Regularised nonlinear blind signal separation using sparsely connected network

A nonlinear approach based on the Tikhonov regularised cost function is presented for blind signal separation of nonlinear mixtures. The proposed approach uses a multilayer perceptron as the nonlinear demixer and combines both information theoretic learning and structural complexity learning into a single framework. It is shown that this approach can be jointly used to extract independent components while constraining the overall perceptron network to be as sparse as possible. The update algorithm for the nonlinear demixer is subsequently derived using the new cost function. Sparseness in the network connection is utilised to determine the total number of layers required in the multilayer perceptron and to prevent the nonlinear demixer from outputting arbitrary independent components. Experiments are meticulously conducted to study the performance of the new approach and the outcomes of these studies are critically assessed for performance comparison with existing methods.     

Designing VLSI network nodes to reduce memory traffic in a shared memory parallel computer

Serialization of memory access can be a critical bottleneck in shared memory parallel computers. The NYU Ultracomputer, a large-scale MIMD (multiple instruction stream, multiple data stream) shared memory architecture, may be viewed as a column of processors and a column of memory modules connected by a rectangular network of enhanced 2×2 buffered crossbars. These VLSI nodes enable the network to combine multiple requests directed at the same memory location. Such requests include a new coordination primitive, fetch- and-add, which permits task coordination to be achieved in a highly parallel manner. Processing within the network is used to reduce serialization at the memory modules.To avoid large network latency, the VLSI network nodes must be high-performance components. Design tradeoffs between architectural features, asymptotic performance requirements, cycle time, and packaging limitations are complex. This report sketches the Ultracomputer architecture and discusses the issues involved in the design of the VLSI enhanced buffered crossbars which are the key element in reducing serialization.This work was supported in part by the Applied Mathematical Sciences subprogram of the Office of Energy Research, U.S. Department of Energy, under contract number DEA-C0276-ER03077-V, and in part by the National Science Foundation, under grant number DCR-8413359.     

Canonical lowpass prototype network for symmetric coupled-resonator bandpass filters

A lowpass prototype network that represents a canonical realisation for symmetric coupled-resonator bandpass filters is presented. A synthesis procedure for the prototype is outlined.     

Anomaly detection with dual-stream memory network

Anomaly detection is an essential but challenging task. Existing DNN-based approaches tend to ignore the impact of network history state on extracting spatio-temporal correlations between video events. To address this problem, a Dual-Stream Memory Network (DSM-Net) has been proposed. It leverages historical information from the network to create a dual-stream memory module serving as complementary knowledge for the anomaly detection network. The memory module performs writing and reading in the form of a queue of data features. The writing records the historic information of video events through a moving average encoder, and the reading uses optical flow to uncover behavioral patterns in RGB images. Using a memory sharing strategy, the semantic information of the appearance branch and the motion branch can be integrated to reinforce the network. Results demonstrate that the proposed method on various standard datasets performs favorably when compared to existing methods.     

Chaotic neural network for associative memory

Based on current research on applications of chaotic neuron network for information processing, the stability and convergence of chaotic neuron network are proved from the viewpoint of energy function. Moreover, a new auto-associative matrix is devised for artificial neural network composed of chaotic neurons, thus, an improved chaotic neuron network for associative memory is built up. Finally, the associative recalling process of the network is analyzed in detail and explanations of improvement are given.     

内存映射处理网络规划仿真大数据的研究

本文介绍了内存映射的基本原理与调用流程,通过内存映射文件技术解决了无线网络规划软件大数据量中间结果的文件读写效率问题,对传统文件技术与内存映射技术进行了性能对比,展示了软件通过中间结果文件生成的最终结果,使软件既能够满足大规模仿真的需求,同时保证了运行的高效性。     

Configuration selection for two-layer memory network pattern classifiers

Appropriate allocation of decision-making tasks between processing levels in a hierarchical memory network pattern classifier can enhance efficient utilisation of resources and reduce implementation complexity. The letter describes and compares two strategies for such resource allocation, with specific reference to decision refinement between processing levels.     

基于反射内存网络的数据组播机制研究

基于以太网的组播速率较低,无法满足实时系统,且无拥塞控制机制,易出现丢包、乱序等现象;同时,基于以太网组播的应用程序不能直接移植到反射内存网。针对上述问题,提出了一种基于反射内存网的组播实现方案,将组播技术与反射内存网技术相结合,实现了参与组播的各节点间的高速通信。该方案的实现,不仅提高了节点间的通信的可靠性,还提高了基于以太网组播的应用程序的可移植性。     

NEURAL MEMORY MODEL AND ITS PIECEWISE-LINEAR NETWORK REALIZATION

This paper studies the neural networks by means of neural functions.The memoryfunction of neural networks is investigated and its mathematical model is given.The model issynthesized by a piecewise-linear resistive network which exhibits many properties of artificialneural network such as parallelism,real-time processing capability,distribution,adaptation.Inaddition,all parameters of the network are expressed analytically by the patterns and featureswhich are memorized in the network.     

Comparison of symmetric and asymmetric routing for fixed two-hop cellular relaying network

In this paper, routing strategies for fixed two-hop cellular relaying networks are discussed in terms of area spectral efficiency. We consider symmetric and asymmetric routing in uplink and downlink. Simulation results show that relaying increases the average throughput in comparison with conventional cellular networks and the area spectral efficiency of asymmetric routing is slightly better than that of the symmetric     

Diffraction by a symmetric material junction simulated withgeneralized sheet transition conditions

When diffraction by a material discontinuity in a thick dielectric/ferrite slab is treated by the dual integral equation approach (a variation of the Weiner-Hopf method), the resulting solution displays unknown constants, characteristic of the incompleteness associated with the generalized transition conditions employed in modeling a thick slab. The constants can be shown to depend on the geometry and properties of the discontinuity. Their explicit determination by enforcing field continuity across the slab junction is treated. The field internal to the slab is determined by first expressing the field as an expansion of discrete and continuous eigenmodes valid in the exterior and interior slab region. The expansion or mode coefficients are then identified by recasting the Weiner-Hopf solution in a suitable form, enabling the solution constants to be numerically computer by matching the field expansions to the left and right of the slab discontinuity at a discrete set of points     

虚拟存储技术在视频网络中的应用

从对称式虚拟存储和非对称式虚拟存储两个方面，详细阐述了虚拟存储技术在视频网络中的应用。     

Efficient classification by neural networks using encoded patterns

The corners and the middle points, which are extracted as features from the line approximation of a given pattern, are overlaid on a radial grid to form the input array for training a backpropagation network for classification. The proposed method is shown to be simple and robust by extensive testing of its performance on patterns both with and without noise     

Corrective Plate With a Gradient Index Media in the Catadioptiric System

1IntroductionIthasbeenprovedthataradialgradientindexmediaplatehasthesameeffectasalens"'..Whenthethicknessoftheplateisextremelyhigh,andtheradiusisverysmall,itcanbeconsideredasanopticalwaveguide.Ithasalsobeenprovedthatalaminategradientindexmediaplatehassome…     

Performance analysis of spectrally encoded hybrid WDM-OCDMA network employing optical orthogonal modulation format against eavesdropper

In this paper, the spectrally encoded hybrid WDM-OCDMA network employing 60 Gbps non-return to zero/differential quadrature phase shift keying (NRZ/DQPSK) orthogonally modulated data signal operating over 100 km SMF+DCF has been proposed. In proposed hybrid WDM-OCDMA network, the orthogonal modulation formats are used to enhance per channel capacity and the spectral amplitude optical coding for enhancing the confidentiality of data from unauthorized user or eavesdropper. The impact of input power, transmission distance and energy per bit to noise power spectral density ratio (E_b/N₀) on the performance of WDM-OCDMA network in terms of output optical power, timing diagram, BER, Q-factor and probability of error free code detection has been investigated. It can also be determined that orthogonal modulation formats are promising option to increase per channel capacity as compared to conventional modulation format and these are less vulnerable to chromatic dispersion (CD) and polarization mode dispersion (PMD). Meanwhile, the performance of proposed hybrid network is compared with existing OCDMA network which show the feasibility of proposed WDM-OCDMA network in future generation optical networking.     

基于长短期记忆神经网络的短期负荷预测

准确的电力负荷预测是电力系统安全、稳定、经济、优质运行的前提,负荷预测的本质是通过历史数据对未来负荷情况做出预先估计。电量的快速增长和用户的多元化对负荷预测提出了更高的要求。文中提出了一种基于长短期记忆网络的负荷预测方法,利用长短期网络数据驱动和对时间序列建模强的特点,对于含非线性、不确定性的系统,提取其负荷数据中的周期特征,具有较强的自适应性。以真实数据为算例,验证了方法的有效性。     

网络存储器在卫星小站数据接收上的应用

文章对网络存储器在卫星小站数据接收上的应用进行了论述,对网络存储器在数据存储上的优点进行了相关介绍,并描述了架设FTP服务器的方式方法和卫星小站软件的相关设置,以此来实现对卫星小站数据接收存储起到降低存储设备成本的目的。     

Dynamic memory management methodology applied to embedded telecom network systems

Presents a new methodology for dynamic memory management of embedded telecom network systems. This methodology enables the designer to further raise the abstraction level of the initial system specification and to achieve optimized embedded system designs. This methodology is well suited for systems characterized by a set of concurrent and dynamic processes, very high-bit-rate data streams, and intensive data transfer and storage, as encountered in telecom network applications. Up to now, it has been successfully applied to four telecom network systems. This methodology can be easily integrated into any C++-based system synthesis approach that bridges the gap between a concurrent process-level system specification and an optimized (for area, performance, or power) embedded implementation of communicating hardware/software processors. This is in contrast to current system design practice, where VHDL/C is derived without room for exploration, refinement, and verification, leading to expensive late design iterations. In this paper, the main focus lies on the system-level specification model and the dynamic memory management applied to two real-life telecom network systems.     

Abnormal traffic detection-based on memory augmented generative adversarial IIoT-assisted network

Wireless Networks - The implementation of IoT in industrial management is referred as Industrial IoT (IIoT). It is used to increase the overall operational efficiency. IIoT is considered as the...     

基于记忆原理的网络课程信息表征设计研究

以往设计出的网络课程信息表征无法有效增强学生对信息的接收能力,学生成绩的提高不明显。现对基于记忆原理的网络课程信息表征进行设计,其根据记忆原理设计网络课程方案,包括学生情绪方案和复习方案。基于记忆原理的网络课程信息表征利用网络课程方案设计教学模块、学习模块和管理模块。管理模块对师生资格确认、师生学籍、学生兴趣点、教学大纲变更、教学课件修改进行管理。拥有权限的教师在教学模块中进行查看个人信息、修改网络课程信息、下载教学资源、填制学生成绩、编制试卷等工作。学生在学习模块中进行教学栏查看与留言、网络课程观看、在线试卷解答和教学资源下载等操作。软件部分对网络课程信息表征功能设计流程进行实现。实验结果表明,该设计能够有效增强学生对信息的接收能力,学生成绩的提高较为明显。