检索结果-内蒙古大学图书馆

Deep learning for pixel-level image fusion: Recent advances and future prospects

INFORMATION FUSION 2018年 42卷 158-173页

作者： Liu, Yu Chen, Xun Wang, Zengfu Wang, Z. Jane Ward, Rabab K. Wang, Xuesong Hefei Univ Technol Dept Biomed Engn Hefei 230009 Anhui Peoples R China Univ Sci & Technol China Dept Elect Sci & Technol Hefei 230026 Anhui Peoples R China Univ Sci & Technol China Dept Automat Hefei 230026 Anhui Peoples R China Univ British Columbia Dept Elect & Comp Engn Vancouver BC Canada China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Peoples R China

By integrating the information contained in multiple images of the same scene into one composite image, pixel-level image fusion is recognized as having high significance in a variety of fields including medical imaging, digital photography, remote sensing, video surveillance, etc. In recent years, deep learning (DL) has achieved great success in a number of computer vision and image processing problems. The application of DL techniques in the field of pixel-level image fusion has also emerged as an active topic in the last three years. This survey paper presents a systematic review of the DL-based pixel-level image fusion literature. Specifically, we first summarize the main difficulties that exist in conventional image fusion research and discuss the advantages that DL can offer to address each of these problems. Then, the recent achievements in DL-based image fusion are reviewed in detail. More than a dozen recently proposed image fusion methods based on DL techniques including convolutional neural networks (CNNs), convolutional sparse representation (CSR) and stacked autoencoders (SAEs) are introduced. At last, by summarizing the existing DL-based image fusion methods into several generic frameworks and presenting a potential DL-based framework for developing objective evaluation metrics, we put forward some prospects for the future study on this topic. The key issues and challenges that exist in each framework are discussed.

关键词： Image fusion Deep learning Convolutional neural network Convolutional sparse representation stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Short-term traffic flow prediction based on SAE and its parallel training

引用

APPLIED INTELLIGENCE 2024年第4期54卷 3650-3664页

作者： Tan, Xiaoxue Zhou, Yonghua Zhao, Lu Mei, Yiduo Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China China Mobile Hangzhou Informat Technol Co Ltd Hangzhou 310006 Peoples R China Zhongguancun Smart City Co Ltd Beijing 100071 Peoples R China

The alleviation of traffic congestion relies on efficient traffic control and traffic guidance, which are based on real-time short-term traffic flow prediction. In this paper, the stacked autoencoder (SAE) deep learning model with powerful feature learning capability is selected to predict the traffic flow on road sections. The process of training SAE includes the pre-training phase and the fine-tuning phase, which mainly apply the BP algorithm. However, the process of training SAE is time-consuming and cannot meet the real-time performance of modern application systems. This paper proposes a parallel training strategy for the SAE prediction model based on data parallel mode. The gradient solution process in our algorithm satisfies the conditions of parallel computing, so the training process can be designed in a parallel manner. The original dataset is distributed to some computing nodes, which are work nodes. The work node is responsible for gradient calculation using the local data. The task of the sole master node is to synthesize the gradient calculation results and then broadcast the updated gradient to each work node. The simulation results show that the SAE-based prediction model achieves better results than the traditional model, and the parallel algorithm reduces the running time of training processes.

关键词： Traffic flow prediction stacked autoencoder Parallel computing Data parallel

来源：评论

学校读者我要写书评

暂无评论

A study on cross-project fault prediction through resampling and feature reduction along with source projects selection

引用

AUTOMATED SOFTWARE ENGINEERING 2024年第2期31卷 67页

作者： Manchala, Pravali Bisi, Manjubala NIT Warangal Comp Sci & Engn Hanamkonda 506004 India

Software Fault Prediction is an efficient strategy to improve the quality of software systems. In reality, there won't be adequate software fault data for a recently established project where the Cross-Project Fault Prediction (CPFP) model plays an important role. CPFP model utilizes other finished projects data to predict faults in ongoing projects. Existing CPFP methods concentrate on discrepancies in distribution between projects without exploring relevant source projects selection combined with distribution gap minimizing methods. Additionally, performing imbalance learning and feature extraction in software projects only balances the data and reduces features by eliminating redundant and unrelated features. This paper proposes a novel SRES method called Similarity and applicability based source projects selection, REsampling, and stacked autoencoder (SRES) model. To analyze the performance of relevant source projects over CPFP, we proposed a new similarity and applicability based source projects selection method to automatically select sources for the target project. In addition, we introduced a new resampling method that balances source project data by generating data related to the target project, eliminating unrelated data, and reducing the distribution gap. Then, SRES uses the stacked autoencoder to extract informative intermediate feature data to further improve the prediction accuracy of the CPFP. SRES performs comparable to or superior to the conventional CPFP model on six different performance indicators over 24 projects by effectively addressing the issues of CPFP. In conclusion, we can ensure that resampling and feature reduction techniques, along with source projects selection can improve cross-project prediction performance.

关键词： Cross-project fault prediction Source projects selection Class imbalance Feature reduction stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Window S-Transform Aided Deep Neural Network Model-Based Power Quality Monitoring Framework in Electrical Power System

引用

IEEE SENSORS JOURNAL 2021年第12期21卷 13695-13703页

作者： Nandi, Kiron Das, Arup Kumar Ghosh, Riddhi Dalai, Sovan Chatterjee, Biswendu Jadavpur Univ Dept Elect Engn Kolkata 700032 India Univ Bologna Dept Elect Elect & Informat Engn I-40126 Bologna Italy

With the fast development of power grid the usage of electrical equipments is increased which led to importance of power quality disturbance sensing for reliable and smooth operation. In this paper, a deep neural network has been designed using stacked autoencoder (SAE) for deep feature extraction from time-frequency spectrum of single and combined PQ disturbances in electrical power system network. For this purpose, synthetic PQ signals are analyzed in time-frequency domain through hyperbolic window stockwell transform (HWST). Thereafter, PQ signal converted HWST time-frequency matrix has been grouped into time-frequency blocks and subsequently fed as input to 3-layer stacked autoencoder model (SAE) for deep feature learning. Finally, the extracted deep features are classified through several machine learning classifier. The results indicate that proposed framework using XGboost classifier can classify 18 different single and combined PQ event with a 99.86% accuracy. The proposed framework also yields satisfactory outcome with real life PQ data. Therefore, proposed framework can be implemented for Power quality monitoring in electrical power system.

关键词： Feature extraction Transforms Time-frequency analysis Sensors Transient analysis Reliability Power system reliability Power quality detection hyperbolic window s-transform deep neural network stacked autoencoder classification

来源：评论

学校读者我要写书评

暂无评论

Palmvein Recognition Using Block-Based WLD Histogram of Gabor Feature Maps and Deep Neural Network With Bayesian Optimization

引用

IEEE ACCESS 2021年 9卷 97337-97353页

作者： El-Ghandour, Mohammed Obayya, Marwa Ismael Yousef, Bedir Areed, Nihal Fayez Mansoura Univ Coll Engn Dept Elect & Commun Engn Mansoura 35516 Egypt Princess Nourah Bint Abdulrahman Univ Coll Engn Dept Biomed Engn Riyadh 84428 Saudi Arabia Kafrelsheikh Univ Fac Engn Dept Elect Engn Kafr Al Sheikh 33516 Egypt Onaizah Coll Fac Engn & Informat Technol Dept Elect Engn Al Qassim 51911 Saudi Arabia

The demand on devices and systems empowered by biometric verification and identification mechanisms has been increasing in recent years as they have become a significant part of our lives. Palm vein biometric is an emerging technology that has drawn considerable attention from researchers and scientists over the last decade. In the present work, a novel feature extraction methodology named GPWLD combing the Gabor features with positional Weber's local descriptor (PWLD) features is proposed. WLD is a highly representative micro-pattern descriptor that performs well against noise and illumination changes in images. However, it lacks the ability to capture the vein pattern features at different orientations. Moreover, its descriptor packs the local information content into a single histogram that does not take the spatial locality of micro-patterns into consideration. To solve these two issues, firstly, the palm vein image is passed through Gabor filter with different orientations to capture the salient rotational features found in the output feature maps. Secondly, the spatiality is achieved by uniformly dividing each feature map into several blocks. Next, Weber's law feature descriptor (WLD) histogram is computed for each block in every feature map. Finally, these histograms are concatenated to compose the final feature vector. Due to the high dimensionality of the final feature vector, Principal component analysis (PCA) algorithm is utilized for feature size reduction. In the classification stage, a deep neural network (DNN) comprising an optimized stacked autoencoder (SAE) with Bayesian optimization and a softmax layer is used. Optimization of the SAE is carried out by using Bayesian optimization to find the optimal SAE structure and the options of the training algorithm. The Experimental results verify the discriminative power of the extracted features and the accuracy of the proposed DNN. For both Identification and verification experiments, the proposed method a

关键词： Veins Feature extraction Biometrics (access control) Optimization Histograms Gabor filters Bayes methods WLD descriptor Gabor filter deep neural network stacked autoencoder Bayesian optimization

来源：评论

学校读者我要写书评

暂无评论

Dual autoencoders features for imbalance classification problem

引用

PATTERN RECOGNITION 2016年 60卷 875-889页

作者： Ng, Wing W. Y. Zeng, Guangjun Zhang, Jiangjun Yeung, Daniel S. Pedrycz, Witold South China Univ Technol Sch Comp Sci & Engn Machine Learning & Cybernet Res Ctr Guangzhou 510006 Guangdong Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 2M7 Canada King Abdulaziz Univ Dept Elect & Comp Engn Fac Engn Jeddah 21589 Saudi Arabia Polish Acad Sci Syst Res Inst Warsaw Poland

Many classification problems encountered in real-world applications exhibit a profile of imbalanced data. Current methods depend on data resampling. In fact, if the feature set provides a clear decision boundary, resampling may not be needed to solve the imbalanced classification problem. Therefore, this work proposes a feature learning method based on the autoencoder to learn a set of features with better classification capabilities of the minority and the majority classes to address the imbalanced classification problems. Two sets of features are learned by two stacked autoencoders with different activation functions to capture different characteristics of the data and they are combined to form the Dual Autoencoding Features. Samples are then classified in the new feature space learned in this manner instead of the original input space. Experimental results show that the proposed method outperforms current resampling-based methods with statistical significance for imbalanced pattern classification problems. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Imbalanced Classification Feature Learning stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Efficient adaptive deep gradient RBF network for multi-output nonlinear and nonstationary industrial processes

引用

JOURNAL OF PROCESS CONTROL 2023年第1期126卷 1-11页

作者： Liu, Tong Chen, Sheng Yang, Po Zhu, Yunpeng Harris, Chris J. Imperial Coll London Dept Chem Engn London SW7 2AZ England Univ Southampton Sch Elect & Comp Sci Southampton SO17 1BJ England Ocean Univ China Fac Informat Sci & Engn Qingdao Peoples R China Univ Sheffield Dept Comp Sci Sheffield S1 4DP England Queen Mary Univ London Sch Engn & Mat Sci London E1 4NS England

Due to the complexity of process operation, industrial process data are often nonlinear and non -stationary, high dimensional, and multivariate with complex interactions between multiple outputs. To address all these issues, this paper proposes a novel industrial predictive model that integrates deep feature extraction and fast online adaptation, and can effectively deal with multiple process outputs. Specifically, a multi-output gradient radial basis function network (MGRBF) with excellent predictive capacity of nonstationary data is first used to provide preliminary prediction of target outputs. This prior quality information is combined with the original process input for deep feature learning and dimensional reduction. Through layer-wise feature extraction by the stacked autoencoder (SAE), deep quality-enhanced features can be obtained, which is further fed into a MGRBF tracker for online prediction. In order to timely capture the fast-changing process characteristics, the first two modules, namely, preliminary MGRBF predictor and SAE feature extractor are frozen after training, while the structure and parameters of the MGRBF tracker are updated online in an efficient manner. Two industrial case studies demonstrate that the proposed adaptive deep MGRBF network outperforms existing state-of-the-art online modeling approaches as well as deep learning models, in terms of both multi-output modeling accuracy and online computational complexity.(c) 2023 Elsevier Ltd. All rights reserved.

关键词： Multivariate nonlinear and nonstationary industrial process Multi-output gradient radial basis function network stacked autoencoder Quality-enhanced feature extraction Online adaptive tracking

来源：评论

学校读者我要写书评

暂无评论

Probabilistic bearing fault diagnosis using Gaussian process with tailored feature extraction

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2022年第3-4期119卷 2059-2076页

作者： Liang, Mingxuan Zhou, Kai China Jiliang Univ Coll Mech & Elect Engn Hangzhou 310018 Peoples R China Michigan Technol Univ Dept Mech Engn Engn Mech Houghton MI 49931 USA

Deep learning methods recently have gained growing interests and are extensively applied in the data-driven bearing fault diagnosis. However, current deep learning methods perform the bearing fault diagnosis in the form of deterministic classification, which overlook the uncertainties that inevitably exist in actual practice. To tackle this issue, in this research, we develop a probabilistic fault diagnosis framework that can account for the uncertainty effect in prediction, which bears practical significance. This framework uses the Gaussian process classifier (GPC) as the mainstay, which fundamentally is built upon the Bayesian inference. To establish the high-fidelity GPC, the tailored feature extraction method can be adaptively determined through the cross validation-based grid search upon a prespecified method pool consisting of various kernel principal component analysis (KPCA) methods and stacked autoencoder. This adaptive strategy can ensure the adequate GPC model training to accurately characterize the complex nonlinear relations between the data features and respective faults. Systematic case studies using the publicly accessible experimental rolling bearing dataset, i.e., CWRU bearing dataset are carried out to validate this new framework. The results clearly illustrate the unique capability of this framework in handling uncertainties. It is also found that this framework outperforms other well-established machine learning and deep learning models in terms of accuracy and robustness. Moreover, the sensor fusion that combines the spatial vibration measurements appears to be an effective technique to further enhance the fault diagnosis performance. By fully leveraging the probabilistic feature of the framework, the future research endeavor, such as the extended fault diagnosis using limited fault labels will be facilitated.

关键词： Rolling bearings Probabilistic fault diagnosis Gaussian process classifier (GPC) Kernel principal component analysis (KPCA) stacked autoencoder Sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Deep packet: a novel approach for encrypted traffic classification using deep learning

引用

SOFT COMPUTING 2020年第3期24卷 1999-2012页

作者： Lotfollahi, Mohammad Siavoshani, Mahdi Jafari Zade, Ramin Shirali Hossein Saberian, Mohammdsadegh Sharif Univ Technol Tehran Iran

Network traffic classification has become more important with the rapid growth of Internet and online applications. Numerous studies have been done on this topic which have led to many different approaches. Most of these approaches use predefined features extracted by an expert in order to classify network traffic. In contrast, in this study, we propose a deep learning-based approach which integrates both feature extraction and classification phases into one system. Our proposed scheme, called "Deep Packet," can handle both traffic characterization in which the network traffic is categorized into major classes (e.g., FTP and P2P) and application identification in which identifying end-user applications (e.g., BitTorrent and Skype) is desired. Contrary to most of the current methods, Deep Packet can identify encrypted traffic and also distinguishes between VPN and non-VPN network traffic. The Deep Packet framework employs two deep neural network structures, namely stacked autoencoder (SAE) and convolution neural network (CNN) in order to classify network traffic. Our experiments show that the best result is achieved when Deep Packet uses CNN as its classification model where it achieves recall of 0.98 in application identification task and 0.94 in traffic categorization task. To the best of our knowledge, Deep Packet outperforms all of the proposed classification methods on UNB ISCX VPN-nonVPN dataset.

关键词： Network traffic classification Application identification Traffic characterization Deep learning Convolutional neural networks stacked autoencoder Deep Packet

来源：评论

学校读者我要写书评

暂无评论

Neuron-Compressed Deep Neural Network and Its Application in Industrial Anomaly Detection

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2023年第7期19卷 7914-7924页

作者： Wang, Kai Yan, Caoyin Mo, Yanfang Yuan, Xiaofeng Wang, Yalin Yang, Chunhua Cent South Univ Sch Automat Changsha 410083 Peoples R China City Univ Hong Kong Hong Kong Inst Data Sci Kowloon Hong Kong 999077 Peoples R China

Data modeling and online monitoring are two critical stages for data-driven anomaly detection. Regarding data modeling, deep neural networks (DNNs) can learn good decision boundaries to separate the anomaly and normal regions, due to their flexible model structures and excellent fitting ability. However, DNNs, using nonlinear activations with specific boundaries, may indirectly cause a limited anomaly detection margin, especially when there are samples far from centroids. Moreover, an anomaly detection model with a narrow detection margin is deemed insensitive to general faults. An anomaly detection model with a tight detection margin will suffer a severe performance degradation. To mitigate the intrinsic drawbacks of DNNs, we develop a new regularizer based on the maximum likelihood of complete data (i.e., observations and latent variables). The regularizer is neuronwise and mathematically acts as compressing neurons, dragging the marginal points into the centroids. Combining the regularizer with the encoding-decoding structure networks, we perform an industrial case study to verify the superiority of the proposed method.

关键词： Anomaly detection deep neural network (DNN) regularization stacked autoencoder

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：