over the whole network. Therefore, identifying the vulnerable stations is essential for improving the MPTN management against the systematic risk caused by accidents. In this paper, we proposed a route diversity‐based approach to measure the vulnerability of stations in MPTN based on the complex network theory. The route constraint parameters were established to reflect the travel time restriction in constructing the set of passengers’ acceptable routes. In addition, an algorithm was formulated to rapidly calculate the route diversity index and meanwhile avoid the “overlapping routes” problem. A simple virtual network was used as a numerical example to compare the proposed approach with the vulnerability evaluation approaches based on degree centrality and betweenness centrality. Finally, the proposed approach was applied to the MPTN of Beijing to explain its effectiveness and potential applications. The results show that the proposed method can efficaciously estimate vulnerable nodes compared with degree centrality and betweenness centrality. Meanwhile, the acceptable routes between any OD pairs in the MPTN are 1–10 according to the constrained parameter. In addition, the average number of acceptable routes between OD pairs of Beijing MPTN is 3.649. By ranking the stations according to their vulnerability, it can be found that the top 5 vulnerable stations are all external traffic hubs or the stations around famous commercial areas. The results suggest that these stations are significant for external transport as well as crucial for internal urban transportation systems. The research output could contribute to the MPTN management in accident prevention and emergency handling.

Texture is a crucial characteristic of roads, closely related to their performance. The recognition of pavement texture is of great significance for road maintenance professionals to detect potential safety hazards and carry out necessary countermeasures. Although deep learning models have been applied for recognition, the scarcity of data has always been a limitation. To address this issue, this paper proposes a few-shot learning model based on the Siamese network for pavement texture recognition with a limited dataset. The model achieved 89.8% accuracy in a four-way five-shot task classifying the pavement textures of dense asphalt concrete, micro surface, open-graded friction course and stone matrix asphalt. To align with engineering practice, global average pooling (GAP) and one-dimensional convolution are implemented, creating lightweight models that save storage and training time. Comparative experiments show that the lightweight model with GAP implemented on dense layers and one-dimensional convolution on convolutional layers reduced storage volume by 94% and training time by 99%, despite a 2.9% decrease in classification accuracy. Moreover, the model with only GAP implemented on dense layers achieved the highest accuracy at 93.5%, while reducing storage volume and training time by 83% and 6%, respectively. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

Access full-text academic articles: J-STAGE is an online platform for Japanese academic journals.

The influence of the built environment on dockless bike-sharing (DBS) trips connecting to urban metro stations has always been a significant problem for planners. However, the evidence for correlations between microscale built-environment factors and DBS-metro transfer trips remains inconclusive. To address this, a framework, augmented by big data, is formulated to analyze the correlation of built environment with DBS–metro transfer trips from the macroscopic and microscopic views, considering Beijing as a case study. The trip density and cycling speed are calculated based on 11,120,676 pieces of DBS data and then used to represent the characteristic of DBS-metro transfer trips in a multiple linear regression model. Furthermore, a novel method is proposed to determine the built-environment sampling area around a station by its corresponding DBS travel distances. Accordingly, 6 microscale built-environment factors are extracted from street-view images using deep learning and integrated into the analysis model, together with 14 macroscale built-environment factors and 8 potential influencing factors of socioeconomic attributes and metro station attributes. The results reveal the significant positive influence of greenery and presence of barriers on trip density and cycling speed. Additionally, presence of streetlights is found to be negatively correlated with both trip density and cycling speed. Presence of signals is also found to have an influence on DBS-metro transfer trips, but it only negatively impacts trip density.

The safety monitoring of transportation infrastructure foundation is crucial for the sustainable service of transportation systems. In recent years, the Ground Penetrating Radar (GPR) has become a powerful tool to identify and locate the subgrade distresses according to the different responses of wave characteristics, preliminarily realizing an intelligent nondestructive detection. To solve the problems like small sample size and unbalanced dataset, this study used a deep data augmentation method, e.g. WGAN-GP network, to augment the original limited B-Scan GPR data of subgrade, and then carried out supervised learning for classification task. The detailed computation steps include the image processing, data augmentation and intelligent analysis. First, the dataset was initially enlarged through the traditional methods after noise filtering, gamma transform and other processing methods. Then, the WGAN-GP network was adopted to generate new high-quality B-Scan images. Finally, the intelligent classification of subgrade distresses was realized by ResNet50 model with a satisfactory accuracy of 90.85%.

Crack is one of the important pavement damages. The number and types of cracks are usually collected and inspected by human, but lately computer vision has shown great potential for automatically identifying pavement cracks. However, training a convolutional neural network (CNN) requires large amount of data. The limited number of crack images and the variety of crack image background put challenges for developing CNN model with high accuracy. This study proposes an intelligent method for crack pattern classification based on limited field images. The proposed method has a two-step data preprocessing. It first applied data augmentation method to enlarge the dataset, solving the data imbalance problem and providing more training data. Then a crack extraction method was applied to convert the original image into a binary back-and-white image. This step significantly reduced the input feature and simplified the model. Both of data preprocessing steps were designed to decrease the bias of the model. Then we performed a model selection and hyper-parameter tunning for CNN. We explored the application of AlexNet, SE-Net, and ResNet with a variety of configurations. The results show that the proposed data augmentation can enlarge the dataset significantly. The crack extraction also significantly increased the test accuracy. The ResNet with 50 layers has the highest test accuracy. With data augmentation, crack extraction and model selection combining together, the final approach can improve the test accuracy from 52.68% to 87.50% compared to the original limited images. The result suggests our proposed method works well to classify crack images of asphalt pavement with limited sample size.

Vision monitoring of distress has emerged as a new trend in intelligent transportation infrastructure systems, including roads and bridges. Recently, transfer learning methods and lightweight networks have been used to realize efficient distress identification without large amount of human-labor work. This paper proposed an engineering approach that integrated transfer learning with lightweight models to classify and detect concrete bridge distresses. Two datasets named Distress Dataset of Asphalt Pavement (DDAP) with 2500 asphalt pavement distresses images and Distress Dataset of Concrete Bridge (DDCB) with 906 concrete bridge distresses images were used. The lightweight models MobileNet and MobileNet-SSD were employed to conduct 6 comparative experiments for exploring the model performance with different transfer learning modes (Mode I and II) and procedures (one-step and two-step procedure) in classification and detection tasks. Based on the comparison of the results, the optimum model for two tasks was respectively recognized. For classification task, the model directly transferred specific parameters of partial convolution layers from ImageNet-based model achieved the highest accuracy of 97.8%. For detection task, the two-step transfer learning model using an intermediate transfer learning step trained by DDAP reached a mean average precision of 87.16%. The proposed approach has the application potential for practical road inspection work in intelligent transportation infrastructure maintenance.