For sparse system identification, a memory-improved proportionate affine projection sign algorithm with a simplified, generalized correntropy induced metric (SGCI-M-IPAPSA) has good filtering performance. However, the SGCI-M-IPAPSA is based on a fixed step size and is not always the best choice. To overcome the limitation of a fixed step size in filtering precision and convergence speed under non-Gaussian impulsive interferences, in this paper, we apply the combined-step-size idea and a variable-step-size method based on the mean-square deviation to the SGCI-M-IPAPSA, respectively, and propose two new robust algorithms to enhance the filtering performance of the SGCI-M-IPAPSA. In addition, by combining the combined-step-size and proposed variable-step-size methods, we propose a fresh combined variable-step-size way and apply it to the SGCI-M-IPAPSA. The convergence of the proposed algorithms is also elaborated, and a conditional decision on the mean-square error is used to cope with abrupt changes. The better performances of the proposed algorithms than the conventional SGCI-M-IPAPSA in terms of the filtering accuracy and convergence rate are demonstrated with non-Gaussian impulsive interferences for sparse system identification, abrupt changes and colored inputs.
The idea of variable step-size was introduced into the Hybrid Affine Projection Algorithm (H-APA) and we propose two variable step size algorithms based on H-APA, which are called the Variable Step-Size Hybrid Affine Projection Algorithm (VSS-H-APA) and the Modified Variable Step-Size Hybrid Affine Projection Algorithm (MVSS-H-APA). These are two variable-step algorithms aim to further improve the robust performance and convergence speed of H-APA under non-Gaussian noise. This allows for faster convergence while maintaining stability. The MVSS-H-APA goes further than VSS-H-APA to estimate the noise in order to achieve better convergence performance. The proposed algorithm performs better than the existing algorithms in system identification under symmetric non-Gaussian noise.
A cluster of affine projection (AP) algorithms has the characteristics of a fast convergence rate under coloured noise. Furthermore, robust mixed-norm algorithms (RMNA) have been confirmed to possess outstanding steady-state properties. Simultaneously, combined step-size methods have the competence to ameliorate the tracking competence of AP-type algorithms. This paper proposes a novel combined step-size affine projection mixed-norm algorithm with a generalized maximum correntropy criterion for robust filtering named CSS-APRMNGMC. The proposed CSS-APRMNGMC integrates the advantages of mix-norm and generalized maximum correntropy criterion and applies new combined step-size methods to ameliorate tracking ability. The superior performance is verified in identification of system, which contains non-gaussian impulsive interferences.
29 December 2023 in IEEE Transactions on Circuits and Systems II: Express Briefs
This paper proposes a novel Combined-Statistical-Distribution generalized maximum correntropy algorithm with affine projection to improve the convergence rate and tracking ability in system identification. We design a new generalized Gaussian kernel to measure the system error and utilize the sigmoid activation function as a transition strategy of the Combined-Statistical-Distribution (CSD) factor. Meanwhile, we use the inequality scaling method to improve the constraints to avoid reducing the convergence rate. Under the α-stable noise scenario and impulsive interference, the superiority of the proposed algorithm is demonstrated in system identification experiments.
A new algorithm called Combined Step Sizes Affine Projection Mixed-norm Algorithm(CSS-APRMNA) is proposed to solve the problem of choosing between convergence rate and steady-state misadjustment of Affine Projection Mixed-norm Algorithm(APRMNA). By using a combination of large and small step sizes, the fast convergence rate of large step size and the low steady-state misadjustment of small step size are simultaneously achieved. At the same time, a modified sigmoidal activation function with parameters is used to accommodate different step-size combinations. The mixed-norm of the system error is used as a criterion for variable mixing parameter updating to synthesize the effect of non-Gaussian impulse interference and the sensitivity of the updating. The CSS-APRMNA algorithm shows good performance in simulations of system identification that contain impulse interference.