检索结果-内蒙古大学图书馆

Oscillatory Neural Networks : In Problems of parallel Information processing

2013年

作者： Kuzmina, Margarita G. Manykin, Eduard A. De Gruyter, Inc.

Understanding of the human brain functioning currently represents a challenging problem. In contrast to usual serial computers and complicated hierarchically organized artificial man-made systems, decentralized, parallel and distributed information processing principles are inherent to the brain. Besides adaptation and learning, which play a crucial role in brain functioning, oscillatory neural activity, synchronization and resonance accompany the brain work. Neural-like oscillatory network models, designed by the authors for image processing, allow to elucidate the capabilities of dynamical, synchronization-based types of image processing, presumably exploited by the brain. The oscillatory network models, studied by means of computer modeling and qualitative analysis, are presented and discussed in the book. Some other problems of parallel distributed information processing are also considered, such as a recall process from network memory for large-scale recurrent associative memory neural networks, performance of oscillatory networks of associative memory, dynamical oscillatory network methods of image processing with synchronization-based performance, optical parallel information processing based on the nonlinear optical phenomenon of photon echo, and modeling random electric fields of quasi-monochromatic polarized light beams using systems of superposed stochastic oscillators. This makes the book highly interesting to researchers dealing with various aspects of parallel information processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

distributed computing method based on mathematical morphology

引用

2nd International Conference on Green Communications and Networks, GCN 2012

作者： Wang, Yanbo Modern Education Technique Center Changchun University of Chinese Medicine Changchun 130117 China

ISBN: (纸本)9783642354694

The mathematical basis of mathematical morphology is set theory, which is widely used in the field of image processing, and distributed computing methods will require significant computing resources case that is broken down into small pieces, it has a plurality of computer parallel collaborative, and finally gives the results. Based on the heterogeneous network workstation as research platform, the mapping hyperspectral image processing technology is studied as a case that discusses the mathematical morphology and distributed computing method in the platform applications surveying and mapping hyperspectral image processing heterogeneous. Hyperspectral imaging is a new remote sensing technology. Its effective response time is the key of space earth science and planetary exploration. In response to this problem, the distributed calculation method is realized based on mathematical morphology to establish performance evaluation indicators. Through comparative analysis, the method is verified that using the morphological algorithm of distributed algorithm has a time advantage, which will contribute to the high spectrum image to select the appropriate distributed computing technology and to adopt a particular application strategy. © 2013 Springer-Verlag.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Soft-Constrained Nonnegative Matrix Factorization via Normalization

Soft-Constrained Nonnegative Matrix Factorization via Normal...

引用

International Joint Conference on Neural Networks

作者： Long Lan Naiyang Guan Xiang Zhang Dacheng Tao Zhigang Luo Science and Technology on Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering and Information Technology University of Technology

ISBN: (纸本)9781479914821

Semi-supervised clustering aims at boosting the clustering performance on unlabeled samples by using labels from a few labeled samples. Constrained NMF (CNMF) is one of the most significant semi-supervised clustering methods, and it factorizes the whole dataset by NMF and constrains those labeled samples from the same class to have identical encodings. In this paper, we propose a novel soft-constrained NMF (SCNMF) method by softening the hard constraint in CNMF. Particularly, SCNMF factorizes the whole dataset into two lower-dimensional factor matrices by using multiplicative update rule (MUR). To utilize the labels of labeled samples, SCNMF iteratively normalizes both factor matrices after updating them with MURs to make encodings of labeled samples close to their label vectors. It is therefore reasonable to believe that encodings of unlabeled samples are also close to their corresponding label vectors. Such strategy significantly boosts the clustering performance even when the labeled samples are rather limited, e.g., each class owns only a single labeled sample. Since the normalization procedure never increases the computational complexity of MUR, SCNMF is quite efficient and effective in practices. Experimental results on face image datasets illustrate both efficiency and effectiveness of SCNMF compared with both NMF and CNMF.

关键词： Matrix decomposition Encoding Vectors Clustering methods Clustering algorithms Time complexity Face

来源：评论

学校读者我要写书评

暂无评论

Efficient lidar point cloud data managing and processing in a Hadoop-based distributed framework 2

Efficient lidar point cloud data managing and processing in ...

引用

2nd International Symposium on Spatiotemporal Computing, ISSC 2017

作者： Wang, C. Hu, F. Sha, D. Han, X. Hainan Geomatics Center National Administration of Surveying Mapping and Geoinformation of China Haikou Hainan570203 China Department of Geography and GeoInformation Science Center for Intelligent Spatial Computing George Mason University FairfaxVA22030-4444 United States

Light Detection and Ranging (LiDAR) is one of the most promising technologies in surveying and mappingï1/4city management, forestry, object recognition, computer vision engineer and others. However, it is challenging to efficiently storage, query and analyze the high-resolution 3D LiDAR data due to its volume and complexity. In order to improve the productivity of Lidar data processing, this study proposes a Hadoop-based framework to efficiently manage and process LiDAR data in a distributed and parallel manner, which takes advantage of Hadoop's storage and computing ability. At the same time, the Point Cloud Library (PCL), an open-source project for 2D/3D image and point cloud processing, is integrated with HDFS and MapReduce to conduct the Lidar data analysis algorithms provided by PCL in a parallel fashion. The experiment results show that the proposed framework can efficiently manage and process big LiDAR data. © Authors 2017.

关键词： distributed computing GIS Hadoop HDFS Lidar data MapReduce PCL Point cloud

来源：评论

学校读者我要写书评

暂无评论

Box-constrained Projective Nonnegative Matrix Factorization via Augmented Lagrangian Method

Box-constrained Projective Nonnegative Matrix Factorization ...

引用

International Joint Conference on Neural Networks

作者： Xiang Zhang Naiyang Guan Long Lan Dacheng Tao Zhigang Luo Science and Technology on Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering and Information Technology University of Technology

ISBN: (纸本)9781479914821

Projective non-negative matrix factorization (PNMF) projects a set of examples onto a subspace spanned by a non-negative basis whose transpose is regarded as the projection matrix. Since PNMF learns a natural parts-based representation, it has been successfully used in text mining and pattern recognition. However, it is non-trivial to analyze the convergence of the optimization algorithms for PNMF because its objective function is non-convex. In this paper, we propose a Box-constrained PNMF (BPNMF) method to overcome this deficiency of PNMF. In particular, BPNMF introduces an auxiliary variable, i.e., the coefficients of examples, and incorporates the following two types of constraints: 1) each entry of the basis is non-negative and upper-bounded, i.e., box-constrained, and 2) the coefficients equal to the projected points of the examples. The first box constraint makes the basis to be bound and the second equality constraint keeps its equivalence to PNMF. Similar to PNMF, BPNMF is difficult because the objective function is non-convex. To solve BPNMF, we developed an efficient algorithm in the frame of augmented Lagrangian multiplier (ALM) method and proved that the ALM-based algorithm converges to local minima. Experimental results on two face image datasets demonstrate the effectiveness of BPNMF compared with the representative methods.

关键词： Accuracy Linear programming Training Convergence Optimization Face Educational institutions

来源：评论

学校读者我要写书评

暂无评论

distributed and parallel Subarray Beamforming for Near-Field 3D Sonar Imaging 3

Distributed and Parallel Subarray Beamforming for Near-Field...

引用

3rd International Conference on Computer Science and Network Technology (ICCSNT)

作者： Han, Yeqiang Fu, Jiabao Zhou, Fan Tian, Xiang Chen, Yaowu Zhejiang Univ Inst Adv Digital Technol & Instrumentat Hangzhou Zhejiang Peoples R China Zhejiang Prov Key Lab Network Multimedia Technol Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781479905614

The computational load is prohibitive in 3D sonar systems for real-time image generation. In the literature, an efficient frequency beamforming method based on the distributed and parallel subarray (DPS) has been introduced for planar arrays working in the far field. This paper extends the DPS beamforming algorithm to process the signals acquired from a scene in the near field. The alogrithm divides the full populated transducer array into two stage distributed subarrays. It performs parallel beamforming on the first-stage subarrays and applies the approximation for time delays in the near-field beam patterns of the second-stage subarray. The computational efficiency is significantly improved as compared with the traditional methods, while achieving the similar resolutions. In addition, a multi-FPGA signal processor is proposed for implementing the underwater 3-D imaging.

关键词： underwater 3D imaging sonar sensor array system sonar signal processing distributed and parallel subarray beamforming

来源：评论

学校读者我要写书评

暂无评论

Multi-label Classification with Clustering for image and Text Categorization

Multi-label Classification with Clustering for Image and Tex...

引用

6th International Congress on image and Signal processing (CISP)

作者： Nasierding, Gulisong Sajjanhar, Atul Xinjiang Normal Univ Sch Comp Sci & Technol 102 Xin Yi Rd Urumqi 830001 Peoples R China Deakin Univ Sch Informat Technol Parallel & Distributed Comp Lab Burwood Vic 3125 Australia

ISBN: (纸本)9781479927630

This paper explores effective multi-label classification methods for multi-semantic image and text categorization. We perform an experimental study of clustering based multi-label classification (CBMLC) for the target problem. Experimental evaluation is conducted for identifying the impact of different clustering algorithms and base classifiers on the predictive performance and efficiency of CBMLC. In the experimental setting, three widely used clustering algorithms and six popular multi-label classification algorithms are used and evaluated on multi-label image and text datasets. A multi-label classification evaluation metrics, micro F1-measure, is used for presenting predictive performances of the classifications. Experimental evaluation results reveal that clustering based multi-label learning algorithms are more effective compared to their non-clustering counterparts.

关键词： multi-label classification clustering image and text categorization

来源：评论

学校读者我要写书评

暂无评论

The best-so-far ABC with multiple patrilines for clustering problems

引用

NEUROCOMPUTING 2013年 116卷 355-366页

作者： Banharnsakun, Anan Sirinaovakul, Booncharoen Achalakul, Tiranee King Mongkuts Univ Technol Thonburi Dept Comp Engn Bangkok Thailand

Clustering is an important process in many application domains such as machine learning, data mining, pattern recognition, image analysis, information retrieval, and bioinformatics. The main objective of clustering is to search for hidden patterns that may exist in datasets. Since the clustering problem is considered to be NP-hard, previous research has applied bio-inspired heuristic methods to solve such problems. In this paper we propose an effective method for clustering using an algorithm inspired by the decision making processes of bee swarms. The algorithm is called the Best-so-far Artificial Bee Colony with multiple patrilines. In the Best-so-far method, the solution direction is biased toward the Best-so-far solution rather than a neighboring solution proposed in the original Artificial Bee Colony algorithm. We introduce another bee-inspired concept called multiple patrilines to further improve the diversity of solutions and allow the calculations to be distributed among multiple computing units. We empirically assess the performance of our proposed method on several standard datasets taken from the UCI Machine Learning Repository. The results show that the proposed method produces solutions that are as good as or better than the current state-of-the-art clustering techniques reported in the literature. Furthermore, to demonstrate the computing performance and scalability of the algorithm, we assess the algorithm on a large disk drive manufacturing dataset. The results indicate that our distributed Best-so-far approach is scalable and produces good solutions while significantly improving the processing time. (C) 2012 Elsevier B.V. All rights reserved.

关键词： Clustering Best-so-far ABC Multiple patrilines Swarm intelligence Optimization distributed environments parallel computing

来源：评论

学校读者我要写书评

暂无评论

Do You See What I See?

Do You See What I See?

引用

IEEE Applied imagery Pattern Recognition (AIPR) Workshop on Sensing for Control and Augmentation

作者： Cerkez, P. S. DCS Corp Lexington Pk MD 20653 USA

ISBN: (纸本)9781479925407

Semagrams are a subset of steganography. When a message is transmitted in a non-textual format, (i.e., in the visual content of an image), it is referred to as a semagram. While semagrams are relatively easy to create (as shown in published papers covering hiding techniques), detecting a hidden message in or embedded as an image-based semagram is a greater magnitude of difficultly than typical digital steganography. US Patents issued based on semagram technology show that this feature has been exploited in the copyright/watermarking world to increase protection. In a semagram, the image is the message and they work well for simple messages and dead drops. Attacks on semagrams are primarily visual examinations of artifacts. In the counter-espionage world, the rule of the thumb is that there is always a message hidden in an image or graphic, it is simply up to the steganalyst to find it. In short, detecting semagrams is a matter of recognizing patterns of patterns that represent a hidden message within an image. This presentation provides a brief summary of the technology underlying semagrams, present a short non-technical discussion of the technology used in the attack on semagrams, followed by a discussion on current work and planned future implementations of the proven semagram detection ANN. It will focus on extending the ANN to other domains (e. g., non-visual spectrums, multi/cross spectrum correlation, scene identification, image classification) and efforts to improve the processing speed and throughput via parallel/distributed methods.

关键词： images imagery (Psychotherapy) Steganography Messages image processing SPEED Spectra Thumb Artificial neural networks Throughput

来源：评论

学校读者我要写书评

暂无评论

Efficient Hardware Calculation of Running Statistics

Efficient Hardware Calculation of Running Statistics

引用

28th International Conference on image and Vision Computing New Zealand (ivCNZ)

作者： Bailey, Donald G. Klaiber, Michael J. Massey Univ Sch Engn & Adv Technol Palmerston North New Zealand Univ Stuttgart Inst Parallel & Distributed Syst Stuttgart Germany

ISBN: (纸本)9781479908837;9781479908820

Calculation of mean, variance and standard deviation are often required for segmentation or feature extraction. In image processing, often an integer approximation is adequate. Conventional methods require division and square root operations, which are expensive to realize in hardware in terms of both the amount of required resources and latency. A new class of iterative algorithms is developed based on integer arithmetic. An implementation of the algorithms as a hardware architecture for a Field-Programmable Gate Array (FPGA) is compared with architectures using the conventional approach, which shows a significantly reduced latency while using less hardware resources.

关键词： Computer hardware hardware resource Field programmable gate arrays hardware architecture Iterative algorithms Feature extraction ARCHITECTURE Integer Latency integer arithmetic segmentation

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：