Search

The multikernel least mean square (MKLMS) algorithm is a classical algorithm of multikernel adaptive filters due to its simplicity. However, the linear growth network structure is a main challenge of MKLMS. To address this issue, a novel multiple random features least mean square (MRFLMS) algorithm is proposed by approximating multiple Gaussian kernels with the multiple random features method. In addition, a combined weight transfer strategy is adopted in MRFLMS to develop another combined multiple random features least mean square (CMRFLMS) algorithm to alleviate the influence of step‐size on filtering performance and convergence rate. CMRFLMS with a fixed dimensional network structure can provide comparable performance and faster convergence rate than MKLMS. Simulations on prediction of synthetic and real non‐linear system identification illustrate the superiorities of the proposed CMRFLMS algorithm from the aspects of filtering accuracy, convergence rate, and tracking performance. [ABSTRACT FROM AUTHOR]

Heart rate (HR) estimated using the photoplethysmography (PPG) signals during intense physical exercise is highly onerous owing to the existence of noise components like motion artifacts (MA’s) in the PPG signal. In this work, a robust de-noising technique for accurate HR estimation from the corrupted PPG signal is reported. The de-noising technique reported employs three pairs of Recursive Least Squares (RLS) as well as Normalized Least Mean Squares (NLMS) adaptive filters. The de-noised PPG signal obtained at the output of RLS and NLMS adaptive filters are combined using the sigmoid function. The three MA reduced PPG signals obtained from each adaptive filter pair are again combined using softmax activation function to form a MA reduced PPG signal from which the HR is estimated. Fast Fourier Transform (FFT) is used to estimate the HR and phase vocoder is used to refine the estimated HR. The proposed method is tested on the publically available 23 PPG datasets and it resulted in an HR estimation error of 1.89 beat per minute (BPM). The HR estimated using the proposed technique is found to be accurate and the HR estimation error is 1.89 BPM which is less when compared to other existing HR estimation mechanisms that reported an error of 1.97 BPM and 2.09 BPM. [ABSTRACT FROM AUTHOR]

The combination of adaptive filters is an effective approach to improve filtering performance. In this paper, we investigate the performance of an adaptive combined scheme between two adaptive multiple-input single-output (MISO) filters, which can be easily extended to the case of multiple outputs. In order to generalize the analysis, we consider the multichannel affine projection algorithm (APA) to update the coefficients of the MISO filters, which increases the possibility of exploiting the capabilities of the filtering scheme. Using energy conservation relations, we derive a theoretical behavior of the proposed adaptive combination scheme at steady state. Such analysis entails some further theoretical insights with respect to the single channel combination scheme. Simulation results prove both the validity of the theoretical steady-state analysis and the effectiveness of the proposed combined scheme. [ABSTRACT FROM AUTHOR]