针对传统高斯混合模型(GMM,Gaussian mixture model)难以自动获取类属数和对噪声敏感问题,提出了一种基于可变类空间约束GMM的遥感图像分割方法。首先在构建的GMM中,将像素类属性建模为马尔可夫随机场(MRF,Markov random field),并在此...针对传统高斯混合模型(GMM,Gaussian mixture model)难以自动获取类属数和对噪声敏感问题,提出了一种基于可变类空间约束GMM的遥感图像分割方法。首先在构建的GMM中,将像素类属性建模为马尔可夫随机场(MRF,Markov random field),并在此基础上定义其先验概率;结合邻域像素类属性的后验概率和先验概率,定义噪声平滑因子,以提高算法的抗噪性;在参数求解过程中,分别采用可逆跳变马尔可夫链蒙特卡罗(RJMCMC,reversible jump Markov chain Monte Carlo)方法和最大似然(ML,maximum likelihood)方法估计类属数和模型参数;最后以最小化噪声平滑因子为准则获取最终分割结果。为了验证提出的分割方法,分别对模拟图像和全色遥感图像进行了可变类分割实验。实验结果表明提出方法的可行性和有效性。展开更多
The maximum likelihood （ML） estimator demonstrates remarkable performance in direction of arrival （DOA） estimation for the multiple input multiple output （MIMO） sonar. However, this advantage comes with prohibit...The maximum likelihood （ML） estimator demonstrates remarkable performance in direction of arrival （DOA） estimation for the multiple input multiple output （MIMO） sonar. However, this advantage comes with prohibitive computational complexity. In order to solve this problem, an ant colony optimization （ACO） is incorporated into the MIMO ML DOA estimator. Based on the ACO, a novel MIMO ML DOA estimator named the MIMO ACO ML （ML DOA estimator based on ACO for MIMO sonar） with even lower computational complexity is proposed. By extending the pheromone remaining process to the pheromone Gaussian kernel probability distribution function in the continuous space, the pro- posed algorithm achieves the global optimum value of the MIMO ML DOA estimator. Simulations and experimental results show that the computational cost of MIMO ACO ML is only 1/6 of the MIMO ML algorithm, while maintaining similar performance with the MIMO ML method.展开更多
In this paper,average bit error probability(ABEP)bound of optimal maximum likelihood(ML)detector is first derived for ultra massive(UM)multiple-input-multiple-output(MIMO)system with generalized amplitude phase modula...In this paper,average bit error probability(ABEP)bound of optimal maximum likelihood(ML)detector is first derived for ultra massive(UM)multiple-input-multiple-output(MIMO)system with generalized amplitude phase modulation(APM),which is confirmed by simulation results.Furthermore,a minimum residual criterion(MRC)based lowcomplexity near-optimal ML detector is proposed for UM-MIMO system.Specifically,we first obtain an initial estimated signal by a conventional detector,i.e.,matched filter(MF),or minimum mean square error(MMSE)and so on.Furthermore,MRC based error correction mechanism(ECM)is proposed to correct the erroneous symbol encountered in the initial result.Simulation results are shown that the performance of the proposed MRC-ECM based detector is capable of approaching theoretical ABEP of ML,despite only imposing a slightly higher complexity than that of the initial detector.展开更多
基金supported by the National Natural Science Foundation of China (60972152)the National Laboratory Foundation of China (9140C2304080607)+1 种基金the Aviation Science Fund (2009ZC53031)the Doctoral Foundation of Northwestern Polytechnical University (CX201002)
文摘The maximum likelihood （ML） estimator demonstrates remarkable performance in direction of arrival （DOA） estimation for the multiple input multiple output （MIMO） sonar. However, this advantage comes with prohibitive computational complexity. In order to solve this problem, an ant colony optimization （ACO） is incorporated into the MIMO ML DOA estimator. Based on the ACO, a novel MIMO ML DOA estimator named the MIMO ACO ML （ML DOA estimator based on ACO for MIMO sonar） with even lower computational complexity is proposed. By extending the pheromone remaining process to the pheromone Gaussian kernel probability distribution function in the continuous space, the pro- posed algorithm achieves the global optimum value of the MIMO ML DOA estimator. Simulations and experimental results show that the computational cost of MIMO ACO ML is only 1/6 of the MIMO ML algorithm, while maintaining similar performance with the MIMO ML method.
基金supported in part by the National Key Research and Development Program of China under Grant 2019YFB1803400in part by the National Science Foundation of China under Grant 62001179in part by the Fundamental Research Funds for the Central Universities under Grant 2020kfyXJJS111.
文摘In this paper,average bit error probability(ABEP)bound of optimal maximum likelihood(ML)detector is first derived for ultra massive(UM)multiple-input-multiple-output(MIMO)system with generalized amplitude phase modulation(APM),which is confirmed by simulation results.Furthermore,a minimum residual criterion(MRC)based lowcomplexity near-optimal ML detector is proposed for UM-MIMO system.Specifically,we first obtain an initial estimated signal by a conventional detector,i.e.,matched filter(MF),or minimum mean square error(MMSE)and so on.Furthermore,MRC based error correction mechanism(ECM)is proposed to correct the erroneous symbol encountered in the initial result.Simulation results are shown that the performance of the proposed MRC-ECM based detector is capable of approaching theoretical ABEP of ML,despite only imposing a slightly higher complexity than that of the initial detector.
