A Forward Selection Method on Customer Credit

In this paper, we discuss a selection and evaluation method of customer credit for the commercial bank loans operation, and put forth a forward selection model by optimization techniques. At last, we also give an example to analyze its application.     

GFMIMU/GPS组合导航系统信息融合技术研究

GFMIMU/GPS(Gyroscope Free Micro Inertial Measurement Unit/Global Positioning System)组合导航系统具有抗高g值冲击、低成本、长寿命、较高精度等优点,在低成本精确制导武器和微小型无人机具有广阔的应用前景。针对工程应用中信息融合的精度和实时性两方面的要求,运用基于模型误差预测的扩展卡尔曼滤波MEP-EKF(Extended Kalman Filter base on Model Error Predictive)方法,将MEMS(Micro Electromechanical Systems)加速度计的误差作为模型误差来考虑,对GFMIMU/GPS组合导航系统进行建模仿真,将其与EKF和UKF(Unscented Kalman Filter)方法进行了仿真比较,在方位误差角的估计上取得了比他们精度高的仿真结果,而且MEP-EKF所需时间是UKF的10%.     

两因素HJM模型下债券、期货、期权的定价

在HJM模型下考虑远期利率由2个独立布朗运动驱动的零息票债券的期限结构,给出零息票债券和债券期货的定价公式,以及债券期货期权的定价公式。     

防火墙技术及其在Linux下的实现

讨论了防火墙技术及分类，并以某学校校园网为例，分别介绍了Cisco PIX515E常规硬件防火墙技术和基于Linux的Iptables软件防火墙技术及其配置方法，实现包过滤、NAT和数据包处理等功能，确保网络安全。     

一种适于强横向变速的高阶差分正演模拟方法

波动方程正演模拟法相对于射线法具有精度高、效率低的特点。为了提高其效率 ,提出了一种高阶差分正演模拟方法。该方法考虑了速度场局部的强横向变化 ,适于复杂介质的正演模拟 ;在相同精度下 ,高阶差分的空间横向间隔可取为低阶差分的 2～ 4倍 ,有较高的计算效率 ;高阶差分加上合适的边界条件能较好地解决网格频散和边界效应问题。通过对Marmousi模型的试算 ,验证了该方法对复杂速度模型的适应性、有效性和实用性。     

瑞利噪声环境中水下目标辐射信号增强算法

提出了基于高阶累积量广义函数迭代的自适应滤波算法，证明了该算法的收敛性，给出了广义函数的几种具体表示式。用该算法对瑞利噪声环境中水下目标辐射信号谱增强进行了仿真研究。结果表明：该算法具有很强的抑制瑞利(白或色)噪声的能力。因此，该算法在提高水下探测系统对水下目标的检测能力方面有重要的应用价值。     

Researching on quadrature conversion structures For an UWB demonstrative receiver

1. INTRODUCTION As the development of technologies of digital signal processing and integrated circuits, the structure of wireless communication system has been improved. Many schemes for software defined radio (SDR) systems have been developed since 1995, and they can be divided into five tiers of solutions according to their developing history and their definitions[1]. The five tiers are conventional hardware-implemented scheme; software-controlled radio scheme; SDR, that implements m…     

PEAK COVARIANCE STABILITY OF A RANDOM RICCATI EQUATION ARISING FROM KALMAN FILTERING WITH OBSERVATION LOSSES

We consider the stability of a random Riccati equation with a Markovian binary jump coefficient. More specifically, we are concerned with the boundedness of the solution of a random Riccati difference equation arising from Kalman filtering with measurement losses. A sufficient condition for the peak covariance stability is obtained which has a simpler form and is shown to be less conservative in some cases than a very recent result in existing literature. Furthermore, we show that a known sufficient condition is also necessary when the observability index equals one.     

船舶运动与受扰Kalman估计精度的统计分析

考察船舶水动力参数在标称值附近按均匀分布发生随机变化时,船舶纵向运动姿态及受扰Kalman估计的统计性能.针对某船,在5级海情,18节航速及45度航向常规工况下,当船舶水动力系数按均匀分布发生士10%、±20%随机变化时,给出船舶姿态及受扰Kalman估计精度的概率建模方法及应用.仿真结果表明,当水动力系数出现摄动时,估计精度服从对数正态分布,平均估计精度与未出现摄动时相比无显著变化.     

一个Markov转移概率函数的确定

利用柯尔莫哥洛夫向前方程计算了电话呼唤次数的随机过程的转移概率函数。