检索结果-内蒙古大学图书馆

2010 IEEE International Conference on Granular computing, GrC 2010

作者： Zhang, Lili Merényi, Erzsébet Department of Electrical and Computer Engineering Rice Quantum Institute Rice University 6100 Main Street Houston TX 77005 United States Department of Electrical and Computer Engineering Rice University 6100 Main Street Houston TX 77005 United States

ISBN: (纸本)9780769541617

Inference of latent variables from complicated data is one important problem in data mining. The high dimensionality and high complexity of real world data often make accurate inference difficult. We approach this challenge with a neural architecture we call Conjoined Twins, which is a two-layer feedforward network with a Self-Organizing Map (SOM) as its hidden layer. its output layer can preferentially use different numbers (κ) of SOM winners for the inference of different latent variables. We introduced this architecture in [1], [2]. In this paper we propose an automated procedure for the customization of κ and demonstrate the effectiveness of the method by the inference of two physical parameters of icy planetary surfaces from spectroscopic data. © 2010 IEEE.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Skel: Generative Software for Producing Skeletal I/O Applications

Skel: Generative Software for Producing Skeletal I/O Applica...

引用

IEEE International Conference on E-Science Workshops

作者： Jeremy Logan Scott Klasky Jay Lofstead Hasan Abbasi Stephane Ethier Ray Grout Seung-Hoe Ku Qing Liu Xiaosong Ma Manish Parashar Norbert Podhorszki Karsten Schwan Matthew Wolf Oak Ridge National Laboratory Oak Ridge TN USA Sandia National Laboratories Albuquerque NM USA Plasma Physics Laboratory Princeton University Princeton NJ USA National Renewable Energy Laboratory Golden CO USA Courant Institute of Mathematical Sciences New York University New York NY USA National Institute for Computational Sciences University of Tennessee Oak Ridge TN USA Department of Computer Science North Carolina State University Raleigh NC USA Department of Electrical & Computer Engineering Rutgers The State University of New Jersey Piscataway NJ USA College of Computing Georgia Tech Atlanta GA USA

Massively parallel computations consist of a mixture of computation, communication, and I/O. Of these three components, implementing an effective parallel I/O solution has often been overlooked by application scientists and has typically been added to large scale simulations only when existing serial techniques have failed. As scientists' teams scaled their codes to run on hundreds of processors, it was common to call on an I/O expert to implement a set of more scalable I/O routines. These routines were easily separated from the calculations and communication, and in many cases, an I/O kernel was derived from the application which could be used for testing I/O performance independent of the application. These I/O kernels developed a life of their own used as a broad measure for comparing different I/O techniques. Unfortunately, as years passed and computation and communication changes required changes to the I/O, the separate I/O kernel used for benchmarking remained static, no longer providing an accurate indicator of the I/O performance of the simulation, and making I/O research less relevant for the application scientists. In this paper we describe a new approach to this problem where I/O kernels are replaced with skeletal I/O applications that are automatically generated from an abstract set of simulation I/O parameters. We realize this abstraction by leveraging the ADIOS [1] middleware's XML I/O specification with additional runtime parameters. Skeletal applications offer all of the benefits of I/O kernels including allowing I/O optimizations to focus on useful I/O patterns. Moreover, since they are automatically generated, it is easy to produce an updated I/O skeleton whenever the simulation's I/O changes. In this paper we analyze the performance of automatically generated I/O skeletal applications for the S3D and GTS codes. We show that these skeletal applications achieve performance comparable to that of the production applications. We wrap up the paper with

关键词： XML Kernel Arrays Benchmark testing Educational institutions Reactive power Hardware

来源：评论

学校读者我要写书评

暂无评论

A network management system based on DPI

A network management system based on DPI

引用

International Conference on Network-Based Information Systems

作者： Yang, Chu-Sing Liao, Ming-Yi Luo, Mon-Yen Wang, Shin-Min Yeh, C. Eugene Department of Electrical Engineering Institute of Computer and Communication Engineering National Cheng Kung University Taiwan Department of Computer Science and Information Engineering National Kaohsiung University of Applied Sciences Kaohsiung Taiwan National Center for High-Performance Computing Taiwan

ISBN: (纸本)9780769541679

More and more network applications have appeared in recent years. Government, university, industry and individual Internet users and network services need more bandwidth and various network applications. Many new network protocols are proposed so that it is now becoming harder to manage the network. In the conditional network, every network protocol uses the fixed port, the so-called well-known port number. In the past, it was easy to classify and manage the network traffic because we could identify the network service by the port number. However, new types of network applications do not use fixed port number. The method of traffic classification with fixed port number is inadequate. In recent years, the DPI (Deep Packet Inspection) is used to classify the traffic. This study deploys a NMS (network management system) based on DPI and SNMP. The NMS controls the network devices and services according to the traffic classification of DPIS (DPI server). The platform of DPIS is implemented on the Netfilter framework in Linux kernel. © 2010 IEEE.

关键词： Network management

来源：评论

学校读者我要写书评

暂无评论

Robust low-rank subspace segmentation with semidefinite guarantees

Robust low-rank subspace segmentation with semidefinite guar...

引用

10th IEEE International Conference on Data Mining Workshops, ICDMW 2010

作者： Ni, Yuzhao Sun, Ju Yuan, Xiaotong Yan, Shuicheng Cheong, Loong-Fah Interactive and Digital Media Institute National University Singapore Singapore Department of Electrical and Computer Engineering National University Singapore Singapore School of Computing National University Singapore Singapore

ISBN: (纸本)9780769542577

Recently there is a line of research work proposing to employ Spectral Clustering (SC) to segment (group)1\ high-dimensional structural data such as those (approximately) lying on subspaces2 or low-dimensional manifolds. By learning the affinity matrix in the form of sparse reconstruction, techniques proposed in this vein often considerably boost the performance in subspace settings where traditional SC can fail. Despite the success, there are fundamental problems that have been left unsolved: the spectrum property of the learned affinity matrix cannot be gauged in advance, and there is often one ugly symmetrization step that post-processes the affinity for SC input. Hence we advocate to enforce the symmetric positive semi definite constraint explicitly during learning (Low-Rank Representation with Positive Semi Definite constraint, or LRR-PSD), and show that factually it can be solved in an exquisite scheme efficiently instead of general-purpose SDP solvers that usually scale up poorly. We provide rigorous mathematical derivations to show that, in its canonical form, LRR-PSD is equivalent to the recently proposed Low-Rank Representation (LRR) scheme[1], and hence offer theoretic and practical insights to both LRR-PSD and LRR, inviting future research. As per the computational cost, our proposal is at most comparable to that of LRR, if not less. We validate our theoretic analysis and optimization scheme by experiments on both synthetic and real data sets. © 2010 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A morphogenetic self-organization algorithm for swarm robotic systems using relative position information

A morphogenetic self-organization algorithm for swarm roboti...

引用

UK Workshop on Computational Intelligence

作者： Jin, Yaochu Meng, Yan Guo, Hongliang Department of Computing University of Surrey Guildford Surrey GU2 7XH United Kingdom Department of Electrical and Computer Engineering Stevens Institute of Technology NJ 07030 United States

ISBN: (纸本)9781424487752

Inspired by the major principles of gene regulation and cellular interactions in multi-cellular development, this paper proposes a distributed self-organizing algorithm for multi-robot shape formation. In this approach, multiple robots are able to self-organize themselves into complex shapes driven by the dynamics of a gene regulatory network model. Particularly, no predefined global coordinate system is needed by building up a relative coordinate system through local interactions and limited communications among the robots. The target shape is represented by the non-uniform rational B-spline (NURBS) and embedded into the gene regulation model, analogous to the morphogen gradients in morphogenesis. Since the self-organization algorithm does not need absolute position information, the target shape can be formed anywhere within the environment based on the current location of the robots. Simulation and experimental results demonstrate that the proposed algorithm is effective for complex shape construction and robust to environmental changes and system failures.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

quantum key distribution over probabilistic quantum repeaters

引用

Physical Review A 2010年第3期82卷 032304-032304页

作者： Jeyran Amirloo Mohsen Razavi A. Hamed Majedi Institute for Quantum Computing and Department of Electrical and Computer Engineering University of Waterloo 200 University Avenue West Waterloo Ontario Canada N2L 3G1

A feasible route toward implementing long-distance quantum key distribution (QKD) systems relies on probabilistic schemes for entanglement distribution and swapping as proposed in the work of Duan, Lukin, Cirac, and Zoller (DLCZ) [Nature (London) 414, 413 (2001)]. Here, we calculate the conditional throughput and fidelity of entanglement for DLCZ quantum repeaters by accounting for the DLCZ self-purification property in the presence of multiple excitations in the ensemble memories as well as loss and other sources of inefficiency in the channel and measurement modules. We then use our results to find the generation rate of secure key bits for QKD systems that rely on DLCZ quantum repeaters. We compare the key generation rate per logical memory employed in the two cases with and without a repeater node. We find the crossover distance beyond which the repeater system outperforms the nonrepeater one. That provides us with the optimum internode distancing in quantum repeater systems. We also find the optimal excitation probability at which the QKD rate peaks. Such an optimum probability, in most regimes of interest, is insensitive to the total distance.

关键词： quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Fusing bottom-up and top-down pathways in neural networks for visual object recognition

Fusing bottom-up and top-down pathways in neural networks fo...

引用

2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010

作者： Zheng, Yuhua Meng, Yan Jin, Yaochu Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ 07030 United States Department of Computing University of Surrey Guildford Surrey GU2 7TW United Kingdom

ISBN: (纸本)9781424469178

In this paper, an artificial neural network model is built up with two pathways: bottom-up sensory-driven pathway and top-down expectation-driven pathway, which are fused to train the neural network for visual object recognition. During the supervised learning process, the bottom-up pathway generates hypotheses as network outputs. Then target label will be applied to update the bottom-up connections. On the other hand, the hypotheses generated by the bottom-up pathway will produce expectations on the sensory input through the top-down pathway. The expectations will be constrained by the real data from the sensory input which can be used to update the top-down connections accordingly. This two-pathway based neural network can also be applied to semi-supervised learning with both labeled and unlabeled data, where the network is able to generate hypotheses and corresponding expectations. Experiments on visual object recognition suggest that the proposed neural network model is promising to recover the object for the cases with missing data in sensory inputs. © 2010 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Human activity detection using spiking neural networks regulated by a gene regulatory network

Human activity detection using spiking neural networks regul...

引用

2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010

作者： Meng, Yan Jin, Yaochu Yin, Jun Conforth, Matthew Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ 07670 United States Department of Computing University of Surrey Guildford Surrey GU2 7XH United Kingdom

ISBN: (纸本)9781424469178

Detecting human activities automatically in a video stream in various scenes is a challenging task. The major difficulty of this task lies in how to extract the spatial and temporal features of video sequences so that the human activities can be recognized. To tackle this problem, we propose a new classifier model using a BCM-based spiking neural network, where the auto-regulated plasticity and meta-plasticity of the BCM network will help to extract the temporal features for the classifier. In the proposed model, the weight, weight plasticity, and meta-plasticity of the BCM network are regulated by a gene regulatory network (GRN), which plays a key role in neural development and neuromodulation. Meanwhile, the GRN will also be influenced by the activity of the neurons it resides in, resulting in a closed loop between the neural network and GRN. By using this new classifier model, only the spatial features need to be extracted from image frames in the preprocessing. Extensive experimental results have demonstrated the efficiency of the proposed model for online human activity detection. © 2010 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A morphogenetic approach to self-reconfigurable modular robots using a hybrid hierarchical gene regulatory network

A morphogenetic approach to self-reconfigurable modular robo...

引用

12th International Conference on the Synthesis and Simulation of Living Systems: Artificial Life XII, ALIFE 2010

作者： Meng, Yan Zhang, Yuyang Jin, Yaochu Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ 07030 United States Department of Computing University of Surrey Guildford Surrey GU2 7XH United Kingdom

ISBN: (纸本)9780262290753

In this paper, we present a morphogenetic approach to self-reconfiguration of a lattice-based simulated modular robot, CrossCube, under dynamic environments. A hybrid hierarchical controller inspired by the embryonic development of multi-cellular organisms is proposed to form different patterns for modular robots to adapt to environmental changes. The first layer is a rule-based controller to generate a number of appropriate target patterns (i.e. configurations) for various environments. The second layer is a gene regulatory network (GRN) based controller to coordinate the modules of CrossCube to transform from its current pattern to the target pattern. This hybrid hierarchical control framework is distributed in the sense that each module makes its own decisions based on its local perception. The global behavior of modular robots emerges from the local interactions with the environment and between the modules. The simulation results demonstrate that the proposed system is efficient and robust in adaptively reconfiguring modular robots to adapt to the changing environment.

关键词： Modular robots

来源：评论

学校读者我要写书评

暂无评论

A novel multi-channel access scheme in cognitive ad hoc networks

A novel multi-channel access scheme in cognitive ad hoc netw...

引用

2nd International Conference on Information Science and engineering, ICISE2010

作者： Lu, Dianjie Huang, Xiao Xia Han, Ren Li, Pan Feng, Shengzhong Fan, Jianping Institute of Computing Technology Chinese Academy of Sciences China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Electrical and Computer Engineering Mississippi State University United States

ISBN: (纸本)9781424480968

Multi-channel access is often used to improve the throughput and spectral efficiency of cognitive ad hoc networks. However, there have been few methods for satisfying the requirements of secondary users while using multiple channels simultaneously. In this paper, we propose a novel multi-channel access scheme for QoS supporting. Considering the time-varying channel characteristics, we propose to calculate the Expected Transmission Time (ETT) of each secondary user based on the channel status estimate. Then, the spectrum access problem is formulated as a constrained optimization problem. The solution gives the optimal multi-channel spectrum access under the QoS constraints of secondary users. Experiment results show that our method meets the requirements of secondary users while effectively improving the stability of channel access. © 2010 IEEE.

关键词： Quality of service

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：