检索结果-内蒙古大学图书馆

Deep relevant representation learning for soft sensing

INFORMATION SCIENCES 2020年 514卷 263-274页

作者： Yan, Xuefeng Wang, Jie Jiang, Qingchao East China Univ Sci & Technol Minist Educ Key Lab Adv Control & Optimizat Chem Proc Shanghai 200237 Peoples R China Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai 200092 Peoples R China

Soft sensing provides a reliable estimation of difficult-to-measure variables and is important for process control, optimization, and monitoring. The extraction of beneficial information from the abundance of available data in modern industrial processes and the development of data-driven soft sensors are becoming areas of increasing interest. In addition, the use of deep neural networks (DNNs) has become a popular data processing and feature extraction technique owing to its superiority in generating high-level abstract representations from massive amounts of data. A deep relevant representation learning (DRRL) approach based on a stacked autoencoder is proposed for the development of an efficient soft sensor. Representations from conventional DNN methods are not extracted for an output prediction, and thus a mutual information analysis is conducted between the representations and the output variable in each layer. Analysis results indicate that irrelevant representations are eliminated during the training of the subsequent layer. Hence, relevant information is highlighted in a layer-by-layer manner. Deep relevant representations are then extracted, and a soft sensor model is established. The results of a numerical example and an industrial oil refining process show that the prediction performance of the proposed DRRL-based soft sensing approach is better than that of other state-of-the-art methods. (C) 2019 Elsevier Inc. All rights reserved.

关键词： Deep neural network stacked autoencoder Deep relevant representation Soft sensing Mutual information

来源：评论

学校读者我要写书评

暂无评论

Classification of high resolution hyperspectral remote sensing data using deep neural networks

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2018年第4期34卷 2273-2285页

作者： Yuksel, Mehmet Emin Basturk, Nurcan Sarikaya Badem, Hasan Caliskan, Abdullah Basturk, Alper Erciyes Univ Engn Fac Dept Biomed Engn Kayseri Turkey Erciyes Univ Fac Aeronaut & Astronaut Dept Aircraft Elect & Elect Kayseri Turkey Erciyes Univ Engn Fac Dept Comp Engn Kayseri Turkey Kahramanmaras Sutcu Imam Univ Engn Fac Dept Comp Engn Kahramanmaras Turkey

The high resolution hyperspectral remote sensing data collected from urban and landscape areas have been extensively studied over the past decades. Recent applications pose an emerging need of analyzing the land cover types based on high resolution hyperspectral remote sensing data originating from remote sensory devices. Toward this goal, we propose a deep neural network (DNN) classifier in this paper. The DNN is constructed by combining a stacked autoencoder with desired numbers of autoencoders and a softmax classifier. Our experimental results based on the hyperspectral remote sensing data demonstrate that the presented DNN classifier can accurately distinguish different land covers including the mixed deciduous broadleaf natural forest and different land covers such as agriculture, roads, buildings, etc. We test the proposed method by using three different benchmark data sets. The proposed method showcases the huge potential of deep neural networks for hyperspectral data analysis.

关键词： Hyperspectral remote sensing deep learning deep neural network softmax classifier stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

The CESAE multiple objection optimization network of the ACO-OFDM VLC system

引用

OPTICS COMMUNICATIONS 2024年 558卷

作者： Hao, Lili Cao, Pan Li, Chengdong Wang, Dongyi Shandong Jianzhu Univ Sch Informat & Elect Engn Intelligent Architecture Lab Shandong Key Lab Inte Jinan Shandong Peoples R China Univ Maryland Fischell Dept Bioengn Bioimaging & Machine Vis Lab College Pk MD 20740 USA Shandong Jianzhu Univ Sch Informat & Elect Engi neering Intelligent Architecture Lab Shandong Key Lab Inte 1000 Fengming Rd Jinan 250101 Shandong Peoples R China

Visible light communication (VLC) is a foreground technology in the sixth generation (6G) communication system. Simultaneously deep learning network is a novel approach to improve the properties of VLC system. In this paper, we put forward an asymmetric clipping optical orthogonal frequency division multiplexing (ACOOFDM) system based on the constant envelope stacked autoencoder (CESAE) network, which is a combination method of phase modulated constant envelope OFDM (CE-OFDM) and the SAE deep learning network. The CESAE network systematically improves the character of the whole system through multiple layers and the loss function. It is shown by the simulation results that tuning the phase modulation index can availably maintain the peak -to -average -power ratio (PAPR) to about 3 dB. In addition, a detailed comparison with traditional method reveals that the presented method fulfils superior BER performance and spectral efficiency.

关键词： Constant envelope stacked autoencoder Peak -to -average -power ratio reduction Visible light communication

来源：评论

学校读者我要写书评

暂无评论

Thrust online fusion estimation of high-flow dual variable cycle engine

引用

AEROSPACE SCIENCE AND TECHNOLOGY 2024年 152卷

作者： Ma, Ansheng Zhou, Xin Zou, Zelong Huang, Jinquan Lu, Feng Nanjing Univ Aeronaut & Astronaut State Key Lab Mech & Control Aerosp Struct Nanjing 210016 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Energy & Power Engn Nanjing 210016 Peoples R China

For the aeroengines, thrust is a crucial performance parameter which is closely related to the mission accessibility. Accurate thrust control is conducive to excavate the potential of the variable cycle engine (VCE) in different operation modes, which meets the requirements of future engine control system. However, the thrust is unmeasured in flight. Besides, the traditional thrust estimation method is difficult to meet the wide-area thrust control requirements due to the strong nonlinearity and large flight envelope for a neoconfiguration VCE of the high-flow triple-bypass, named high-flow dual variable cycle engine (HDVCE). This paper proposes a novel online fusion thrust estimation method mainly under single operation mode for the HDVCE. The problem of individual engine differences is also focused, and the combination of model and data-driven is to generate the thrust estimation with fusion strategy. At first, a multi-combustion chamber coupled dynamic model is established for the HDVCE, and an adaptive network is used for model optimization to improve the model accuracy. On this basis, an EKF-based thrust estimator is built. Secondly, a data-driven thrust estimator is pre-trained by a stacked autoencoder (SAE) and then tuned by back propagation (BP) neural network. Subsequently, the thrust integration is incorporated based on estimation results from the EKF-based and data-driven one using Euclidean distance fusion strategy. Simulation results show that the fusion estimation method proposed in this paper, on the one hand, reduces the effect of model instability on EKF. On the other hand, it ensures the estimation accuracy of SAE-BP far from the training point. The comparisons also reveal that the fusion one produces more than 97% in thrust estimation accuracy and is better than the remaining ones, which is promising for thrust control applications.

关键词： High-flow dual variable cycle engine Thrust fusion estimation Extended Kalman Filter stacked autoencoder Euclidean distance

来源：评论

学校读者我要写书评

暂无评论

Energy-and trust-aware secure routing algorithm for big data classification using MapReduce framework in IoT networks

引用

International Journal of Modeling, Simulation, and Scientific Computing 2021年第2期12卷 80-103页

作者： S.Md.Mujeeb R.Praveen Sam K.Madhavi Department of CSE Jawaharlal Nehru Technological University Anantapur(JNTUA)Ananthapuramu-515002 Andhra PradeshIndia Department of Computer Science and Engineering G.Pulla Reddy Engineering College(Autonomous)Nandyal Road Kurnool 518007Andhra PradeshIndia

Due to the open nature of wireless data transmission,routing and data security pose an important research challenge in the Internet of Things(IoT)-enabled ***,the characteristic features,like constrained resources,heterogeneity,uncontrolled environment,and scalability requirement,make the security issues even more ***,an effective and secure routing protocol named modified Energy Harvesting Trust-aware Routing Algorithm(mod-EHTARA)is proposed to increase the energy efficiency and the lifespan of the *** proposed mod-EHTARA is designed by adopting the Link Lifetime(LLT)model with the traditional *** optimal secure routing path is effectively selected by the proposed mod-EHTARA using the cost metric,which considers the factors like delay,LLT,energy,and *** big data classification process is carried out at the Base Station(BS)using the MapReduce ***,the big data classification is progressed using a stacked autoencoder,which is trained by the Adaptive E-Bat *** Adaptive E-Bat algorithm is developed by integrating the adaptive concept with the Bat Algorithm(BA)and Exponential Weighted Moving Average(EWMA).The proposed mod-EHTARA showed better performance by obtaining a maximal energy of 0.9855.

关键词： stacked autoencoder big data classification Internet of Things secure routing energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia

引用

NEUROIMAGE 2016年第PT A期124卷 127-146页

作者： Kim, Junghoe Calhoun, Vince D. Shim, Eunsoo Lee, Jong-Hwan Korea Univ Dept Brain & Cognit Engn Seoul 136713 South Korea Univ New Mexico Dept Elect & Comp Engn Albuquerque NM 87131 USA Samsung Elect Samsung Adv Inst Technol Suwon South Korea Mind Res Network Albuquerque NM USA LBERI Albuquerque NM USA

Functional connectivity (FC) patterns obtained from resting-state functional magnetic resonance imaging data are commonly employed to study neuropsychiatric conditions by using pattern classifiers such as the support vector machine (SVM). Meanwhile, a deep neural network (DNN) with multiple hidden layers has shown its ability to systematically extract lower-to-higher level information of image and speech data from lower-to-higher hidden layers, markedly enhancing classification accuracy. The objective of this study was to adopt the DNN for whole-brain resting-state FC pattern classification of schizophrenia (SZ) patients vs. healthy controls (HCs) and identification of aberrant FC patterns associated with SZ. We hypothesized that the lower-to-higher level features learned via the DNN would significantly enhance the classification accuracy, and proposed an adaptive learning algorithm to explicitly control the weight sparsity in each hidden layer via L1-norm regularization. Furthermore, the weights were initialized via stacked autoencoder based pre-training to further improve the classification performance. Classification accuracy was systematically evaluated as a function of (1) the number of hidden layers/nodes, (2) the use of L1-norm regularization, (3) the use of the pre-training, (4) the use of frame wise displacement (FD) removal, and (5) the use of anatomical/functional parcellation. Using FC patterns from anatomically parcellated regions without FD removal, an error rate of 14.2% was achieved by employing three hidden layers and 50 hidden nodes with both L1-norm regularization and pre-training, which was substantially lower than the error rate from the SVM (22.3%). Moreover, the trained DNN weights (i.e., the learned features) were found to represent the hierarchical organization of aberrant FC patterns in SZ compared with HC. Specifically, pairs of nodes extracted from the lower hidden layer represented sparse FC patterns implicated in SZ, which was quantifie

关键词： Deep learning Functional connectivity Resting-state functional magnetic resonance imaging Schizophrenia Sparsity stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Data-driven inverse modeling with a pre-trained neural network at heterogeneous channel reservoirs

引用

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING 2018年 170卷 785-796页

作者： Ahn, Seongin Park, Changhyup Kim, Jaejun Kang, Joe M. Samsung Heavy Ind Dept Energy Plant Researching Seongnam 13486 Gyeonggi South Korea Kangwon Natl Univ Dept Energy & Resources Engn Chunchon 24341 Kangwon South Korea Seoul Natl Univ Dept Energy Syst Engn Seoul 08826 South Korea

This paper develops a reliable and efficient data-integration method, based on artificial neural networks (ANN) incorporated with a stacked autoencoder (SAE) in a deep neural network's framework. To handle scale-different static and dynamic data of heterogeneous channel reservoirs, the workflow suggests an unsupervised pretraining process coupled with ANN-based inverse modeling. The performances of the proposed neural network, i.e. the training efficiency, the predictability of future production rates and the computing time, are compared to those with an optimal ANN and the impact of hidden neurons are discussed. The pre-trained neural network demonstrates a reliable estimation of reservoir properties with the spatial characteristics of a true channel reservoir while the ANN fails with respect to the spatial heterogeneity. The pre-trained neural network decreases the mean absolute error of future oil production rates up to 9.1% which is less than 25% of the comparison case's level, i.e. the optimal ANN model. Its efficiency is validated by a computing time 14 times faster than that of the optimal ANN workflow. The pre-trained neural network evaluates the spatial characteristics of reservoir properties and facies models in a reasonable manner and is thus able to predict the water production rates and also the breakthrough time accurately. This pre-trained neural network manifests its applicability with robustness as an efficient method to integrate static and dynamic data.

关键词： stacked autoencoder Deep neural network Pretraining Inverse model Data integration

来源：评论

学校读者我要写书评

暂无评论

Lightweight 3D Dense autoencoder Network for Hyperspectral Remote Sensing Image Classification

引用

SENSORS 2023年第20期23卷 8635-8635页

作者： Bai, Yang Sun, Xiyan Ji, Yuanfa Fu, Wentao Duan, Xiaoyu Guilin Univ Elect Technol Informat & Commun Schnool Guilin 541004 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Precis Nav Technol & Applicat Guilin 541004 Peoples R China Natl & Local Joint Engn Res Ctr Satellite Nav Posi Guilin 541004 Peoples R China

The lack of labeled training samples restricts the improvement of Hyperspectral Remote Sensing Image (HRSI) classification accuracy based on deep learning methods. In order to improve the HRSI classification accuracy when there are few training samples, a Lightweight 3D Dense autoencoder Network (L3DDAN) is proposed. Structurally, the L3DDAN is designed as a stacked autoencoder which consists of an encoder and a decoder. The encoder is a hybrid combination of 3D convolutional operations and 3D dense block for extracting deep features from raw data. The decoder composed of 3D deconvolution operations is designed to reconstruct data. The L3DDAN is trained by unsupervised learning without labeled samples and supervised learning with a small number of labeled samples, successively. The network composed of the fine-tuned encoder and trained classifier is used for classification tasks. The extensive comparative experiments on three benchmark HRSI datasets demonstrate that the proposed framework with fewer trainable parameters can maintain superior performance to the other eight state-of-the-art algorithms when there are only a few training samples. The proposed L3DDAN can be applied to HRSI classification tasks, such as vegetation classification. Future work mainly focuses on training time reduction and applications on more real-world datasets.

关键词： hyperspectral remote sensing image classification deep learning dense connection stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

LaMeta: An efficient locality aware metadata management technique for an ultra-large distributed storage system

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2022年第10期34卷 8323-8335页

作者： Singh, Harcharan Jit Bawa, Seema Thapar Inst Engn & Technol Deemed Univ Dept Comp Sci & Engn Patiala 147004 Punjab India

The locality of metadata is a critical parameter of data storage and retrieval performance for an ultra -large distributed storage system. The data of an ultra-large distributed storage system is accessed through its distributed metadata servers (MDSs). The distributed MDSs store and cache partial metadata for scalability and performance. The MDSs are connected through varied latencies multipath network connections of using various metadata distribution techniques. The locality of MDS in the metadata dis-tribution techniques improves the metadata query routing and enhances the performance of the dis-tributed storage system. Motivated by this insight, this work introduces an intelligent locality-aware metadata management technique based on recommendation system that exploits MDS path ratings in a globally distributed ultra-large storage system and proposes a novel locality-aware metadata query routing algorithm. The proposed metadata server locality aware employs collaborative filtering with stacked autoencoder to address the sparsity of the path rating matrix and its overfitting issue. The exten-sive experiments on real datasets show that the proposed metadata server locality aware technique enhances the locality of metadata operations and improves aggregate operations throughput by 12% to 21% of contemporary distributed metadata management techniques in ultra-large distributed storage systems. (c) 2022 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Deep learning stacked autoencoder Machine learning High performance computing Distributed metadata management Locality Storage system

来源：评论

学校读者我要写书评

暂无评论

UCAV situation assessment method based on C-LSHADE-Means and SAE-LVQ

引用

Journal of Systems Engineering and Electronics 2023年第5期34卷 1235-1251页

作者： XIE Lei TANG Shangqin WEI Zhenglei XUAN Yongbo WANG Xiaofei Institute of Aeronautics Engineering Air Force Engineering UniversityXi’an 710038China China Aerodynamics Research&Development Center Mianyang 621000China Blue Sky Innovation Center for Frontier Science Beijing 100000China

The unmanned combat aerial vehicle(UCAV)is a research hot issue in the world,and the situation assessment is an important part of *** overcome shortcomings of the existing situation assessment methods,such as low accuracy and strong dependence on prior knowledge,a datadriven situation assessment method is *** clustering and classification are combined,the former is used to mine situational knowledge,and the latter is used to realize rapid *** evaluation factor and distance evaluation factor are proposed to transform multi-dimensional air combat information into two-dimensional features.A convolution success-history based adaptive differential evolution with linear population size reduc-tion-means(C-LSHADE-Means)algorithm is *** convolutional pooling layer is used to compress the size of data and preserve the distribution *** LSHADE algorithm is used to initialize the center of the mean clustering,which over-comes the defect of initialization *** experi-ment with the seven clustering algorithms is done on the UCI data set,through four clustering indexes,and it proves that the method proposed in this paper has better clustering performance.A situation assessment model based on stacked autoen-coder and learning vector quantization(SAE-LVQ)network is constructed,and it uses SAE to reconstruct air combat data fea-tures,and uses the self-competition layer of the LVQ to achieve efficient *** with the five kinds of assess-ments models,the SAE-LVQ model has the highest ***,three kinds of confrontation processes from air combat maneuvering instrumentation(ACMI)are selected,and the model in this paper is used for situation *** assessment results are in line with the actual situation.

关键词： unmanned combat aerial vehicle(UCAV) situation assessment clustering K-means stacked autoencoder learn-ing vector quantization

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：