The current bridge maintenance practice generally involves manual visual inspection, which is highly subjective and unreliable. A technique that can automatically detect defects, for example, surface ...cracks, is essential so that early warnings can be triggered to prevent disaster due to structural failure. In this study, to permit automatic identification of concrete cracks, an ad‐hoc faster region‐based convolutional neural network (faster R‐CNN) was applied to contaminated real‐world images taken from concrete bridges with complex backgrounds, including handwriting. A dataset of 5,009 cropped images was generated and labeled for two different objects, cracks and handwriting. The proposed network was then trained and tested using the generated image dataset. Four full‐scale images that contained complex disturbance information were used to assess the performance of the trained network. The results of this study demonstrate that faster R‐CNN can automatically locate crack from raw images, even with the presence of handwriting scripts. For comparative study, the proposed network is also compared with You Only Look Once v2 detection technique.
Cracking is a common pavement distress that would cause further severe problems if not repaired timely, which means that it is important to accurately extract the information of pavement cracks ...through detection and segmentation. Automated pavement crack detection and segmentation using deep learning are more efficient and accurate than conventional methods, which could be further improved. While many existing studies have utilized deep learning in pavement crack segmentation, which segments cracks from non‐crack regions, few studies have taken the exact pavement crack detection into account, which identifies cracks in the images from other objects. A two‐step pavement crack detection and segmentation method based on convolutional neural network was proposed in this paper. An automated pavement crack detection algorithm was developed using the modified You Only Look Once 3rd version in the first step. The proposed crack segmentation method in the second step was based on the modified U‐Net, whose encoder was replaced with a pre‐trained ResNet‐34 and the up‐sample part was added with spatial and channel squeeze and excitation (SCSE) modules. Proposed method combines pavement crack detection and segmentation together, so that the detected cracks from the first step are segmented in the second step to improve the accuracy. A dataset of pavement crack images in different circumstances were also built for the study. The F1 score of proposed crack detection and segmentation methods are 90.58% and 95.75%, respectively, which are higher than other state‐of‐the‐art methods. Compared with existing one‐step pavement crack detection or segmentation methods, proposed two‐step method showed advantages of accuracy.
Early detection of malignant thyroid nodules leading to patient-specific treatments can reduce morbidity and mortality rates. Currently, thyroid specialists use medical images to diagnose then follow ...the treatment protocols, which have limitations due to unreliable human false-positive diagnostic rates. With the emergence of deep learning, advances in computer-aided diagnosis techniques have yielded promising earlier detection and prediction accuracy; however, clinicians' adoption is far lacking. The present study adopts Xception neural network as the base structure and designs a practical framework, which comprises three adaptable multi-channel architectures that were positively evaluated using real-world data sets. The proposed architectures outperform existing statistical and machine learning techniques and reached a diagnostic accuracy rate of 0.989 with ultrasound images and 0.975 with computed tomography scans through the single input dual-channel architecture. Moreover, the patient-specific design was implemented for thyroid cancer detection and has obtained an accuracy of 0.95 for double inputs dual-channel architecture and 0.94 for four-channel architecture. Our evaluation suggests that ultrasound images and computed tomography (CT) scans yield comparable diagnostic results through computer-aided diagnosis applications. With ultrasound images obtained slightly higher results, CT, on the other hand, can achieve the patient-specific diagnostic design. Besides, with the proposed framework, clinicians can select the best fitting architecture when making decisions regarding a thyroid cancer diagnosis. The proposed framework also incorporates interpretable results as evidence, which potentially improves clinicians' trust and hence their adoption of the computer-aided diagnosis techniques proposed with increased efficiency and accuracy.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The development of advanced cathode materials for aqueous the zinc ion battery (ZIB) represents a crucial step toward building future large‐scale green energy conversion and storage systems. ...Recently, significant progress has been achieved in the development of manganese‐based oxides for ZIB via defect engineering, whereby the intrinsic capacity and energy density have been enhanced. In this review, an overview of the recent progress in the defect engineering of manganese‐based oxides for aqueous ZIBs is summarized in the following order: 1) the structures and properties of the commonly used manganese‐based oxides, 2) the classification of the various types of defect engineering commonly reported, 3) the various strategies used to create defects in materials, and 4) the effects of the various types of defect engineering on the electrochemical performance of manganese‐based oxides. Finally, a perspective on the defect engineering of manganese‐based oxides is proposed to further enhance their electrochemical performance as a ZIB cathode.
An overview of the recent progress in the defect engineering of manganese‐based oxides for aqueous ZIBs is summarized, including the structures and properties of manganese‐based oxides, classification of defect engineering, strategies for creating defects, and effects of defect engineering on electrochemical performance. Finally, a perspective on the defect engineering of manganese‐based oxides is proposed, to further enhance their electrochemical performance.
Anomaly Detection in Dynamic Graphs via Transformer Liu, Yixin; Pan, Shirui; Wang, Yu Guang ...
IEEE transactions on knowledge and data engineering,
2023-Dec.-1, 2023-12-1, Letnik:
35, Številka:
12
Journal Article
Recenzirano
Odprti dostop
Detecting anomalies for dynamic graphs has drawn increasing attention due to their wide applications in social networks, e-commerce, and cybersecurity. Recent deep learning-based approaches have ...shown promising results over shallow methods. However, they fail to address two core challenges of anomaly detection in dynamic graphs: the lack of informative encoding for unattributed nodes and the difficulty of learning discriminate knowledge from coupled spatial-temporal dynamic graphs. To overcome these challenges, in this paper, we present a novel T ransformer-based A nomaly D etection framework for DY namic graphs ( TADDY ). Our framework constructs a comprehensive node encoding strategy to better represent each node's structural and temporal roles in an evolving graphs stream. Meanwhile, TADDY captures informative representation from dynamic graphs with coupled spatial-temporal patterns via a dynamic graph transformer model. The extensive experimental results demonstrate that our proposed TADDY framework outperforms the state-of-the-art methods by a large margin on six real-world datasets.
Manganese‐based oxide is arguably one of the most well‐studied cathode materials for zinc‐ion battery (ZIB) due to its wide oxidation states, cost‐effectiveness, and matured synthesis process. As a ...result, there are numerous reports that show significant strides in the progress of Mn‐based oxides as ZIB cathode. However, ironically, due to the sheer number of Mn‐based oxides that have been published in recent years, there remain certain contemplations with regards to the electrochemical performance of each type of Mn‐based oxides and their performance comparison among various Mn polymorphs and oxidation states. Thus, to provide a clearer indication of the development of Mn‐based oxides, the recent progress in Mn‐based oxides as ZIB cathode was summarized systematically in this Review. More specifically, (1) the classification of Mn‐based oxides based on the oxidation states (i. e., MnO2, Mn3O4, Mn2O3, and MnO), (2) their respective polymorphs (i. e., α‐MnO2 and δ‐MnO2) as ZIB cathode, (3) the modification strategies commonly employed to enhance the performance, and (4) the effects of these modification strategies on the performance enhancement were reviewed. Lastly, perspectives and outlook of Mn‐based oxides as ZIB cathode were discussed at the end of this Review.
Mn‐based aqueous ZIB: Mn‐based oxides have been intensively studied as cathode for aqueous zinc‐ion battery (ZIB) applications. Studies range from different classifications of Mn‐based oxides to their respective polymorphs. Various modification strategies to enhance their electrochemical performances are demonstrated. A Review to elucidate these past achievements in Mn‐based aqueous ZIB is presented with some highlights for its future developments.
The detection of cracks in concrete structures is a pivotal aspect in assessing structural robustness. Current inspection methods are subjective, relying on the inspector’s experience and mental ...focus. In this study, an ad hoc You Only Look Once version 2 object detector was applied to automatically detect concrete cracks from real-world images, which were taken from diverse concrete bridges and contaminated with handwriting scripts. A total of 3010 cropped images were used to generate the dataset, labelled for two different detection classes, that is, cracks and handwriting. The proposed network was then trained and tested using the generated image dataset. Three full-scale images that contained disturbing background information were used to evaluate the robustness of the trained detector. The influence of labelling handwriting as an object class for network training on the overall crack detection accuracy was assessed as well. The results of this study show that the You Only Look Once version 2 could automatically locate crack with bounding boxes from raw images, even with the presence of handwriting scripts. As a comparative study, the proposed network was also compared with faster region-based convolutional neural network. The results showed that You Only Look Once version 2 performed better in terms of both accuracy and inference speed.
A
bstract
Models of Dark Matter (DM) can leave unique imprints on the Universe’s small scale structure by boosting density perturbations on small scales. We study the capability of Pulsar Timing ...Arrays to search for, and constrain, subhalos from such models. The models of DM we consider are ordinary adiabatic perturbations in ΛCDM, QCD axion miniclusters, models with early matter domination, and vector DM produced during inflation. We show that ΛCDM, largely due to tidal stripping effects in the Milky Way, is out of reach for PTAs. Axion miniclusters may be within reach, although this depends crucially on whether the axion relic density is dominated by the misalignment or string contribution. Models where there is matter domination with a reheat temperature below 1 GeV may be observed with future PTAs. Lastly, vector DM produced during inflation can be detected if it is lighter than 10
−
16
GeV. We also make publicly available a Python Monte Carlo tool for generating the PTA time delay signal from any model of DM substructure.
Automated pavement distress detection based on 2D images is facing various challenges. To efficiently complete the crack and pothole segmentation in a practical environment, an automated pixel-level ...pavement distress detection framework integrating stereo vision and deep learning is developed in this study. Based on the multi-view stereo imaging system, multi-feature pavement image datasets containing color images, depth images and color-depth overlapped images are established, providing a new perspective for deep learning. To alleviate computational burden, a modified U-net deep learning architecture introducing depthwise separable convolution is proposed for crack and pothole segmentation. These methods are tested in asphalt roads with different circumstances. The results show that the 3D pavement image achieves millimeter-level accuracy. The enhanced 3D crack segmentation model outperforms other models in terms of segmentation accuracy and inference speed. After obtaining the high-resolution pothole segmentation map, the automated pothole volume measurement is realized with high accuracy.
•Stereo vision and deep learning were integrated for automated pavement crack and pothole segmentation.•Multi-feature image datasets containing 2D, 3D and enhanced-3D images were established by stereo vision.•A modified U-net embedding depthwise separable convolution was proposed for faster segmentation.•The deep learning efficiency using different types of images was investigated.•Automated pothole volume measurement was achieved based on 3D image segmentation.
We study quantum fluctuations in the light-cone metric of the 4D Einstein-Hilbert action via dimensional reduction to Jackiw-Teitelboim (JT) gravity. In particular, we show that, in Einstein gravity, ...the causal development of a region in flat Minkowski spacetime, near a horizon defined by light sheets, can be described by an effective two-dimensional dilaton theory. This enables us to make use of known solutions of the JT action, where the spacetime position of a horizon has quantum uncertainty due to metric fluctuations. This quantum uncertainty can be then directly related to the original 4D light-cone coordinates, allowing us to compute the uncertainty in the time of a photon to travel from tip-to-tip of a causal diamond in flat 4D Minkowski space. We find that both Planck and infrared scales (with the latter set by the size of the causal diamond) enter the uncertainty in photon travel time, such that the quantum fluctuation in the arrival time may be observably large.
PDF
