检索结果-内蒙古大学图书馆

A distributed parallel Algorithm Based on Low-Rank and Sparse Representation for Anomaly Detection in Hyperspectral images

引用

SENSORS 2018年第11期18卷 3627-3627页

作者： Zhang, Yi Wu, Zebin Sun, Jin Zhang, Yan Zhu, Yaoqin Liu, Jun Zang, Qitao Plaza, Antonio Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China Lianyungang E Port Informat Dev Co Ltd Lianyungang 222042 Peoples R China Univ Extremadura Dept Technol Computers & Commun Hyperspectral Comp Lab Caceres 10003 Spain

Anomaly detection aims to separate anomalous pixels from the background, and has become an important application of remotely sensed hyperspectral image processing. Anomaly detection methods based on low-rank and sparse representation (LRASR) can accurately detect anomalous pixels. However, with the significant volume increase of hyperspectral image repositories, such techniques consume a significant amount of time (mainly due to the massive amount of matrix computations involved). In this paper, we propose a novel distributed parallel algorithm (DPA) by redesigning key operators of LRASR in terms of MapReduce model to accelerate LRASR on cloud computing architectures. Independent computation operators are explored and executed in parallel on Spark. Specifically, we reconstitute the hyperspectral images in an appropriate format for efficient DPA processing, design the optimized storage strategy, and develop a pre-merge mechanism to reduce data transmission. Besides, a repartitioning policy is also proposed to improve DPA's efficiency. Our experimental results demonstrate that the newly developed DPA achieves very high speedups when accelerating LRASR, in addition to maintaining similar accuracies. Moreover, our proposed DPA is shown to be scalable with the number of computing nodes and capable of processing big hyperspectral images involving massive amounts of data.

关键词： hyperspectral images anomaly detection distributed and parallel computing apache spark clouds

来源：评论

学校读者我要写书评

暂无评论

Investigation of image processing Techniques for Glaucoma Detection in Human Eyes

Investigation of Image Processing Techniques for Glaucoma De...

引用

International Conference on parallel distributed and Grid Computing (PDGC)

作者： Shilpa Kaushal Sunil Datt Sharma Shruti Jain Dept. of Electronics & Comm. Engg. Jaypee University of Information Technology Himachal Pradesh India

ISBN: (纸本)9781728106489

Glaucoma is a disease associated with retina of eye. Presently, millions of human being is suffering from this disease. Early detection of these diseases can save the people from blindness. Therefore, various methods have been developed for its detection. In this paper, we have studied the reported methods and summarized their performance in terms of accuracy of detection.

关键词： Feature extraction Databases Optical imaging Support vector machines Transforms Retina Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning-based Depth Estimation aided Visual SLAM Approach

arXiv

引用

arXiv 2019年

作者： Geng, Mingyang Shang, Suning Ding, Bo Wang, Huaimin Zhang, Pengfei Zhang, Lei National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology China National Key Laboratory of Integrated Automation of Process Industry Northeastern University China

Existing visual-based SLAM systems mainly utilize the three-dimensional environmental depth information from RGB-D cameras to complete the robotic synchronization localization and map construction task. However, the RGB-D camera maintains a limited range for working and is hard to accurately measure the depth information in a far distance. Besides, the RGB-D camera will easily be influenced by strong lighting and other external factors, which will lead to a poor accuracy on the acquired environmental depth information. Recently, deep learning technologies have achieved great success in the visual SLAM area, which can directly learn high-level features from the visual inputs and improve the estimation accuracy of the depth information. Therefore, deep learning technologies maintain the potential to extend the source of the depth information and improve the performance of the SLAM system. However, the existing deep learning-based methods are mainly supervised and require a large amount of ground-truth depth data, which is hard to acquire because of the realistic constraints. In this paper, we first present an unsupervised learning framework, which not only uses image reconstruction for supervising but also exploits the pose estimation method to enhance the supervised signal and add training constraints for the task of monocular depth and camera motion estimation. Furthermore, we successfully exploit our unsupervised learning framework to assist the traditional ORB-SLAM system when the initialization module of ORB-SLAM method could not match enough features. Qualitative and quantitative experiments have shown that our unsupervised learning framework performs the depth estimation task comparably to the supervised methods and outperforms the previous state-of-the-art approach by 13.5% on KITTI dataset. Besides, our unsupervised learning framework could significantly accelerate the initialization process of ORB-SLAM system and effectively improve the accuracy on environme

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A (multi) GPU iterative reconstruction algorithm based on Hessian penalty term for sparse MRI

引用

INTERNATIONAL JOURNAL OF GRID AND UTILITY COMPUTING 2018年第2期9卷 139-156页

作者： Cuomo, Salvatore De Michele, Pasquale Piccialli, Francesco Univ Naples Federico II Dept Math & Applicat Naples Italy Univ Naples Federico II Dept Elect Engn & Informat Technol Naples Italy

A recent trend in the Magnetic Resonance Imaging (MRI) research field is to design and adopt machines that are able to acquire undersampled clinical data, reducing the time for which the patient is lying in the body scanner. Unfortunately, the missing information in these undersampled acquired datasets leads to artefacts in the reconstructed image;therefore, computationally expensive image reconstruction techniques are required. In this paper, we present an iterative regularisation strategy with a second-order derivative penalty term for the reconstruction of undersampled image datasets. Moreover, we compare this approach with other constrained minimisation methods, resulting in improved accuracy. Finally, an implementation on a massively parallel architecture environment, a multi Graphics processing Unit (GPU) system, of the proposed iterative algorithm is presented. The resulting performance gives clinically-feasible reconstruction run times, speed-up and improvements in terms of reconstruction accuracy of the undersampled MRI images.

关键词： compressed sensing MRI iterative reconstruction numerical regularisation graphics processing unit parallel and scientific computing

来源：评论

学校读者我要写书评

暂无评论

distributed Particle Metropolis-Hastings Schemes

Distributed Particle Metropolis-Hastings Schemes

引用

IEEE/SP Workshop on Statistical Signal processing (SSP)

作者： Luca Martino Víctor Elvira Gustau Camps-Valls Image Processing Laboratory Universitat de València Spain IMT Lille Douai CRISTAL (UMR 9189) Villeneuve d’Ascq France

We introduce a Particle Metropolis-Hastings algorithm driven by several parallel particle filters. The communication with the central node requires the transmission of only a set of weighted samples, one per filter. Furthermore, the marginal version of the previous scheme, called distributed Particle Marginal Metropolis-Hastings (DPMMH) method, is also presented. DPMMH can be used for making inference on both a dynamical and static variable of interest. The ergodicity is guaranteed, and numerical simulations show the advantages of the novel schemes.

关键词： Proposals Signal processing algorithms Probability density function State-space methods Signal processing Monte Carlo methods Conferences

来源：评论

学校读者我要写书评

暂无评论

Identifying Interpretable Link Communities with User Interactions and Messages in Social Networks

Identifying Interpretable Link Communities with User Interac...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Wei Li Meng Qin Kai Lei ICNLAB School of Electronics and Computer Engineering (SECE) Peking University Shenzhen China PCL Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Community detection is a fundamental step in social network analysis. In this study, we focus on the hybrid identification of overlapping communities with network topology (e.g., user interaction) and edge-induced content (e.g., user messages). Conventional hybrid methods tend to combine topology and node-induced content to explore disjoint communities, but fail to integrate edge-induced content and to derive overlapping communities. Moreover, although several semantic community detection approaches have been developed, which can generate the semantic description for each community besides the partition result, they can only incorporate the word-level content to derived coarse-grained descriptions. We propose a novel Semantic Link Community Detection (SLCD) model based on non-negative matrix factorization (NMF). It adopts the perspective of link communities to integrate topology and edge-induced content, where the partitioned link communities can be further transformed into an overlapping node-induced membership. Moreover, SLCD incorporates both the word-level and sentence-level content while considering the diversity of user messages. Hence, it can also derive strongly interpretable and multi-view community descriptions simultaneously when community partition is finished. SLCD's superior performance and powerful application ability over other state-of-the-art competitors are further demonstrated in our experiments on a series of real social networks.

关键词： Semantics Network topology Topology Social networking (online) image edge detection Task analysis Cultural differences

来源：评论

学校读者我要写书评

暂无评论

Environmental Sound Classification Based on Multi-temporal Resolution Convolutional Neural Network Combining with Multi-level Features 19th

Environmental Sound Classification Based on Multi-temporal R...

引用

19th Pacific-Rim Conference on Multimedia (PCM)

作者： Zhu, Boqing Xu, Kele Wang, Dezhi Zhang, Lilun Li, Bo Peng, Yuxing Natl Univ Def Technol Sci & Technol Parallel & Distributed Lab Changsha Hunan Peoples R China Natl Univ Def Technol Coll Informat Commun Wuhan Hubei Peoples R China Natl Univ Def Technol Coll Meteorol & Oceanog Changsha Hunan Peoples R China Beijing Univ Posts & Telecommun Beijing Peoples R China

ISBN: (纸本)9783030007676;9783030007669

Motivated by the fact that characteristics of different sound classes are highly diverse in different temporal scales and hierarchical levels, a novel deep convolutional neural network (CNN) architecture is proposed for the environmental sound classification task. This network architecture takes raw waveforms as input, and a set of separated parallel CNNs are utilized with different convolutional filter sizes and strides, in order to learn feature representations with multi-temporal resolutions. On the other hand, the proposed architecture also aggregates hierarchical features from multi-level CNN layers for classification using direct connections between convolutional layers, which is beyond the typical single-level CNN features employed by the majority of previous studies. This network architecture also improves the flow of information and avoids vanishing gradient problem. The combination of multi-level features boosts the classification performance significantly. Comparative experiments are conducted on two datasets: the environmental sound classification dataset (ESC-50), and DCASE 2017 audio scene classification dataset. Results demonstrate that the proposed method is highly effective in the classification tasks by employing multi-temporal resolution and multi-level features, and it outperforms the previous methods which only account for single-level features.

关键词： Audio scene classification Multi-temporal resolution Multi-level Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Frame Segmentation Networks for Temporal Action Localization 19th

Frame Segmentation Networks for Temporal Action Localization

引用

19th Pacific-Rim Conference on Multimedia (PCM)

作者： Yang, Ke Qiao, Peng Wang, Qiang Li, Shijie Niu, Xin Li, Dongsheng Dou, Yong Natl Univ Def Technol Natl Lab Parallel & Distributed Proc Coll Comp Changsha Hunan Peoples R China

ISBN: (纸本)9783030007676;9783030007669

Temporal action localization is an important task of computer vision. Though many methods have been proposed, it still remains an open question how to predict the temporal location of action segments precisely. Most state-of-the-art works train action classifiers on video segments pre-determined by action proposal. However, recent work found that a desirable model should move beyond segment-level and make dense predictions at a fine granularity in time to determine precise temporal boundaries. In this paper, we propose a Frame Segmentation Network (FSN) that places a temporal CNN on top of the 2D spatial CNNs. Spatial CNNs are responsible for abstracting semantics in spatial dimension while temporal CNN is responsible for introducing temporal context information and performing dense predictions. The proposed FSN can make dense predictions at frame-level for a video clip using both spatial and temporal context information. FSN is trained in an end-to-end manner, so the model can be optimized in spatial and temporal domain jointly. Experiment results on public dataset show that FSN achieves superior performance in both frame-level action localization and temporal action localization.

关键词： Temporal action localization Convolutional neural network Frame-level action prediction

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Identifying Lateral Movement Attacks Based on Network Embedding

A Novel Approach for Identifying Lateral Movement Attacks Ba...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Mingyi Chen Yepeng Yao Junrong Liu Bo Jiang Liya Su Zhigang Lu School of Cyber Security University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728111421;9781728111414

The growing targeted incidents constitute a permanent menace to internal security with more frequent data breach and service interruption events nowadays. Attackers move laterally and reside in the internal systems for accessing valuable information continuously. This paper proposed a novel approach based on network embedding synthesizing the information on hosts, traffics and correlations to forestall further loss under a deliberate attack. The approach begins with constructing a host communication graph with features extracted from the original data recorded in the internal network and the topology structures of the constructed network. Inspired by previous works, the approach uses a features aggregation learning method, that is composing the features on vertices and edges with neighbors' features to aggregate new composite features. Then the features are selected and learned iteratively. The ultimately selected features were reduced to lower dimension for training and used for the malicious host classification task. Besides, the approach can reemployment the classification results to optimize the dimensionality reduction. Compared with the state-of-the-art models and methods, the proposed approach is (i) flexible with multiple types of data and exchangeable methods, (ii) accurate in feature learning, selecting and extracting with the remarkably average accuracy of 99.9% and the average precision of 91.3%.

关键词： Feature extraction Topology Training Biological system modeling image edge detection Security Data mining

来源：评论

学校读者我要写书评

暂无评论

DEEP image CLUSTERING USING CONVOLUTIONAL AUTOENCODER EMBEDDING WITH INCEPTION-LIKE BLOCK

DEEP IMAGE CLUSTERING USING CONVOLUTIONAL AUTOENCODER EMBEDD...

引用

IEEE International Conference on image processing

作者： Qiang Wang Jiaqing Xu Rongchun Li Peng Qiao Ke Yang Shijie Li Yong Dou National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China School of Computer National University of Defense Technology Changsha China

image clustering is one of the challenging tasks in machine learning, and has been extensively used in various applications. Recently, various deep clustering methods has been proposed. These methods take a two-stage approach, feature learning and clustering, sequentially or jointly. We observe that these works usually focus on the combination of reconstruction loss and clustering loss, relatively little work has focused on improving the learning representation of the neural network for clustering. In this paper, we propose a deep convolutional embedded clustering algorithm with inception-like block (DCECI). Specifically, an inception-like block with different type of convolution filters are introduced in the symmetric deep convolutional network to preserve the local structure of convolution layers. We simultaneously minimize the reconstruction loss of the convolutional autoencoders with inception-like block and the clustering loss. Experimental results on multiple image datasets exhibit the promising performance of our proposed algorithm compared with other competitive methods.

关键词： Convolutional codes Convolution Clustering algorithms image reconstruction Decoding Clustering methods Task analysis

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：