Article
Ecology
Edwin Hui, Richard Stafford, Iain M. Matthews, V. Anne Smith
Summary: In today's world, understanding and predicting the response of ecosystems to disturbance is crucial. Bayesian networks have the potential to recover species interaction networks and improve the interpretability and predictive power of ecological models.
ECOLOGICAL INFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Ivo Perez Colo, Carolina Saavedra Sueldo, Mariano De Paula, Gerardo G. Acosta
Summary: Early fault detection is crucial in industrial processes to ensure product quality and avoid expensive repairs or process shutdown. The development of intelligent systems based on Industry 4.0 and deep learning has enabled automatic fault prediction. However, most existing solutions are specific to certain cases and lack scalability to industrial environments. This paper proposes an intelligent failure detection system that integrates deep neural networks with Bayesian Optimization for self-tuning of hyperparameters, aiming to facilitate industrialization and online integration in real production systems.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Mathematics
Maria Morales, Antonio Salmeron, Ana D. Maldonado, Andres R. Masegosa, Rafael Rumi
Summary: This study analyzes the impact of continuous assessment on students' final exam performance, concluding that while it is possible to predict whether a student passes or fails the final exam, a detailed forecast of the grade obtained is not possible.
Article
Environmental Sciences
Li Shen, Yao Lu, Hao Chen, Hao Wei, Donghai Xie, Jiabao Yue, Rui Chen, Shouye Lv, Bitao Jiang
Summary: This study introduces a building-change-detection dataset named S2Looking, which consists of large-scale side-looking satellite images and tens of thousands of annotated change instances, for training deep-learning algorithms. The dataset offers larger viewing angles, illumination variances, and complexity of rural images compared to existing datasets, and preliminary tests suggest higher level of challenges for deep-learning algorithms.
Article
Computer Science, Artificial Intelligence
Federico Carli, Manuele Leonelli, Gherardo Varando
Summary: Generative models for classification use the joint probability distribution of the class variable and the features to construct a decision rule. Bayesian networks and naive Bayes classifiers are commonly used generative models, providing a graphical representation of variable relationships. However, they restrict relationships by not allowing for context-specific independence. This study introduces a new class of generative classifiers, staged tree classifiers, which formally account for context-specific independence and show competitive accuracy with state-of-the-art classifiers.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Information Systems
Haozhe Chen, Hang Zhou, Jie Zhang, Dongdong Chen, Weiming Zhang, Kejiang Chen, Gang Hua, Nenghai Yu
Summary: In recent years, various methods for protecting model intellectual property (IP) have been proposed, but the problem of quickly detecting copied models among a large number of models on the Internet has not received enough attention. This article introduces a novel model copy detection mechanism called perceptual hashing for convolutional neural networks (CNNs), which can efficiently retrieve similar versions of a query model by comparing hash codes. The experiment demonstrates the superior copy detection performance of the proposed perceptual hashing scheme on a model library of 3,565 models.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2023)
Article
Engineering, Multidisciplinary
Inho Jeong, Hyejin Kim, Haeseong Cho, Hyungbum Park, Taeseong Kim
Summary: To prevent the destruction of the entire structure, it is crucial to detect and act on damage at an early stage. This study proposes a method using digital image correlation and a class activation map network to monitor damage locations. Experimental results show that this method has good performance in classifying and detecting damage locations.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2023)
Article
Engineering, Civil
Xinzhe Yuan, Jian Zhong, Yanping Zhu, Genda Chen, Cihan Dagli
Summary: This study aims to develop an ANN-based approach for regional seismic damage evaluation and investigates the impact of changing structural properties on ANN performance. By training ANN seismic classifiers with multiple intensity measures (IMs) as inputs and damage states as outputs, the importance ranking of IMs for classification is found to vary with structural properties. The classification accuracy higher than 92% on a structure portfolio shows the robustness and accuracy of the ANN-based approach for regional seismic damage evaluation.
Article
Environmental Sciences
Farkhanda Abbas, Feng Zhang, Fazila Abbas, Muhammad Ismail, Javed Iqbal, Dostdar Hussain, Garee Khan, Abdulwahed Fahad Alrefaei, Mohammed Fahad Albeshr
Summary: The most frequent and noticeable natural calamity in the Karakoram region is landslides, which frequently occur along Karakoram Highway, causing a major loss of life and property. Therefore, it is necessary to develop an early warning system and assess landslide susceptibility to mitigate these losses.
Article
Chemistry, Multidisciplinary
Chenhui Jiang, Qifeng Zhou, Jiayan Lei, Xinhong Wang
Summary: This paper proposes a two-stage structural damage detection method, utilizing a divide-and-conquer strategy. In the first stage, a 1D-CNN model is used for damage feature extraction and identification. In the second stage, a support vector machine (SVM) model and wavelet packet decomposition technique are combined for further damage quantification. Experimental results demonstrate the superiority of the proposed method compared to existing approaches.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Interdisciplinary Applications
Hau T. Mai, Seunghye Lee, Joowon Kang, Jaehong Lee
Summary: In this work, an effective Damage-Informed Neural Network (DINN) is developed for pinpointing the position and extent of structural damage. By using a deep neural network and Bayesian optimization algorithm, the proposed method outperforms other algorithms in terms of accuracy and efficiency.
COMPUTERS & STRUCTURES
(2024)
Article
Engineering, Civil
Marios Impraimakis
Summary: This paper examines the response-only model class selection capability of a novel deep convolutional neural network method. The method allows the network to select the model class of new and unlabeled signals without the need for system input information, providing a powerful tool for structural health monitoring applications.
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS
(2023)
Article
Mathematics
Dario Ramos-Lopez, Ana D. Maldonado
Summary: Multi-class classification in imbalanced datasets presents a challenging problem where traditional validation metrics may not be suitable. A cost-sensitive variable selection procedure is proposed to build a Bayesian network classifier, optimizing a specified cost function. Fine-tuning the objective validation function can improve prediction quality in imbalanced data or when considering asymmetric misclassification costs.
Article
Computer Science, Artificial Intelligence
Yu Zhou, Ronggang Cao, Ping Li, Xiao Ma, Xueyi Hu, Fadong Li
Summary: This paper proposes an automated damage detection system for the inner bore of electromagnetic railgun launcher, which achieves rapid detection of railgun inner bore damages and reaches the state-of-the-art level in the detection task.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Mathematics
Ana D. Maldonado, Maria Morales, Francisco Navarro, Francisco Sanchez-Martos, Pedro A. Aguilera
Summary: In this study, the predictive performance of Bayesian networks (BNs) and artificial neural networks (ANNs) in modeling groundwater temperature variations associated with precipitation events was compared. The results showed that while both tools were equally accurate in predicting groundwater temperature drops, the computational cost associated with Bayesian networks was significantly lower, and the resulting BN models were more versatile.
Article
Acoustics
Reza Soleimanpour, Ching-Tai Ng
Summary: This study investigates the higher harmonic generation of Lamb waves at delaminations in composite laminates due to contact acoustic nonlinearity. Both numerical and experimental studies were conducted, and a three-dimensional finite element model was proposed and verified using experimental data. The results show that the proposed numerical model can predict higher harmonics generated by contact acoustic nonlinearity, with delamination identified as the main source of this nonlinearity. Additionally, a mode conversion study was carried out to gain further insight into the physical mechanisms behind the higher harmonic generation of Lamb waves at delaminations.
JOURNAL OF VIBRATION AND CONTROL
(2022)
Article
Engineering, Multidisciplinary
Mohammad Ali Fakih, Samir Mustapha, Mohammad Harb, Ching-Tai Ng
Summary: This study investigated the propagation behavior of fundamental Lamb-wave modes interacting with welded joints of dissimilar materials, using numerical scrutiny and experimental validation. The effects of incidence angle on reflection, transmission, and mode conversion of the incident modes were analyzed in both forward and backward propagation directions. Results showed that the reflection of the SH0 mode from the joint was pronounced, while its transmission to the other material was weak.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2022)
Article
Engineering, Multidisciplinary
Tingyuan Yin, Ching Tai Ng, James Vidler, Van Dac Ho, Andrei Kotousov
Summary: This study proposes an amplitude-modulation vibro-acoustic (AMVA) technique to track the evolution of thermal damage in pristine graphene mortar. The results show that the proposed AMVA technique is more sensitive and feasible to serve as the tool for thermal damage detection in cement-based material.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2023)
Article
Acoustics
Hankai Zhu, Ching Tai Ng, Andrei Kotousov
Summary: This study evaluates fatigue damage based on the growth rate of combinational harmonics generated by mixing Lamb waves. The incorporation of the phase reversal approach improves the evaluation of harmonics and avoids the influence of unwanted harmonics. Results show that combinational harmonics are more sensitive to weak material nonlinearities compared to second harmonics. Experiments on damaged samples demonstrate that the sum of combinational harmonics has better sensitivity to progressive fatigue damage than second harmonics.
Article
Construction & Building Technology
Xianwen Hu, Tingyuan Yin, Hankai Zhu, Ching-Tai Ng, Andrei Kotousov
Summary: This paper investigates the application of nonlinear guided wave mixing technique in the detection of a partially immersed aluminum plate loaded with water. Experimental results show that the amplitudes of the guided wave signals and the relative nonlinearity parameters on the partially immersed plate are different from their counterparts on the plate without water. Numerical simulations also reveal that both the second harmonics and the combination harmonics are sensitive to the material nonlinearity of the plate loaded with water on one side.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Engineering, Mechanical
James Vidler, Andrei Kotousov, James M. Hughes, Anna Paradowska, Mark Reid, Ching -Tai Ng
Summary: This study explores the feasibility of using Neutron Diffraction method to evaluate early high-cycle fatigue damage in G350 steel samples. The outcomes demonstrate that it is feasible to evaluate severe fatigue damage using the ND method, although more accurate evaluation may require higher spatial resolution and a larger number of measurement points.
ENGINEERING FAILURE ANALYSIS
(2022)
Article
Engineering, Multidisciplinary
Li Zou, Heung Fai Lam, Jun Hu
Summary: This study proposes a novel fault diagnosis method utilizing adaptive resize-residual deep neural networks, which converts vibration signals into time-frequency images using continuous wavelet transform, enhances image contrast with histogram equalization algorithm, and achieves superior recognition accuracy.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2023)
Article
Engineering, Civil
Alireza Ghiasi, Ching-Tai Ng, Abdul Hamid Sheikh
Summary: This paper proposes a novel combined damage detection approach for the classification of various extents and degrees of corrosion losses in steel railway bridges. By using a finite element model and field testing data for training and testing, the proposed technique has been proven to be practical and accurate in classifying damages.
Article
Engineering, Civil
Mujib Olamide Adeagbo, Heung-Fai Lam, Yung-Jeh Chu
Summary: This study focuses on the comparison between time and modal domain system identification of a rail-sleeper-ballast system, utilizing different analytical methods and validating the accuracy of the Bayesian algorithm in identifying ballast damage. The results demonstrate that the time domain is more suitable for system identification of the considered system.
ASCE-ASME JOURNAL OF RISK AND UNCERTAINTY IN ENGINEERING SYSTEMS PART A-CIVIL ENGINEERING
(2022)
Article
Materials Science, Characterization & Testing
Hankai Zhu, Ching Tai Ng, Andrei Kotousov
Summary: Evaluation of fatigue damage using nonlinear guided wave mixing has been extensively studied. Combinational harmonics resulting from wave mixing of quasi-synchronized wave modes have attractive features and are sensitive to fatigue damage. However, limited research has been done on the frequency pair selection and time shifting of wave mixing signals. This study proposes a method and theoretical equations to guide the selection of wave mixing frequency pairs and introduces a new time shifting technique to enhance the generation of harmonics. These findings can further advance the development of damage detection methods using guided wave mixing.
NDT & E INTERNATIONAL
(2023)
Article
Neurosciences
Jinhang Wu, Chang Jiang, Han Fang, Ching-Tai Ng
Summary: This paper evaluates the feasibility of using the feature guided wave (FGW) technique to detect weld defects in steel T-welded joint structures. The Semi-Analytical Finite Element (SAFE) method is used to obtain modal solutions in the waveguide, and a new algorithm is developed to obtain FGW modes with high energy concentration and low attenuation. The study confirms the capability and robustness of the identified FGW mode (RTW) in detecting small weld defects.
Article
Engineering, Civil
Zheng Yi Fu, Mujib Olamide Adeagbo, Heung Fai Lam
Summary: This paper proposes a novel time-domain response reconstruction method based on model condensation and modal decomposition, which improves the efficiency of large-scale civil engineering structures. The accuracy and efficiency of the proposed methodology are verified through numerical and experimental case studies, showing its outstanding performance compared to traditional methods.
INTERNATIONAL JOURNAL OF STRUCTURAL STABILITY AND DYNAMICS
(2023)
Article
Acoustics
Hankai Zhu, Andrei Kotousov, Ching Tai Ng
Summary: This article proposes a quasi-fundamental antisymmetric mode of edge wave (QEA0) for evaluating defects on curved edges. Compared with the conventional guided waves and its symmetric counterpart (QES0), the QEA0 mode has a longer propagation distance and better defect sensitivity, allowing it to distinguish multiple defects and determine their locations. Therefore, the QEA0 mode shows great potential for non-destructive evaluation and structural health monitoring of structural edges with complex cross-sectional areas.
JOURNAL OF SOUND AND VIBRATION
(2023)
Proceedings Paper
Construction & Building Technology
Mujib Olamide Adeagbo, Heung-Fai Lam
Summary: For the application of structural health monitoring in civil engineering structures, optimizing sensor placement is crucial for obtaining the most optimal amount of information from measurement data while ensuring economical monitoring systems. This study addressed the issue by developing a simple Bayesian scheme based on information entropy and progressive increment or decrement in the number of sensors. The proposed scheme showed significant improvement in configurations' optimality with minimal computational cost, making it a robust and efficient solution.
PROCEEDINGS OF THE 17TH EAST ASIAN-PACIFIC CONFERENCE ON STRUCTURAL ENGINEERING AND CONSTRUCTION, EASEC-17 2022
(2023)
Proceedings Paper
Construction & Building Technology
Yung-Jeh Chu, Heung-Fai Lam, Hua-Yi Peng
Summary: The study investigates the power and thrust performance of a new two-fold blades wind turbine design using QBlade software. The wind turbine consists of a root fold axis and a mid-span fold axis, with sections shaped by the SD8000 airfoil. The folding of the blades alters the pitch and cone angles, affecting the angle of attack and changing the power and thrust performance. Results show that the two-fold blades wind turbine outperformed the benchmark at low tip speed ratios, confirming its potential application in the wind energy industry.
PROCEEDINGS OF THE 17TH EAST ASIAN-PACIFIC CONFERENCE ON STRUCTURAL ENGINEERING AND CONSTRUCTION, EASEC-17 2022
(2023)
Article
Engineering, Civil
Renbing An, Jiacong Yuan, Yi Pan, Duhang Yi
Summary: Traditional timber structures built on sloped land are more susceptible to seismic damage compared to structures built on flat land. The upper portion of the structure is found to be the weak point on sloped land, with potential issues such as tenon failure and column foot sliding.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Elyas Bayat, Federica Tubino
Summary: The current design guidelines for assessing floor vibration performance do not consider the influence of variability in the walking path on the dynamic response of floors. This study investigates the dynamic response of floors under a single pedestrian walking load, taking into account the randomness of the walking path and load. The effectiveness of the current guidelines in predicting floor response is critically assessed.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Gao Ma, Chunxu Hou, Hyeon-Jong Hwang, Linghui Chen, Zhenhao Zhang
Summary: Minimizing earthquake damage and improving repair efficiency are the main principles of resilient structures. This study proposed a repairable column with UHPC segments and replaceable energy dissipaters. The test results showed that the columns with UHPC segments and replaceable dissipaters exhibited high strength, deformation capacity, and energy dissipation.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Kartheek S. M. Sonti, Pavan Kumar Penumakala, Suresh Kumar Reddy Narala, S. Vincent
Summary: In this study, the compressive behavior of alumina hollow particles reinforced aluminum matrix syntactic foams (AMSF) was investigated using analytical, numerical, and experimental methods. The results showed that the FE solver ABAQUS could accurately predict the elastic and elastio-plastic behavior of AMSFs. The study also suggested that FE models have great potential in developing new materials and composites under compression loading.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Zheqi Peng, Xin Wang, Zhishen Wu
Summary: In this study, the statistical modeling of fiber-reinforced polymer (FRP) cables using the classic fiber bundle model is explored. The study considers important features of large-scale multi-tendon FRP cables, such as initial random slack and uneven tensile deformation among tendons. A parametric study and reliability analysis are conducted to predict the load-displacement relation and design thousand-meter-scale FRP cables. The study emphasizes the relation between the reliability index beta of the cable and the safety factor gamma of the FRP material.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Yanchao Shi, Shaozeng Liu, Ye Hu, Zhong-Xian Li, Yang Ding
Summary: This paper introduces a damage assessment method for reinforced concrete (RC) columns under blast loading, using modal parameter measurement as the evaluation index. The validity of the proposed method is validated through numerical and experimental analysis. The results show that this modal-based damage assessment method is applicable for non-destructive evaluation of blast-induced damage of RC columns.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Xiaolin Zou, Maosheng Gong, Zhanxuan Zuo, Qifang Liu
Summary: This paper proposes an efficient framework for assessing the collapse capacity of structures in earthquake engineering. The framework is based on an accurate equivalent single-degree-of-freedom (ESDOF) system, calibrated by a meta-heuristic optimization method. The proposed framework has been validated through case studies, confirming its accuracy and efficiency.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Jie Hu, Weiping Wen, Chenyu Zhang, Changhai Zhai, Shunshun Pei, Zhenghui Wang
Summary: A deep learning-based rapid peak seismic response prediction model is proposed for the most common two-story and three-span subway stations. The model predicts the peak seismic responses of subway stations using a data-driven approach and limited information, achieving good predictive performance and generalization ability, and demonstrating significantly higher computational efficiency compared to numerical simulation methods.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Jin Ho Lee, Jeong-Rae Cho
Summary: A simplified model is proposed to estimate the earthquake responses of a rectangular liquid storage tank considering the fluid-structure interactions. The complex three-dimensional structural behavior of the tank is represented by a combination of fundamental modes of a rectangular-ring-shaped frame structure and a cantilever beam. The system's governing equation is derived, and earthquake responses such as deflection, hydrodynamic pressure, base shear, and overturning moment are obtained from the solution.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
W. J. Lewis, J. M. Russell, T. Q. Li
Summary: The work discusses the key features and advantages of optimal 2-pin arches shaped by statistically prevalent load and constant axial stress. It extends the design space of symmetric arches to cover asymmetric forms and provides minimum values of constant stress for form-finding of such arches made of different materials. The analysis shows that constant stress arches exhibit minimal stress response and have potential implications for sustainability and durability of future infrastructure.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Wen-ming Zhang, Han-xu Zou, Jia-qi Chang, Tian-cheng Liu
Summary: Saddle position is crucial in the construction and control of suspension bridges. This study proposes an analytical approach to estimate the saddle positions in the completed bridge state and discusses the calculation under different definitions. The relationship between the saddle position and the tower's centerline is analyzed, along with the eccentric compression of the tower. The feasibility of the proposed method is verified through a real-life suspension bridge.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Shaise K. John, Alessio Cascardi, Yashida Nadir
Summary: This study experimentally investigated the use of TRM material for reinforcing concrete columns. The results showed that increasing the number of textile layers effectively increased the axial strength. Additionally, the choice of fiber type and hybrid textile configuration also had a significant impact on strength improvement. A new design model that considers the effects of both the confining matrix and textile was proposed.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Chandrashekhar Lakavath, S. Suriya Prakash
Summary: This study experimentally investigated the shear behavior of post-tensioned UHPFRC girders, considering factors such as prestress level, fiber volume fraction, and types of steel fibers. The results showed that increasing prestress and fiber dosage could enhance the ultimate load-carrying capacity of the girders, reduce crack angle, and increase shear cracking load.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Vahid Goodarzimehr, Siamak Talatahari, Saeed Shojaee, Amir H. Gandomi
Summary: In this paper, an Improved Marine Predators Algorithm (IMPA) is proposed for size and shape optimization of truss structures subject to natural frequency constraints. The results indicate that IMPA performs better in solving these nonlinear structural optimization problems compared to other state-of-the-art algorithms.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Chun-Xu Qu, Jin-Zhao Jiang, Ting-Hua Yi, Hong-Nan Li
Summary: In this paper, a computer vision-based method is proposed to monitor the deformation and displacement of building structures by obtaining 3D coordinates of surface feature points. The method can acquire a large number of 3D coordinates in a noncontact form, improve the flexibility and density of measurement point layout, and is simple and cost-effective to operate.
ENGINEERING STRUCTURES
(2024)