DUAN Y C , SHEN X H , WANG H Y . Time-domain anti-interference method for ship radiated noise signal [J ] . EURASIP Journal on Advances in Signal Processing , 2022 , 2022 ( 1 ): 1 - 12 . DOI: 10.1186/s13634-021-00832-5 http://doi.org/10.1186/s13634-021-00832-5 With the continuous increase in social pressure and people’s higher urgency for physical health, the concept of healthy physical fitness has become more and more important and prominent. However, the research and standards for the validity of the health fitness monitoring test indicators have not been determined. In order to compare the validity of the health fitness test indicators, we adopt the cardiopulmonary track and field sensor technology to monitor the health fitness cardiopulmonary track and field sensor. A comparative study on the validity of test indicators, mainly to test the rationality of the cardiopulmonary endurance evaluation indicators of healthy physical fitness, and to carry out a new design of the concept of healthy physical fitness in track and field teaching, so that it is more inclined to improve the healthy physical fitness of athletes fitness. Research data shows that the average absolute value of the athlete’s maximum oxygen consumption is 2.51 L/min, the highest value is 3.96 L/min, and the lowest is 2.03 L/min. The average value of the absolute maximum oxygen consumption of girls is 1.79 L/min, the highest value is 2.89 L/min, and the minimum is 1.51 L/min. From these data, we can know that compared with traditional cardiopulmonary monitoring methods, the sensor monitoring studied in this paper has higher accuracy and wider application range. The peak cardiopulmonary power of athletes’ cardiopulmonary function detection using this method is closer to the actual value, while for the peak cardiopulmonary power detected by traditional methods, there is a big difference between the power and the actual value. For different athletes, the advantages of the algorithm in this paper are more obvious, indicating that the method in this paper has a higher detection accuracy for the cardiopulmonary function test of athletes during aerobic training.

YANG H H , LI J H , SHENG M P . Underwater acoustic target multi-attribute correlation perception method based on deep learning [J ] . Applied Acoustics , 2022 , 190 : 108 - 644 .

ALAM S , SONBHADRA S K , AGARWAL S , et al. One-class support vector classifiers: a survey [J ] . Knowledge-Based Systems , 2020 , 196 : 105754 . DOI: 10.1016/j.knosys.2020.105754 http://doi.org/10.1016/j.knosys.2020.105754 https://linkinghub.elsevier.com/retrieve/pii/S0950705120301647 https://linkinghub.elsevier.com/retrieve/pii/S0950705120301647

LIU B , XIE H X , XIAO Y S . Multi-task analysis discriminative dictionary learning for one-class learning [J ] . Knowledge-Based Systems , 2021 , 227 : 107195 . DOI: 10.1016/j.knosys.2021.107195 http://doi.org/10.1016/j.knosys.2021.107195 https://linkinghub.elsevier.com/retrieve/pii/S0950705121004573 https://linkinghub.elsevier.com/retrieve/pii/S0950705121004573

武玉坤 , 李伟 , 倪敏雅 , 等 . 单类支持向量机融合深度自编码器的异常检测模型 [J ] . 计算机科学 , 2022 , 49 ( 3 ): 144 - 151 . DOI: 10.11896/jsjkx.210100142 http://doi.org/10.11896/jsjkx.210100142 大规模高维不平衡数据是异常检测中的重大挑战。单类支持向量机在处理不平衡数据方面非常有效,但不适合大规模高维数据,同时单类支持向量机的核函数对检测性能也具有重要的影响。文中提出了一个深度自编码器与单类支持向量机相结合的异常检测模型,深度自编码器不仅负责提取特征和降维,同时拟合出了一个自适应核函数。深度自编码器与单类支持向量机共享损失函数,实现了端到端的训练。作为一个整体,模型采用梯度下降法进行联合训练。在4个公开数据集上与其他异常检测方法进行了对比实验。实验结果表明,在AUC以及召回率(RECALL)方面,所提模型的性能优于单核和多核单类支持向量机以及其他模型,并且所提模型在不同异常率时是鲁棒的,在时间复杂度方面也具有非常大的优势。

WU Y K , LI W , NI M Y , et al . Anomaly detection model based on one-class support vector machine and deep autoencoder [J ] . Computer Science , 2022 , 49 ( 3 ): 144 - 151 . (in Chinese)

LI H D , LI B , TAN S Q , et al . Identification of deep network generated images using disparities in color components [J ] . Signal Processing , 2020 , 174 : 107616 . DOI: 10.1016/j.sigpro.2020.107616 http://doi.org/10.1016/j.sigpro.2020.107616 https://linkinghub.elsevier.com/retrieve/pii/S0165168420301596 https://linkinghub.elsevier.com/retrieve/pii/S0165168420301596

GAUTAM C , TIWARI A , MISHRA P K , et al . Graph-embedded multi-layer kernel ridge regression for one-class classification [J ] . Cognitive Computation , 2021 , 13 : 552 - 569 . DOI: 10.1007/s12559-020-09804-7 http://doi.org/10.1007/s12559-020-09804-7

LEE J , LEE Y C , KIM J T . Fault detection based on one-class deep learning for manufacturing applications limited to an imbalanced database-ScienceDirect [J ] . Journal of Manufacturing Systems , 2020 , 57 : 357 - 366 . DOI: 10.1016/j.jmsy.2020.10.013 http://doi.org/10.1016/j.jmsy.2020.10.013 https://linkinghub.elsevier.com/retrieve/pii/S0278612520301825 https://linkinghub.elsevier.com/retrieve/pii/S0278612520301825

ABATI D , PORRELLO A , CALDERARA S , et al . Latent space autoregression for novelty detection [C ] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern recognition. Long Beach, CA , US : IEEE , 2019 : 481 - 490 .

WU P , LIU J , SHEN F . A deep one-class neural network for anomalous event detection in complex scenes [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2020 , 31 ( 7 ): 2609 - 2622 . DOI: 10.1109/TNNLS.2019.2933554 http://doi.org/10.1109/TNNLS.2019.2933554 How to build a generic deep one-class (DeepOC) model to solve one-class classification problems for anomaly detection, such as anomalous event detection in complex scenes? The characteristics of existing one-class labels lead to a dilemma: it is hard to directly use a multiple classifier based on deep neural networks to solve one-class classification problems. Therefore, in this article, we propose a novel DeepOC neural network, termed as DeepOC, which can simultaneously learn compact feature representations and train a DeepOC classifier. Only with the given normal samples, we use the stacked convolutional encoder to generate their low-dimensional high-level features and train a one-class classifier to make these features as compact as possible. Meanwhile, for the sake of the correct mapping relation and the feature representations' diversity, we utilize a decoder in order to reconstruct raw samples from these low-dimensional feature representations. This structure is gradually established using an adversarial mechanism during the training stage. This mechanism is the key to our model. It organically combines two seemingly contradictory components and allows them to take advantage of each other, thus making the model robust and effective. Unlike methods that use handcrafted features or those that are separated into two stages (extracting features and training classifiers), DeepOC is a one-stage model using reliable features that are automatically extracted by neural networks. Experiments on various benchmark data sets show that DeepOC is feasible and achieves the state-of-the-art anomaly detection results compared with a dozen existing methods.

莫少慧 , 古兰拜尔·吐尔洪,买日旦·吾守尔.高维混合入侵检测数据的单类分类算法研究 [J ] . 计算机应用与软件 , 2022 , 39 ( 4 ): 300 - 310 .

MS S H , GULANBAIER T , MAIRIDAN W . Research on one-class classification algorithm for high-dimensional mixed intrusion detection data [J ] . Computer Applications and Software , 2022 , 39 ( 4 ): 300 - 310 . (in Chinese)

曾凡霞 , 何泽文 , 张文生 . 有噪条件下的新类检测算法 [J ] . 计算机辅助设计与图形学学报 , 2021 , 33 ( 5 ): 682 - 693 .

ZENG F X , HE Z W , ZHANG Y S . Novel class detection algorithm in noisy conditions [J ] . Journal of Computer Aided Design and Graphics , 2021 , 33 ( 5 ): 682 - 693 . (in Chinese)

SARMADI H , KARAMODIN A . A novel anomaly detection method based on adaptive Mahalanobis-squared distance and one-class knn rule for structural health monitoring under environmental effects [J ] . Mechanical Systems and Signal Processing , 2020 , 140(Jun.) :106495. 1 - 106495 .24.

MAK A , SK B , YDZ C , et al . Prediction of COVID-19-Pneumonia based on selected deep features and one class kernel extreme learning machine [J ] . Computers & Electrical Engineering , 2021 , 90 : 106960 .

梁家菲 , 李婷 , 杨佳琪 , 等 . 融合自注意力和自编码器的视频异常检测 [J ] . 中国图象图形学报 , 2023 , 28 ( 4 ): 1029 - 1040 .

LIANG J F , LI T , YANG J Q , et al. Video anomaly detection by fusing self-attention and autoencoder [J ] . Journal of Image and Graphics , 2023 , 28 ( 4 ): 1029 - 1040 . (in Chinese) DOI: 10.11834/jig.211147 http://doi.org/10.11834/jig.211147 http://www.cjig.cn/jig/ch/reader/view_abstract.aspx?file_no=211147 http://www.cjig.cn/jig/ch/reader/view_abstract.aspx?file_no=211147

YU J H , KANG S K . Clustering-based proxy measure for optimizing one-class classifiers [J ] . Pattern Recognition Letters , 2019 , 117 : 37 - 44 . DOI: 10.1016/j.patrec.2018.11.017 http://doi.org/10.1016/j.patrec.2018.11.017 One-class classification is a type of unsupervised learning task wherein only information on the target class is available and that on other classes is not. As this corresponds to many real-world data scenarios, considerable research efforts have been focused on developing one-class classification algorithms to build well-performing one-class classifiers. The performance of one-class classifiers largely depends on their hyperparameters. However, optimizing hyperparameters is inherently difficult and challenging because conventional validation procedures are not directly applicable in the absence of non-target class information. The existing methods have focused on specific one-class classification algorithms, and therefore, could not be extended to other algorithms. In this study, we present a clustering-based proxy measure to evaluate the quality of different hyperparameter candidates for a one-class classification algorithm when only the target class information is given. The proposed proxy measure utilizes conventional measures of classification performance by introducing pseudo non-target classes that are derived based on clustering. The best hyperparameters for the algorithm can be estimated by alternatively optimizing this measure. It does not require incorporating any prior knowledge, and can be implemented with various types of one-class classification algorithms. We demonstrate the effectiveness through experiments comprising benchmark problems. (C) 2018 Elsevier B.V.

HOFFMANN H . Kernel PCA for novelty detection [J ] . Pattern Recognition , 2007 , 40 ( 3 ): 863 - 874 . DOI: 10.1016/j.patcog.2006.07.009 http://doi.org/10.1016/j.patcog.2006.07.009 https://linkinghub.elsevier.com/retrieve/pii/S0031320306003414 https://linkinghub.elsevier.com/retrieve/pii/S0031320306003414

FAVARELLI E , GIORGETTI A . Machine learning for automatic processing of modal analysis in damage detection of bridges [J ] . IEEE Transactions on Instrumentation and Measurement , 2020 , 99 : 1 - 1 .

CHENG T Y , DAIRI A HARROU F , et al . Monitoring influent conditions of wastewater treatment plants by nonlinear data-based techniques [J ] . IEEE Access , 2019 , 99 : 1 - 1 .

NGUYEN H D , TRAN K P , THOMASSEY S , et al. Forecasting and anomaly detection approaches using LSTM and LSTM Autoencoder techniques with the applications in supply chain management [J ] . International Journal of Information Management , 2021 , 57 : 102282 . DOI: 10.1016/j.ijinfomgt.2020.102282 http://doi.org/10.1016/j.ijinfomgt.2020.102282 https://linkinghub.elsevier.com/retrieve/pii/S026840122031481X https://linkinghub.elsevier.com/retrieve/pii/S026840122031481X

OZA P , PATEL V M . One-class convolutional neural network [J ] . IEEE Signal Processing Letters , 2019 , 26 ( 2 ): 277 - 281 . DOI: 10.1109/LSP.2018.2889273 http://doi.org/10.1109/LSP.2018.2889273 We present a novel convolutional neural network (CNN) based approach for one-class classification. The idea is to use a zero centered Gaussian noise in the latent space as the pseudo-negative class and train the network using the cross-entropy loss to learn a good representation as well as the decision boundary for the given class. A key feature of the proposed approach is that any pre-trained CNN can be used as the base network for one-class classification. The proposed one-class CNN is evaluated on the UMDAA-02 Face, Abnormality-1001, and FounderType-200 datasets. These datasets are related to a variety of one-class application problems such as user authentication, abnormality detection, and novelty detection. Extensive experiments demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods. The source code is available at: github.com/otkupjnoz/oc-cnn.

WANG X H , JIN B H , DU Y , et al . One-class graph neural networks for anomaly detection in attributed networks [J ] . Neural Computing and Applications , 2021 , 33 : 12073 - 12085 . DOI: 10.1007/s00521-021-05924-9 http://doi.org/10.1007/s00521-021-05924-9

JIAN P , CHEN K M , CHENG W . GAN-based one-class classification for remote-sensing image change detection [J ] . IEEE Geoscience and Remote Sensing Letters , 2021 , 19 : 1 - 5 .

LI W , DING W , SADASIVAM R , et al. His-GAN:a histogram-based GAN model to improve data generation quality [J ] . Neural Networks , 2019 , 119 : 31 - 45 . DOI: 10.1016/j.neunet.2019.07.001 http://doi.org/10.1016/j.neunet.2019.07.001 https://linkinghub.elsevier.com/retrieve/pii/S0893608019301893 https://linkinghub.elsevier.com/retrieve/pii/S0893608019301893

LIU K H , YE Z H , GUO H Y , et al . FISS GAN:a generative adversarial network for foggy image semantic segmentation [J ] . IEEE/CAA Journal of Automatica Sinica , 2021 , 8 ( 8 ): 1428 - 1439 . DOI: 10.1109/JAS.2021.1004057 http://doi.org/10.1109/JAS.2021.1004057 https://ieeexplore.ieee.org/document/9459610/ https://ieeexplore.ieee.org/document/9459610/

SHAHRIAR S . GAN computers generate arts? a survey on visual arts, music, and literary text generation using generative adversarial network:arXiv : 2108 .03857[R ] . Ithaca,NY , US : Cornell University , 2021 :2108.03857.

SONG L D , LI Y Y , LU N . ProfileSR-GAN:a GAN based super-resolution method for generating high-resolution load profiles [J ] . IEEE Transactions on Smart Grid , 2022 , 13 ( 4 ): 3278 - 3289 . DOI: 10.1109/TSG.2022.3158235 http://doi.org/10.1109/TSG.2022.3158235 https://ieeexplore.ieee.org/document/9731506/ https://ieeexplore.ieee.org/document/9731506/

PERERA P , NALLAPATI R , XIANG B . OCGAN: one-class novelty detection using GANs with constrained latent representations [C ] //Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington,D.C.,US:IEEE , 2019 : 2893 - 2901 .

TSA B , PSA B , SMW B , et al . f-AnoGAN: fast unsupervised anomaly detection with generative adversarial networks [J ] . Medical Image Analysis , 2019 , 56 : 30 - 44 .

PIDHORSKYI S , ALMOHSEN R , ADJEROH D A , et al . Generative probabilistic novelty detection with adversarial autoencoders:arXiv : 1807 .02588[R ] . Ithaca,NY , US : Cornell University , 2018 :1807.02588.

ZAHEER M Z , LEE J , ASTRID M , et al. Old is gold: Redefining the adversarially learned one-class classifier training paradigm [C ] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle, WA, US:IEEE , 2020 : 14183 - 14193 .

SABOKROU M , FATHY M , ZHAO G , et al . Deep end-to-end one-class classifier [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2020 , 99 : 1 - 10 .

TAGAWA Y , MASKELIÜNAS R , DAMAŠEVIČIUS R . Acoustic anomaly detection of mechanical failures in noisy real-life factory environments [J ] . Electronics , 2021 , 10 ( 19 ): 2329 . DOI: 10.3390/electronics10192329 http://doi.org/10.3390/electronics10192329 https://www.mdpi.com/2079-9292/10/19/2329 https://www.mdpi.com/2079-9292/10/19/2329 Anomaly detection without employing dedicated sensors for each industrial machine is recognized as one of the essential techniques for preventive maintenance and is especially important for factories with low automatization levels, a number of which remain much larger than autonomous manufacturing lines. We have based our research on the hypothesis that real-life sound data from working industrial machines can be used for machine diagnostics. However, the sound data can be contaminated and drowned out by typical factory environmental sound, making the application of sound data-based anomaly detection an overly complicated process and, thus, the main problem we are solving with our approach. In this paper, we present a noise-tolerant deep learning-based methodology for real-life sound-data-based anomaly detection within real-world industrial machinery sound data. The main element of the proposed methodology is a generative adversarial network (GAN) used for the reconstruction of sound signal reconstruction and the detection of anomalies. The experimental results obtained in the Malfunctioning Industrial Machine Investigation and Inspection (MIMII) show the superiority of the proposed methodology over baseline approaches based on the One-Class Support Vector Machine (OC-SVM) and the Autoencoder–Decoder neural network. The proposed schematics using the unscented Kalman Filter (UKF) and the mean square error (MSE) loss function with the L2 regularization term showed an improvement of the Area Under Curve (AUC) for the noisy pump data of the pump.

赖丽娜 , 米瑜 , 周龙龙 , 等 . 生成对抗网络与文本图像生成方法综述 [J/OL ] . 计算机工程与应用 , 1-23[2023-05-06]

LAI L N , MI Y , ZHOU L L , et al . A survey of generative adversarial networks and text image generation methods [J/OL ] . Computer Engineering and Applications , 1-23[2023-05-06] . (in Chinese)

丁文华 , 杜军威 , 侯磊 , 等 . 基于生成对抗网络的时尚内容和风格迁移 [J/OL ] . 计算机工程与应用 , 1-11[2023-05-06] .

DING W H , DU J W , HOU L , et al . Fashion content and style transfer with generative adversarial networks [J/OL ] . Computer Engineering and Applications . 1-11[2023-05-06] . (in Chinese)

胡兵兵 , 唐华 , 吴幼龙 . 基于互信息约束的生成对抗网络分类模型 [J ] . 中国科学院大学学报 , 2022 , 39 ( 4 ): 551 - 560 . DOI: 10.7523/j.ucas.2020.0037 http://doi.org/10.7523/j.ucas.2020.0037 传统的机器学习方法需要大量的含标注数据集来训练模型,并且容易引发过拟合,而生成对抗网络可以无监督地进行训练。此外,互信息约束能够让模型生成指定类别的数据,可用于扩充数据集。提出InfoCatGAN和C-InfoGAN两种模型,前者在CatGAN的基础上增加了互信息约束,使得生成的图片更加逼真;后者使用InfoGAN模型中的辅助网络Q做分类,能够在生成高质量图片的同时,达到较好的分类准确率。二者均能通过隐变量控制生成图片的类别,这对数据增强具有一定意义。另外,在加入少量标签信息之后,模型的准确率能有所提升。

HU B B , TANG H , WU Y L . Generative adversarial network classification model based on mutual information constraint [J ] . Journal of University of Chinese Academy of Sciences , 2022 , 39 ( 4 ): 551 - 560 . (in Chinese)

李理 , 李向欣 , 殷敬伟 . 基于生成对抗网络的舰船辐射噪声分类方法研究 [J ] . 电子与信息学报 , 2022 , 44 ( 6 ): 1974 - 1983 .

LI L , LI X X , YIN J W . Research on ship radiated noise classification method based on generative adversarial networks [J ] . Journal of Electronics and Information Technology , 2022 , 44 ( 6 ): 1974 - 1983 . (in Chinese)

尹明 , 吴浩杨 , 谢胜利 , 等 . 基于自注意力对抗的深度子空间聚类 [J ] . 自动化学报 , 2022 , 48 ( 1 ): 271 - 281 .DOI: 10.16383/j.aas.c200302 https://dx.doi.org/10.16383/j.aas.c200302 .

YIN M , WU H Y , XIE S L , et al. Deep subspace clustering with self-attention adversarial [J ] . Acta Automatica Sinica . 2022 , 48 ( 1 ): 271 - 281 .DOI: 10.16383/j.aas.c200302 https://dx.doi.org/10.16383/j.aas.c200302 . (in Chinese)

张智 , 毕晓君 . 基于风格转换的无监督聚类行人重识别 [J ] . 智能系统学报 , 2021 , 16 ( 1 ): 48 - 56 .

ZHANG Z , BI X J . Unsupervised clustering person re-identification with style transfer [J ] . Journal of Intelligent Systems , 2021 , 16 ( 1 ): 48 - 56 . (in Chinese)

SHI W Z , CABALLERO J , HUSZÁR F , et al . Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network [C ] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Seattle, WA, US:IEEE , 2016 : 1874 - 1883 .

DONAHUE J , SIMONYAN K . Large scale adversarial representation learning:arXiv : 1907 .02544 [R ] . Ithaca,NY , US : Cornell University , 2019 :1907.02544.

ZENATI H , ROMAIN M , FOO C S , et al. Adversarially learned anomaly detection [C ] //Proceedings of 2018 IEEE International Conference on Data Mining.Washitngon,D.C.,US:IEEE , 2018 : 727 - 736 .

CHEN Y H , TIAN Y , PANG G S , et al . Deep one-class classification via interpolated gaussian descriptor [C ] //Proceedings of the AAAI Conference on Artificial Intelligence. Reston, VA, US:AIAA , 2022 , 36 ( 1 ): 383 - 392 .

HOJJATI H , ARMANFARD N . Dasvdd: deep autoencoding support vector data descriptor for anomaly detection:arXiv : 2106 .05410[R ] . Ithaca,NY , US : Cornell University , 2021 :2106.05410.

RUFF L , VANDERMEULEN R , GOERNITZ N , et al . Deep one-class classification [C ] //Proceedings of International Conference on Machine Learning.Stockholm, Sweden:PMLR , 2018 : 4393 - 4402 .

AKCAY S , ATAPOUR-ABARGHOUEI A , BRECKON T P . GANomaly:semi-supervised anomaly detection via adversarial training [C ] //Proceedings of Asian Conference on Computer Vision.Cham,Germany:Springer , 2018 : 622 - 637 .

AKÇAY S , ATAPOUR-ABARGHOUEI A , BRECKON T P . Skip-ganomaly:skip connected and adversarially trained encoder-decoder anomaly detection [C ] //Proceedings of 2019 International Joint Conference on Neural Network.Washington,D.C.,US:IEEE , 2019 : 1 - 8 .

WANG R , LIU C W , MOU X D , et al . Deep contrastive one-class time series anomaly detection:arXiv . 2207 .01472[R ] . Ithaca,NY , US : Cornell University , 2022 : 2207.01472.