One is the bss based on kernel density estimation ( kde ) and genetic algorithm ( ga ) , the other is the blind deconvolution based on high order cross cumulants and ga . without nlf , the performance of separation in both algorithms is independent with the kurtosis of the sources 两种算法的实现无需引入非线性函数,因此都与源信号的峭度性质无关;另外,选取全局搜索的遗传算法进行寻优,避免了梯度法搜索的局部性,使得算法均能收敛到问题的全局最优解。
Secondly , we propose a multi - user detection based on kurtosis . this method can suppress not only mai ( multiple - access interference ) but also isi ( inter - symbol interference ) . all needs in the detection are only the desire user ' s spreading code 并在此基础上，提出了一种基于峭度的盲检测方法，这种方法不但可以抑制多址干扰mai ( multiple - accessinterference ) ，还可以抑制符号间干扰isi ( inter - symbolinterference ) ，而且在检测时只需要期望用户的扩频码信息，是一种全盲检测方法。
A open - close mathematic model is introduced into calculation of torsional vibration . results show : kurtosisness and high harmonic will increase when crankshaft have crack . 5 . cylinder score is also diagnosed by torsional vibration in this paper , when cylinder score occurring , the friction of piston will decrease the action of air pressure 本文借鉴了裂纹转子刚度的开闭模型，首次对含有变刚度单元的柴油机动力装置进行了扭振计算，结果表明柴油机曲轴有裂纹后，扭振的角位移和附加振动力矩的高谐次分量会增加，峭度值增加。
The heuristic analysis , some concepts and theorems of constrained optimization are employed , e . g . , linear feasible direction ( lfd ) , and then the proof is first provided for the uniqueness , i . e . , maximum nongaussianity is the sufficient and necessary condition to independent source recovery . moreover , based on the conclusion of the uniqueness of maximum nongaussianity , the paper also proposes an alternative but straightforward approach to the proof for the well known “ one - bit - matching ” conjecture presented in multi - unit approaches 和基于启发性分析等传统方法和结论比较,文中引入了线性化可行方向( linearfeasibledirection , lfd )等约束优化概念和理论,首次给出了基于峭度的最大非高斯估计的唯一性证明,指出最大非高斯估计是独立源提取的充分和必要条件。
After analyzing the traditional methods of generating exciting signals in vibration control system of electrodynamic ( electrohydraulic ) shaker , a new method of adjusting the skewness and kurtosis of exciting signals by second phase modulation is proposed . based on this method , a new algorithm for generating super - gaussian and quasi - random vibration exciting signals with specified psd , skewness and kurtosis is proposed . simulation and experimental results validate the algorithm 2 .通过分析目前电动(液)振动台数字式随机振动控制系统中广泛采用的激励信号生成原理,在其基础上提出了一种通过二次相位调制来控制激励信号峭度值和偏斜度值的方法,分别得到了频谱可控的对称和非对称分布超高斯伪随机激励信号生成算法,并进行了数值仿真和试验验证,为研究频谱可控的超高斯真随机激励信号生成技术奠定了基础。
At last we verify the performance of the improved adaptive method and the blind adaptive multi - user detection by simulations . it is shown that the improved adaptive method converges faster than lms . the blind adaptive multi - user detection can suppress mai and isi at the same time , and its output ber performance is better than other blind or semi - blind detectors 论文最后还验证了结合峭度，子空间和改进的自适应方法的全盲自适应检测方法的性能，通过与其它盲检测方法性能的比较，可以看出这种方法抗多址能力比其它盲检测方法大大提高，而且具有较好的抗多径，时变信道的性能。
