Automatic pavement crack detection is essential for evaluating maintenance requirements and ensuring driving safety. Crack detection plays a primary role in realising the automatic evaluation of pavement condition. Most existing researches on pavement crack detection rely on laborious work, which is a time- and cost-intensive process. Although there has been considerable research on pavement crack detection, it remains a challenging task owing to diverse complex pavement conditions. Recently, deep learning-based algorithms have achieved significant success in computer vision tasks. However, the techniques still have limitations for automatic pavement distress detection. To overcome the current limitations, this study proposes a method for detecting signs of pavement distress based on faster region based convolutional neural network (Faster R-CNN). The study focuses on the detection of longitudinal cracks, transverse cracks, alligator cracks, and partial patching in pavement images. A framework for applying the Faster R-CNN technique to a full-size pavement image is also proposed, which allows the sliding window size to be reduced, thus enabling the detection of larger images. The performance of the proposed method was validated against a dataset containing actual pavement images. The experimental test results show that the proposed method could successfully detect cracks and partial patching with accuracy.

Three-dimensional ground penetrating radar data are often ambiguous and complex to interpret when attempting to detect only underground cavities because ground penetrating radar reflections from various underground objects can appear like those from cavities. In this study, we tackle the issue of ambiguity by proposing a system based on deep convolutional neural networks, which is capable of autonomous underground cavity detection beneath urban roads using three-dimensional ground penetrating radar data. First, a basis pursuit-based background filtering algorithm is developed to enhance the visibility of underground objects. The deep convolutional neural network is then established and applied to automatically classify underground objects using the filtered three-dimensional ground penetrating radar data as represented by three types of images: A-, B-, and C-scans. In this study, we utilize a novel two-dimensional grid image consisting of several B- and C-scan images. Cavity, pipe, manhole, and intact features extracted from in situ three-dimensional ground penetrating radar data are used to train the convolutional neural network. The proposed technique is experimentally validated using real three-dimensional ground penetrating radar data obtained from urban roads in Seoul, South Korea.

Ground-penetrating radar is a typical sensor system for analyzing underground facilities such as pipelines and rebars. The technique also can be used to detect an underground cavity, which is a potential sign of urban sinkholes. Multichannel ground-penetrating radar devices are widely used to detect underground cavities thanks to the capacity of informative three-dimensional data. Nevertheless, the three-dimensional ground-penetrating radar data interpretation is unclear and complicated when recognizing underground cavities because similar ground-penetrating radar data reflected from different underground objects are often mixed with the cavities. As it is prevalently known that the deep learning algorithm-based techniques are powerful at image classification, deep learning-based techniques for underground object detection techniques using two-dimensional GPR (ground-penetrating radar) radargrams have been researched upon in recent years. However, spatial information of underground objects can be characterized better in three-dimensional ground-penetrating radar voxel data than in two-dimensional ground-penetrating radar images. Therefore, in this study, a novel underground object classification technique is proposed by applying deep three-dimensional convolutional neural network on three-dimensional ground-penetrating radar data. First, a deep convolutional neural network architecture was developed using three-dimensional convolutional networks for recognizing spatial underground objects such as, pipe, cavity, manhole, and subsoil. The framework of applying the three-dimensional convolutional neural network into three-dimensional ground-penetrating radar data was then proposed and experimentally validated using real three-dimensional ground-penetrating radar data. In order to do that, three-dimensional ground-penetrating radar block data were used to train the developed three-dimensional convolutional neural network and to classify unclassified three-dimensional ground-penetrating radar data collected from urban roads in Seoul, South Korea. The validation results revealed that four underground objects (pipe, cavity, manhole, and subsoil) are successfully classified, and the average classification accuracy was 97%. In addition, a false alarm was rarely indicated.

This paper proposes a 3D ground penetrating radar (GPR) image-based underground cavity detection network (UcNet) for preventing sinkholes in complex urban roads. UcNet is developed based on convolutional neural network (CNN) incorporated with phase analysis of super-resolution (SR) GPR images. CNNs have been popularly used for automated GPR data classification, because expert-dependent data interpretation of massive GPR data obtained from urban roads is typically cumbersome and time consuming. However, the conventional CNNs often provide misclassification results due to similar GPR features automatically extracted from arbitrary underground objects such as cavities, manholes, gravels, subsoil backgrounds and so on. In particular, non-cavity features are often misclassified as real cavities, which degrades the CNNs’ performance and reliability. UcNet improves underground cavity detectability by generating SR GPR images of the cavities extracted from CNN and analyzing their phase information. The proposed UcNet is experimentally validated using in-situ GPR data collected from complex urban roads in Seoul, South Korea. The validation test results reveal that the underground cavity misclassification is remarkably decreased compared to the conventional CNN ones.

In the environment, bacteria show close association, such as interspecies interaction, with other bacteria as well as host organisms. The type VI secretion system (T6SS) in gram‐negative bacteria is involved in bacterial competition or virulence. The plant pathogen Burkholderia glumae BGR1, causing bacterial panicle blight in rice, has four T6SS gene clusters. The presence of at least one T6SS gene cluster in an organism indicates its distinct role, like in the bacterial and eukaryotic cell targeting system. In this study, deletion mutants targeting four tssD genes, which encode the main component of T6SS needle formation, were constructed to functionally dissect the four T6SSs in B. glumae BGR1. We found that both T6SS group_4 and group_5, belonging to the eukaryotic targeting system, act independently as bacterial virulence factors toward host plants. In contrast, T6SS group_1 is involved in bacterial competition by exerting antibacterial effects. The ΔtssD1 mutant lost the antibacterial effect of T6SS group_1. The ΔtssD1 mutant showed similar virulence as the wild‐type BGR1 in rice because the ΔtssD1 mutant, like the wild‐type BGR1, still has key virulence factors such as toxin production towards rice. However, metagenomic analysis showed different bacterial communities in rice infected with the ΔtssD1 mutant compared to wild‐type BGR1. In particular, the T6SS group_1 controls endophytic plant‐associated bacteria such as Luteibacter and Dyella in rice plants and may have an advantage in competing with endophytic plant‐associated bacteria for settlement inside rice plants in the environment. Thus, B. glumae BGR1 causes disease using T6SSs with functionally distinct roles.

By virtue of the advances in sensing techniques, finite element (FE) model updating (FEMU) using static and dynamic data has been recently employed to improve identification on updating parameters. Using heterogeneous data can provide useful information to improve parameter identifiability in FEMU. It is worth noting that the useful information from the heterogeneous data may be diluted in the conventional FEM framework. The conventional FEMU framework in previous studies have used heterogeneous data at once to compute residuals in the objective function, and they are condensed to be a scalar. In this implementation, it should be careful to formulate the objective function with proper weighting factors to consider the scale of measurement and relative significances. Otherwise, the information from heterogeneous data cannot be efficiently utilized. For FEMU of the bridge, parameter compensation may exist due to mutual dependence among updating parameters. This aggravates the parameter identifiability to make the results of the FEMU worse. To address the limitation of the conventional FEMU method, this study proposes a sequential framework for the FEMU of existing bridges. The proposed FEMU method uses two steps to utilize static and dynamic data in a sequential manner. By using them separately, the influence of the parameter compensation can be suppressed. The proposed FEMU method is verified through numerical and experimental study. Through these verifications, the limitation of the conventional FEMU method is investigated in terms of parameter identifiability and predictive performance. The proposed FEMU method shows much smaller variabilities in the updating parameters than the conventional one by providing the better predictions than those of the conventional one in calibration and validation data. Based on numerical and experimental study, the proposed FEMU method can improve the parameter identifiability using the heterogeneous data and it seems to be promising and efficient framework for FEMU of the existing bridge.