Distributed memory systems for simulating artificial neural networks

In executing tasks involving intelligent information processing, the human brain performs better than the digital computer. The human brain derives its power from a large number [O(10¹¹)] of neurons which are interconnected by a dense interconnection network [O(10⁵) connections per neuron]. Artificial neural network (ANN) paradigms adopt the structure of the brain to try to emulate the intelligent information processing methods of the brain. ANN techniques are being employed to solve problems in areas such as pattern recognition, and robotic processing. Simulation of ANNs involves implementation of large number of neurons and a massive interconnection network. In this paper, we discuss various simulation models of ANNs and their implementation on distributed memory systems. Our investigations reveal that communication-efficient networks of distributed memory systems perform better than other topologies in implementing ANNs.     

美籍华裔专家讲通信工程技术新动态

本文扼要介绍１９９５年北京中美工程技术研讨会通信组五位美籍华裔专家关于通信技术新动态的专题报告。一是宽带综合业务数字网的同步数字系列（ＳＤＨ）和异步转移模式（ＡＴＭ）；二是光纤通信系统的光放大器（ＯＦＡ）、波分多路（ＷＤＭ）、光电子集成（ＯＥＩＣ）、色散补偿和新型光纤；三是蜂窝网车载移动通信和全国性个人通信业务（ＰＣＳ）、时分多址（ＴＤＭＡ）和码分多址（ＣＤＭＡ），四是智能网（ＩＮ）体系结构、概念模型和业务管理系统（ＳＭＳ）；五是数字传输网的恢复（ＦＡＳＴＡＲ）、维护（ＴＭＰ）和供应（ＴＳＮＯＷ）三种管理平台，及综合网络管理系统（ＩＮＭＳ）。     

不断进取的AXE10

有近２０年历史的爱立信ＡＸＥ１０交换机在信息时代到来之际再放异彩，目前，它作为公共平台广泛应用于ＰＳＴＮ、ＩＳＤＮ、ＩＮ，ＰＬＭＮ、信令网和商务通信等。     

媒体网关控制技术及其在Alcatel 5020 MGC中的应用

分析了目前公用交换电话网(PSTN)中存在的问题和下一代网络(NGN)的优越性,分析了NGN中的关键技术媒体网关控制技术,探讨了媒体网关控制技术在Alcatel5020MGC中的实际应用,讨论了Alcatel5020MGC的软硬件系统架构。最后强调了在PSTN向NGN发展过程中基于演进产品的方法的重要性。     

GSM与WCDMA无线网络规划比较

WCDMA与GSM在空中接口上存在较大差异,WCDMA基于码分多址技术,GSM基于时分多址技术。GSM主要处理语音和低速数据,而WCDMA引入了多种速率的数据业务,根据业务的QoS进行资源控制和分配,因此在无线网络规划方法上,WCDMA与GSM存在较大差异。文章从容量规划、覆盖规划、蜂窝布局、规划流程、网络评估等方面对WCDMA与GSM的无线网络规划进行了比较和分析。     

RSFM网络及其在信号滤波中的应用

介绍了一种适用于模式识别的新型神经网络模型--局部有监督特征映射（Reglonal Supervised Feature Mapping,RSFM）网络,描述了该网络的拓扑结构和学习算法,研究了网络的基本性能,最后将其应用到了信号滤波中.理论研究和仿真实验表明,该网络结构简单、算法简洁,收敛速度快、识别精度高,适用于需要大样本训练、随机干扰严重的复杂模式的分类与识别.     

A pattern recognition-based approach for phylogenetic network construction with constrained recombination

The tree representation of evolutionary relationship oversimplifies the view of the process of evolution as it cannot take into account the events such as horizontal gene transfer, hybridization, homoplasy and genetic recombination. Several algorithms exist for constructing phylogenetic networks which result from events such as horizontal gene transfer, hybridization and homoplasy. Very little work has been published on the algorithmic detail of phylogenetic networks with constrained recombination. The problem of minimizing the number of recombinations in a phylogenetic network, constructed using binary DNA sequences, is NP-hard. In this paper, we propose a pattern recognition-based O(n²) time approach for constructing the phylogenetic network, where n is the number of nodes or sequences in the input data. The network is constructed with the restriction that no two cycles in the network share a common node.     

Self-Organized Monitoring in Ad-Hoc Networks

We propose in this paper a self-organized monitoring architecture for mobile ad-hoc networks based on a selective scheme where subsets of nodes are managed. These nodes are determined based on their network behavior in order to favor subsets of well-connected nodes. The key idea is to relax the requirements of the management plane, and to use these manageable subsets to monitor the performance of the overall network. We therefore propose a new performance metric to be monitored, in order to estimate the capability of ad-hoc nodes to communicate end-to-end in the network. Extensive simulations show how different parameters affect this metric.     

Prediction of Final Product Properties After Cocurrent Spray Drying

The effect of drying and atomization conditions on the physical properties of powders for agglomerate-like materials and skin-forming material are studied in this article. A neural model is used for powder bulk and tapped density predictions.