基于离散余弦变换的车道识别算法

车道识别技术是自动驾驶领域的研究热点。通过对车载摄像机获取的公路车道线图像特征的分析,提出了一种基于图像频率域特征的车道识别算法。该算法的核心是提取车道线在离散余弦变换域的特征,再结合道路模型的先验知识利用贝叶斯决策原理,识别出路面上的车道线。实验表明,该算法在不同的路面和光照条件下均可得到良好的识别效果。     

基于改进粒子群算法的中药提取过程PID优化控制

提出了一种适合于中药提取过程的基于改进粒子群算法的PID优化控制方法;针对粒子群算法存在早熟和局部收敛的问题对算法进行了改进,采用一种非线性动态自适应方法作为惯性因子权值调整策略,使惯性权值随粒子目标值的变化而自动改变;将该法应用于中药提取温度控制系统PID控制器参数优化设计,首先利用广义Hermite-Biehler定理计算控制对象的PID控制器参数稳定域;然后在参数稳定域范围内采用改进粒子群算法寻优得到了满足指定性能指标(ITAE)最小的最佳控制器参数值;最后针对中药提取工段的温度控制二阶时滞系统进行了仿真,验证了该方法的有效性。     

基于迁移学习的无监督跨域人脸表情识别

本文主要研究了基于迁移学习的无监督跨域人脸表情识别。在过去的几年里,提出的许多方法在人脸表情识别方面取得了令人满意的识别效果。但这些方法通常认为训练和测试数据来自同一个数据集,因此其具有相同的分布。而在实际应用中,这一假设通常并不成立,特别当训练集和测试集来自不同的数据集时,即跨域人脸表情识别问题。为了解决这一问题,本文提出将一种基于联合分布对齐的迁移学习方法(domain align learning)应用于跨域人脸表情识别,该方法通过找到一个特征变换,将源域和目标域数据映射到一个公共子空间中,在该子空间中联合对齐边缘分布和条件分布来减小域之间的分布差异,然后对变换后的特征进行训练得到一个域适应分类器来预测目标域样本标签。为了验证提出算法的有效性,在CK+、Oulu-CASIA NIR和Oulu-CASIA VIS这3个不同的数据库上做了大量实验,实验结果证明所提算法在跨域表情识别上是有效性的。     

灰色二层多目标线性规划问题及其解法

针对二层多目标线性规划问题,结合灰色系统的特性,提出了一般灰色二层多目标线性规划问题,并给出了模型的相关定义和定理.针对漂移型灰色二层多目标线性规划问题,提出一种具有全局收敛性质的求解算法.首先通过线性加权模理想点法把多目标转化为单目标;然后当可行域为非空紧集时,利用库恩塔克条件把双层转化为单层,再利用粒子群算法搜索单目标单层线性规划即可得到原问题的解;最后通过算例表明了该算法的有效性.     

基于最小包含球的大数据集域自适应快速算法

相同应用领域,不同时间、地点或设备检测到的数据域不一定完整。文中针对如何进行数据域间知识传递问题,提出相同领域的概率分布差异可用两域最小包含球中心点表示且其上限与半径无关的定理。基于上述定理,在原有支持向量域描述算法基础上,提出一种数据域中心校正的领域自适应算法,并利用人造数据集和KDDCUP99入侵检测数据集验证该算法。实验表明,这种领域自适应算法具有较好的性能。     

基于稀疏表示的雷达辐射源信号级融合识别算法

针对现有融合识别算法难以兼顾信息完备性和节点通信数据量的问题,提出一种基于信号稀疏表示的雷达辐射源信号级融合识别算法。该方法将接收信号投影到稀疏域并进行压缩,从而在稀疏域完成融合,最后利用融合后的稀疏系数进行识别。该方法既降低了通信数据量,又较好地保证了信息的完整性。仿真实验表明,相对于单一传感器和决策级融合,所提出的方法可有效提高信号识别性能。     

基于配对方法的自动定理证明

ＰｅｔｅｒＢ．Ａｎｄｒｅｗｓ提出了自动定理证明的配对方法的理论和算法．本文针对该算法的缺点，给出了一个无需回溯的实现算法，并得到一个高阶逻辑的自动定理证明系统.     

基于嵌入式图像处理的仪表自动识别技术研究

针对远程抄表系统中的仪表读数识别问题,提出了一种有效的识别算法。依据仪表图像的特点,在均值滤波、形态学运算以及最大类间方差法对仪表图像预处理之后,利用轮廓检测以及连通域分割等方法对表盘区域和单个数字进行分割,并依据数字结构特征,对分割出的数字进行识别。将该算法移植到以S3C2440A为核心的ARM-Linux系统中进行测试,可以有效识别,获得了满意的效果。     

一种新型ARTII无监督分类算法

ART是一种典型的、无监督的、能够对复杂输入模式实现自稳定和自组织识别的神经网络。该文针对标准ARTII算法的预处理信号畸变问题,提出了新的非线性变换函数和竞争学习算法,该新型ARTII算法的输入域由原来的非负实数域扩大到整个实数域,且分类性能良好,以多种分类问题对该算法的性能进行验证,结果表明该算法性能优良,能自适应地识别未知故障模式,分类准确。     

一种新型ARTⅡ无监督分类算法

ＡＲＴ是一种典型的、无监督的、能够对复杂输入模式实现自稳定和自组织识别的神经网络。该文针对标准ＡＲＴⅡ算法的预处理信号畸变问题,提出了新的非线性变换函数和竞争学习算法,该新型ＡＲＴⅡ算法的输入域由原来的非负实数域扩大到整个实数域,且分类性能良好,以多种分类问题对该算法的性能进行验证,结果表明该算法性能优良,能自适应地识别未知故障模式,分类准确。     

Feedback control on Nash equilibrium for discrete-time stochastic systems with Markovian jumps: Finite-horizon case

In this paper, we consider the feedback control on nonzero-sum linear quadratic (LQ) differential games in finite horizon for discrete-time stochastic systems with Markovian jump parameters and multiplicative noise. Four-coupled generalized difference Riccati equations (GDREs) are obtained, which are essential to find the optimal Nash equilibrium strategies and the optimal cost values of the LQ differential games. Furthermore, an iterative algorithm is given to solve the four-coupled GDREs. Finally, a suboptimal solution of the LQ differential games is proposed based on a convex optimization approach and a simplification of the suboptimal solution is given. Simulation examples are presented to illustrate the effectiveness of the iterative algorithm and the suboptimal solution.     

A Polynomial-Time Algorithm to Find von Neumann-Morgenstern Stable Matchings in Marriage Games

This paper considers von Neumann-Morgenstern (vNM) stable sets in marriage games. Ehlers (Journal of Economic Theory 134: 537–547, 2007) showed that if a vNM stable set exists in a marriage game, the set is a maximal distributive lattice of matchings that includes all core matchings. To determine what matchings form a vNM stable set, we propose a polynomial-time algorithm that finds a man-optimal matching and a woman-optimal matching in a vNM stable set of a given marriage game. This algorithm also generates a modified preference profile such that a vNM stable set is obtained as the core of a marriage game with the modified preference profile. It is well known that cores of marriage games are nonempty. However, the nonemptiness of cores does not imply the existence of a vNM stable set. It is proved using our algorithm that there exists a unique vNM stable set for any marriage game.     

Conditions for optimality and transition surfaces using the reprisal concept†

The concept of optimality in zero-sum, two-player differential games introduced by the authors in a previous paper is studied. Furthermore, a number of tools to aid in the study of differential games in which there exist ‘ non-terminating ’ strategies are developed.

In the all-terminating case it is shown that for C^(z)) strategies or for strategies containing a specified class of discontinuities, satisfying Isaacs' equation is both necessary and sufficient for optimality. In linear, all-terminating games, easily verifiable necessary and sufficient conditions are given and it is shown that, subject to one condition, points of transition surfaces must necessarily be in the zero-set of one of two switching functions.

In ‘ non-terminating ’ games, satisfying Isaacs' equation is necessary for optimality but no longer sufficient. Sufficiency conditions for optimality in these games are then proven along with three alternative necessary conditions which points of transition surfaces must satisfy. An example illustrating the application of these results is included together with a heuristic discussion of the ‘ double transition surface ’ phenomenon.     

基于预测控制的时滞多机器人编队脉冲控制

针对多机器人编队控制的时滞问题, 提出一种基于预测控制的脉冲控制方法. 首先, 利用一致性思想将多机器人编队控制转换为系统稳定性问题; 然后构建预测模型, 采用脉冲控制协议, 利用Schur 稳定性定理推导实现多机器人编队控制的充分条件; 最后, 在数值仿真中随机设置一种包含生成树的通信拓扑关系, 并比较了不同采样时间间隔下时滞系统的控制效果. 仿真结果验证了所提出方法的有效性.

     

线性Markov 切换系统的随机Nash 微分博弈及混合H2/H∞ 控制

研究线性Markov切换系统的随机Nash微分博弈问题。首先借助线性Markov切换系统随机最优控制的相关结果,得到了有限时域和无线时域Nash均衡解的存在条件等价于其相应微分(代数) Riccati方程存在解,并给出了最优解的显式形式;然后应用相应的微分博弈结果分析线性Markov切换系统的混合H2/H∞控制问题;最后通过数值算例验证了所提出方法的可行性。     

一类定量微分对策理论中最优策略的算法及其收敛性

本文利用不动点原理讨论了一类定量微分对策理论中最优策略的计算方法问题.首先构 造出了一种迭代方法,然后利用不动点原理分析了该迭代法的收敛性.本文给出的方法还可 用于一类Nash微分对策的Nash策略的分散计算方法.     

A Nash algorithm for a class of non-zero sum differential games

An algorithm is proposed for solving a class of non-zero sum differential games. The ‘ping-pong’ algorithm assumes initial discrete control values, and then integrates a set of state equations forward and the corresponding set of co-state equations backward, alternately, until a stopping criterion is met. Cost calculation on each forward integration run provides a means of measure of cost improvement, and hence the stopping criterion based on convergence within some small value.

This algorithm is tested on an appropriate nonzero sum differential game: the Apartment Heating Problem. In this problem, the conflict arises from the system equations. Each tenant desires to heat his apartment at a minimum cost. Each tenant is free to adjust his control such that his desires are met. But since these tenants share a common wall, their desires may not be achieved, as heat can flow through this wall. In addition, each tenant cannot measure the state, so the problem is ‘open loop’ in the sense of control theory.

This problem is formulated and solved under various assumptions on the number of apartments involved, the different comfort levels of the tenants, and the range of admissible controls. Results are tabulated and discussed. Each solution is checked to insure that it meets the criterion for a Nash Equilibrium Solution.     

Weighted pseudo-almost automorphic solutions of high-order Hopfield neural networks with neutral distributed delays

In this paper, a class of high-order Hopfield neural networks with neutral distributed delays is considered. Some sufficient conditions are obtained for the existence, uniqueness and global exponential stability of weighted pseudo-almost automorphic solutions for this class of networks by employing the Banach fixed-point theorem and differential inequality techniques. The results of this paper are completely new. An example is given to show the effectiveness of the proposed method and results.

     

Efficient Parallel Solution of Nonlinear Parabolic Partial Differential Equations by a Probabilistic Domain Decomposition

Initial- and initial-boundary value problems for nonlinear one-dimensional parabolic partial differential equations are solved numerically by a probabilistic domain decomposition method. This is based on a probabilistic representation of solutions by means of branching stochastic processes. Only few values of the solution inside the space-time domain are generated by a Monte Carlo method, and an interpolation is then made so to approximate suitable interfacial values of the solution inside the domain. In this way, a fully decoupled set of sub-problems is obtained. This method allows for an efficient massively parallel implementation, is scalable and fault tolerant. Numerical examples, including some for the KPP equation and beyond are given to show the performance of the algorithm.