Recursive least squares filter

About: Recursive least squares filter is a research topic. Over the lifetime, 8907 publications have been published within this topic receiving 191933 citations.

Adaptive equalization for co-channel interference in a multipath fading environment

Abstract: The paper concerns the feasibility and achievable performance of adaptive filtering in an interference-limited multipath fading environment as encountered in indoor wireless communications. In a typical cellular radio application, the performance-limiting impairment is interference due to synchronous data streams from other co-channel and adjacent channel users (CCI and ACI). The receiver under consideration employs an adaptive fractionally spaced decision feedback equalizer (DFE) Which exploits the correlation of the cyclostationary interference to achieve superior performance relative to the worst case when the interference is stationary noise. The paper presents ideal calculations which confirm that significant DFE performance gains are potentially achievable by explicitly accounting for the cyclostationary CCI. Two adaptive DFE strategies are considered. One approach is to adapt the DFE directly using iterative algorithms such as least mean square (LMS) or recursive least squares (RLS). Another approach is to compute the minimum mean square error DFE using an RLS channel impulse response (CIR) estimate and a sample estimate of the CCI autocorrelation obtained from the CIR estimation error during training. The best approach for adaptive equalization, in terms of adaptation speed and system performance, is to employ an RLS DFE which does not explicitly estimate the CIR or the CCI autocorrelation. >

Consistent normalized least mean square filtering with noisy data matrix

Abstract: When the ordinary least squares method is applied to the parameter estimation problem with noisy data matrix, it is well-known that the estimates turn out to be biased. While this bias term can be somewhat reduced by the use of models of higher order, or by requiring a high signal-to-noise ratio (SNR), it can never be completely removed. Consistent estimates can be obtained by means of the instrumental variable method (IVM),or the total/data least squares method (TLS/DLS). In the adaptive setting for the such problem, a variety of least-mean-squares (LMS)-type algorithms have been researched rather than their recursive versions of IVM or TLS/DLS that cost considerable computations. Motivated by these observations, we propose a consistent LMS-type algorithm for the data least square estimation problem. This novel approach is based on the geometry of the mean squared error (MSE) function, rendering the step-size normalization and the heuristic filtered estimation of the noise variance, respectively, for fast convergence and robustness to stochastic noise. Monte Carlo simulations of a zero-forcing adaptive finite-impulse-response (FIR) channel equalizer demonstrate the efficacy of our algorithm.

Adaptive fuzzy modeling of interval-valued stream data and application in cryptocurrencies prediction

Abstract: This paper introduces an adaptive interval fuzzy modeling method using participatory learning and interval-valued stream data. The model is a collection of fuzzy functional rules in which the rule base structure and the parameters of the rules evolve simultaneously as data are input. The evolving nature of the method allows continuous model adaptation using the stream interval input data. The method employs participatory learning to cluster the interval input data recursively, constructs a fuzzy rule for each cluster, uses the weighted recursive least squares to update the parameters of the rule consequent intervals, and returns an interval-valued output. The method is evaluated using actual data to model and forecast the daily lowest and highest prices of the four most traded cryptocurrencies, BitCoin, Ethereum, XRP, and LiteCoin. The performance of the adaptive interval fuzzy modeling is compared with the adaptive neuro-fuzzy inference system, long short-term memory neural network, autoregressive integrated moving average, exponential smoothing state model, and the naive random walk methods. Results show that the suggested interval fuzzy model outperforms all these methods in predicting prices in the digital coin market, especially when considering directional accuracy measure.

Adaptive tracking of multiple sinusoids whose power levels are widely separated

Abstract: The behavior of the gradient transversal filter (LMS), the gradient lattice (GL), and the least squares lattice (LSL) when used to track multiple sinusoidal (or narrow-band) components whose power levels are widely separated is investigated. These approaches to the realization of the pth-order one-step linear predictor of the time series are recursive in time. The lags of the instantaneous frequency estimates from their actual underlying values are of particular interest. The frequency tracking characteristics of the LMS, GL, and LSL algorithms are illustrated in several situations. Included are simulations of dual sinusoids undergoing a variety of frequency versus time dynamics and a formant tracking example of real speech.

Tracking improvements in fast RLS algorithms using a variable forgetting factor

Abstract: The concept of a variable forgetting factor (VFF) is incorporated into fast recursive least-squares (FRLS) algorithms. Compromises in the data matrix that are needed to do this are examined. Both prewindowed and growing memory covariance algorithms are presented in transversal and lattice structures. Forgetting-factor adaptation schemes, which improve tracking performance over conventional FRLS algorithms, are suggested. Finally, the bias introduced by the use of the VFF is analyzed. >