检索结果-内蒙古大学图书馆

Supervised convolutional autoencoder-based fault-relevant feature learning for fault diagnosis in industrial processes

引用

JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS 2022年第0期132卷 104200-104200页

作者： Yu, Feng Liu, Jianchang Liu, Dongming Wang, Honghai Northeastern Univ Dept Informat Sci & Engn Shenyang 110819 Peoples R China Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110819 Peoples R China

Background: convolutional autoencoder (CAE) is an unsupervised feature learning method and shows excellent performance in multivariate fault diagnosis. However, CAE cannot guarantee that the extracted feature is always related to the fault type due to its unsupervised self-reconstruction in the pretraining ***: To solve this problem, a new feature learning method, supervised convolutional autoencoder (SCAE) is proposed to pretrain the network and learn representative feature containing internal spatial information and fault information. In the SCAE, process sample and corresponding label are reconstructed by multilayer encoding-decoding the raw sample. Meanwhile, to prevent label information overfitting the network, a minimum difference transformation function is introduced into the loss ***: The obtained fault-relevant features can be obviously distinguished between different fault types. The trained pretraining network provides more appropriate predefined parameters for fine-tuning to improve the classification performance. The effectiveness of the proposed method is evaluated by the continuous stirred tank reactor (CSTR) process and the Tennessee Eastman (TE) process.(c) 2021 Taiwan Institute of Chemical Engineers. Published by Elsevier B.V. All rights reserved.

关键词： convolutional autoencoder Deep learning Fault-relevant feature Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

VGG-CAE: Unsupervised Visual Place Recognition Using VGG16-Based convolutional autoencoder 4th

VGG-CAE: Unsupervised Visual Place Recognition Using VGG16-B...

引用

4th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Xu, Zhenyu Zhang, Qieshi Hao, Fusheng Ren, Ziliang Kang, Yuhang Cheng, Jun Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China Univ Chinese Acad Sci Shenzhen Coll Adv Technol Beijing Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9783030880071;9783030880064

Visual Place Recognition (VPR) is a challenging task in Visual Simultaneous Localization and Mapping (VSLAM), which expects to find out paired images corresponding to the same place in different conditions. Although most methods based on convolutional Neural Network (CNN) perform well, they require a large number of annotated images for supervised training, which is time and energy consuming. Thus, to train the CNN in an unsupervised way and achieve better performance, we propose a new place recognition method in this paper. We design a VGG16-based convolutional autoencoder (VGG-CAE), which uses the features outputted by VGG16 as the label of images. In this case, VGG-CAE learns the latent representation from the label of images and improves the robustness against appearance and viewpoint variation. When deploying VGG-CAE, features are extracted from query images and reference images with post-processing, the Cosine similarities of features are calculated respectively and a matrix for feature matching is formed accordingly. To verify the performance of our method, we conducted experiments with several public datasets, showing our method achieves competitive results comparing to existing approaches.

关键词： Visual place recognition convolutional autoencoder VGG-16

来源：评论

学校读者我要写书评

暂无评论

HYPERSPECTRAL ANOMALY DETECTION OF HIDDEN CAMOUFLAGE OBJECTS BASED ON convolutional autoencoder 3

HYPERSPECTRAL ANOMALY DETECTION OF HIDDEN CAMOUFLAGE OBJECTS...

引用

Conference on Artificial Intelligence and Machine Learning in Defense Applications III Held as Part of SPIE Security+Defence Conference

作者： Kuester, Jannick Gross, Wolfgang Middelmann, Wolfgang Fraunhofer IOSB Fraunhofer Ctr Machine Learning Ettlingen Germany

ISBN: (数字)9781510645851

ISBN: (纸本)9781510645851;9781510645844

The rising availability of hyperspectral data has increased the attention of anomaly detection for various applications. Anomaly detection aims to find a small number of pixels in the hyperspectral data for which the spectral signatures differ significantly from the background. However, for anomalies like camouflage objects in a rural area, the spectral signatures distinguish only by small features. For this purpose, we use a 1D-convolutional autoencoder, which extracts the background spectra's most specific features to reconstruct the spectral signature by minimizing the loss function's error. The difference between the original and the reconstructed data can be exploited for anomaly detection. Since the loss function is minimized based on predominant background spectra, areas with anomalies exhibit higher error values. The proposed anomaly detection method's performance is tested on hyperspectral data in the range of 1000 to 2500 nm. The data was recorded with a drone-based Headwall sensor at approximately 80 m over a rural area near Greding, Germany. The anomalies consist mainly of camouflage materials and vehicles. We compare the performance of a 1D-convolutional autoencoder trained on a data set without the target anomalies for different models. This is done to quantify the number of anomalies in the data set before they inhibit the detection process. Additionally, the detection results are compared to the state-of-the-art Reed-Xiaoli anomaly detector. We present the results by counting the correct detections in relation to the false positives with the receiver operating characteristic and discuss more suitable evaluation approaches for small targets. We show that the 1D-CAE outperforms the Reed-Xiaoli anomaly detector for a false alarm rate of 0.1% by reconstructing the background with a low error and the anomalies with a higher error. The 1D-CAE is suitable for camouflage anomaly detection.

关键词： hyperspectral anomaly detection compression error convolutional autoencoder target detection camouflage

来源：评论

学校读者我要写书评

暂无评论

Robust Deep 3D convolutional autoencoder for Hyperspectral Unmixing with Hypergraph Learning

引用

Journal of Harbin Institute of Technology(New Series) 2021年第5期28卷 1-8页

作者： Peiyuan Jia Miao Zhang Yi Shen Department of Control Science and Engineering Harbin Institute of TechnologyHarbin 150001China

Hyperspectral unmixing aims to acquire pure spectra of distinct substances(endmembers)and fractional abundances from highly mixed *** this paper,a deep unmixing network framework is designed to deal with the noise *** contains two parts:a three⁃dimensional convolutional autoencoder(denoising 3D CAE)which recovers data from noised input,and a restrictive non⁃negative sparse autoencoder(NNSAE)which incorporates a hypergraph regularizer as well as a l2,1⁃norm sparsity constraint to improve the unmixing *** deep denoising 3D CAE network was constructed for noisy data retrieval,and had strong capacity of extracting the principle and robust local features in spatial and spectral domains efficiently by training with corrupted ***,a part⁃based nonnegative sparse autoencoder with l2,1⁃norm penalty was concatenated,and a hypergraph regularizer was designed elaborately to represent similarity of neighboring pixels in spatial *** experiments were conducted on synthetic and real⁃world data,which both demonstrate the effectiveness and robustness of the proposed network.

关键词： deep learning unsupervised unmixing convolutional autoencoder hypergraph hyperspectral data

来源：评论

学校读者我要写书评

暂无评论

RUL prediction for rolling bearings based on convolutional autoencoder and status degradation model

引用

APPLIED SOFT COMPUTING 2022年 130卷

作者： Xu, Weiyang Jiang, Quansheng Shen, Yehu Xu, Fengyu Zhu, Qixin Suzhou Univ Sci & Technol Sch Mech Engn Suzhou 215009 Peoples R China Nanjing Univ Posts & Telecommun Sch Automat Nanjing 210003 Peoples R China

The remaining useful life (RUL) prediction of rolling bearings plays a key role in improving the safety and reliability assessment for rotating machinery. To accurately describe the degradation degree of bearings and perform RUL prediction, an RUL prediction method of rolling bearing combining convolutional autoencoder (CAE) networks and status degradation model is proposed. Firstly, the CAE is used to extract the features from the degraded bearing data;then the status degradation model is built, and the multi-dimensional health status mapping function is used to downscale the extracted features, and the reduced data points are fused with the Euclidean distance to establish the health status index that can characterize the degraded bearing. Finally, the status degradation function in the constructed model and the online update and prediction algorithm are used to adaptively estimate the RUL. The proposed method is validated with PHM datasets for RUL prediction, and its prediction performance is compared with eight prediction methods. The experimental results show that the proposed approach effectively predicts the RUL of rolling bearings and accurately evaluates the degradation degree of the bearing in a future stage.

关键词： RUL prediction Rolling bearings convolutional autoencoder Status degradation model Online update and prediction

来源：评论

学校读者我要写书评

暂无评论

CNN and convolutional autoencoder (CAE) based real-time sensor fault detection, localization, and correction

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2022年 169卷 108723-108723页

作者： Jana, Debasish Patil, Jayant Herkal, Sudheendra Nagarajaiah, Satish Duenas-Osorio, Leonardo Rice Univ Dept Civil & Environm Engn Houston TX 77005 USA Rice Univ Dept Mech Engn Houston TX 77005 USA

Increasing advances in sensing technologies and analytics have led to the proliferation of sensors to monitor structural and infrastructural systems. Accurate sensor data can provide information about structural health, aid in prognosis, and help calculate forces for vibration control. However, sensors are susceptible to faults such as loss of data, random noise, bias, drift, etc., due to the aging of sensors, defects, or environmental factors. Although traditional signal processing techniques can detect and isolate faults and reconstruct corrupt or missing sensor data, they demand significant human intervention. The continuous rise in computational power and demonstrated efficacy in numerous domains motivates the use of deep learning to minimize human-in-the-loop techniques. In this work, we introduce a novel, deep learning framework for linear systems with time-invariant parameters that identifies the presence and type of fault in sensor data, location of the faulty sensor and subsequently reconstructs the correct sensor data for fault detection, fault classification, and reconstruction. In our framework, first, a convolutional Neural Network (CNN) is used to detect the presence of a fault and identify its type. Next, a suite of individually trained convolutional autoencoder (CAE) networks corresponding to each type of fault are employed for reconstruction. We demonstrate the efficacy of our framework to address both single and multiple sensor faults in synthetically generated data of a simple shear-type structure and experimentally measured data from a simplified arch bridge. While the framework is agnostic of fault-type, we demonstrate its use for four types of fault namely, missing, spiky, random, and drift. For both simulated and experimental datasets with a single fault, our models performed well, achieving 100% accuracy in faulty sensor localization, more than 98.7% accuracy in fault type detection, and more than 99% accuracy in reconstruction. Our framework

关键词： Faulty sensor Fault detection Fault classification Data reconstruction convolutional neural network convolutional autoencoder Deep learning

来源：评论

学校读者我要写书评

暂无评论

Audio based depression detection using convolutional autoencoder

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年 189卷 116076-116076页

作者： Sardari, Sara Nakisa, Bahareh Rastgoo, Mohammed Naim Eklund, Peter Shiraz Univ Engn & IT Dept Comp Sci Shiraz Iran Deakin Univ Sch Informat Technol Fac Sci Engn & Built Environm Geelong Vic Australia Queensland Univ Technol Sch Elect Engn & Comp Sci Brisbane Qld Australia

Depression is a serious and common psychological disorder that requires early diagnosis and treatment. In severe episodes the condition may result in suicidal thoughts. Recently, the need for building an effective audio-based Automatic Depression Detection (ADD) system has sparked the interest of the research community. To date, most of the reported approaches to recognize depression rely on hand-crafted feature extraction for audio data representation. They combine wide variety of audio-related features to improve the classification performance. However, combining many hand-crafted features including relevant and less-relevant can enlarge the feature space which can lead to high-dimensionality issues as not all the features would carry significant information regarding depression. Having high number of features can make the pattern recognition more difficult and increase the risk of overfitting. To overcome these limitations, an audio-based framework of depression detection which includes an adaptation of a deep learning (DL) technique is proposed to automatically extract the highly relevant and compact feature set. This proposed framework uses an end-to-end convolutional Neural Network based autoencoder (CNN AE) technique to learn the highly relevant and discriminative features from raw sequential audio data, and hence to detect depressed people more accurately. In addition, to address the sample imbalance problem we use a cluster-based sampling technique which highly reduces the risk of bias towards the major class (non-depressed). To evaluate the performance and effectiveness of the proposed pipeline, we perform the experiments on Distress Analysis Interview Corpus-Wizard of Oz (DAIC-WOZ) dataset and compare them with the hand-crafted feature extraction methods and other outstanding studies in this domain. The results show that proposed method outperforms other well-known audio-based ADD models with at least 7% improvement in F-measure for classifying depression

关键词： Audio depression detection Semi-supervised learning convolutional autoencoder Early depression detection

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised visual anomaly detection based on convolutional autoencoder and transfer learning

引用

MACHINE LEARNING WITH APPLICATIONS 2023年 11卷

作者： Saeedi, Jamal Giusti, Alessandro Dalle Molle Inst Artificial Intelligence IDSIA USI Lugano Switzerland

Recent advances in deep neural networks have shown that reconstruction -based methods using autoencoders have potential for anomaly detection in visual inspection tasks. However, there are challenges when applying these methods to high -resolution images, such as the need for large network training and computation of anomaly scores. autoencoder-based methods detect anomalies by comparing an input image to its reconstruction in pixel space, which can result in poor performance due to imperfect reconstruction. In this paper, we propose a method to address these challenges by using a conditional patch -based convolutional autoencoder and one -class deep feature classification. We train an autoencoder using only normal images and compute anomaly maps as the difference between the input and output of the autoencoder. We then embed these anomaly maps using a pretrained convolutional neural network feature extractor. Using the deep feature embeddings from the anomaly maps of training samples, we train a one -class classifier to compute an anomaly score for an unseen sample. A simple threshold -based criterion is used to determine if the unseen sample is anomalous or not. We compare our proposed algorithm to state-of-the-art methods on multiple challenging datasets, including a dataset of zipper cursors and eight datasets from the MVTec dataset collection. We find that our approach outperforms alternatives in all cases, achieving an average precision score of 94.77% for zipper cursors and 96.51% for MVTec datasets.

关键词： Anomaly detection Visual inspection convolutional autoencoder Deep feature embedding One-class classifier

来源：评论

学校读者我要写书评

暂无评论

From data to dynamics: Reconstructing soliton collision phenomena in optical fibers using a convolutional autoencoder

引用

Results in Physics 2024年 67卷

作者： Xu, Qibo Rong, Jifang Zeng, Qilin Yuan, Xiaofang Huang, Longnv Yang, Hua College of Computer Science and Electronic Engineering Hunan University Hunan Changsha 410082 China Department of Information Engineering Hunan Mechanical and Electrical of Polytechnic Hunan Changsha 410151 China Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Beijing 100094 China Department of Electric Engineering and Information Hunan University Hunan Changsha 410082 China

In this study, a convolutional autoencoder is constructed to extract and reconstruct the dynamical processes of soliton collisions in optical fibers. The model demonstrates exceptional reconstruction capabilities, accurately capturing the evolution of optical event horizons and reproducing nonlinear phenomena such as complex frequency conversions and energy exchange processes. The reconstruction results show high consistency with the numerical simulations, with RMSE values of 0.0220 and 0.0174 in the temporal and frequency domains, respectively. Additionally, by adjusting the training parameters of the convolutional autoencoder model, its reconstruction performance for nonlinear dynamic processes was further validated. This method is expected to provide a different perspective for studying nonlinear phenomena in optical fibers while reducing the consumption of computational resources. © 2024

关键词： convolutional autoencoder Optical event horizon Soliton collisions

来源：评论

学校读者我要写书评

暂无评论

Construction Method of the Distribution Transform Load Feature Database Based on Deep convolutional autoencoder

引用

FRONTIERS IN ENERGY RESEARCH 2022年 10卷

作者： Xu, Bin Gao, Yuan Liu, Jun Lu, Yang Yang, Yifeng Xu, Feng Xu, Xiaoqing Shanghai Univ Elect Power Coll Elect Engn Shanghai Peoples R China State Grid Zhejiang Anji Cty PowerSupply Co Ltd Huzhou Peoples R China

With the large-scale access of distributed resources to distribution network operation, there are more and more prosumers on the user side. It forms the basis of load prediction and demand-side management to identify different power consumption patterns and establish a typical load characteristic database according to the load data of prosumers. Therefore, a method to build a prosumer load characteristic database based on a deep convolutional autoencoder is proposed. First, the autoencoder network was used to extract the features of the load data collected to reduce the data dimension. Then, the density weight canopy algorithm was used to precluster the data after dimensionality reduction to obtain the initial clustering center and the optimal clustering number K value. The pre-clustering results were combined with the k-means algorithm for clustering, and the typical load characteristic database of prosumers was obtained. Finally, the comparison between the clustering index and the traditional k-means clustering algorithm and the improved k-means direct clustering algorithm proves that the method can effectively improve the accuracy of clustering results.

关键词： prosumer convolutional autoencoder load classification dimensionality reduction clustering neural network

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：