检索结果-内蒙古大学图书馆

Weak ultrasonic guided wave signal recognition based on one-dimensional convolutional neural network denoising autoencoder and its application to small defect detection in pipelines

引用

MEASUREMENT 2025年 242卷

作者： Wu, Jing Yang, Yingfeng Lin, Zeyu Lin, Yizhou Wang, Yan Zhang, Weiwei Ma, Hongwei Dongguan Univ Technol Sch Mech Engn Dongguan 523808 Peoples R China Guangdong Prov Key Lab Intelligent Disaster Preven Dongguan 523808 Peoples R China Dongguan Univ Technol Sch Environm & Civil Engn Dongguan 523808 Peoples R China

Pipeline failures are often caused by the expansion of small defects. Structural damage to pipelines can lead to major safety accidents. When ultrasonic guided wave (UGW) technology is used for pipeline failure detection, the echoes produced by small defects manifest as weak UGW signals amidst significant noise. The low amplitude of these signals or complete drowning by noise makes them difficult to recognize. This study innovatively introduces a one-dimensional convolutional neural network denoising autoencoder (1DCNN-based DAE) for noise reduction in UGW signals using deep learning. To improve the conventional DAE, the model incorporated the Parametric Rectified Linear Unit (PReLU) activation function and a CNN for enhanced feature extraction, resulting in the proposed 1DCNN-based DAE. The model is trained on an extensive dataset of mixed signals with strong noise and their corresponding clean signals, enabling autonomous denoising in an unsupervised manner. Additionally, this paper proposes the application of the window-shifted power spectrum method for analyzing the denoised signals to identify and locate pipeline defects. The method involves traversing the signal with a window to intercept fragments, calculating their power, and plotting the power spectrum curve. Defects are then located based on the peak positions of this curve. Numerical simulation and experimental signals were used to validate the proposed method. Simulation results showed that the proposed 1DCNN-based DAE effectively improved the signal-to-noise ratio (SNR) of UGW mixed signals from -9 dB to 21.63 dB, representing an improvement of up to 30.63 dB. Experimental results demonstrated that the method accurately detected weak UGW signals from small defective pipes with a 2 % cross-section loss rate, achieving over 90 % recognition confidence and less than 1.5 % axial positioning error rate. In summary, the proposed 1DCNN-based DAE can effectively improve the SNR of the signal, reduce the noise i

关键词： Ultrasonic guided waves denoising autoencoder Convolutional neural networks Defect recognition Pipelines

来源：评论

学校读者我要写书评

暂无评论

VLSI Architecture Design for Compact Shortcut denoising autoencoder Neural Network of ECG Signal

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2025年第4期72卷 1621-1633页

作者： Lai, Shin-Chi Wang, Szu-Ting Morsalin, S. M. Salahuddin Lin, Jia-He Hsia, Shih-Chang Chang, Chuan-Yu Sheu, Ming-Hwa Natl Formosa Univ Dept Automat Engn Huwei 632301 Yunlin County Taiwan Natl Formosa Univ Smart Machinery & Intelligent Mfg Res Ctr Huwei 632301 Yunlin County Taiwan Natl Formosa Univ Program Smart Ind Technol Res & Dev Huwei 632301 Taiwan Natl Yunlin Univ Sci & Technol Dept Elect Engn Touliu 64002 Yunlin County Taiwan Natl Yunlin Univ Sci & Technol Dept Comp Sci & Informat Engn Touliu 64002 Yunlin County Taiwan

The Electrocardiogram (ECG) test detects and records cardiac-related electrical activity of the heart. The ECG test identifies and documents cardiac-related electrical activity in the heart. The use of ECG signals for cardiovascular disease nursing as a crucial component of preoperative evaluation is increasing. ECG signals need to denoise and display in a clear waveform due to the numerous noises. We have introduced Compact Shortcut denoising Auto-encoder (CS-DAE) neural network, which reduces the noise from ECG signals. The Compact Shortcut approach compresses the features passed through the shortcut layers, which lowers the operation's memory needs and improves the noise reduction impact. In addition, the encoder and decoder process the Pixel-Unshuffled and Pixel-Shuffled, which effectively mitigates the feature loss caused by down-sampling and up-sampling operations. As a result, the CS-DAE algorithm decreases the computation and required memory size while maintaining higher accuracy. We have used MITDB and NSTDB datasets for training and testing the proposed CS-DAE model, resulting in the average Percentage of Root Mean Square Difference (PRD) being 46.30% and the improvement of Signal-to-Noise Ratio (SNRimp) being 10.50. In addition, we have designed VLSI architect ure for the proposed CS-DAE neural network to accelerate low hardware cost and less computation. The TUL PYNQTM-Z2 development platform runs the Verilog code, which is used for VLSI architecture and has the lowest power consumption of 1.65W.

关键词： Electrocardiography Noise reduction Decoding Noise Neural networks Convolution Very large scale integration Heart Hardware Signal to noise ratio Electrocardiogram compact shortcut denoising autoencoder neural network ECG signals shortcut layers pixel-unshuffled and pixel-shuffled VLSI architecture hardware design

来源：评论

学校读者我要写书评

暂无评论

denoising autoencoder multilayer perceptron spiking neural network for isonicotinic acid yield prediction on real industrial dataset

引用

ADVANCED ENGINEERING INFORMATICS 2025年 65卷

作者： Ren, Pinze Wang, Yitian Wang, Zisheng Peng, Dandan Liu, Chenyu Han, Te Tsinghua Univ Dept Chem Engn Beijing Peoples R China Univ Calif San Diego Sch Comp Sci San Diego CA USA Tsinghua Univ Dept Ind Engn Beijing Peoples R China Hong Kong Polytech Univ Dept Elect & Elect Engn Hong Kong Peoples R China Northwestern Polytech Univ Mech & Elect Engn Xiamen Peoples R China Beijing Inst Technol Ctr Energy & Environm Policy Res Beijing Peoples R China

Isonicotinic acid (INA) has attracted considerable interest as a crucial pharmaceutical intermediate, especially for the production of the anti-tuberculosis drug isoniazid. Nonetheless, industrial production of INA encompasses intricate procedures that are highly sensitive to process parameters, leading to yield variability. Hence, an efficient prediction model for forecasting INA yield is essential for enhancing production yields and ensuring the consistency of INA in pharmaceutical manufacturing processes. To address this challenge, the present study developed a brain-inspired spiking neural network (SNN) tailored to the prediction of INA yield. Specifically, we propose a novel denoising autoencoder multilayer perceptron based spiking neural network (DAEMLP-SNN) for this purpose. The SNN is designed to accurately emulate the dynamic behavior of biological neurons while maintaining low power consumption, thereby ensuring high biological plausibility. Drawing upon the principles of autoencoders, our research constructs a denoising autoencoder SNN capable of extracting meaningful latent features and compressing high-dimensional industrial data. Moreover, we concatenated the extracted features with the original data, thereby creating a more comprehensive representation of the input. This enriched input was then fed into the multilayer perceptron SNN, which markedly enhances the robustness and precision of INA yield predictions. Experimental findings demonstrated the superior performance of DAEMLP-SNN, as it consistently achieved accurate predictions across diverse process parameters.

关键词： INA yield prediction denoising autoencoder Spiking Neural Network Industrial data process

来源：评论

学校读者我要写书评

暂无评论

Reducing false damage detections in guided ultrasonic wave monitoring systems using a denoising autoencoder

引用

NONDESTRUCTIVE TESTING AND EVALUATION 2025年第4期40卷 1610-1640页

作者： Chen, Yon Kong Bakhary, Norhisham Padil, Khairul Hazman Li, Jun Shamsudin, Mohd Fairuz Univ Teknol Malaysia Fac Civil Engn Skudai Johor Malaysia Res & Dev Dept VRG Dinamik Sdn Bhd Kuala Lumpur Malaysia Univ Teknol Malaysia Inst Noise & Vibrat Kuala Lumpur Malaysia Univ Teknol Malaysia Inst Smart Infrastruct & Innovat Construct Forens Engn Ctr Skudai Johor Malaysia Curtin Univ Ctr Infrastructural Monitoring & Protect Sch Civil & Mech Engn Bentley WA Australia Univ Teknol Malaysia Fac Mech Engn Skudai Johor Malaysia

Guided ultrasonic wave (GUW) monitoring systems for pipeline structures are gaining much attention in critical sectors such as the petrochemical, nuclear and energy sectors. However, the effects of environmental and operational conditions (EOCs), especially temperature, may generate substantial false damage detections. The temperature effect may interfere with different coherent noise sources and generate unwanted peaks that are falsely identified as damage. In this paper, a denoising autoencoder (DAE) is proposed to reduce the frequency of false damage detections in GUW monitoring systems. A DAE decodes high dimensional data into low-dimensional features and reconstructs the original data from these low-dimensional features. By providing signals at a reference temperature with the fewest false damage detections, this structure forces the DAE to learn the essential features hidden within complex data. A database of GUW signals is formed based on the experimental measurements using a six-metre-long stainless steel Schedule 20 pipe. Variations in temperature and damage severity are applied to develop the database to mimic a simple step change in damage growth under EOCs. The outcomes obtained from this study show that the proposed methodology can reduce false damage detections during GUW monitoring and is valuable for pipeline safety evaluations.

关键词： Torsional guided ultrasonic wave denoising autoencoder structural health monitoring unsupervised neural network

来源：评论

学校读者我要写书评

暂无评论

Multi-Source Data with Laplacian Eigenmaps and denoising autoencoder for Predicting Microbe-Disease Associations via Convolutional Neural Network

引用

Journal of Computer Science and Technology 2025年第2期40卷 588-604页

作者： Lei, Xiu-Juan Chen, Ya-Li Pan, Yi School of Computer Science Shaanxi Normal University Xi’an China Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Science Shenzhen China

Identifying microbes associated with diseases is important for understanding the pathogenesis of diseases as well as for the diagnosis and treatment of diseases. In this article, we propose a method based on a multi-source association network to predict microbe-disease associations, named MMHN-MDA. First, a heterogeneous network of multi-molecule associations is constructed based on associations between microbes, diseases, drugs, and metabolites. Second, the graph embedding algorithm Laplacian eigenmaps is applied to the association network to learn the behavior features of microbe nodes and disease nodes. At the same time, the denoising autoencoder (DAE) is used to learn the attribute features of microbe nodes and disease nodes. Finally, attribute features and behavior features are combined to get the final embedding features of microbes and diseases, which are fed into the convolutional neural network (CNN) to predict the microbe-disease associations. Experimental results show that the proposed method is more effective than existing methods. In addition, case studies on bipolar disorder and schizophrenia demonstrate good predictive performance of the MMHN-MDA model, and further, the results suggest that gut microbes may influence host gene expression or compounds in the nervous system, such as neurotransmitters, or metabolites that alter the blood-brain barrier.

关键词： convolutional neural network denoising autoencoder Laplacian eigenmap microbe-disease association multi-source data

来源：评论

学校读者我要写书评

暂无评论

FeatDAE: Introducing Features with denoising autoencoder for Anomaly Detection

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Zhou, Zheyuan Wang, Jichun Yu, Zian Wang, Zili Liu, Xiaojian Qiu, Lemiao Zhang, Shuyou Zhejiang University State Key Laboratory of Fluid Power & Mechatronic Systems Hangzhou 310058 China

Anomaly detection is a critical task in manufacturing inspection. Reconstructive anomaly detection methods restore the normal appearance of an object, ideally modifying only the anomalous regions. However, previously commonly used reconstruction-based architecture always struggles with over-generalization and over-fitting problems, leading to poor reconstruction performance on real defective samples. In this study, we propose a more general denoising autoencoder, by introducing a feature hierarchy design to address these challenges in unsupervised anomaly detection. In particular, we operate feature transformation in the latent space to cope with the robustness of unseen anomalies in reality. Furthermore, the method enhances the discriminative capability of the model by focusing on multiple knowledge, including pixel color, HOG feature, and deep features. Additionally, a feature alignment module is proposed to manage the varied sizes and morphologies of features. Experiments conducted on both the MVTec AD dataset and the VisA dataset demonstrate that our FeatDAE significantly outperforms existing methods, achieving state-of-the-art results with high efficiency. © 1963-2012 IEEE.

关键词： Anomaly detection denoising autoencoder Industrial defect detection Self-supervised learning Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

denoising autoencoder Self-Organizing Map (DASOM)

引用

NEURAL NETWORKS 2018年 105卷 112-131页

作者： Ferles, Christos Papanikolaou, Yannis Naidoo, Kevin J. Univ Cape Town Sci Comp Res Unit Fac Sci ZA-7701 Rondebosch South Africa Univ Cape Town Dept Chem Fac Sci ZA-7701 Rondebosch South Africa Aristotle Univ Thessaloniki Dept Informat Thessaloniki 54124 Greece Univ Cape Town Inst Infect Dis & Mol Med Fac Heath Sci ZA-7701 Rondebosch South Africa

In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex functions. A fundamental approach is the use of higher-level representations devised by restricted Boltzmann machines and (denoising) autoencoders. We present the denoising autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map. In so doing the parameters are adjusted by the proposed unsupervised learning algorithm. The model therefore maintains the clustering properties of its predecessor, whereas by extending and enhancing its visualization capacity enables an inclusion and an analysis of the intermediate representation space. A comprehensive series of experiments comprising optical recognition of text and images, and cancer type clustering and categorization is used to demonstrate DASOM's efficiency, performance and projection capabilities. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Unsupervised learning denoising autoencoder Self-organizing map Clustering Visualization

来源：评论

学校读者我要写书评

暂无评论

denoising autoencoder-Based Missing Value Imputation for Smart Meters

引用

IEEE ACCESS 2020年 8卷 40656-40666页

作者： Ryu, Seunghyoung Kim, Minsoo Kim, Hongseok Sogang Univ Dept Elect Engn Seoul 4107 South Korea

Electric load data are essential for data-driven approaches (including deep learning) in smart grid, and advanced smart meter technologies provide fine-grained data with reliable communications. Despite the recent development of smart metering devices, however, missing data still arise due to unexpected device power off, communication failure, measuring error, or other unknown reasons. In this paper, we investigate a deep learning framework for missing imputation of smart meter data by leveraging a denoising autoencoder (DAE). Then, we compare the performance of the proposed DAE with traditional methods as well as other recently developed generative models, e.g., variational autoencoder and Wasserstein autoencoder. The proposed DAE based imputation shows significantly better results compared to other methods in terms of root mean square error (RMSE) by up to 28.9% for point-wise error, and by up to 56% for daily-accumulated error.

关键词： Machine learning Smart meters Noise reduction Smart grids Load modeling Deep learning smart grid missing imputation smart meters denoising autoencoder generative model daily load profile (DLP)

来源：评论

学校读者我要写书评

暂无评论

denoising autoencoder, A Deep Learning Algorithm, Aids the Identification of A Novel Molecular Signature of Lung Adenocarcinoma

引用

Genomics, Proteomics & Bioinformatics 2020年第4期18卷 468-480页

作者： Jun Wang Xueying Xie Junchao Shi Wenjun He Qi Chen Liang Chen Wanjun Gu Tong Zhou Department of Thoracic Surgery Jiangsu Province People’s Hospital and the First Affiliated Hospital of Nanjing Medical UniversityNanjing 210029China State Key Laboratory of Bioelectronics School of Biological Sciences and Medical EngineeringSoutheast UniversityNanjing 210096China Department of Physiology and Cell Biology University of NevadaReno School of MedicineRenoNV 89557USA State Key Lab of Respiratory Disease Guangzhou Medical UniversityGuangzhou 510000China

Precise biomarker development is a key step in disease management. However, most of the published biomarkers were derived from a relatively small number of samples with supervised approaches. Recent advances in unsupervised machine learning promise to leverage very large datasets for making better predictions of disease biomarkers. denoising autoencoder(DA) is one of the unsupervised deep learning algorithms, which is a stochastic version of autoencoder techniques. The principle of DA is to force the hidden layer of autoencoder to capture more robust features by reconstructing a clean input from a corrupted one. Here, a DA model was applied to analyze integrated transcriptomic data from 13 published lung cancer studies, which consisted of 1916 human lung tissue samples. Using DA, we discovered a molecular signature composed of multiple genes for lung adenocarcinoma(ADC). In independent validation cohorts, the proposed molecular signature is proved to be an effective classifier for lung cancer histological subtypes. Also, this signature successfully predicts clinical outcome in lung ADC, which is independent of traditional prognostic factors. More importantly, this signature exhibits a superior prognostic power compared with the other published prognostic genes. Our study suggests that unsupervised learning is helpful for biomarker development in the era of precision medicine.

关键词： denoising autoencoder Unsupervised learning Lung cancer Prognosis Molecular signature

来源：评论

学校读者我要写书评

暂无评论

denoising autoencoder Aided Spectrum Reconstruction for Colloidal Quantum Dot Spectrometers

引用

IEEE SENSORS JOURNAL 2021年第5期21卷 6450-6458页

作者： Zhang, Jinhui Zhu, Xueyu Bao, Jie Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Univ Iowa Dept Math Iowa City IA 52242 USA

Recently, the colloidal quantum dot spectrometer has received much attention due to its advantages in cost, size, and operation. Yet, just like many other filter-based miniature spectrometers, spectrum reconstruction for the colloidal quantum dot spectrometer is typically prone to the measurement noise due to the correlation of the filters. In this paper, we propose an effective spectrum reconstruction method for the colloidal quantum dot spectrometer, which can recover high-quality spectra in noisy environments. Specifically, we employ a denoising autoencoder, a machine-learning approach, to reduce noise in the filters' raw measurements before performing the reconstruction. After that, we reconstruct the spectra with the denoised data by a sparse recovery algorithm. We investigate the feasibility of the proposed reconstruction approach on a synthetic dataset and an experimental dataset collected by the colloidal quantum dot spectrometer. The results demonstrate that the proposed approach could deliver accurate reconstruction results even when data are corrupted with the measurement noise.

关键词： Sensors Noise reduction Image reconstruction Reconstruction algorithms Quantum dots Noise measurement Sensitivity Miniature spectrometer denoising autoencoder spectrum reconstruction

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：