检索结果-内蒙古大学图书馆

auto-encoder-based inverse characterization of Transport properties of acoustic foams

APPLIED ACOUSTICS 2025年 228卷

作者： Chen, Jianglong Xu, Yiqin Zhao, Xiaoliang Miao, Menghe Meng, Jiaguang Yu, Lingjie Zhi, Chao Xian Polytech Univ Sch Text Sci & Engn Xian 710048 Shaanxi Peoples R China Xian Polytech Univ State Key Lab Intelligent Text Mat & Prod Xian 710048 Shaanxi Peoples R China Univ Melbourne Dept Mech Engn Grattan St Parkville Vic 3010 Australia

The characterization of non-acoustic parameters is critically important for understanding the acoustic property and structural design of polyurethane (PU) foams. However, inverse characterization of acoustic PU foams through experiments and simulations often results in prolonged cycles and high resource wastage. To address the above issue, an innovative approach based on the auto-encoder (AE) was proposed in this paper. In the AE approach, the decoder module was utilized for the forward prediction part, while the encoder was used for the inverse characterization. A sample database of 96,730 data sets covering PU foams' sound absorption coefficients at 500-6000 Hz was established to train the AE model. To verify the effectiveness of the trained model, a comparative experiment with numerical simulations was firstly conducted. The results revealed that the coefficient of determination (R2) of forward prediction module surpasses 0.99, while the prediction time is significantly rapid, averaging 0.0005 s per sample, which is 1/22,000 of numerical simulation time. Another comparative experiment was conducted between the inverse characterization results of the machine learning model and the experimental data from real samples. The results showed that the average error of the characterization parameters (non-acoustic parameters and material thickness) is about 8.70 %. In summary, this study provides an intelligent inverse characterization method for targeted sound absorption of PU foams, with potential extensions to the inverse characterization of other acoustic porous materials.

关键词： Polyurethane foams Acoustic properties Non-acoustic parameters auto-encoder Inverse characterization

来源：评论

学校读者我要写书评

暂无评论

Efficient and robust de-speckling filter for ultrasound images based on an attentional auto-encoder

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2025年第1期19卷 1-13页

作者： Ahmed, Anas Fouad Al Iraqia Univ Coll Engn Dept Elect Engn Baghdad 6029 Iraq

The existence of speckle noise in medical ultrasound (US) images greatly diminishes image quality and decreases diagnostic accuracy. The recent models for de-noising US images suffer from poor generalizability, a loss of texture information, and over-smoothing of the US images, especially at high noise levels. This study suggests an efficient and robust de-speckling filter for US images based on an attentional auto-encoder. This filter incorporates two distinct and efficient attention levels. The channel attention level (CAL) and large kernel attention level (KAL). These levels are integrated into the down-sampling and up-sampling steps, respectively. A skip link is added before the up-sampling stage to avoid the gradient vanishing during training. The performance of the introduced model was assessed using subjective visual evaluations and objective determination indices. The outcomes of the suggested approach on online databases achieved the minimum execution time (AET), the maximum values for structural similarity (SSIM), and peak signal-to-noise ratio (PSNR) indices over all levels of noise, exceeding other recent algorithms. For instance, at a high level of noise, the presented technique based on the breast database achieves the following mean values: 0.005, 0.81, and 23.71 dB for the AET, SSIM, and PSNR, respectively. Also, in clinical settings, the introduced model attained the highest values for the equivalent number of looks (ENL = 18.78), contrast-to-noise ratio (CNR = 5.12), and highest resolution (alpha similar to\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\alpha<^>{\sim }$$\end{document} = 0.28). These findings prove that the presented architecture is more efficient and robust for rejecting noise while maintaining image details than other recent techniques.

关键词： Ultrasound images Speckle noise Filtering Attention strategy auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Gearbox fault identification using auto-encoder without training data from the damaged machine

引用

MEASUREMENT 2025年第PartA期242卷

作者： Pawlik, Pawel Kania, Konrad Przysucha, Bartosz AGH Univ Krakow Fac Mech Engn & Robot Dept Mech & Vibroacoust al A Mickiewicza 30 PL-30059 Krakow Poland Lublin Univ Technol Fac Management Dept Quantitat Methods Management ul Nadbystrzycka 38 PL-20618 Lublin Poland

Deep learning methods work well in machine diagnostics where operating conditions affect diagnostic signals. Classifiers are often used for fault identification, but these methods require training data sets measured for each fault. The solution to the lack of data is autoencoder-based network models, but these models can only detect, not identify faults. This article presents a new fault identification method based on auto-encoders (AE-based Fault Identification Technique AE-FIT) that does not require training data from the damaged machine. This method diagnoses pinion gearboxes operating under variable conditions (variable load, load-induced rotational speed, and temperature). The result of the technique is an interpretable diagnostic spectrum (AE-based Interpretable Order Spectrum AE- IOS). The method has been tested on two laboratory benches to detect misalignment, unbalance, and gearbox degradation. The damages introduced were used to validate a technique based on an auto-encoder trained only with data from undamaged machines.

关键词： Fault identification Degradation process Variable working conditions Neural networks Deep learning auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Markov transition fields and auto-encoder-based preprocessing for event recognition of Φ-OTDR

引用

OPTICA APPLICATA 2024年第2期54卷 217-229页

作者： Hu, Xin Dai, Jingyi Wei, Ziyi Shen, Wei Yu, Hao Wu, Haiyang Xu, Yingwen Hu, Chengyon Deng, Chuanlu Huang, Yi China State Grid Taizhou Power Supply Co Taizhou 225300 Peoples R China Shanghai Univ Key Lab Specialty Fiber Opt & Opt Access Networks Shanghai 200444 Peoples R China

To improve the model training efficiency and the classification performance of the phase-sensitive optical time-domain reflectometer (Phi-OTDR) in disturbance events recognition, a preprocessing method based on Markov transition fields (MTF) and auto-encoder (AE) is proposed. The phase time series, derived from demodulation of the original scattering signals, are converted into images by using the MTF method. Subsequently, an auto-encoder is introduced to perform a dimensionality reduction characterization of the MTF images, and the outputs of the encoder will be used as features for classification. The experimental results demonstrate that, compared with directly processing time series using 1-D CNN and classifying MTF images using CNN, the features obtained by the proposed method can accelerate the training process and improve the recognition performance of the classification model. The recognition accuracy for the four classes of events on the fence reaches 95.6%, representing a 12% increase.

关键词： distributed optical fiber sensing Phi-OTDR disturbance recognition Markov transition fields auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Hybrid model of convolutional auto-encoder and ellipse characteristic for unsupervised high impedance fault detection

引用

ELECTRIC POWER SYSTEMS RESEARCH 2025年 238卷

作者： Yang, Junjie Delinchant, Benoit Niyato, Dusit Hadjsaid, Nouredine CNRSCREATE LTD Singapore 138602 Singapore Univ Grenoble Alpes CNRS Grenoble INP G2Elab F-38031 Grenoble France Nanyang Technol Univ Coll Comp & Data Sci CCDS Singapore 639798 Singapore

High impedance faults (HIFs) present significant safety hazards such as fires and electric shock accidents, urging the development of reliable HIF detection approaches. Unfortunately, conventional protection relays often fail to detect HIFs due to their low fault currents. The growing utilization of sensors in distribution grids enables the monitoring of node signals, offering a promising way for accurate HIF detection. Nevertheless, challenges persist due to the scarcity of faulty data and the high costs associated with data collection. To tackle this challenge, we propose a hybrid artificial intelligence (AI) approach that combines the unsupervised learning capabilities of auto-encoders with the reliable physical knowledge of voltage waveform. This approach involves the transformation of node voltage signals into phase diagram curves, leveraging the ellipse characteristics of the curve to normalize the model's learning process. Performance evaluation conducted using the IEEE-34 and IEEE 13 nodes test feeders demonstrates its effectiveness in achieving highly accurate HIF detection across diverse fault conditions and locations. Comparative analysis against other unsupervised HIF detection methods reveals its superiority in terms of high detection accuracy and strong robustness to switching disturbances. The simulation data and codes relevant to this study are openly accessible, serving as a benchmark for research in HIF detection.

关键词： High impedance fault Unsupervised learning Fault detection PINN Phase diagram curve auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature learning using locality-preserved auto-encoder with complexity-invariant distance for intelligent fault diagnosis of machinery

引用

APPLIED INTELLIGENCE 2025年第6期55卷 1-14页

作者： Lu, Zhenghua Chu, Zhaobi Zhu, Min Dong, Xueping Hefei Univ Technol Sch Elect Engn & Automat Hefei 230009 Peoples R China

Unsupervised feature learning (UFL) has been recognized as a promising feature extractor in machinery fault diagnosis, where the auto-encoder is a very popular UFL framework. For the auto-encoder methods, however, it is still a great challenge to learn discriminative features from complex signals in an unsupervised manner. In this paper, a new UFL method named locality-preserved auto-encoder (LPAE) is proposed by explicitly designing a locality-preserved penalty term. Concretely, the penalty term constrains local geometry of samples in the original space to be well preserved in the reconstruction space, enabling more discriminative features to be learned accordingly. To better formulate this term, the complexity-invariant distance (CID) is employed to measure similarity between two mechanical signals so as to construct a reliable neighbor graph. On a rolling bearing dataset, experimental results verify that the proposed LPAE can learn sufficiently discriminative features from complex vibration signals collected from varying operating conditions, and achieves a remarkable and superior diagnosis performance over the existing advanced UFL methods. Moreover, the effectiveness of CID has been adequately validated by comparing with several other distance measurement methods. The proposed LPAE can be applied to the feature extraction stage of machinery fault diagnosis, which provides a potential solution for engineers to realize unsupervised learning of discriminative features.

关键词： Unsupervised feature learning Machinery fault diagnosis auto-encoder Locality Complexity-invariant distance

来源：评论

学校读者我要写书评

暂无评论

Self-Attention Enhanced auto-encoder for Link Weight Prediction With Graph Compression

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2024年第1期11卷 89-99页

作者： Liu, Zhen Zuo, Wenbo Zhang, Dongning Zhou, Chuan Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China 54th Res Inst CETC Shijiazhuang 050081 Peoples R China Chinese Acad Sci Acad Math & Syst Sci Beijing 100045 Peoples R China

Predicting unobservable or missing weights over links on various real-world networks is of fundamental scientific significance in disparate disciplines like sociology, biology, and physics, as it has been revealed by scientists that link weights, representing strong or weak ties, are able to help us understand the mechanism of link formation, community growth, and network evolution. Nevertheless, previous studies mainly relied on shallow graph features to fulfill the task of link weight prediction and thus the proposed models have relatively poor predictive performance. By learning deep graph features to improve the predictive capability, a Self-attention Enhanced graph auto-encoder called SEA is proposed. To resolve the challenge of the model's scalability for large graph applications, a two-phased link weight prediction framework is further proposed, which comprises the modules of graph compression and SEA. Experiments on seven real-world networks (four uncompressed networks and three compressed networks) demonstrated that SEA can achieve an average 6% improvement of accuracy in missing link weight prediction against state-of-the-art methods. Some extended experiments and analyses verified that the proposed framework can significantly reduce the network's size by 60%-80% while maintaining the predictive power.

关键词： Predictive models Proteins Task analysis Evolution (biology) Computational modeling Visualization Time complexity auto-encoder graph compression link weight prediction self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

KFDAE: CircRNA-Disease Associations Prediction Based on Kernel Fusion and Deep auto-encoder

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第5期28卷 3178-3185页

作者： Kang, Wen-Yue Gao, Ying-Lian Wang, Ying Li, Feng Liu, Jin-Xing Qufu Normal Univ Sch Comp Sci Rizhao 276826 Peoples R China Qufu Normal Univ Qufu Normal Univ Lib Rizhao 276826 Peoples R China Univ Hlth & Rehabil Sci Sch Hlth & Life Sci Qingdao 266113 Peoples R China

CircRNA has been proved to play an important role in the diseases diagnosis and treatment. Considering that the wet-lab is time-consuming and expensive, computational methods are viable alternative in these years. However, the number of circRNA-disease associations (CDAs) that can be verified is relatively few, and some methods do not take full advantage of dependencies between attributes. To solve these problems, this paper proposes a novel method based on Kernel Fusion and Deep auto-encoder (KFDAE) to predict the potential associations between circRNAs and diseases. Firstly, KFDAE uses a non-linear method to fuse the circRNA similarity kernels and disease similarity kernels. Then the vectors are connected to make the positive and negative sample sets, and these data are send to deep auto-encoder to reduce dimension and extract features. Finally, three-layer deep feedforward neural network is used to learn features and gain the prediction score. The experimental results show that compared with existing methods, KFDAE achieves the best performance. In addition, the results of case studies prove the effectiveness and practical significance of KFDAE, which means KFDAE is able to capture more comprehensive information and generate credible candidate for subsequent wet-lab.

关键词： CircRNA-disease association similarity network fusion auto-encoder multi-layer perceptron

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection for Medical Images Using Heterogeneous auto-encoder

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 2770-2782页

作者： Lu, Shuai Zhang, Weihang Zhao, He Liu, Hanruo Wang, Ningli Li, Huiqi Beijing Inst Technol Beijing 100081 Peoples R China Univ Liverpool Dept Eye & Vis Sci Liverpool L7 8TX England Capital Med Univ Beijing Tongren Hosp Beijing Inst Ophthalmol Beijing 100054 Peoples R China Henan Prov Acad Med Sci Zhengzhou 450046 Peoples R China

Anomaly detection is an important task for medical image analysis, which can alleviate the reliance of supervised methods on large labelled datasets. Most existing methods use a pixel-wise self-reconstruction framework for anomaly detection. However, there are two challenges of these studies: 1) they tend to overfit learning an identity mapping between the input and output, which leads to failure in detecting abnormal samples;2) the reconstruction considers the pixel-wise differences which may lead to an undesirable result. To mitigate the above problems, we propose a novel heterogeneous auto-encoder (Hetero-AE) for medical anomaly detection. Our model utilizes a convolutional neural network (CNN) as the encoder and a hybrid CNN-Transformer network as the decoder. The heterogeneous structure enables the model to learn the intrinsic information of normal data and enlarge the difference on abnormal samples. To fully exploit the effectiveness of Transformer in the hybrid network, a multi-scale sparse Transformer block is proposed to trade off modelling long-range feature dependencies and high computational costs. Moreover, the multi-stage feature comparison is introduced to reduce the noise of pixel-wise comparison. Extensive experiments on four public datasets (i.e., retinal OCT, chest X-ray, brain MRI, and COVID-19) verify the effectiveness of our method on different imaging modalities for anomaly detection. Additionally, our method can accurately detect tumors in brain MRI and lesions in retinal OCT with interpretable heatmaps to locate lesion areas, assisting clinicians in diagnosing abnormalities efficiently.

关键词： Anomaly detection Magnetic resonance imaging auto-encoder heterogeneous network

来源：评论

学校读者我要写书评

暂无评论

Generalization error guaranteed auto-encoder-based nonlinear model reduction for operator learning

引用

APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS 2025年 74卷

作者： Liu, Hao Dahal, Biraj Lai, Rongjie Liao, Wenjing Hong Kong Baptist Univ Dept Math Hong Kong Peoples R China Georgia Inst Technol Sch Math Atlanta GA 30332 USA Purdue Univ Dept Math W Lafayette IN USA

Many physical processes in science and engineering are naturally represented by operators between infinite-dimensional function spaces. The problem of operator learning, in this context, seeks to extract these physical processes from empirical data, which is challenging due to the infinite or high dimensionality of data. An integral component in addressing this challenge is model reduction, which reduces both the data dimensionality and problem size. In this paper, we utilize low-dimensional nonlinear structures in model reduction by investigating auto-encoder- based Neural Network (AENet). AENet first learns the latent variables of the input data and then learns the transformation from these latent variables to corresponding output data. Our numerical experiments validate the ability of AENet to accurately learn the solution operator of nonlinear partial differential equations. Furthermore, we establish a mathematical and statistical estimation theory that analyzes the generalization error of AENet. Our theoretical framework shows that the sample complexity of training AENet is intricately tied to the intrinsic dimension of the modeled process, while also demonstrating the robustness of AENet to noise.

关键词： Deep learning theory Generalization error Model reduction auto-encoder Operator learning

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：