检索结果-内蒙古大学图书馆

denoising of partial discharge signal using a hybrid framework of total variation denoising-autoencoder

MEASUREMENT 2023年 223卷

作者： Chaudhuri, Sayanti Ghosh, Saibal Dey, Debangshu Munshi, Sugata Chatterjee, Biswendu Dalai, Sovan Jadavpur Univ Dept Elect Engn Kolkata India

Partial discharge (PD) measurement is an essential task for assessing the condition of electrical insulations. Different types of noises, such as random noise and discrete spectral interference creep into the captured PD signals during their measurement. As a result, there is a need for an efficient denoising technique to reduce the effects of these disturbances during the PD measurement. This paper proposes a denoising scheme through a hybrid approach, which uses a total variation denoising filter followed by a denoising autoencoder. The proposed filter is used here to denoise partial discharge (PD) signal corrupted with artificially induced white Gaussian noise. The efficacy of the proposed work is evaluated with the help of some denoising metrics such as signal-tonoise ratio (SNR), root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and mean absolute error (MAE). The results amply indicate the notable performance of the proposed scheme, compared to the existing state-of-the-art PD denoising techniques.

关键词： Condition monitoring denoising autoencoder Partial discharge Spectrogram Total variation denoising filter

来源：评论

学校读者我要写书评

暂无评论

Variational Type Graph autoencoder for denoising on Event Recommendation

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2025年第1期43卷 1-27页

作者： Zhang, Shuo Meng, Xiangwu Zhang, Yujie Beijing Univ Posts & Telecommun Sch Comp Sci Natl Pilot Software Engn Sch Beijing Key Lab Intelligent Telecommun Software & Beijing Peoples R China

Recommendations for events play a pivotal role in facilitating the discovery of upcoming intriguing events within Event-Based Social Networks (EBSNs). Previous research has established the crucial significance of mining contextual features and implicit relationships to enhance recommendation performance and alleviate data sparsity issues. However, the noise inherent in contextual features exacerbates data sparsity and hampers the ability of previous methods to explore implicit relationships for mitigating data sparsity. To address this challenge, we propose a variational type graph autoencoder model that attenuates the influence of noise in different types of context features by introducing type-specific latent variables. First, we introduce a heterogeneous denoising convolution module composed of two components: (1) denoising attention aggregation is proposed to mitigate the influence of noisy structures and uncover implicit relationships. (2) A heterogeneous normalization module leverages context features within the same type to alleviate the effects of noise in context features and data sparsity. Furthermore, we propose a learnable heterogeneous mixture prior that assists in assigning different priors to distinct types of latent variables, effectively modeling different types of contextual features. Through comprehensive experiments conducted on real-world datasets, we demonstrate the compelling performance of our model compared to state-of-the-art competitive approaches.

关键词： Event-based social networks Event recommendation Data sparsity Heterogeneous Information graph Variational autoencoder denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Wireless recording and autoencoder denoising of intestinal activity in freely moving rats

引用

JOURNAL OF PHARMACOLOGICAL SCIENCES 2025年第1期158卷 54-58页

作者： Ishii, Yamato Matsumoto, Nobuyoshi Ikegaya, Yuji Kashima, Tetsuhiko Univ Tokyo Grad Sch Pharmaceut Sci Tokyo 1130033 Japan Univ Tokyo Inst AI & Beyond Tokyo 1130033 Japan Natl Inst Informat & Commun Technol Ctr Informat & Neural Networks Suita Osaka 5650871 Japan

Conventional wired systems for recording intestinal motility using strain-gauge transducers physically limit animal movement and are not ideal for long-term studies. Here, we developed a wireless recording system that allows continuous monitoring of intestinal activity in freely moving rats. We also developed a denoising autoencoder that isolates intestinal motility signals from locomotor noise while maintaining a 10-s temporal resolution. The refined data revealed decreased intestinal motility while the rats were behaviorally active. This system has broad applications for in vivo physiological research.

关键词： intestinal activity Free-moving denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Framework for Road Surface Classification: Integrating autoencoder-Based denoising and CNN-Based Classification

Hybrid Deep Learning Framework for Road Surface Classificati...

引用

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Kumar, Ajay Tiwari, Raj Gaurang Trivedi, Naresh Kumar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798331527495

This study uses a hybrid deep learning technique to classify asphalt, pavement, and unpaved roads. In real-world circumstances, image data noise can damage image categorization algorithms. This issue can be addressed by a deep neural network (DNN)-based classification system that uses advanced denoising algorithms to improve input images before categorization. We start by denoising noisy native images with autoencoder (AE) approaches. We use two autoencoders: denoising autoencoder(DAE) and Convolutional denoising autoencoder(CDAE). Proper categorization requires models that filter noise and increase visual clarity. The CDAE employs convolutional layers to maintain spatial hierarchies and local characteristics during denoising, whereas the DAE involves encoding and decoding to rebuild images. The rebuilt images are classified using a CNN after denoising. The CNN is a preferred DNN architecture for this job since it can gather and represent complex visual input. CNN identifies classification-boosting features using noise-free image training. Experiments show this hybrid model works. With 97.92% classification accuracy, the CDAE-CNN architecture could recognize road surface types and conditions under noisy environments. This performance proves the hybrid approach's durability despite training on noise-corrupted images. It improves image classification in noisy data. denoising algorithms improve deep learning classifier accuracy and make them more relevant in real-world applications with low image quality. These hybrid DAE-CNN/CDAE-CNN models minimize noise and properly categorize road surfaces. © 2025 IEEE.

关键词： Convolutional denoising autoencoder Convolutional Neural Networks Deep Neural Networks denoising autoencoder Hybrid Deep Learning Image Reconstruction Noise Reduction Techniques Noisy Image Classification Road Surface Classification

来源：评论

学校读者我要写书评

暂无评论

Open-Set Specific Emitter Identification Leveraging Enhanced Metric denoising autoencoders

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第4期12卷 3453-3462页

作者： Huang, Shennan Guo, Lantu Fu, Xue Peng, Yang Guo, Yongan Wang, Yu Zhang, Qianyun Gui, Guan Sari, Hikmet Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn Nanjing 210003 Peoples R China China Res Inst Radiowave Propagat Res Dept 5 Qingdao 266107 Peoples R China Nanjing Univ Posts & Telecommun Jiangsu Key Lab Intelligent Informat Proc & Commun Nanjing 210003 Peoples R China Beihang Univ Sch Cyber Sci & Technol Beijing 100191 Peoples R China

Specific emitter identification (SEI) is pivotal for ensuring the security of the Internet of Things (IoT). Traditional deep learning-based SEI techniques often falter in real-world applications, particularly when distinguishing between legitimate and rogue devices amid noisy conditions and low-signal-to-noise ratios (SNRs). To surmount these challenges, we propose a novel open-set SEI (OS-SEI) strategy that utilizes a metric-enhanced denoising autoencoder (MeDAE) architecture. This advanced framework incorporates a deep residual shrinkage network, significantly augmenting the denoising autoencoder's capability, thereby bolstering its resilience against noisy environments. Further, the integration of discriminative metrics, such as center loss, markedly enhances feature discrimination, resulting in heightened accuracy of device identification. Our comprehensive experimental assessments, conducted on an automatic dependent surveillance-broadcast (ADS-B) data set, underscore the superiority of our proposed OS-SEI method over existing models. The findings confirm our approach's enhanced robustness to noise and its superior accuracy in device identification within open-set scenarios.

关键词： Deep learning (DL) deep metric learning denoising autoencoder noise robustness open set specific emitter identification (SEI) Deep learning (DL) deep metric learning denoising autoencoder noise robustness open set specific emitter identification (SEI)

来源：评论

学校读者我要写书评

暂无评论

TrustEMG-Net: Using Representation-Masking Transformer With U-Net for Surface Electromyography Enhancement

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2025年第4期29卷 2506-2520页

作者： Wang, Kuan-Chen Liu, Kai-Chun Yeh, Ping-Cheng Peng, Sheng-Yu Tsao, Yu Natl Taiwan Univ Grad Inst Commun Engn Taipei 10617 Taiwan Univ Massachusetts Amherst Coll Informat & Comp Sci Amherst MA 01003 USA Natl Taiwan Univ Sci & Technol Dept Elect Engn Taipei 106 Taiwan Acad Sinica Res Ctr Informat Technol Innovat Taipei 115 Taiwan Chung Yuan Christian Univ Dept Elect Engn Taoyuan 320 Taiwan

Surface electromyography (sEMG) is a widely employed bio-signal that captures human muscle activity via electrodes placed on the skin. Several studies have proposed methods to remove sEMG contaminants, as non-invasive measurements render sEMG susceptible to various contaminants. However, these approaches often rely on heuristic-based optimization and are sensitive to the contaminant type. A more potent, robust, and generalized sEMG denoising approach should be developed for various healthcare and human-computer interaction applications. This paper proposes a novel neural network (NN)-based sEMG denoising method called TrustEMG-Net. It leverages the potent nonlinear mapping capability and data-driven nature of NNs. TrustEMG-Net adopts a denoising autoencoder structure by combining U-Net with a Transformer encoder using a representation-masking approach. The proposed approach is evaluated using the Ninapro sEMG database with five common contamination types and signal-to-noise ratio (SNR) conditions. Compared with existing sEMG denoising methods, TrustEMG-Net achieves exceptional performance across the five evaluation metrics, exhibiting a minimum improvement of 20%. Its superiority is consistent under various conditions, including SNRs ranging from -14 to 2 dB and five contaminant types. An ablation study further proves that the design of TrustEMG-Net contributes to its optimality, providing high-quality sEMG and serving as an effective, robust, and generalized denoising solution for sEMG applications.

关键词： Surface electromyography sEMG contam-inant removal denoising autoencoder U-Net U-Net transformer transformer transformer

来源：评论

学校读者我要写书评

暂无评论

Intelligent cognitive internet of things-based spectrum sensing algorithm for future communication

引用

INTERNATIONAL JOURNAL OF WEB AND GRID SERVICES 2025年第1期21卷 18-41页

作者： Byeon, Haewon Alsaadi, Mahmood Quraishi, Aadam Keshta, Ismail Soni, Mukesh Kumar, Pankaj Bhadla, Mohit Khan, Muhammad Attique Damasevicius, Robertas Inje Univ Dept Digital Antiaging Healthcare Gimhae 50834 South Korea Al Maarif Univ Coll Dept Comp Sci Al Anbar 31001 Iraq Intervent Treatment Inst Houston TX USA AlMaarefa Univ Coll Appl Sci Comp Sci & Informat Syst Dept Riyadh Saudi Arabia Lovely Profess Univ Div Res & Dev Phagwara India Dr DY Patil Vidyapeeth Dr DY Patil Sch Sci & Technol Pune India GL Bajaj Inst Technol & Management Dept Comp Sci & Engn Greater Noida 201306 Uttar Pradesh India Swarnim Startup & Innovat Univ Gandhinagar India Prince Mohammad Bin Fahd Univ Dept AI Dhahran Saudi Arabia Kaunas Univ Technol Kaunas Lithuania

The emergence of fifth-generation (5G) mobile communication technologies has propelled the advancement of the internet of things (IoT). Nevertheless, the intricate nature of the IoT mobile communication environment and the fluctuating characteristics of the signal's present substantial obstacles to current spectrum detection techniques for future communication. Hence, an artificial intelligent spectrum sensing technique is introduced, which integrates artificial intelligent, IoT and denoising autoencoder (DAE) with an enhanced long-short-term memory (LSTM) neural network. The DAE utilises encoding and decoding to retrieve the fundamental structural characteristics of mobile signals, while the enhanced LSTM spectrum sensing classifier model incorporates previous moment information features to classify the time-series signal sequences. This method has demonstrated a 45% improvement in perception performance compared to SVM, RNN, LeNet5, LVQ, and Elman algorithm.

关键词： future communication internet of things IoT spectrum sensing artificial intelligent long-short-term memory LSTM denoising autoencoder DAE

来源：评论

学校读者我要写书评

暂无评论

Self-supervised fusion of deep soft assignments for multi-view diagnosis of machine faults

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2025年第4期36卷 2493-2507页

作者： Li, Chuan Wu, Yifan Xiong, Manjun Yang, Shuai Bai, Yun Chongqing Technol & Business Univ Sch Management Sci & Engn Chongqing 400067 Peoples R China Chongqing Technol & Business Univ Res Ctr Syst Hlth Maintenance Chongqing 400067 Peoples R China

Fault patterns are often unavailable for machine fault diagnosis without prior knowledge. This makes it challenging to diagnose the existence of machine faults and their types. To address this issue, a novel scheme of deep soft assignments fusion network (DSAFN) is proposed for the self-supervised multi-view diagnosis of machine faults. To enhance the robustness of the model and prevent overfitting, random noise is added to the collected signals. In each view, vibration features are extracted by a denoising autoencoder. Using the extracted deep features, a soft assignment fusion strategy is proposed to fully utilize both the public and complementary information of multiple views. Critical diagnosis missions, including novel fault detection and fault clustering, are accomplished through binary clustering and multi-class clustering of DSAFN, respectively. Two diagnostic experiments are conducted to validate the proposed method. The results indicate that the proposed method performs better than state-of-the-art peer methods in terms of diagnostic accuracy and noise robustness.

关键词： Machine fault Multi-view diagnosis denoising autoencoder Self-supervised fusion Deep soft assignment

来源：评论

学校读者我要写书评

暂无评论

Wavelet Integrated Convolutional Neural Network for ECG Signal denoising 31st

Wavelet Integrated Convolutional Neural Network for ECG Sign...

引用

31st International Conference on Multimedia Modeling

作者： Terada, Takamasa Toyoura, Masahiro Univ Yamanashi 4-3-11 Takeda Kofu Yamanashi 4008511 Japan

ISBN: (纸本)9789819620708;9789819620715

Wearable electrocardiogram (ECG) measurement using dry electrodes has a problem with high-intensity noise distortion. Hence, a robust noise reduction method is required. However, overlapping frequency bands of ECG and noise make noise reduction difficult. Hence, it is necessary to provide a mechanism that changes the characteristics of the noise based on its intensity and type. This study proposes a convolutional neural network (CNN) model with an additional wavelet transform layer that extracts the specific frequency features in a clean ECG. Testing confirms that the proposed method effectively predicts accurate ECG behavior with reduced noise by accounting for all frequency domains. In an experiment, noisy signals in the signal-to-noise ratio (SNR) range of -10-10 are evaluated, demonstrating that the efficiency of the proposed method is higher when the SNR is small.

关键词： Electrocardiogram Wavelet transform denoising autoencoder Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

denoising autoencoders for Non-Intrusive Load Monitoring: Improvements and comparative evaluation

引用

ENERGY AND BUILDINGS 2018年 158卷 1461-1474页

作者： Bonfigli, Roberto Felicetti, Andrea Principi, Emanuele Fagiani, Marco Squartini, Stefano Piazza, Francesco Univ Politecn Marche Dept Informat Engn Via Brecce Bianche I-60131 Ancona Italy

Non-Intrusive Load Monitoring (NILM) is the task of determining the appliances individual contributions to the aggregate power consumption by using a set of electrical parameters measured at a single metering point. NILM allows to provide detailed consumption information to the users, that induces them to modify their habits towards a wiser use of the electrical energy. This paper proposes a NILM algorithm based on the Deep Neural Networks. In particular, the NILM task is treated as a noise reduction problem addressed by using denoising autoencoder (dAE) architecture, i.e., a neural network trained to reconstruct a signal from its noisy version. This architecture has been initially proposed by Kelly and Knottenbelt (2015), and here is extended and improved by conducting a detailed study on the topology of the network, and by intelligently recombining the disaggregated output with a median filter. An additional contribution of this paper is an exhaustive comparative evaluation conducted with respect to one of the reference work in the field of Hidden Markov Models (HMM) for NILM, i.e., the Additive Factorial Approximate Maximum a Posteriori (AFAMAP) algorithm. The experiments have been conducted on the AMPds, UK-DALE, and REDD datasets in seen and unseen scenarios both in presence and in absence of noise. In order to be able to evaluate AFAMAP in presence of noise, an HMM model representing the noise contribution has been introduced. The results showed that the dAE approach outperforms the AFAMAP algorithm both in seen and unseen condition, and that it exhibits a significant robustness in presence of noise. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Non-Intrusive Load Monitoring (NILM) Active power denoising autoencoder Deep Neural Network (DNN) Factorial Hidden Markov Model (FHMM)

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：