Designing a Hybrid Intelligent Mining System for Credit Risk Evaluation

In this study, a novel hybrid intelligent mining system integrating rough sets theory and support vector machines is developed to extract efficiently association rules from original information table for credit risk evaluation and analysis. In the proposed hybrid intelligent system, support vector machines are used as a tool to extract typical features and filter its noise, which are different from the previous studies where rough sets were only used as a preprocessor for support vector machines. Such an approach could reduce the information table and generate the final knowledge from the reduced information table by rough sets. Therefore, the proposed hybrid intelligent system overcomes the difficulty of extracting rules from a trained support vector machine classifier and possesses the robustness which is lacking for rough-set-based approaches. In addition, the effectiveness of the proposed hybrid intelligent system is illustrated with two real-world credit datasets.     

Positive observer design for positive Markovian jump systems with partly known transition rates

The paper is concerned with positive observer design for positive Markovian jump systems with partly known transition rates. By applying a linear co-positive type Lyapunov-Krasovskii function, a sufficient condition is proposed to ensure the stochastic stability of the error positive system and the existence of the positive observer, which is computed in linear programming. Finally, an example is given to demonstrate the validity of the main results.     

Spectral Properties and Positivity of Flows in Infinite Networks with Dynamic Boundary Control Nodes

In this paper we study transport processes on infinite networks with dynamic boundary control nodes. These flows can be modeled by operator semigroups on a suitable Banach space. Using functional analytical and graph theoretical methods, we investigate its spectral properties of the system and positivity of the semigroup under appropriate assumptions on the network.     

三回路驾驶仪开环穿越频率约束极点配置设计

针对在三回路驾驶仪设计中,希望对开环穿越频率进行约束,以保证设计完成后的系统在考虑驾驶仪各硬件动态特性后仍能满足稳定性要求.在极点配置的计算方法基础上,构造以系统非主导极点为变量,以开环穿越频率为约束的非线性方程,利用方程求解程序求解相应的非主导极点值,进而完成驾驶仪设计.驾驶仪设计实例验证表明,这一方法便捷可行,非常适用于三回路驾驶仪工程设计.     

一类模糊跳变系统的采样控制器设计

针对含有马尔可夫跳变参数的模糊系统,采用多李亚普诺夫函数方法,设计采样控制器,保证模糊跳变系统指数均方稳定和随机稳定。为便于工程应用,考虑到控制系统多为数字控制系统,计算机的输入、输出控制信号是数字信号,而被控对象常为连续时间系统,文中采用离散的控制器控制连续的被控对象。系统模型中的每个跳变模态对应的子系统均是T-S模糊系统,对每个模糊子系统采用平行分布补偿的控制方法,保证子系统渐近稳定。控制器的求解等效为线性矩阵不等式的可解性问题,便于求解。数值仿真结果验证了方法的可行性和有效性。     

基于协方差矩阵重构的单基地MIMO阵列无网格DOA估计方法

提出了一种单基地多输入多输出(multiple-input multiple-output, MIMO)阵列中的协方差矩阵重构的无网格波达方向(direction-of-arrival, DOA)估计方法。该方法通过降维处理将MIMO阵列等效为信噪比(signal-to-noise ratio, SNR)提升的均匀线列阵,将目标方位估计问题转化为混合范数最小化(mixed norm minimization, MixNM)稀疏信号重构问题。进一步给出了与该稀疏重构问题等价的基于网格的凸优化问题,并模型化为半定规划来求解。为了解决网格大小影响估计性能的问题,利用了等价均匀线列阵的托普利兹结构,模型化为半定规划问题来重构无噪声协方差矩阵,最后通过范德蒙分解来估计目标方位。与传统的基于MixNM方位估计方法相比,该方法减少了优化变量个数。与其他离网格方法相比,该方法估计精度不受网格大小的影响,且能够估计相干源目标。实验仿真验证了该方法的有效性。     

干扰效果在线评估参数筛选与特征表示方法

针对利用雷达侦察信号进行干扰效果在线评估时参数冗余、信号变化程度判别不清的问题,提出雷达干扰效果在线评估参数筛选与特征表示方法。对多功能海上雷达信号,利用信息熵筛选剧烈变化参数,通过盒维数和皮尔逊相关系数提取信号变化特征,结合支持向量机实现对未知威胁的干扰效果在线评估。仿真实验表明,当信号参数偏离误差小于10%时,新方法的评估准确率高于92%,显著提高了雷达干扰效果在线评估的可靠性。     

基于计算机仿真的Buck-Boost电路研究

Buck-Boost电路中含有丰富的非线性现象。它工作过程中电路拓扑结构的循环切换导致了谐波、分叉和混沌等非线性行为。基于PSPICE仿真,研究了电流控制DC/DC Buck-Boost开关转换器中的倍周期现象。而且,建立了开关转换器的数学模型和叠代映射来解释这种非线性现象。基于MATLAB仿真,从叠代映射中得到了系统分叉图。     

Adaptive Control of the Structural Balance for a Class of Complex Dynamical Networks

In social networks, the structural balance is a state of a group of individuals(nodes) with established mutual relationships(connection relationships) between them. It is easy to see that a social network can be described by a complex dynamical network model composed of the nodes subsystem(NS) and the connection relationships subsystem(CS), where the two subsystems are usually coupled with each other. It implies that the dynamic changes of nodes' states may cause the structural balance in CS. However, few papers have discussed the relationship between the structural balance and the specific dynamic changes of the nodes' states. This paper proposes a model of complex dynamical networks, and mainly focuses on the dynamic changes of states in NS which can lead to the structural balance in CS. It is proved that if each state in NS is doing a specific dynamic motion via the controller with the parameter adaptive law, then the CS can track a given structural balance matrix via the effective coupling and the structural balance can be achieved. Such a result can be regarded as an explanation of the relationship between the structural balance and the specific dynamic changes of the nodes' states. Finally, the simulations verify the effectiveness of the proposed method.     

基于改进智能水滴算法的动态车辆配送路径优化

针对当前车辆配送过程中存在的配送路径不合理、配送效率低和需求不确定性等问题,提出一种基于改进智能水滴算法的动态车辆配送路径优化方法。构建软时间窗惩罚函数,考虑顾客对配送时间的要求,建立顾客满意度函数。综合车辆配送过程的车速、货损成本、惩罚成本、顾客满意度等特征,建立车辆路径优化模型。采用智能水滴算法对车辆路径优化模型进行求解,使用灰狼优化算法改善智能水滴算法的搜索能力,获取最优路径。实验结果表明该方法能够提供实时优化的路径,减少调配成本。