检索结果-内蒙古大学图书馆

Lamb wave-based damage imaging of CFRP composite structures using autoencoder and delay-and-sum

COMPOSITE STRUCTURES 2023年 303卷

作者： Yu, Yinghong Liu, Xiao Wang, Yihan Wang, Yishou Qing, Xinlin Xiamen Univ Sch Aerosp Engn Xiamen 361005 Fujian Peoples R China

Ultrasonic guided wave is a promising technique for structural health monitoring and nondestructive testing. However, due to the anisotropy and complexity of composite materials, the imaging performance of numerous signal processing methods deteriorates with significant artifacts and unsatisfactory accuracy. To obtain a better damage imaging performance of Lamb waves in noisy and noise-free conditions, a weighted delay-and-sum (DAS) imaging method based on denoising autoencoder (DAE) learning is developed for complex composite structures. The traditional DAS formulation is modified to be more compatible with anisotropic materials. The DAE with feature learning capability is then employed to extract potentially efficient features and remove noise from ultrasonic signals. Several verification experiments conducted on flat or curved and stiffened composite structures have confirmed the ability of the DAE-DAS method to suppress artificial noise and to intensify sin-gularities induced by the anomalies. By comparing with the unweighted DAS methods and the weighted DAS method without feature extraction, the proposed algorithm has satisfactory robustness to achieve higher local-ization accuracy and fewer artifacts.

关键词： Ultrasonic guided wave Composite structures Delay-and-sum denoising autoencoder Damage imaging

来源：评论

学校读者我要写书评

暂无评论

Bi-channel hybrid GAN attention based anomaly detection system for multi-domain SDN environment

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2024年第1期46卷 457-478页

作者： Prabu, Saranya Padmanabhan, Jayashree Anna Univ Dept Comp Technol MIT Campus Chennai Tamil Nadu India

Software-Defined Networking (SDN) is a strategy that leads the network via software by separating its control plane from the underlying forwarding plane. In support of a global digital network, multi-domain SDN architecture emerges as a viable solution. However, the complex and ever-evolving nature of network threats in a multi-domain environment presents a significant security challenge for controllers in detecting abnormalities. Moreover, multi-domain anomaly detection poses a daunting problem due to the need to process vast amounts of data from diverse domains. Deep learning models have gained popularity for extracting high-level feature representations from massive datasets. In this work, a novel deep neural network architecture, supervised learning based LD-BiHGA (Low Dimensional Bi-channel Hybrid GAN Attention) system is designed to learn class-specific features for accurate anomaly detection. Two asymmetric GANs are employed for learning the normal and abnormal network flows separately. Then, to extract more relevant features, a bi-channel attention mechanism is added. This is the first study to introduce an innovative hybrid architecture that merges bi-channel hybrid GANs with attention models for the purpose of anomaly detection in a multi-domain SDN environment that effectively handles real-time unbalanced data. The suggested architecture demonstrates its effectiveness on three benchmark datasets, achieving an average accuracy improvement of 7.225% on balanced datasets and 3.335% on imbalanced datasets compared to previous intrusion detection system (IDS) architectures in the literature.

关键词： Hybrid GAN intrusion detection deep learning attention model dimensionality reduction denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

A GAN noise modeling based blind denoising method for guided waves

引用

MEASUREMENT 2022年 188卷

作者： Cui, Xiushi Li, Dongsheng Li, Ziqi Ou, Jinping Dalian Univ Technol Sch Civil Engn Dalian 116024 Liaoning Peoples R China

In the detection using guided waves, the signal often carries a high level of non-Gaussian noise. The traditional denoising method cannot estimate and use the prior information of the signal, which leads to poor denoising effect. To tackle this problem, this paper proposed a denoising network based on the combination of generative adversarial network (GAN) and autoencoder (AE). First, GAN is used to estimate the distribution characteristics of the extracted noise and generate samples. Second, according to the characteristics of the guided wave, a pair of datasets are generated to train DAE network. The trained denoising AE has strong robustness. As a result, the proposed GAN-AE based denoiser (GAD) can effectively can effectively reduce the noise level and has the ability to accurately recover the peak time of the wave packet. In particular, the proposed method significantly outperforms conventional denoising methods in low signal-to-noise (SNR) conditions.

关键词： Guided waves Generative adversarial network denoising autoencoder Prior information non-Gaussian features

来源：评论

学校读者我要写书评

暂无评论

Enhancing deep learning nuclear quadrupole resonance detection using transfer learning and autoencoders

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年 207卷

作者： Monea, Cristian Univ Politehn Bucuresti Doctoral Sch Elect Telecommun & Informat Technol 1-3 Iuliu Maniu Blvd Bucharest 061071 Romania Mira Technol Grp Res & Dev Dept 13 Nicolae Grigorescu St Otopeni 075100 Ilfov Romania

Nuclear quadrupole resonance is a highly specific spectroscopy technique for analyzing solid substances with applications ranging from laboratory analysis to security screening screening for prohibited substances. The technique has the drawback of a very low signal-to-noise ratio and multiple signal processing and analysis so-lutions have been proposed for noise rejection and detection. Among these, the deep learning approach using the AlexNet network was recently shown to outperform previous solutions. This paper proposes the enhancement of deep learning detection using transfer learning to extend the applicability of the detection algorithm to other spectrometers and denoising autoencoders to improve its performance at very low signal-to-noise ratios. The transfer learning technique is demonstrated by training the AlexNet network on a simulated data set and transferring the gained knowledge to a real data set. The resulting model achieves a detection accuracy of 98%, close to that obtained by the initial model trained on the real data. Two denoising architectures are proposed, such as deep neural network-based autoencoder and convolutional autoencoder. A comparative evaluation is performed at multiple signal-to-noise ratio conditions in the range [-30, 20] dB, and the convolutional autoencoder is shown to provide the best results, by significantly increasing the detection accuracy by approx. 20% at-30 dB.

关键词： Nuclear quadrupole resonance Deep learning Transfer learning denoising autoencoder Neural network Accuracy

来源：评论

学校读者我要写书评

暂无评论

Growing Hierarchical Self-Organising Representation Map (GHSORM)

引用

INFORMATION SCIENCES 2023年 642卷

作者： Coulson, Matthew Ferles, Christos Winberg, Simon Naidoo, Kevin J. Univ Cape Town Fac Sci Sci Comp Res Unit ZA-7701 Rondebosch South Africa Univ Cape Town Fac Sci Dept Chem ZA-7701 Rondebosch South Africa Univ Cape Town Fac Engn & Built Environm Dept Elect Engn ZA-7701 Rondebosch South Africa

The Growing Hierarchical Self-Organising Representation Map (GHSORM) is a model fusing the denoising autoencoder, used to better represent a dataset, and the Growing Hierarchical Self -Organising Map, used for organizing and projecting the input data in clusters of varying detail. It is shown here that the GHSORM is instrumental in sub-grouping clusters that are not fully separable by a single SOM. This combined approach is first tested and illustrated on the problem of clustering handwritten digits where a modification of the Activation Maximisation method for use at the SOM output layer demonstrates the benefit of hierarchical growth in the GHSORM. In particular, the SOM Node Activation Maximisation method is used to visually represent the best approximation of each of the SOM nodes at the output layer. This demonstrates the improvement in representing difficult to separate digits in the hierarchical case. To test and measure the effi-cacy of the GHSORM hierarchical model in class and sub-class separation the method is applied to complex digital gene expression data. A cancer dataset, comprising of gene expression data that has samples of different classes and sub-classes, is used for this purpose. The GHSORM demon-strates robust capabilities to cluster and sub-cluster the different classes and subclasses of cancer, where the results are superior to both linear methods, currently in use, as well as the methods of its constituent algorithms.

关键词： Unsupervised learning Hierarchical Self -organizing map denoising autoencoder Cancer clustering Cancer sub -typing

来源：评论

学校读者我要写书评

暂无评论

Detection and reconstruction of measurements against false data injection and DoS attacks in distribution system state estimation: A deep learning approach

引用

MEASUREMENT 2023年 210卷

作者： Raghuvamsi, Y. Teeparthi, Kiran Natl Inst Technol Andhra Pradesh Dept Elect Engn Tadepalligudem 534101 India

In a smart grid, the presence of advanced measurement devices and communication channels is significantly vulnerable due to cyberattacks such as false data injection attacks (FDIAs), and denial-of-service (DoS) attacks. To tackle these cyberattacks, a data-driven approach namely, the attention-based temporal convolutional denoising autoencoder is proposed which combines the advantages of the attention mechanism and temporal convolutional network to capture spatio-temporal information. This model identifies the FDIA location and also replaces the corresponding measurements with the reconstructed values. The robustness of the proposed technique is evaluated with different levels of FDIAs as well as missing data caused by DoS attacks. The simulations have been performed on IEEE 13-bus and IEEE 37-bus distribution systems and their reconstruction results along with the classification metrics are presented. Finally, the model's effectiveness is compared with other denoising autoencoder approaches and ML/DL approaches. From the simulations, the results show that the proposed model outperforms in reconstruction and classification.

关键词： False data injection attack DoS attack Distribution system state estimation denoising autoencoder Temporal convolutional network Smart meters

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model for Nonlinear Regression with Missing Data UsingQuasilinearKernel

引用

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2020年第12期15卷 1791-1800页

作者： Zhu, Huilin Tian, Yanling Ren, Yanni Hu, Jinglu Waseda Univ Grad Sch Informat Prod & Syst Wakamatsu Ku Hibikino 2-7 Kitakyushu Fukuoka 8080135 Japan

In both the research and engineering fields, missing data is a serious problem that cannot be overlooked. Therefore, available datasets with missing data are a challenge to be modeled by conventional global prediction models. In this paper, we propose a hybrid model consisting of an autoencoder and a gated linear network for solving the regression problem under missing value scenario. A sophisticated modeling and identifying algorithm is developed. First, an extended affinity propagation (AP) clustering algorithm is applied to obtain a self-organized competitive net dividing the datasets into several clusters. Second, a multiple imputation tool with topp%winner-take-all denoising autoencoders (DAE) is introduced to realize better predictions of missing values, in which rough estimates of missing values by using the mean imputation and similarity method within the clusters are used as teacher signals of DAE. Finally, a gated linear network is designed to construct a piecewise linear regression model with interpolations in the exact same way as a support vector regression with a quasilinear kernel composed using the cluster information obtained in the AP clustering step. Based on the experiments of five datasets, our proposed method demonstrates its effectiveness and robustness compared with other traditional kernels and state-of-the-art methods, even on datasets with a large percentage of missing values. (c) 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

关键词： nonlinear regression missing data affinity propagation algorithm denoising autoencoder support vector regression quasilinear kernel

来源：评论

学校读者我要写书评

暂无评论

Latent feature learning via autoencoder training for automatic classification configuration recommendation

引用

KNOWLEDGE-BASED SYSTEMS 2023年 261卷

作者： Deng, Liping Xiao, MingQing Southern Illinois Univ Carbondale Sch Math & Stat Sci Carbondale IL 62901 USA

The Combined Algorithm Selection and Hyperparameter Optimization problem, in short, CASH, seeks the most suitable classifiers and hyperparameters for the underlying classification problems. In current literature, the common approaches in dealing with CASH problem are conducted via search-based methods such as sequential model-based optimization (SMBO) along with various active tests. Different from current existing approaches, in this paper, we propose a new method by incorporating the so-called denoising autoencoder (DAE) approach into meta-learning (MtL) for automatic configuration (both algorithms and their hyperparameters) recommendation, which appears to be quite effective compared to standard search-based approaches. More specifically, we set up the configuration search space for CASH and produce the metadata, and generate the classification performance on a set of collected historical datasets. Then both encoder and decoder in the DAE system are trained with the masked metadata as inputs and the unmasked metadata as targets to extract the subtle latent variables of metadata and recover the unmasked inputs subsequently. Under our framework, the performance over the entire configuration space can be predicted effectively through two different settings, and the configuration with the highest predictive performance is thus recommended. The first recommendation approach is by inactivating some inputs and then to recover their entries via the trained encoder and decoder for new problems, while in the second approach, the relationship between the acquired latent variables and the meta-features of historical datasets via kernel multivariate multiple regression (MMR) is enacted, leading to the performance estimation of new datasets being pursued directly through MMR and the decoder of DAE without requiring any new configuration evaluations. An automatic classification configuration recommendation system, including 81 historical problems and 11 common classifiers with

关键词： Classifier and hyperparameter recommendation denoising autoencoder Meta-learning

来源：评论

学校读者我要写书评

暂无评论

A novel lidar signal noise reduction algorithm based on improved deep belief network

引用

PHYSICA SCRIPTA 2023年第12期98卷 126004-126004页

作者： Li, Shun Mao, Jiandong Gong, Xin Li, Zhiyuan North Minzu Univ Sch Elect & Informat Engn North Wenchang Rd Yinchuan 750021 Peoples R China Key Lab Atmospher Environm Remote Sensing Ningxia North Wenchang Rd Yinchuan 750021 Peoples R China

To reduce noise in the lidar return signal, an improved deep belief network (DBN) denoising algorithm is proposed in this study. In the traditional implementation process of DBN, a multi-layer fully connected network is realized by stacking restricted Boltzmann machines (RBMs). However, the RBM is an undirected graph model, and there is no clear causal relationship between random variable nodes. The denoising autoencoder (DAE) can avoid this problem and produce field generalization performance by adding random contamination during training and stacking, thereby achieving better performance than the traditional DBN. In this study, a new multi-layer DBN called DADBN is implemented by stacking DAE and RBM. First, the multi-layer DAE is placed in the beginning layer of the network as the primary filter of the signal to provide data dimensionality reduction and feature extraction. Then, the RBM is used as the lower layer, the hidden layer is calculated according to the initial value of the visible layer by the contrast of the divergence algorithm, and the visible layer is reconstructed from the samples of the hidden layer. And the sparse representation penalty is added to the RBM model to solve the assimilation phenomenon of hidden layer nodes in the RBM model. It not only optimizes the log-likelihood function when training data, but also makes the probability of each hidden layer node being activated tend to a minimum value, so as to sparsely activate the sparse hidden layer nodes. The weight matrix W is obtained by computing the results of the hidden layer twice. Finally, the original input signal was reconstructed by Gibbs sampling layer and the reconstructed signal was decoded by the decoder to achieve the purpose of noise reduction. To verify its effectiveness, this method is compared with four other denoising methods: wavelet packet algorithm, complete ensemble empirical modal decomposition (CEEMDAN), wavelet transform and empirical mode decomposition (WT-EMD), and

关键词： lidar deep learning deep belief network denoising autoencoder noise reduction

来源：评论

学校读者我要写书评

暂无评论

A synchronized heterogeneous autoencoder with feature-level and label-level knowledge distillation for the recommendation

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2021年 106卷

作者： Pan, Yiteng He, Fazhi Yan, Xiaohu Li, Haoran DongGuan Univ Technol Sch Cyberspace Secur Dongguan Peoples R China Wuhan Univ Sch Comp Sci Wuhan Peoples R China Shenzhen Polytech Sch Artificial Intelligence Shenzhen Peoples R China Xidian Univ ISN State Key Lab Xian Peoples R China

Motivated by the success of deep learning techniques, there are numerous deep learning models developed for recommender systems. User-oriented autoencoder (UAE) and item-oriented autoencoder (IAE) are two typical approaches developed for the recommendation by learning features from items or users respectively. Existing works demonstrate that IAE model outperforms UAE model for rating prediction tasks, while UAE model outperforms IAE model for top-N recommendation task. This fact motivates us to develop a new synchronized heterogeneous autoencoder (SHAE) for top-N recommendation by considering both features learned by IAE and UAE models. Especially, we develop two novel heterogeneous knowledge distillation methods in feature level and label-level to build relations between IAE and UAE models. Compared with matrix factorization approaches, our methods are more efficient with acceptable computational complexity for the recommendation. We conduct comprehensive experiments on public datasets to compare with several state-of-the-art approaches. Experimental results demonstrate that the proposed method significantly outperforms other comparisons for top-N recommendation tasks.

关键词： Deep learning Recommender systems denoising autoencoder Knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：