Monitoring of yeast fermentation by ion mobility spectrometry measurement and data visualisation with Self-Organizing Maps

Ion mobility spectrometry (IMS) measurement combined with unsupervised neurocomputing is considered as a new potential method for on-line monitoring of fermentation and other processes producing volatile compounds that involve micro-organisms. This was demonstrated in a model system in which a strain of brewer’s yeast (Saccharomyces cerevisiae) was cultivated in a bench-top fermenter. Five phases of yeast growth could be detected from measurements of the exhaust gases from the fermenter, as indicated by the changes in ion mobility spectra analysed by computational methods.The data were first processed using the Self-Organizing Map (SOM) algorithm, the results showing that the phases of fermentation can be detected and identified. The cultivations were also shown by Sammon’s mapping to be comparable to a certain level of accuracy. Contaminated cultivation could be detected by its distinctive ion mobility spectrometry profile.     

SON中基于蚂蚁网络的QoS单播路由机制

 本文提出一种基于群体智能的自组织网络SON (Self-Organizing Network)中的服务质量QoS (Quality of Service)单播路由机制,通过引入模糊数学相关知识描述不精确路由信息,通过引入微观经济学相关知识兼顾网络提供方和用户利益,基于蚂蚁网络寻找使各方效用达到或接近Nash均衡下Pareto最优的QoS单播路径.基于网络仿真器NS2 (Network Simulator 2)对该机制进行了仿真实现和性能评价,结果表明,该机制在用户效用、网络提供方效用、路径综合评价值、Nash均衡下Pareto最优比和路由成功率等方面具有良好性能.     

An introduction to physical theory of molecular evolution

This work is a tutorial in Molecular Evolution from the point of view of Physics. We discuss Eigen's model, a link between evolutionary theory and physics. We will begin by assuming the existence of (marco) molecules or replicators with the template property, that is, the capacity to self-replicate. According to this assumption, information will be randomly generated and destroyed by mutations in the code (i.e., errors in the copying process) and new bits of information will be fixed (made stable) by the existence of an external pressure on the system (i.e., selection), and the ability of the molecules to replicate themselves. Our aim is to build a model in order to describe molecular evolution from as general a standpoint as possible. As we will see, even very simple models from the theoretical point of view will have surprisingly deep consequences.     

基于自组织特征映射聚类算法的研究与应用

讨论了基于自组织特征映射网络聚类算法的基本原理，并给出了基于关系数据库的具体实现方法，通过对实例的具体测试，证明算法是有效的，并对算法的参数进行了讨论．     

Self-Organizing Maps and Support Vector Regression as aids to coupled chromatography: illustrated by predicting spoilage in apples using volatile organic compounds

The paper describes the application of SOMs (Self-Organizing Maps) and SVR (Support Vector Regression) to pattern recognition in GC-MS (gas chromatography-mass spectrometry). The data are applied to two groups of apples, one which is a control and one which has been inoculated with Penicillium expansum and which becomes spoiled over the 10-day period of the experiment. GC-MS of SPME (solid phase microextraction) samples of volatiles from these apples were recorded, on replicate samples, over time, to give 58 samples used for pattern recognition and a peak table obtained. A new approach for finding the optimum SVR parameters called differential evolution is described. SOMs are presented in the form of two-dimensional maps. This paper shows the potential of using machine learning methods for pattern recognition in analytical chemistry, particularly as applied to food chemistry and biology where trends are likely to be non-linear.     

基于集群的增量分布式RSOM聚类方法

对于海量和高维的大规模数据聚类问题,其数据个数以及模式种类通常处于一个动态增加的过程之中,为此进行增量、并行算法的设计,以提供更好的计算能力是十分必要的.注意到人脑增量学习的本质和RSOM(Recursive Self-Organizing Map)的层次化、分布式结构特点,本文研究了基于高性能集群并行计算环境的增量、分布式RSOM并行算法,并以视频图像特征集实例证实了算法的可行性.     

基于自组织可增长映射的移动机器人仿生定位算法研究

为提高移动机器人在同步定位和地图构建(SLAM)中的定位精度,该文提出一种基于自组织可增长映射 (GSOM)的仿生定位算法。该方法将位置细胞的激活特性和神经网络输出层神经元建立响应连接,通过GSOM神经网络构建空间的拓扑地图,利用感知距离信息实现位置细胞的激活响应从而估计机器人位置,以此还原机器人的运行路径。实验结果表明细胞间隔R对定位精度有较大影响,选取合适的细胞间隔能有效地减少神经网络的学习时间,提高定位精度,该文算法平均误差在0.153 m以内,定位精度达到90.243%,均优于原有算法。经验证该文算法建立的模型能够实现机器人的空间位置表征,提高了机器人在实验场景下的定位精度,表现出良好的位置估计性能。     

浅析TD-LTE自优化功能实现方法

自优化功能是LTE系统中自组网技术的关键功能之一,多个无线网络参数将直接影响优化结果。文章对LTE中可调优化参数的相关性进行深入分析,以定量和定性两个方面准确地衡量各个参数之间的关系以及其自身重要程度,并提出自组网优化架构及相关流程,为工程实施提供指引。     

用于光纤机敏材料与结构损伤估计的人工神经网络

本文以光纤机敏材料与结构中的损伤估计为目的,根据光纤阵列传感信号处理的需要,在给出人工神经网络处理原理与结构基础上,结合应用详细地阐述了适用的反向传播神经网络(BP)模型、自组织特征映射神经网络(Kohonen)模型及其变化形式(LVQ1,LVQ2,LVQ3,LVQ4及LVQ5等),同时给出了仿真实验的结果.     

基于SOM神经网络的航舵故障分类方法

为解决航舵故障诊断的复杂非线性模式分类问题,提出一种基于自组织特征映射(SOM)神经网络的航舵故障诊断方法,构造一个2层SOM神经网络,训练后多个权值向量位于输入向量聚类中心,实现快速有效的自适应分类.仿真结果表明:SOM网络经过100次训练即可实现聚类,对有限故障测试样本分类准确率可达90％,对航舵故障诊断具有一定的参考价值.