关于DNA序列分类问题的模型

本文提出了一种将人工神经元网络用于 DNA分类的方法 .作者首先应用概率统计的方法对 2 0个已知类别的人工 DNA序列进行特征提取 ,形成 DNA序列的特征向量 ,并将之作为样本输入 BP神经网络进行学习 .作者应用了 MATLAB软件包中的 Neural Network Toolbox(神经网络工具箱 )中的反向传播 ( Backpropagation BP)算法来训练神经网络 .在本文中 ,作者构造了两个三层 BP神经网络 ,将提取的 DNA特征向量集作为样本分别输入这两个网络进行学习 .通过训练后 ,将 2 0个未分类的人工序列样本和 1 82个自然序列样本提取特征形成特征向量并输入两个网络进行分类 .结果表明 :本文中提出的分类方法能够以很高的正确率和精度对 DNA序列进行分类 ,将人工神经元网络用于 DNA序列分类是完全可行的     

用二维游动描述DNA系列

在文献中,DNA序列曾被描述为一维游动和三维游动.对前者,一个游动对应于多个DNA序列;对后者,游动和DNA序列一一对应.我们发现在三维游动(xn,yn,zn)中,由xn,yn和zn中任意有序的两个给出的二维游动已经与DNA序列一一对应,且余下的一维游动由该二维游动完全决定.因此,二维游动似乎是描述DNA序列最合适的模型.4个碱基A,C,G和T共有4 !=24个排序.每一个排序都给出DNA序列用二维游动的一种描述.两个游动(x'n,y'n)和(x"n,y"n)被看作是等价的,如果(x'n,y'n)=(εx"n,δy"n)或(εy"n,δx"n),这里ε=±1,且δ=±1.于是这24个类型的游动被分成三个等价类;它们的代表分别是(xn,yn),(yn,zn),和(xn,zn),这里(xn,yn,zn)正好是张和张的三维游动.     

最优组合预测的短期气候预报建模研究

以预报量序列建立均生函数短期气候预报模型及根据500hPa月平均高度场预报因子分别建立的BP网络模型、回归预报模型为基础,用"误差绝对值和最小"作为最优准则,建立月平均降水量的短期气候组合预测模型.采用线性规划方法计算得到组合预测模型的各权系数,对这种短期气候组合预测模型的预报能力进行了分析研究,结果表明,该组合预测模型的预报精度优于各子方法,具有很好的应用价值.     

基于支持向量机的神经元形态分类

针对神经元的空间几何形态特征分类问题以及神经元的生长预测问题进行了探讨.结合神经元的形态数据,分别建立了基于支持向量机的神经元形态分类模型、基于主成分分析和支持向量机的神经元分类模型以及基于遗传算法和RBF网络的神经元生长预测模型,在较合理的假设下,对各个模型进行求解,得到了较理想的结果.     

DNA序列的分类模型

本文针对 DNA序列分类这个实际问题 ,提出了相应的数学模型 .为了很好的体现 DNA序列的局部性和全局性的特征 ,我们给出了衡量分类方法优劣的标准 ,即在满足一定限制条件的情况下 ,是否能充分反映序列的各方面特性 .依据我们提出的判别标准 ,单一标准的分类是无法满足要求的 .我们的方法是侧重点不同的三种方法的综合集成 .这三种方法分别体现了序列中元素出现的概率 ,序列中元素出现的周期性 ,序列所带有的信息含量 .利用这个方法 ,完成了对未知类型的人工序列及自然序列的分类工作 .最后 ,对分类模型的优缺点进行了分析 ,并就模型的推广作了讨论     

指数型弥散过程的解析解

对具有指数型弥散系数的弥散过程建立了数学模型,应用积分变换把变系数的偏微分方程变为变系数的常微分方程,应用超几何函数方法和反演技术得到了两类边界条件下的解析解.利用解析解的表达式和计算结果,分析了指数型弥散过程和经典线性弥散过程的差异.     

2011年研究生建模竞赛B题的评阅综述

本题从一项科研项目中提炼、并结合目前成为关注热点的隐身技术而设计,侧重于数学建模.结合题中的2个问题,可以抽象出3个平时比较少见的数学模型:几何模型,反射投影模型和积分方程模型.在竞赛中,前2个模型都有部分同学正确地得出,可惜的是,问题2所要求的积分方程模型,在近500份答卷,却无人得出,甚为遗憾.问题2属于一个需要同时确定数个彼此关联影响的函数的问题,处理这样问题的基本方法是建立以这些函数为变量的方程组,在这里由于确定相互影响的定量关系必须用积分,所以最终得出的是一个积分方程组.微分积分是大学数学中最基本最重要的概念和方法,由此不难看出,我们的基础教育中的弊病与问题,这需要引起有识之士们的反思.     

基于结构矩阵的DNA序列的相似性模型

通过一维映射把DNA序列转化为时间序列,即把数字1,2,3,4分别分配给组成DNA序列的核苷酸A,T,G,C,用时间序列的结构矩阵来描述DNA序列的结构特征,并根据结构矩阵的一些性质定义了结构矩阵的相似性度量,进而利用结构矩阵之间的相似性度量构建了比较DNA序列的相似性模型,以9个不同物种的β-球蛋白基因的第一个外显子(表1)为例验证了该模型的适用性.并得到了较好得结果.     

GA-BP嵌套算法的理论及应用

分析了BP算法、遗传算法以及GA-BP-APARTING算法的特点,提出了GA-BP-NESTING算法.在人工神经网络的在线学习和离线学习方式下,分别对BP算法、GA算法、GA-BP-APARTING算法和GA-BP-NESTING算法进行了比较研究,研究发现:第一,网络初始权值的赋值对人工神经网络训练影响很大;第二,离线学习方式下GA-BP-NESTING算法效果最佳.     

DNA分类模型

本模型充分利用了所给数据的特点 ,运用统计、最优化等数学方法 ,从已知样本序列中提炼出能较好代表两类特征的关键字符串 ,据此提出量化的分类标准 ,能较好的对任给 DNA序列进行分类 .首先 ,从已知样本序列中用广度优先法选出所有重复出现的字符串 ,并计算其标准化频率及分散度 .然后 ,利用样本数据结合最小二乘法确定两类字符串各自的优先级函数 ,并且逐步优化其参数使之达到稳定 ,提高了可信度 .最后 ,根据优先级函数找出关键词 ,然后确定权数 ,用层次分析法对未知样本进行分类 ,并定出显著水平 ,从而得到了一个比较通用的分类方法 .经过检验 ,此方法对 2 1— 4 0号待测样本进行了很好的分类 ,对后面的1 82个 DNA序列进行同样的操作 ,也有较好的效果     

Discrete-time analogues of integrodifferential equations modelling bidirectional neural networks

We formulate discrete-time analogues of integrodifferential equations modelling bidirectional neural networks studied by Gopalsamy and He. The discrete-time analogues are considered to be numerical discretizations of the continuous-time networks and we study their dynamical characteristics. It is shown that the discrete-time analogues preserve the equilibria of the continuous-time networks. By constructing a Lyapunov-type sequence, we obtain easily verifiable sufficient conditions under which every solution of the discrete-time analogue converges exponentially to the unique equilibrium. The sufficient conditions are identical to those obtained by Gopalsamy and He for the uniqueness and global asymptotic stability of the equilibrium of the continuous-time network. By constructing discrete-time versions of Halanay-type inequalities, we obtain another set of easily verifiable sufficient conditions for the global exponential stability of the unique equilibrium of the discrete-time analogue. The latter sufficient conditions have not been obtained in the literature of continuous-time bidirectional neural networks. Several computer simulations are provided to illustrate the advantages of our discrete-time analogue in numerically simulating the continuous-time network with distributed delays over finite intervals.     

Role and Results of statistical methods in protein fold class prediction

Statistical methods of discrimination and classification are used for the prediction of protein structure from amino acid sequence data. This provides information for the establishment of new paradigms of carcinogenesis modeling on the basis of gene expression. Feed forward neural networks and standard statistical classification procedures are used to classify proteins into fold classes. Logistic regression, additive models, and projection pursuit regression from the family of methods based on a posterior probabilities; linear, quadratic, and a flexible discriminant analysis from the class of methods based on class conditional probabilities, and the nearest-neighbors classification rule are applied to a data set of 268 sequences. From analyzing the prediction error obtained with a test sample (n = 125) and with a cross validation procedure, we conclude that the standard linear discriminant analysis and nearest-neighbor methods are at the same time statistically feasible and potent competitors to the more flexible tools of feed forward neural networks. Further research is needed to explore the gain obtainable from statistical methods by the application to larger sets of protein sequence data and to compare the results with those from biophysical approaches.     

Existence and Attractivity of <Emphasis Type="Italic">k</Emphasis>-Pseudo Almost Automorphic Sequence Solution of a Model of Bidirectional Neural Networks

In this paper we discuss the existence and global attractivity of k-pseudo almost automorphic sequence solution of a model of bidirectional cellular neural networks. We consider the corresponding difference equation analogue of the model system using suitable discretization method and obtain certain conditions for the existence of solution. The k-pseudo almost automorphic sequence solutions generalize the results of pseudo almost periodic, almost periodic and almost automorphic sequences solutions. Moreover the results proved in this paper are new and compliment the existing one.     

Neural network forecasting for seasonal and trend time series

Neural networks have been widely used as a promising method for time series forecasting. However, limited empirical studies on seasonal time series forecasting with neural networks yield mixed results. While some find that neural networks are able to model seasonality directly and prior deseasonalization is not necessary, others conclude just the opposite. In this paper, we investigate the issue of how to effectively model time series with both seasonal and trend patterns. In particular, we study the effectiveness of data preprocessing, including deseasonalization and detrending, on neural network modeling and forecasting performance. Both simulation and real data are examined and results are compared to those obtained from the Box–Jenkins seasonal autoregressive integrated moving average models. We find that neural networks are not able to capture seasonal or trend variations effectively with the unpreprocessed raw data and either detrending or deseasonalization can dramatically reduce forecasting errors. Moreover, a combined detrending and deseasonalization is found to be the most effective data preprocessing approach.     

A CS-AdaBoost-BP model for product quality inspection

Quality inspection is essential in preventing defective products from entering the market. Due to the typically low percentage of defective products, it is generally challenging to detect them using algorithms that aim for the overall classification accuracy. To help solve this problem, we propose an ensemble learning classification model, where we employ adaptive boosting (AdaBoost) to cascade multiple backpropagation (BP) neural networks. Furthermore, cost-sensitive (CS) learning is introduced to adjust the loss function of the basic classifier of the BP neural network. For clarity, this model is called a CS-AdaBoost-BP model. To empirically verify its effectiveness, we use data from home appliance production lines from Bosch. We carry out tenfold cross-validation to evaluate and compare the performance between the CS-AdaBoost-BP model and three existing models: BP neural network, BP neural network based on sampling, and AdaBoost-BP. The results show that our proposed model not only performs better than the other models but also significantly improves the ability to identify defective products. Furthermore, based on the mean value of the Youden index, our proposed model has the highest stability.

     

具有跳跃的随机神经网络的均方稳定性

研究了一类新的具有脉冲跳跃的Hopfield神经网络系统模型,其中脉冲时刻的跳跃是由一般的随机序列所引起,通过运用Lyapunov函数方法,获取了一些新的均方稳定性结果.由于脉冲的跳跃使得不稳定的神经网络变成稳定,因而所得的结果也可以运用到其他相关领域.     

Global exponential stability for interval general bidirectional associative memory (BAM) neural networks with proportional delays

This paper is concerned with interval general bidirectional associative memory (BAM) neural networks with proportional delays. Using appropriate nonlinear variable transformations, the interval general BAM neural networks with proportional delays can be equivalently transformed into the interval general BAM neural networks with constant delays. The sufficient condition for the existence and uniqueness of equilibrium point of the model is established by applying Brouwer's fixed point theorem. By constructing suitable delay differential inequalities, some sufficient conditions for the global exponential stability of the model are obtained. Two examples are given to illustrate the effectiveness of the obtained results. This paper ends with a brief conclusion. Copyright © 2016 John Wiley & Sons, Ltd.     

一类细胞神经网络输入—输出控制

对于一类细胞神经网络,以系统的输入、输出的反馈权值为参数,构成参数空间,引入几何方法,将参数空间分解分块成有限个区域,当系统参数在某一确定的区域上时,研究系统的输入—输出间关系,并给出输入、输出之间控制的一类判别方法.