检索结果-内蒙古大学图书馆

An innovative coupled model in view of wavelet transform for predicting short-term PM10 concentration

JOURNAL OF ENVIRONMENTAL MANAGEMENT 2021年 289卷 112438-112438页

作者： Qiao, Weibiao Wang, Yining Zhang, Jianzhuang Tian, Wencai Tian, Yu Yang, Quan Yan Shan Univ Sch Vehicle & Energy Qinhuangdao 066004 Hebei Peoples R China North China Univ Water Resources & Elect Power Sch Environm & Municipal Engn Zhengzhou 450046 Peoples R China Beijing Univ Technol Fac Architecture Civil & Transportat Engn Beijing 100124 Peoples R China

Wavelet transform (WT) is an advanced preprocessing technique, which has been widely used in PM 10 prediction. However, this technique cannot provide stable performance due to the empirical selection of wavelet's layers. For fixing the optimal wavelet's layers in PM10 forecasting, an innovative coupled model based on WT, long short-term memory (LSTM), and SAE (stacked autoencoder) are proposed. This study designs a crossover experiment with 960 high- and low-frequency components by wavelet decomposition and predicts each component with SAE-LSTM based on 12 samples from different regions. The results indicate that the developed model outperforms other BiLSTM (Biredictional LSTM) and LSTM based on some error evaluation indicators (i.e. Nash-Sutcliffe efficiency coefficient (NSEC)), and compared with other steps, the accuracy of two-step prediction is the highest in view of root mean squares error (RMSE). In addition, for 12 samples, the prediction accuracy by using high layers is higher than that by adopting low layers for decomposing them. This paper fixes the optimal wavelet' layers in PM10 prediction, which provides a meaningful reference in other prediction scenarios based on the application of WT.

关键词： PM10 Long short-term memory stacked autoencoder Wavelet transform Prediction

来源：评论

学校读者我要写书评

暂无评论

The Forecasting of PM2.5 Using a Hybrid Model Based on Wavelet Transform and an Improved Deep Learning Algorithm

引用

IEEE ACCESS 2019年 7卷 142814-142825页

作者： Qiao, Weibiao Tian, Wencai Tian, Yu Yang, Quan Wang, Yining Zhang, Jianzhuang North China Univ Water Resources & Elect Power Sch Environm & Municipal Engn Zhengzhou 450046 Henan Peoples R China Sinopec Zhongyuan Petr Engn Co Ltd Zhengzhou 450046 Henan Peoples R China

In recent years, the haze has caused serious troubles to peoples lives, with the continuous increase of PM2.5 emissions. The accurate prediction of PM2.5 is very crucial for policy makers to make predictive measures. Due to the nonlinearity of the PM2.5 time series, it is difficult to predict accurately. Despite some studies about PM2.5 being proposed, the problem of the LSTM (long short-term memory) gradient disappearance and random selection of wavelet orders and layers isnt still solved. In this study, a novel model based on WT (wavelet transform)-SAE (stacked autoencoder)-LSTM is proposed. Firstly, six study sites from China are taken as examples and WT is used to decompose PM2.5 time series into several low-and high- frequency components based on different samples. Secondly, the decomposed components are predicted based on SAE-LSTM. Finally, the predicted results are reconstructed in view of all low-and high-frequency components and the predicted results are obtained. The results imply that: (1) the forecasting performance of SAE-LSTM is better than that of other models (e.g., BP (back propagation)) used for comparison;(2) for six different PM 2.5 samples, four orders five layers, five orders six layers, five orders seven layers, three orders six layers, five orders seven layers, and five orders six layers are the most appropriate. The conclusion that such a novel model may help to enhance the accuracy of PM 2.5 prediction can be drawn.

关键词： Predictive models Forecasting Wavelet transforms Logic gates Neural networks Atmospheric modeling PM 2 5 time series wavelet transform stacked autoencoder long short-term memory prediction

来源：评论

学校读者我要写书评

暂无评论

Discriminative feature learning for blade icing fault detection of wind turbine

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2020年第11期31卷 115102-115102页

作者： Yi, Huaikuan Jiang, Qinchao East China Univ Sci & Technol Minist Educ Key Lab Adv Control & Optimizat Chem Proc Shanghai 200237 Peoples R China

The early detection of blade icing is gaining increasing attention due to its importance in guaranteeing wind turbine safety and operation efficiency. In this study, a wind turbine icing fault detection method based on discriminative feature learning is proposed. First, a stacked autoencoder (SAE) is trained to generate representations, which utilizes a large amount of normal operating data, as well as time series correlation information. Second, discriminative features are obtained by combining the original data, SAE-extracted features, and the residual vector. Third, the sparse linear discriminant analysis is performed on the discriminative features to achieve simultaneous feature selection and dimension reduction. Finally, the wind turbine operation status is examined using the learned discriminative feature. The proposed discriminative feature learning-based fault detection scheme is tested on a benchmark wind turbine icing dataset. Results of the comparative trial verify the feasibility and superiority of the proposed method.

关键词： fault detection stacked autoencoder wind turbine discriminative feature learning

来源：评论

学校读者我要写书评

暂无评论

Spatial-Adaptive Siamese Residual Network for Multi-/Hyperspectral Classification

引用

REMOTE SENSING 2020年第10期12卷 1640-1640页

作者： He, Zhi He, Dan Sun Yat Sen Univ Sch Geog & Planning Southern Marine Sci & Engn Guangdong Lab Zhuhai Guangdong Prov Key Lab Urbanizat & GeoSimulatCtr Guangzhou 510275 Guangdong Peoples R China Dongguan Univ Technol City Coll Dongguan 511700 Peoples R China

Deep learning methods have been successfully applied for multispectral and hyperspectral images classification due to their ability to extract hierarchical abstract features. However, the performance of these methods relies heavily on large-scale training samples. In this paper, we propose a three-dimensional spatial-adaptive Siamese residual network (3D-SaSiResNet) that requires fewer samples and still enhances the performance. The proposed method consists of two main steps: construction of 3D spatial-adaptive patches and Siamese residual network for multiband images classification. In the first step, the spectral dimension of the original multiband images is reduced by a stacked autoencoder and superpixels of each band are obtained by the simple linear iterative clustering (SLIC) method. Superpixels of the original multiband image can be finally generated by majority voting. Subsequently, the 3D spatial-adaptive patch of each pixel is extracted from the original multiband image by reference to the previously generated superpixels. In the second step, a Siamese network composed of two 3D residual networks is designed to extract discriminative features for classification and we train the 3D-SaSiResNet by pairwise inputting the training samples into the networks. The testing samples are then fed into the trained 3D-SaSiResNet and the learned features of the testing samples are classified by the nearest neighbor classifier. Experimental results on three multiband image datasets show the feasibility of the proposed method in enhancing classification performance even with limited training samples.

关键词： remote sensing classification stacked autoencoder superpixel Siamese network

来源：评论

学校读者我要写书评

暂无评论

An Efficient Framework for Animal Breeds Classification Using Semi-Supervised Learning and Multi-Part Convolutional Neural Network (MP-CNN)

引用

IEEE ACCESS 2019年 7卷 151783-151802页

作者： Meena, S. Divya Agilandeeswari, L. Vellore Inst Technol Sch Informat Technol & Engn Vellore 632014 Tamil Nadu India

The automatic classification of animal images is an onerous task due to the challenging image conditions, especially when it comes to animal breeds. In this paper, we built a semi-supervised learning based Multi-part Convolutional Neural Network (MP-CNN) that classifies 35,992 animal images from ImageNet into 27 different classes of animals. The proposed model classifies the animals on both generic and fine-grained level. The animal breeds are accurately classified using Multi-part Convolutional Neural Network with a hybrid feature extraction framework of Fisher Vector based stacked autoencoder. Furthermore, with Semi-supervised learning based pseudo-labels, the model classifies new classes of unlabeled images too. Modified Hellinger Kernel classifier has been used to re-train the misclassified classes of animals and thereby improve the performance obtained from MP-CNN. The model has experimented with varied tasks to analyze its performance in each of the cases. The experimental results have proved that the coalesced approach of MP-CNN with pseudo-labels can accurately classify animal breeds and we have achieved an accuracy of 99.95 from the proposed model.

关键词： Feature extraction Convolutional neural networks Dogs Semisupervised learning Image classification Fisher vector inception-V3 modified hellinger Kernel classifier multi-part based convolutional neural network pseudo-labels semi-supervised learning stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Soft sensor method of multimode BOF steelmaking endpoint carbon content and temperature based on vMF-WSAE dynamic deep learning

引用

HIGH TEMPERATURE MATERIALS AND PROCESSES 2023年第1期42卷

作者： Yang, Lu Liu, Hui Chen, Fugang Kunming Univ Sci & Technol Fac Informat Engn & Automation Kunming 650500 Yunnan Peoples R China Kunming Univ Sci & Technol Yunnan Key Lab Artificial Intelligence Kunming 650500 Yunnan Peoples R China Yunnan Kungang Elect & Informat Sci Ltd Kunming 650302 Yunnan Peoples R China

The difficulty of endpoint determination in basic oxygen furnace (BOF) steelmaking lies in achieving accurate real-time measurements of carbon content and temperature. For the characteristics of serious nonlinearity between process data, deep learning can perform excellent nonlinear feature representation for complex structural data. However, there is a process drift phenomenon in BOF steelmaking, and the existing deep learning-based soft sensor models cannot adapt to changes in the characteristics of samples, which may lead to their performance degradation. To deal with this problem, considering the characteristics of multimode distribution of process data, an adaptive updating deep learning model based on von-Mises Fisher (vMF) mixture model and weighted stacked autoencoder is proposed. First, the stacked autoencoder (SAE) and vMF mixture model are constructed for complex structural data, which can initially establish nonlinear mapping relationships and division of different distributions. Second, for each query sample, the basic SAE network will perform online adaptive fine-tuning according to its data with the same distribution to achieve dynamic updating. Moreover, each sample is assigned a weight according to its similarity with the query sample. Through the designed weighted loss function, the updated deep network will better match the working conditions of the query sample. Experimental studies with numerical examples and actual BOF steelmaking process data are provided to demonstrate the effectiveness of the proposed method.

关键词： BOF steelmaking endpoint stacked autoencoder vMF mixture model similarity measure adaptive weighted updating

来源：评论

学校读者我要写书评

暂无评论

Deep Semi-Supervised Just-in-Time Learning Based Soft Sensor for Mooney Viscosity Estimation in Industrial Rubber Mixing Process

引用

POLYMERS 2022年第5期14卷 1018页

作者： Zhang, Yan Jin, Huaiping Liu, Haipeng Yang, Biao Dong, Shoulong Kunming Univ Sci & Technol Fac Informat Engn & Automat Dept Automat Kunming 650500 Yunnan Peoples R China Yunnan Key Lab Comp Technol Applicat Kunming 650500 Yunnan Peoples R China Beijing Inst Technol Sch Chem & Chem Engn Dept Chem Engn Beijing 100081 Peoples R China

Soft sensor technology has become an effective tool to enable real-time estimations of key quality variables in industrial rubber-mixing processes, which facilitates efficient monitoring and a control of rubber manufacturing. However, it remains a challenging issue to develop high-performance soft sensors due to improper feature selection/extraction and insufficiency of labeled data. Thus, a deep semi-supervised just-in-time learning-based Gaussian process regression (DSSJITGPR) is developed for Mooney viscosity estimation. It integrates just-in-time learning, semi-supervised learning, and deep learning into a unified modeling framework. In the offline stage, the latent feature information behind the historical process data is extracted through a stacked autoencoder. Then, an evolutionary pseudo-labeling estimation approach is applied to extend the labeled modeling database, where high-confidence pseudo-labeled data are obtained by solving an explicit pseudo-labeling optimization problem. In the online stage, when the query sample arrives, a semi-supervised JITGPR model is built from the enlarged modeling database to achieve Mooney viscosity estimation. Compared with traditional Mooney-viscosity soft sensor methods, DSSJITGPR shows significant advantages in extracting latent features and handling label scarcity, thus delivering superior prediction performance. The effectiveness and superiority of DSSJITGPR has been verified through the Mooney viscosity prediction results from an industrial rubber-mixing process.

关键词： soft sensor Mooney viscosity just-in-time learning semi-supervised learning stacked autoencoder gaussian process regression rubber mixing process

来源：评论

学校读者我要写书评

暂无评论

Detection of impact on aircraft composite structure using machine learning techniques

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2021年第8期32卷

作者： Ai, Li Soltangharaei, Vafa Bayat, Mahmoud Van Tooren, Michel Ziehl, Paul Univ South Carolina Dept Civil & Environm Engn Columbia SC 29208 USA Collins Aerostruct Chula Vista CA USA Univ South Carolina Columbia SC 29208 USA

Aircraft structures are exposed to impact damage caused by debris and hail during their service life. One of the design concerns in composite structures is the resistance of layered surfaces to damage, which occurs from impacts with various foreign objects. Therefore, the impact localization and damage quantification of impacts should be studied and considered to address flight safety and to reduce costs associated with a regularly scheduled visual inspection. Since the structural components of the aircraft are large scale, visual inspection and monitoring are challenging and subject to human error. This paper presents a promising solution that can automatically detect and localize an impact that may occur during flight. To achieve this goal, acoustic emission (AE) is employed as an impact monitoring approach. Random forest and deep learning were adopted for training the source location models. An AE dataset was collected by conducting an impact experiment on a full-size thermoplastic aircraft elevator in a laboratory environment. A dataset consisting of AE parametric features and a dataset consisting of AE waveforms were assigned to a random forest classifier and deep learning network for the investigation of their applicability of impact source localization. The results obtained were compared using the source localization approach in previous research using a conventional artificial neural network. The analysis of results shows the random forest and deep learning leads to better event localization performance. In addition, the random forest model can provide the importance of features. By deleting the least important features, the storage required to save the input and the computing time for the random forest is greatly reduced, and an acceptable localization performance can still be obtained.

关键词： impact monitoring acoustic emission artificial neural network random forest stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based retrieval of cyanobacteria pigment in inland water for in-situ and airborne hyperspectral data

引用

ECOLOGICAL INDICATORS 2020年第0期110卷 105879-000页

作者： Yim, Inhyeok Shin, Jihoon Lee, Hyuk Park, Sanghyun Nam, Gibeom Kang, Taegu Cho, Kyung Hwa Cha, YoonKyung Univ Seoul Sch Environm Engn Seoul 130743 South Korea Natl Inst Environm Res Water Qual Assessment Res Div Environm Res Complex Incheon South Korea Ulsan Natl Inst Sci & Technol Sch Urban & Environm Engn Ulsan 689798 South Korea

Worldwide proliferation of cyanobacteria blooms in inland waters not only affects the intended use of water but potentially threatens human and animal health. In this study, a stacked autoencoder-deep neural network (SAE-DNN) was developed to estimate phycocyanin (PC) concentration by using in situ reflectance spectra in productive inland water. The estimated PC using the SAE-DNN was in close agreement with the measured PC, with an R-2 of 0.87, root mean square error (RMSE) of 14.45 mu g/L, and relative RMSE of 86.42%. The performance of the SAE-DNN was superior to that of the DNN and band-ratio algorithms. An analysis on the deep spectral features extracted using the SAE yielded the most useful spectral bands, namely 538, 596, and 735 nm, for the retrieval of PC. The estimation accuracy of the SAE-DNNPeaks, using only the aforementioned spectral bands as input variables, was comparable to that of the SAE-DNN, demonstrating that the high-level of abstraction using the SAE facilitated the improvement in feature learning. The application of the SAE-DNNPeak to airborne hyperspectral image data resulted in an acceptable estimation accuracy, despite a bias toward underestimation, potentially arising from uncertainty associated with atmospheric correction, at high PC concentrations. Our results suggest that simple, empirical-based approaches, such as the SAE-DNNPeak have the potential to serve as a rapid assessment tool for the abundance and spatial distribution of cyanobacteria.

关键词： Cyanobacteria Phycocyanin Hyperspectral imaging Deep learning Deep neural networks stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

An Advertising Fraud Detection Method based on Automatic Feature Mining of Time Series Data

International Core Journal of Engineering

引用

International Core Journal of Engineering 2021年第11期7卷 275-282页

作者： Shuo Wang Kang Yang Tongle Wang

With the continuous development of the mobile Internet, the digital advertising marketing market is also showing a trend of vigorous development. The market scale is increasing year by year, and the subsequent advertising fraud problem has gradually become a stubborn disease in the digital advertising marketing market. The traditional rule-based method does not consider the update speed, complexity and randomness of advertising fraud, while the method based on machine learning often ignores the importance of data form and the timing dependence of fraudulent user behavior. In order to solve the above problems, this paper proposes an advertising fraud detection method based on time series data automatic feature mining. First of all, considering the importance of the data form, we constructed the user behavior time series data based on the original data, and then used the improved LSTM-based autoencoder to extract high-level features for the automatic mining of user fraud characteristics, taking into account the timing dependence of fraudulent user behavior It uses multi-scale convolutional neural network to extract local salient features of different scales. In order to avoid information loss, the residual network idea is used to combine high-level features and local salient features as extracted user fraud features. Finally, a fully connected layer is used to merge Use softmax to map user fraud characteristics to whether a user is fraudulent. This article conducts experiments on real advertising traffic data. The experimental results show that the method in this article has effectively improved the F1 value.

关键词： Advertising anti-fraud Automatic Feature Mining stacked autoencoder Multi-CNN

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：