Automated damage diagnosis of concrete jack arch beam using optimized deep stacked autoencoders and multi-sensor fusion

Yu, Yang; Li, Jiantao; Li, Jianchun; Xia, Yong; Ding, Zhenghao; Samali, Bijan

doi:10.1016/j.dibe.2023.100128

Cited by 46 publications

(26 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, an optimizing algorithm was designed to modify its configuration to make Linear SVM an effective component learner in AdaBoost. The authors in Yu et al [ 343 ] proposed a hybrid framework for structural damage diagnosis based on principal component analysis (PCA), deep stacked autoencoders (DSAE), and data fusion. To improve the diagnosis model, the authors optimized the meta-parameters of DSAE using the enhanced whale optimization algorithm (EWOA), which included the dropout parameter, the weight decay coefficient, the learning rate, and the hidden layer neuron numbers.…”

Section: Optimization Algorithmsmentioning

confidence: 99%

A Systematic Review of Optimization Algorithms for Structural Health Monitoring and Optimal Sensor Placement

Hassani

Dackermann

2023

Sensors

View full text Add to dashboard Cite

In recent decades, structural health monitoring (SHM) has gained increased importance for ensuring the sustainability and serviceability of large and complex structures. To design an SHM system that delivers optimal monitoring outcomes, engineers must make decisions on numerous system specifications, including the sensor types, numbers, and placements, as well as data transfer, storage, and data analysis techniques. Optimization algorithms are employed to optimize the system settings, such as the sensor configuration, that significantly impact the quality and information density of the captured data and, hence, the system performance. Optimal sensor placement (OSP) is defined as the placement of sensors that results in the least amount of monitoring cost while meeting predefined performance requirements. An optimization algorithm generally finds the “best available” values of an objective function, given a specific input (or domain). Various optimization algorithms, from random search to heuristic algorithms, have been developed by researchers for different SHM purposes, including OSP. This paper comprehensively reviews the most recent optimization algorithms for SHM and OSP. The article focuses on the following: (I) the definition of SHM and all its components, including sensor systems and damage detection methods, (II) the problem formulation of OSP and all current methods, (III) the introduction of optimization algorithms and their types, and (IV) how various existing optimization methodologies can be applied to SHM systems and OSP methods. Our comprehensive comparative review revealed that applying optimization algorithms in SHM systems, including their use for OSP, to derive an optimal solution, has become increasingly common and has resulted in the development of sophisticated methods tailored to SHM. This article also demonstrates that these sophisticated methods, using artificial intelligence (AI), are highly accurate and fast at solving complex problems.

show abstract

Section: Optimization Algorithmsmentioning

confidence: 99%

A Systematic Review of Optimization Algorithms for Structural Health Monitoring and Optimal Sensor Placement

Hassani

Dackermann

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The use of machine learning (ML) and deep learning (DL) for categorization and identification purposes has been a hot topic for a while. In recent years, artificial intelligence (AI) technology based on CNN has been widely applied in various fields [21,22]. This study evaluates the proposed method using the LC25000 histopathology imaging dataset of lung cancer, which was released in 2020.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification

et al. 2023

View full text Add to dashboard Cite

The most dangerous disease in recent decades is lung cancer. The most accurate method of cancer diagnosis, according to research, is through the use of histopathological images that are acquired by a biopsy. Deep learning techniques have achieved success in bioinformatics, particularly medical imaging. In this paper, we present an innovative method for rapidly identifying and classifying histopathology images of lung tissues by combining a newly proposed Convolutional Neural Networks (CNN) model with a few total parameters and the enhanced Light Gradient Boosting Model (LightGBM) classifier. After the images have been pre-processed in this study, the proposed CNN technique is provided for feature extraction. Then, the LightGBM model with multiple threads has been used for lung tissue classification. The simulation result, applied to the LC25000 dataset, demonstrated that the novel technique successfully classifies lung tissue with 99.6% accuracy and sensitivity. Furthermore, the proposed CNN model has achieved the lowest training parameters of only one million parameters, and it has also achieved the shortest processing time of just one second throughout the feature extraction process. When this result is compared with the most recent state-of-the-art approaches, the suggested approach has increased effectiveness in the areas of both disease classification accuracy and processing time.

show abstract

“…In many complex situations, different classes of signals are not easily classified manually, even if the unique and important features of the signals are well selected, in which case feature learning becomes crucial. As opposed to manual learning, in the early 21st century, researchers have applied various machine learning algorithms to signal recognition: Yu et al uses principal component analysis to eliminate the noise caused by the vibration response of the structure [30]. Aslam et al combine genetic programming and K-nearest neighbor for automatic modulation classification, and experiments show that four modulation types, including BPSK, QPSK, QAM16 and QAM64, can be effectively distinguished from each other [31].…”

Section: Related Workmentioning

confidence: 99%

A novel multi-featured decision system for multi-classification tasks

Xu¹

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Feature engineering is a difficult task, and for real signal data, it is difficult to find a certain feature that can easily distinguish all classes. Multiple features can provide more information, which means the fusion of multi-feature learning strategies has potential significant advantages. Based on this premise, this paper proposes a multi-class framework based on the multi-featured decision to distinguish all the different classes, and takes Automatic Dependent Surveillance-Broadcast (ADS-B) signal data as an example, first extracts the phase features and wavelet decomposition features of the signal data, then selects the features with high discrimination between classes, then proposes a one-dimensional residual neural network based on 16 convolutional layers to learn the unique features of different features and classes separately, and finally proposes a novel multi-featured decision method based on voting method and a priori probability. Results show that the proposed one-dimensional residual neural network has better performance metrics on the test set compared to some machine learning-based and neural network-based algorithms, with classification accuracies of 86.1%, 84.6% and 83.6% on wavelet decomposition features, raw features and phase features, respectively, on ADS-B preamble signals. The proposed feature decision framework based on the voting method and a priori probability has a recall, precision and F1 value of 80.24%, 89.89% and 84.79% on ADS-B preamble signals, respectively.

show abstract

Automated damage diagnosis of concrete jack arch beam using optimized deep stacked autoencoders and multi-sensor fusion

Cited by 46 publications

References 34 publications

A Systematic Review of Optimization Algorithms for Structural Health Monitoring and Optimal Sensor Placement

A Systematic Review of Optimization Algorithms for Structural Health Monitoring and Optimal Sensor Placement

An Efficient Combination of Convolutional Neural Network and LightGBM Algorithm for Lung Cancer Histopathology Classification

A novel multi-featured decision system for multi-classification tasks

Contact Info

Product

Resources

About