The random noises of multi-sensor and the environment make observations uncertain and correlative, so the performance of fusion algorithms is reduced by using observations directly. To solve this problem, a multi-laye...The random noises of multi-sensor and the environment make observations uncertain and correlative, so the performance of fusion algorithms is reduced by using observations directly. To solve this problem, a multi-layer track fusion algorithm based on supporting degree matrix is proposed. Combined with the track fusion algorithm based on filtering step by step, it uses multi-sensor observations to establish supporting degree matrix and realize multi-layer fusion. Simulation results show its estimation precision is higher than the original algorithm and is increased by 20% around. Therefore, it solves the problem of target tracking further in the distributed track fusion system.展开更多
传统聚类算法进行混叠矩阵估计时存在的聚类中心个数不确定和初始聚类中心的随机选取导致陷入局部最优的问题,为此提出一种基于密度峰值的改进模糊聚类算法进行欠定盲源分离的混叠矩阵估计。通过短时傅里叶变换提取信号在频域中的稀疏特...传统聚类算法进行混叠矩阵估计时存在的聚类中心个数不确定和初始聚类中心的随机选取导致陷入局部最优的问题,为此提出一种基于密度峰值的改进模糊聚类算法进行欠定盲源分离的混叠矩阵估计。通过短时傅里叶变换提取信号在频域中的稀疏特性,利用寻找密度峰值聚类算法(clustering by fast search and find of density peaks,CFSFDP)自动获取聚类簇的数目和初始聚类中心;将获得的聚类数目和聚类结果作为模糊聚类算法(fuzzy c-means clustering,FCM)的初始输入参数,提高FCM聚类结果的精度。实验结果表明,该算法可以准确估计源信号的数目,相比传统FCM、层次聚类、基于密度峰值改进的粒子群等聚类算法,可以有效提高欠定盲源分离的混叠矩阵估计精度。展开更多
基金Supported by the Aviation Science Funds (20090580013)the Fundamental Research Funds for the Central Universities (ZYGX2009J092)
文摘The random noises of multi-sensor and the environment make observations uncertain and correlative, so the performance of fusion algorithms is reduced by using observations directly. To solve this problem, a multi-layer track fusion algorithm based on supporting degree matrix is proposed. Combined with the track fusion algorithm based on filtering step by step, it uses multi-sensor observations to establish supporting degree matrix and realize multi-layer fusion. Simulation results show its estimation precision is higher than the original algorithm and is increased by 20% around. Therefore, it solves the problem of target tracking further in the distributed track fusion system.
文摘传统聚类算法进行混叠矩阵估计时存在的聚类中心个数不确定和初始聚类中心的随机选取导致陷入局部最优的问题,为此提出一种基于密度峰值的改进模糊聚类算法进行欠定盲源分离的混叠矩阵估计。通过短时傅里叶变换提取信号在频域中的稀疏特性,利用寻找密度峰值聚类算法(clustering by fast search and find of density peaks,CFSFDP)自动获取聚类簇的数目和初始聚类中心;将获得的聚类数目和聚类结果作为模糊聚类算法(fuzzy c-means clustering,FCM)的初始输入参数,提高FCM聚类结果的精度。实验结果表明,该算法可以准确估计源信号的数目,相比传统FCM、层次聚类、基于密度峰值改进的粒子群等聚类算法,可以有效提高欠定盲源分离的混叠矩阵估计精度。
