An improved generative adversarial network with modified loss function for crack detection in electromagnetic nondestructive testing

Tian, Lulu; Wang, Zidong; Liu, Weibo; Cheng, Yuhua; Alsaadi, Fuad E.; Liu, Xiaohui

doi:10.1007/s40747-021-00477-9

Cited by 14 publications

(4 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, a rising trend of applying advanced deep learning technologies to solve complex problems [16,17] has emerged. The research of talent related complex problems is personnel performance prediction [18], personality trait recognition [19], two critical issues (i.e., talent turnover and job performance) of Person-Organization ft (P-O ft) in talent management [15], turnover prediction [3,6], etc.…”

Section: Related Workmentioning

confidence: 99%

Neural network fusion with fine-grained adaptation learning for turnover prediction

Xue

Sun

Wang

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Turnover prediction has an important impact on alleviating the brain drain, which can help organizations reduce costs and enhance competitiveness. Existing studies on turnover are mainly based on analyzing the turnover correlation, using different models to predict various employee turnover scenarios, and only predicting turnover category, while the class imbalance and turnover possibility have been ignored. To this end, in this paper, we propose a novel fine-grained adaptation-based turnover prediction neural network (FATPNN) model. Specifically, we first employ a GRU to learn profile-aware features representations of the personnel samples. Then, to evaluate the contribution of various turnover factors, we further exploit an attention mechanism to model the profile information. Finally, we creatively design a weighted-based probability loss function suitable for our turnover prediction tasks. Experimental results show the effectiveness and universality of the FATPNN model in terms of turnover prediction.

show abstract

Section: Related Workmentioning

confidence: 99%

Neural network fusion with fine-grained adaptation learning for turnover prediction

Xue

Sun

Wang

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Although deep neural network based (DNN-based) object detectors [1][2][3] exhibit outstanding performance surpassing that of humans, they are vulnerable to adversarial examples (AEs) [4][5][6][7][8][9]. Attackers generate AEs by adding indistinguishable perturbations to input images.…”

Section: Introductionmentioning

confidence: 99%

DIB-UAP: enhancing the transferability of universal adversarial perturbation via deep information bottleneck

Wang,

Zheng,

Chen

et al. 2024

Complex Intell. Syst.

View full text Add to dashboard Cite

Significant structural differences in DNN-based object detectors hinders the transferability of adversarial attacks. Studies show that intermediate features extracted by the detector contain more model-independent information, and disrupting these features can enhance attack transferability across different detectors. However, the challenge lies in selecting crucial features that impact detection from redundant intermediate features. To address this issue, we introduce the Deep information bottleneck universal adversarial perturbation (DIB-UAP). DIB-UAP utilizes the deep information bottleneck to establish a link between intermediate features and model output, extracting crucial intermediate features and disrupting them to generate UAP with strong attack transferability. Additionally, we propose a data augmentation method, Scale & Tile, which effectively enhances the attack performance of UAP on medium and large-scale objects. Testing on two benchmark datasets with eight comparative methods across four black-box mainstream detectors has confirmed the attack transferability of DIB-UAP. Furthermore, practical utility validation of DIB-UAP has been conducted on a commercial object detection platform.

show abstract

“…Data-based methods such as that of the reference [ 27 ] use SMOTE to extend the NILD dataset by a small number of samples so that the number of samples is equal for all classes. Conversely, model-based methods involve reweighting the loss function or directly modifying the loss function [ 28 ]. In addition, the classification performance and efficiency of LightGBM are closely related to the hyperparameter values of the model.…”

Section: Introductionmentioning

confidence: 99%

Optimized LightGBM Power Fingerprint Identification Based on Entropy Features

Lin

Zhang

Zhang³

et al. 2022

Entropy

View full text Add to dashboard Cite

The huge amount of power fingerprint data often has the problem of unbalanced categories and is difficult to upload by the limited data transmission rate for IoT communications. An optimized LightGBM power fingerprint extraction and identification method based on entropy features is proposed. First, the voltage and current signals were extracted on the basis of the time-domain features and V-I trajectory features, and a 56-dimensional original feature set containing six entropy features was constructed. Then, the Boruta algorithm with a light gradient boosting machine (LightGBM) as the base learner was used for feature selection of the original feature set, and a 23-dimensional optimal feature subset containing five entropy features was determined. Finally, the Optuna algorithm was used to optimize the hyperparameters of the LightGBM classifier. The classification performance of the power fingerprint identification model on imbalanced datasets was further improved by improving the loss function of the LightGBM model. The experimental results prove that the method can effectively reduce the computational complexity of feature extraction and reduce the amount of power fingerprint data transmission. It meets the recognition accuracy and efficiency requirements of a massive power fingerprint identification system.

show abstract

An improved generative adversarial network with modified loss function for crack detection in electromagnetic nondestructive testing

Cited by 14 publications

References 56 publications

Neural network fusion with fine-grained adaptation learning for turnover prediction

Neural network fusion with fine-grained adaptation learning for turnover prediction

DIB-UAP: enhancing the transferability of universal adversarial perturbation via deep information bottleneck

Optimized LightGBM Power Fingerprint Identification Based on Entropy Features

Contact Info

Product

Resources

About