Adaptive detection of range-spread targets without secondary data is addressed in a multichannel autoregressive Gaussian disturbance with unknown space–time covariance matrix, by utilizing the Rao test. The proposed Rao test without secondary data is theoretically proved to be asymptotically (large-sample in the number of temporal observations) constant false alarm rate with respect to unknown space–time covariance matrix, thanks to an asymptotic equivalence between the Rao test and the generalized likelihood ratio test. Moreover, the performance loss due to no secondary data can be remedied by appropriately increasing the temporal dimension. The performance assessment conducted by Monte Carlo simulation, also in comparison with the existing detector without secondary data, confirms the effectiveness of the proposed detectors. 相似文献
In order to curb the model expansion of the kernel learning methods and adapt the nonlinear dynamics in the process of the nonstationary time series online prediction, a new online sequential learning algorithm with sparse update and adaptive regularization scheme is proposed based on kernel-based incremental extreme learning machine (KB-IELM). For online sparsification, a new method is presented to select sparse dictionary based on the instantaneous information measure. This method utilizes a pruning strategy, which can prune the least “significant” centers, and preserves the important ones by online minimizing the redundancy of dictionary. For adaptive regularization scheme, a new objective function is constructed based on basic ELM model. New model has different structural risks in different nonlinear regions. At each training step, new added sample could be assigned optimal regularization factor by optimization procedure. Performance comparisons of the proposed method with other existing online sequential learning methods are presented using artificial and real-word nonstationary time series data. The results indicate that the proposed method can achieve higher prediction accuracy, better generalization performance and stability.