Research

17 pages, 4826 KiB

Open AccessArticle

A Sparse Learning Method with Regularization Parameter as a Self-Adaptation Strategy for Rolling Bearing Fault Diagnosis

by Yijie Niu, Wu Deng, Xuesong Zhang, Yuchun Wang, Guoqing Wang, Yanjuan Wang and Pengpeng Zhi

Electronics 2023, 12(20), 4282; https://doi.org/10.3390/electronics12204282 - 16 Oct 2023

Cited by 1 | Viewed by 601

Abstract

Sparsity-based fault diagnosis methods have achieved great success. However, fault classification is still challenging because of neglected potential knowledge. This paper proposes a combined sparse representation deep learning (SR-DEEP) method for rolling bearing fault diagnosis. Firstly, the SR-DEEP method utilizes prior domain knowledge [...] Read more.

Sparsity-based fault diagnosis methods have achieved great success. However, fault classification is still challenging because of neglected potential knowledge. This paper proposes a combined sparse representation deep learning (SR-DEEP) method for rolling bearing fault diagnosis. Firstly, the SR-DEEP method utilizes prior domain knowledge to establish a sparsity-based fault model. Then, based on this model, the corresponding regularization parameter regression networks are trained for different running states, whose core is to explore the latent relationship between the regularization parameters and running states. Subsequently, the performance of the fault classification is improved by embedding the trained regularization parameter regression networks into the sparse representation classification method. This strategy improves the adaptability of the sparse regularization parameter, further improving the performance of the fault classification method. Finally, the applicability of the SR-DEEP method for rolling bearing fault diagnosis is validated with the CWRU platform and QPZZ-II platform, demonstrating that SR-DEEP yields superior accuracies of 100% and 99.20% for diagnosing four and five running states, respectively. Comparative studies show that the SR-DEEP method outperforms four sparse representation methods and seven classical deep learning classification methods in terms of the classification performance. Full article

(This article belongs to the Special Issue Artificial Intelligence Based on Data Mining)

► Show Figures

Figure 1

25 pages, 7815 KiB

Open AccessArticle

Improvement of DBSCAN Algorithm Based on K-Dist Graph for Adaptive Determining Parameters

by Lifeng Yin, Hongtao Hu, Kunpeng Li, Guanghai Zheng, Yingwei Qu and Huayue Chen

Electronics 2023, 12(15), 3213; https://doi.org/10.3390/electronics12153213 - 25 Jul 2023

Cited by 1 | Viewed by 1777

Abstract

For the shortcomings of an unstable clustering effect and low accuracy caused by the manual setting of the two parameters Eps and MinPts of the DBSCAN (density-based spatial clustering of applications with noise) algorithm, this paper proposes an adaptive determination method for DBSCAN [...] Read more.

For the shortcomings of an unstable clustering effect and low accuracy caused by the manual setting of the two parameters Eps and MinPts of the DBSCAN (density-based spatial clustering of applications with noise) algorithm, this paper proposes an adaptive determination method for DBSCAN algorithm parameters based on the K-dist graph, noted as X-DBSCAN. The algorithm uses the least squares polynomial curve fitting method to fit the curve in the K-dist graph to generate a list of candidate Eps parameters and uses the mathematical expectation method and noise reduction threshold to generate the corresponding MinPts parameter list. According to the clustering results of each group of parameters in the Eps and MinPts parameter lists, a stable range of cluster number changes is found, and the MinPts and Eps corresponding to the maximum K value in the stable range are selected as the optimal algorithm parameters. The optimality of this parameter was verified using silhouette coefficients. A variety of experiments were designed from multiple angles on the artificial dataset and the UCI real dataset. The experimental results show that the clustering accuracy of X-DBSCAN was 21.83% and 15.52% higher than that of DBSCAN on the artificial and real datasets, respectively. The X-DBSCAN algorithm was also superior to other algorithms through comprehensive evaluation and analysis of various clustering indicators. In addition, experiments on four synthetic Gaussian datasets of different dimensions showed that the average clustering indices of the proposed algorithm were above 0.999. The X-DBSCAN algorithm can select parameters adaptively in combination with the characteristics of the dataset; the clustering effect is better, and clustering process automation is realized. Full article

(This article belongs to the Special Issue Artificial Intelligence Based on Data Mining)

► Show Figures

Figure 1

15 pages, 4814 KiB

Open AccessArticle

Rail Surface Defect Detection Based on Image Enhancement and Improved YOLOX

by Chunguang Zhang, Donglin Xu, Lifang Zhang and Wu Deng

Electronics 2023, 12(12), 2672; https://doi.org/10.3390/electronics12122672 - 14 Jun 2023

Cited by 4 | Viewed by 2028

Abstract

During the long and high-intensity railway use, all kinds of defects emerge, which often produce light to moderate damage on the surface, which adversely affects the stable operation of trains and even endangers the safety of travel. Currently, models for detecting rail surface [...] Read more.

During the long and high-intensity railway use, all kinds of defects emerge, which often produce light to moderate damage on the surface, which adversely affects the stable operation of trains and even endangers the safety of travel. Currently, models for detecting rail surface defects are ineffective, and self-collected rail surface images have poor illumination and insufficient defect data. In light of the aforementioned problems, this article suggests an improved YOLOX and image enhancement method for detecting rail surface defects. First, a fusion image enhancement algorithm is used in the HSV space to process the surface image of the steel rail, highlighting defects and enhancing background contrast. Then, this paper uses a more efficient and faster BiFPN for feature fusion in the neck structure of YOLOX. In addition, it introduces the NAM attention mechanism to increase image feature expression capability. The experimental results show that the detection of rail surface defects using the algorithm improves the mAP of the YOLOX network by 2.42%. The computational volume of the improved network increases, but the detection speed can still reach 71.33 fps. In conclusion, the upgraded YOLOX model can detect rail surface flaws with accuracy and speed, fulfilling the demands of real-time detection. The lightweight deployment of rail surface defect detection terminals also has some benefits. Full article

(This article belongs to the Special Issue Artificial Intelligence Based on Data Mining)

► Show Figures

Figure 1

13 pages, 2411 KiB

Open AccessArticle

Laser Image Enhancement Algorithm Based on Improved EnlightenGAN

by Youchen Fan, Yitong Wang, Kai Feng, Yuntian Liu, Yawen Jiang, Jiaxuan Xie, Yufei Niu and Hongyan Wang

Electronics 2023, 12(9), 2081; https://doi.org/10.3390/electronics12092081 - 02 May 2023

Viewed by 1137

Abstract

In distance-selected imaging, the contrast of laser images is reduced due to long imaging distances, insufficient laser power, and atmospheric turbulence. An enhancement algorithm based on the EnlightenGAN network is proposed to improve the contrast of laser images. Firstly, the laser images are [...] Read more.

In distance-selected imaging, the contrast of laser images is reduced due to long imaging distances, insufficient laser power, and atmospheric turbulence. An enhancement algorithm based on the EnlightenGAN network is proposed to improve the contrast of laser images. Firstly, the laser images are acquired using a distance selection pass system to establish the laser image dataset and expand the dataset, and the traditional algorithm is used to enhance the images and establish the mapping relationship between low-quality images and high-quality images. The global discriminator based on PatchGAN with the improved VGG model is used to regularize the self-feature retention loss and construct the depth link between the global discriminator and the local discriminator to improve the generalization ability of the model; adjust the attention map to the second layer before the CLB convolution module and also add the residual structure in the second layer CLB to improve the robustness of the model; adopt the idea of gray-scale layering with a low drop and high rise to improve the self regularization mechanism to achieve the enhancement of the key region; finally, use the improved EnlightenGAN to fit the relationship between a low-quality image and high-quality image. Finally, EnlightenGAN is used to fit the relationship between low-quality images and high-quality images, extract laser image features, and enhance low-quality images. The experimental results show that the improved algorithm improves PSNR by 12.3% and 0.7% on average, SSIM by 57% and 10.3% on average, and NIQE by 21% and 13% on average compared to other algorithms and the original EnlightenGAN algorithm, respectively. The algorithm improves the signal-to-noise ratio and contrast of laser images with richer image details. It provides a new idea for pre-processing laser images. Full article

(This article belongs to the Special Issue Artificial Intelligence Based on Data Mining)

► Show Figures

Figure 1

18 pages, 5017 KiB

Open AccessArticle

Improved Salp Swarm Algorithm for Tool Wear Prediction

by Yu Wei, Weibing Wan, Xiaoming You, Feng Cheng and Yuxuan Wang

Electronics 2023, 12(3), 769; https://doi.org/10.3390/electronics12030769 - 03 Feb 2023

Cited by 4 | Viewed by 1125

Abstract

To address the defects of the salp swarm algorithm (SSA) such as the slow convergence speed and ease of falling into a local minimum, a new salp swarm algorithm combining chaotic mapping and decay factor is proposed and combined with back propagation (BP) [...] Read more.

To address the defects of the salp swarm algorithm (SSA) such as the slow convergence speed and ease of falling into a local minimum, a new salp swarm algorithm combining chaotic mapping and decay factor is proposed and combined with back propagation (BP) neural network to achieve an effective prediction of tool wear. Firstly, the chaotic mapping is used to enhance the formation of the population, which facilitates the iterative search and reduces the trapping in the local optimum; secondly, the decay factor is introduced to improve the update of the followers so that the followers can be updated adaptively with the iterations, and the theoretical analysis and validation of the improved SSA are carried out using benchmark test functions. Finally, the improved SSA with a strong optimization capability to solve BP neural networks for the optimal values of hyperparameters is used. The validity of this is verified by using the actual tool wear data set. The test results of the benchmark test function show that the algorithm presented has a better convergence speed and solution accuracy. Meanwhile, compared with the original algorithm, the R² value of the part life prediction model proposed is improved from 0.962 to 0.989, the MSE value is reduced from the original 34.4 to 9.36, which is a 72% improvement compared with the original algorithm, and a better prediction capability is obtained. Full article

(This article belongs to the Special Issue Artificial Intelligence Based on Data Mining)

► Show Figures

Figure 1

14 pages, 1398 KiB

Open AccessArticle

Analysis of Differences in Self-Regulated Learning Behavior Patterns of Online Learners

by Zi Ye, Lei Jiang, Yang Li, Zhaoting Wang, Guodao Zhang and Huiling Chen

Electronics 2022, 11(23), 4013; https://doi.org/10.3390/electronics11234013 - 03 Dec 2022

Cited by 5 | Viewed by 1899

Abstract

Self-regulated learning is one of the important skills to achieve learning goals and is also the key factor to ensure the quality of online learning. With the rapid development of intelligent education and information technology, online learning behavior has become a new trend [...] Read more.

Self-regulated learning is one of the important skills to achieve learning goals and is also the key factor to ensure the quality of online learning. With the rapid development of intelligent education and information technology, online learning behavior has become a new trend in the development of education modernization. Behavior data of online learning platforms are an important carrier to reflect the learners’ initiative to plan, monitor, and regulate their learning process. Self-regulated learning (SRL) is one of the important skills to achieve learning goals and is an essential means to ensure the quality of online learning. However, there are still great challenges in studying the types and sequential patterns of learners’ self-regulated learning behaviors in online environments. In addition, for higher education, the defects of the traditional education mode are increasingly prominent, and self-regulated learning (SRL) has become an inevitable trend. Based on Zimmerman’s self-regulation theory model, this paper first classifies learning groups using the hierarchical clustering method. Then, lag sequence analysis is used to explore the most significant differences in SRL behavior and its sequence patterns among different learning groups. Finally, the differences in academic achievement among different groups are discussed. The results are as follows: (1) The group with more average behavior frequency tends to solve online tasks actively, presenting a “cognitive oriented” sequential pattern, and this group has the best performance; (2) the group with more active behavior frequency tends to improve in the process of trial and error, showing a “reflective oriented” sequence pattern, and this group has better performance; (3) the group with the lowest behavior frequency tends to passively complete the learning task, showing a “negative regulated” sequence pattern, and this group has poor performance. From the aspects of stage and outcome of self-regulated learning, the behavior sequence and learning performance of online learning behavior mode are compared, and the learning path and learning performance of different learning modes are fully analyzed, which can provide reference for the improvement of online learning platform and teachers’ teaching intervention. Full article

(This article belongs to the Special Issue Artificial Intelligence Based on Data Mining)

► Show Figures

Figure 1

20 pages, 1045 KiB

Open AccessArticle

Privacy-Enhanced Federated Learning: A Restrictively Self-Sampled and Data-Perturbed Local Differential Privacy Method

by Jianzhe Zhao, Mengbo Yang, Ronglin Zhang, Wuganjing Song, Jiali Zheng, Jingran Feng and Stan Matwin

Electronics 2022, 11(23), 4007; https://doi.org/10.3390/electronics11234007 - 02 Dec 2022

Cited by 3 | Viewed by 1669

Abstract

As a popular distributed learning framework, federated learning (FL) enables clients to conduct cooperative training without sharing data, thus having higher security and enjoying benefits in processing large-scale, high-dimensional data. However, by sharing parameters in the federated learning process, the attacker can still [...] Read more.

As a popular distributed learning framework, federated learning (FL) enables clients to conduct cooperative training without sharing data, thus having higher security and enjoying benefits in processing large-scale, high-dimensional data. However, by sharing parameters in the federated learning process, the attacker can still obtain private information from the sensitive data of participants by reverse parsing. Local differential privacy (LDP) has recently worked well in preserving privacy for federated learning. However, it faces the inherent problem of balancing privacy, model performance, and algorithm efficiency. In this paper, we propose a novel privacy-enhanced federated learning framework (Optimal LDP-FL) which achieves local differential privacy protection by the client self-sampling and data perturbation mechanisms. We theoretically analyze the relationship between the model accuracy and client self-sampling probability. Restrictive client self-sampling technology is proposed which eliminates the randomness of the self-sampling probability settings in existing studies and improves the utilization of the federated system. A novel, efficiency-optimized LDP data perturbation mechanism (Adaptive-Harmony) is also proposed, which allows an adaptive parameter range to reduce variance and improve model accuracy. Comprehensive experiments on the MNIST and Fashion MNIST datasets show that the proposed method can significantly reduce computational and communication costs with the same level of privacy and model utility. Full article

(This article belongs to the Special Issue Artificial Intelligence Based on Data Mining)

► Show Figures

Graphical abstract

26 pages, 2512 KiB

Open AccessArticle

Vertically Federated Learning with Correlated Differential Privacy

by Jianzhe Zhao, Jiayi Wang, Zhaocheng Li, Weiting Yuan and Stan Matwin

Electronics 2022, 11(23), 3958; https://doi.org/10.3390/electronics11233958 - 29 Nov 2022

Viewed by 1722

Abstract

Federated learning (FL) aims to address the challenges of data silos and privacy protection in artificial intelligence. Vertically federated learning (VFL) with independent feature spaces and overlapping ID spaces can capture more knowledge and facilitate model learning. However, VFL has both privacy and [...] Read more.

Federated learning (FL) aims to address the challenges of data silos and privacy protection in artificial intelligence. Vertically federated learning (VFL) with independent feature spaces and overlapping ID spaces can capture more knowledge and facilitate model learning. However, VFL has both privacy and utility problems in framework construction. On the one hand, sharing gradients may cause privacy leakage. On the other hand, the increase in participants brings a surge in the feature dimension of the global model, which results in higher computation costs and lower model accuracy. To address these issues, we propose a vertically federated learning algorithm with correlated differential privacy (CRDP-FL) to meet FL systems’ privacy and utility requirements. A privacy-preserved VFL framework is designed based on differential privacy (DP) between organizations with many network edge devices. Meanwhile, feature selection is performed to improve the algorithm’s efficiency and model performance to solve the problem of dimensionality explosion. We also propose a quantitative correlation analysis technique for VFL to reduce the correlated sensitivity and noise injection, balancing the utility decline due to DP protection. We theoretically analyze the privacy level and utility of CRDP-FL. A real vertically federated learning scenario is simulated with personalized settings based on the ISOLET and Breast Cancer datasets to verify the method’s effectiveness in model accuracy, privacy budget, and data correlation. Full article

(This article belongs to the Special Issue Artificial Intelligence Based on Data Mining)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence Based on Data Mining

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI