共查询到18条相似文献,搜索用时 863 毫秒
1.
2.
3.
智能粒子滤波通过借鉴遗传算法思想能够减轻粒子退化现象。在基于遗传算法的智能粒子滤波基础上,该文提出对低权值粒子的改进的智能粒子滤波(IIPF)处理策略。在对粒子进行分离、交叉后,优化遗传算子,对低权值粒子进行自适应处理。低权值粒子根据权值大小自行判断是否为底层粒子;底层粒子将直接进行变异,其余低权值粒子将根据变异概率随机变异。仿真结果表明,改进的智能粒子滤波(IIPF)性能优于智能粒子滤波、一般粒子滤波算法和拓展卡尔曼滤波。在1维仿真实验中,改进的智能粒子滤波误差较一般粒子滤波算法和智能粒子滤波分别降低了10.5%和8.5%,且具有更好的收敛性;在多维仿真实验中,改进的智能粒子滤波较智能粒子滤波在高度均方根误差和平均误差上分别降低了8.5%和7.5%,在速度均方根误差和平均误差上分别降低了11.5%和7.6%;在乘性噪声和非高斯随机噪声中,改进的智能粒子滤波依旧有10%以上的性能优势。 相似文献
4.
5.
传统粒子滤波(PF)直接采用状态转移先验分布作为重要性密度函数来近似后验概率密度函数,使得后验概率密度函数未包含量测信息。针对此问题,提出了一种改进高阶容积粒子滤波(CPF)的系统状态估计算法。算法采用七阶正交容积卡尔曼滤波(7th-CQKF)对PF的粒子进行传递,使得先验分布更新阶段融入最新量测信息;通过7th-CQKF设计重要性密度函数,提高对状态后验概率密度的逼近程度;通过反比例函数计算粒子权重,突出大噪声粒子与小噪声粒子权重差别,提高粒子有效性。仿真结果表明,改进高阶容积粒子滤波的估计精度高于容积粒子滤波(CPF)。 相似文献
6.
本文针对EKPF算法在固定单站无源定位目标跟踪的应用中运算量大、实时性差的问题,通过对部分粒子进行EKF采样,将EKPF算法进行改进,改进的EKPF算法不仅有效降低了运算量,同时增加了粒子的多样性,使粒子集更能体现概率密度函数的真实分布。Matlab仿真表明,与传统的EKPF算法相比,改进算法在保证滤波性能基本不变的前提下,算法运算量大幅下降。 相似文献
7.
提出了基于雁群启示的粒子群优化算法改进的AdaBoost.M2-SVM算法.首先训练多个支持向量机作为弱分类器,用AdaBoost.M2算法将多个弱分类器集成为最终的强分类器,实现多类分类;采用GeesePSO算法对AdaBoost.M2算法计算出的权值进行优化得到一组最优的权值,提高最终强分类器的提升能力.实验结果表明,在低信噪比语音识别中,与SVM相比,改进的AdaBoost.M2-SVM表现出更好的泛化能力,提高了识别准确率. 相似文献
8.
9.
10.
采用高斯粒子滤波算法进行姿态估计算法设计,将四元数离散方程作为状态方程。算法由采样调节粒子、采样粒子、权值计算、均值协方差计算和Cholesky 5个模块组成。通过采用非标准化权值计算四元数"平均"值和协方差阵,并且改写协方差阵计算公式,实现流水线高斯粒子滤波算法。同时提出了并行化设计方案,利用FPGA剩余资源进一步优化运行速率。给出的简化粒子滤波算法与高斯粒子滤波算法设计不仅可用于无人机姿态估计,对于其他非线性估计问题及应用亦适用。仿真结果表明了本设计的可行性和有效性。 相似文献
11.
H.W. Schüssler 《Signal processing》1983,5(4):319-323
The common error analysis of a numerical calculation yields mean and variance of the error, if a stochastic model is used. This paper deals with the question, up to which bit the result of a calculation can be considered as being correct with a certain probability, if in addition the probability density function of the error is known. Results will be presented especially for the case of a Gaussian distribution of the error. 相似文献
12.
改进的概率假设密度滤波多目标检测前跟踪算法 总被引:4,自引:1,他引:3
基于概率假设密度滤波(Probability Hypothesis Density,PHD)的检测前跟踪(Track before detect,TBD)技术可以有效解决未知目标数的弱小点目标检测前跟踪问题.文章针对现有PHD-TBD算法存在目标数估计不准、目标发现延时较久的问题进行研究.从标准PHD滤波出发,更为合理地推导出PHD-TBD算法的粒子权重更新计算表达式,实现对目标数的准确估计;同时利用贝叶斯滤波理论,推导出基于量测的新生粒子概率密度采样函数,完成对目标的快速发现.仿真实验表明,与现有的PHD-TBD相比,改进算法能够适应目标扩散情况,准确估计目标数目,并实现对目标的快速发现和位置准确估计. 相似文献
13.
The probability density function for the amplitude of a Gaussian-shaped pulse of unknown arrival time is derived together with its mean and variance, when the time argument of the pulse is randomly distributed according to a Gaussian probability distribution or a uniform distribution. Then using the amplitude density as a prior distribution, the marginal density function for the pulse plus stationary Gaussian noise and its attendant expression for the probability of detection are derived. Applications to the calculation of detection probabilities in the presence of pulse peak location errors are cited. 相似文献
14.
经典序贯蒙特卡罗概率假设密度(Sequential Mote Carlo Probability Hypothesis Density, SMC-PHD)滤波中, 将目标状态转移密度函数做为建议密度函数, 没有利用当前观测信息, 导致大部分预测粒子状态偏离目标真实状态, 粒子退化严重.针对上述问题, 提出利用均方根容积卡尔曼滤波产生建议密度函数, 对其进行采样得到预测粒子状态, 该方法有严格理论基础, 能有效减轻SMC-PHD滤波中的粒子退化, 且适用性很强.仿真实验对比了该算法、经典SMC-PHD和基于无迹卡尔曼的SMC-PHD算法的跟踪性能, 验证了该方法无论对势估计还是对目标状态估计的精度都优于其他两种算法. 相似文献
15.
16.
17.
This paper presents a probability density function formula for predicting the polarization dependent loss (PDL) in an optical transmission system composed of passive devices and connecting fibers. A new calculation technique, which enables the probability density function formula to be obtained theoretically, is used instead of the most complicated part of the Muller-matrix or Jones-matrix calculations, which has been thought to be necessary for analyzing PDL. This technique involves calculation of the transmission coefficients of the transmission system and its devices from their PDLs. In the theoretical development, the central limit theorem is used as the sole approximation. A Monte Carlo numerical simulation was done to verify the validity of the analytical theory. Very good agreement between simulation and analytical theory is obtained when the number of devices having PDL is four or more. An experiment also demonstrated the validity of the analytical theory. The theory can also explain some phenomena that occur in systems composed of optical amplifiers, even though it had originally been developed to explain PDL-related phenomena in systems composed of passive devices only 相似文献