Article
Computer Science, Interdisciplinary Applications
Seyed Omid Sajedi, Xiao Liang
Summary: This paper explores the use of deep learning and Bayesian inference in structural health monitoring, addressing prediction uncertainty and conducting three case studies. The uncertainty metrics show correlations with misclassifications, and a surrogate model is proposed to trigger human interventions.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2021)
Review
Construction & Building Technology
Raza Ali, Joon Huang Chuah, Mohamad Sofian Abu Talip, Norrima Mokhtar, Muhammad Ali Shoaib
Summary: This article reviews the application of Convolutional Neural Networks (CNN) in civil structure crack detection, emphasizing the importance of CNN in image classification and segmentation, as well as analyzing recent developments. In addition to discussing machine learning methods, it also introduces the limitations of manual processing and image processing techniques in crack detection.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Computer Science, Artificial Intelligence
Ji-Wan Ham, Siheon Jeong, Min-Gwan Kim, Joon-Young Park, Ki-Yong Oh
Summary: This paper proposes a novel and practical crack-detection method for infrastructure using a multiscale multilevel mask deep convolutional neural network and a line similarity index. Field tests demonstrate the effectiveness of the proposed method in accurately estimating crack candidates and eliminating non-crack candidates, even when trained with only public image-sets.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Vidyanand Mishra, Lalit Kane
Summary: The paper proposes a genetic algorithm-based method for selecting a convolutional neural network architecture. By optimizing the encoding scheme, the initialization of the population, the generation of offspring, and the fitness function, the algorithm's efficiency and performance are improved. Experimental results on the MNIST, Fashion_MNIST, and CIFAR-10 datasets demonstrate that the method achieves comparable accuracy, convergence rate, and computation resources consumption to the best manual and automatic approaches.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Chemistry, Analytical
Youheng Guo, Xuesong Shen, James Linke, Zihao Wang, Khalegh Barati
Summary: Aging infrastructure is a global concern due to its potential economic and social destruction if it collapses. This paper proposes an efficient approach that utilizes 3D point cloud reconstruction and deep learning technology to accurately detect and quantify minor defects on complicated infrastructures.
Article
Materials Science, Characterization & Testing
Roberto Miorelli, Clement Fisher, Andrii Kulakovskyi, Bastien Chapuis, Olivier Mesnil, Oscar D'Almeida
Summary: This paper presents an automatic defect localization and sizing procedure for Structural Health Monitoring using guided waves imaging, applied to an aluminum plate with active piezoelectric sensors. The strategy utilizes a convolutional neural network trained on numerical simulations of guided wave signals and processed by the delay and sum imaging algorithm, showing effectiveness in inverting both synthetic and experimental data.
NDT & E INTERNATIONAL
(2021)
Article
Computer Science, Artificial Intelligence
Nhung Hong Thi Nguyen, Stuart Perry, Don Bone, Ha Thanh Le, Thuy Thi Nguyen
Summary: This paper proposes a new method utilizing a two-stage convolutional neural network for road crack detection and segmentation, which outperforms existing approaches in handling noisy, low-resolution images, and imbalanced datasets with an F1-measure of over 0.91 on three datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Vidyanand Mishra, Lalit Kane
Summary: This article presents a comprehensive study on recent approaches in the design and training of CNN architecture, discussing the advantages and disadvantages of manual and automated CNN architecture selection. A comparison is made between them based on accuracy and parameter range in existing benchmark datasets. The ongoing issues and challenges involved in evolutionary algorithms-based CNN architecture design are also discussed.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Chemistry, Analytical
Daegyun Choi, William Bell, Donghoon Kim, Jichul Kim
Summary: Structural cracks are crucial in assessing the health of aging structures. This study proposes a framework for detecting and locating cracks using image data from a UAV and a deep learning model, showcasing an effective way to identify cracks and their positions.
Article
Engineering, Electrical & Electronic
Bin Zhang, Xiaobin Hong, Yuan Liu
Summary: The proposed deep convolutional neural network probability imaging algorithm provides an automatic high-level damage index extraction method for guided wave imaging, overcoming the limitations of manual feature extraction and showing good generalization and performance in detecting damage.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Construction & Building Technology
Xingzhong Nong, Xu Luo, Shan Lin, Yanmei Ruan, Xijun Ye
Summary: This paper proposes an automatic data anomaly diagnosis method for SHM based on a multimodal deep neural network. By fusing 2D and 1D sensor data features, the detection accuracy is improved, and the effectiveness and feasibility of the proposed method are verified on monitored data of a long-span cable-stayed bridge. The proposed method shows a promising future as a reliable AI-assisted digital tool for safety assessment in structural health monitoring systems.
Article
Construction & Building Technology
Xiaojian Han, Zhicheng Zhao, Lingkun Chen, Xiaolun Hu, Yuan Tian, Chencheng Zhai, Lu Wang, Xiaoming Huang
Summary: This article proposes a hybrid technique based on CNN and digital image processing to identify fractures in photos of concrete structures. With transfer learning, a CNN trained on a small dataset achieves high accuracy.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Engineering, Multidisciplinary
Youzhi Tang, Allen A. Zhang, Lei Luo, Guolong Wang, Enhui Yang
Summary: This paper introduces an encoder-decoder network (EDNet) for crack segmentation to address the quantity imbalance issue between crack and non-crack pixels. Experimental results demonstrate that EDNet outperforms other state-of-the-art models in crack detection.
Review
Computer Science, Interdisciplinary Applications
Majdi Flah, Itzel Nunez, Wassim Ben Chaabene, Moncef L. Nehdi
Summary: Machine learning algorithms have gained great interest in the field of Structural Health Monitoring for their ability to efficiently detect damage in civil engineering structures. This systematic review categorizes the diverse ML algorithms into vibration-based SHM and image-based SHM, providing detailed analysis and recommendations for future research.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2021)
Article
Multidisciplinary Sciences
Yuyeon Jung, Taewan Kim, Mi-Ryung Han, Sejin Kim, Geunyoung Kim, Seungchul Lee, Youn Jin Choi
Summary: In this study, a convolutional neural network model was developed to classify ovarian tumors using pre-processed and augmented ultrasound images. The performance of the model was evaluated through cross-validation and validated qualitatively using Grad-CAM. The results demonstrated the accuracy and feasibility of the model.
SCIENTIFIC REPORTS
(2022)
Article
Energy & Fuels
Ehsan Sorooshnia, Payam Rahnamayiezekavat, Maria Rashidi, Mahsan Sadeghi, Bijan Samali
Summary: The penetration of daylight has a significant impact on the thermal and daylight performance of buildings, providing sunlight and creating a pleasant indoor environment. Recently, there has been more attention on providing daylight in the rear part of indoor spaces for sustainable building design. Passive Anidolic Daylighting Systems (ADS) are effective tools for collecting and redistributing sunlight towards the back of the room. This study aims to find the optimum curve for optimizing daylight admission without the need for an expensive active tracking system, considering visual and thermal comfort as well as energy consumption. By optimizing the ADS curve, significant improvements were achieved in daylight factor, heating load, artificial lighting energy, and predicted percentage dissatisfied.
Article
Construction & Building Technology
Faraz Sadeghi, Mohsen Mousavi, Xinqun Zhu, Maria Rashidi, Bijan Samali, Amir H. Gandomi
Summary: This paper presents a novel method for detecting damage in steel-concrete composite beams by using variational mode decomposition (VMD) of shear slip data. The results show that the proposed method is successful in detecting damage and can be considered as a reliable and robust technique.
JOURNAL OF STRUCTURAL ENGINEERING
(2023)
Article
Engineering, Mechanical
Zhenghao Ding, Yang Yu, Yong Xia
Summary: In this paper, a method based on long short-term memory neural network is proposed to identify nonlinear hysteresis parameters. The accuracy and generalization ability are improved by applying principal component analysis technique and attention mechanism. Numerical and experimental results demonstrate the effectiveness and computational efficiency of the proposed method.
NONLINEAR DYNAMICS
(2023)
Article
Instruments & Instrumentation
Xingyang Xie, Yuguo Cui, Yang Yu, Pan Chen
Summary: This paper proposes a computationally efficient model to describe the nonlinear and hysteresis behaviors of PZT actuators. The model parameters are analyzed and a modified cuckoo search algorithm is used to identify the parameters. The performance of the proposed model is validated using experimental data, and the rate-dependence of the parameters is analyzed.
SMART MATERIALS AND STRUCTURES
(2023)
Review
Computer Science, Interdisciplinary Applications
De-Graft Joe Opoku, Srinath Perera, Robert Osei-Kyei, Maria Rashidi, Keivan Bamdad, Tosin Famakinwa
Summary: Digital twin (DT) has great potential in the construction industry (CI) but there are barriers hindering its adoption. This study identifies and categorizes these barriers to provide a framework for the adoption of DT in the CI. The top five barriers include low knowledge level, low technology acceptance, lack of clear value propositions, project complexities, and static nature of building data.
Article
Environmental Sciences
Azadeh Noori Hoshyar, Maria Rashidi, Yang Yu, Bijan Samali
Summary: Structural health monitoring (SHM) is crucial in engineering to manage degradation risks caused by defects. Various models implementing machine learning techniques have been developed to quantify the health state of bridges. In this study, support vector machine (SVM) algorithms are proposed and compared with basic SVM in a laboratory experiment at Western Sydney University, aiming to automate and improve SHM.
Article
Computer Science, Information Systems
Mohd Anjum, Sana Shahab, Yang Yu, Habib Figa Guye
Summary: In the Internet of Things (IoT), security is crucial for secure communication, transactions, and authentication. The Permutated Security Framework (PSF) is designed to address the security issues in IoT by providing secure communication, transactions, and authentication. The framework utilizes time intervals and end-verifiable keys generated using the RSA technique to manage transaction security and adapt to changes in the system.
Article
Medicine, General & Internal
Malathi Velu, Rajesh Kumar Dhanaraj, Balamurugan Balusamy, Seifedine Kadry, Yang Yu, Ahmed Nadeem, Hafiz Tayyab Rauf
Summary: While the world is focusing on repairing the damage caused by COVID-19, there is a growing concern about the monkeypox virus becoming a global pandemic. This paper presents two strategies, based on reinforcement learning and parameter optimization, for improving the precision of monkeypox image classification. The proposed methods show promising results in terms of accuracy and effectiveness.
Article
Medicine, General & Internal
Mohd Anjum, Sana Shahab, Yang Yu
Summary: Neurodegenerative diseases involve the progressive loss of function of neurons in the brain and spinal cord, resulting in a range of symptoms. The causes are poorly understood, but factors like ageing, genetics, medical conditions, toxins, and environmental exposures contribute. Early recognition of these diseases is essential, and advanced AI technologies are being used in healthcare systems for detection. This research article introduces a method for early detection and monitoring using deep recurrent learning and pattern recognition, which achieved high accuracy and reduced variance and verification time.
Review
Chemistry, Analytical
Arash Rayegani, Ali Matin Nazar, Maria Rashidi
Summary: The development of triboelectric nanogenerators (TENGs) has led to significant advancements in self-powered sensing, with improved efficiency, effectiveness, and sensitivity. TENGs have high sensitivity and efficiency, and previous research has shown that road conditions play a major role in accidents. This paper discusses monitoring driving behavior and self-powered sensors impacted by TENGs, as well as energy harvesting and sustainability in smart road environments. It provides valuable insights for utilizing these technologies for innovative purposes.
Article
Engineering, Civil
Saeid Talaei, Xinqun Zhu, Jianchun Li, Yang Yu, Tommy H. T. Chan
Summary: In this research, a novel transfer learning-based approach is presented for identifying the location of damage in concrete bridges utilizing the time-frequency characteristics from dynamic responses of the bridge under moving vehicles.
Article
Construction & Building Technology
Feng Guo, Yuzhuo Zhang, Chunguang Chang, Yang Yu
Summary: The construction industry accounts for nearly 40% of global carbon emissions, making it a high-energy-consumption industry. Prefabricated assembly technology is effective in reducing carbon emissions, but the higher cost of prefabricated components compared to cast-in-place components discourages enterprises from choosing this technology. This study aims to analyze the relationship between carbon emissions and costs in prefabricated buildings and proposes a dual-objective optimization method to minimize both cost and carbon emissions. The results show that a prefabrication rate of 35-40% can achieve the maximum carbon reduction effect with the minimum cost. This study provides valuable insights for government policies on energy conservation and emission reduction in prefabricated buildings, as well as for enterprise decision-making regarding carbon emission reduction and cost.
Article
Engineering, Civil
Masoud Mohammadi, Maria Rashidi, Mojtaba Gorji Azandariani, Vahid Mousavi, Yang Yu, Bijan Samali
Summary: With the rise of construction of structures worldwide, there is an increasing demand for structural health monitoring and assessment. Terrestrial laser scanner (TLS) is a state-of-the-art technology that simplifies structural survey and assessment by rapidly acquiring high-precision 3D data points from the entire structure surface. This technology has the potential to greatly benefit engineers in generating realistic 3D models and identifying structural deformities. However, there is limited research on the accuracy of TLS in structural monitoring and assessment.
Article
Pharmacology & Pharmacy
Yimin Yu, Jingjing He, Zhiwei Huang, Yan Li, Ying Wu, Yifeng Shen, Yanling Zhou, Cungang Bao, Zhiping Jin, Huafang Li
Summary: This study evaluated the pharmacokinetic profiles and safety of JX11502MA in healthy volunteers, and found that it was well tolerated at doses ranging from 0.25 to 3 mg, suggesting it has the potential to be a favorable treatment option for schizophrenia patients.
EXPERT OPINION ON INVESTIGATIONAL DRUGS
(2023)
Article
Construction & Building Technology
Jiehong Li, Ailar Hajimohammadi, Yang Yu, Bang Yeon Lee, Taehwan Kim
Summary: This research quantitatively analyzed the microstructural properties of Polyvinyl alcohol (PVA) fiber-reinforced foam concretes and found that fiber size and content have a significant impact on the compressive strength of foam concrete. The study also revealed that the mechanism of reinforcement differs in high-density and low-density foam concretes, with fiber distribution having a dominant influence in high-density foam concrete and significant influence on pore structure in low-density foam concrete.
JOURNAL OF MATERIALS IN CIVIL ENGINEERING
(2023)