Adaptive Filters

2011 ◽  
pp. 190-224
Author(s):  
Sergio L. Netto ◽  
Luiz W.P. Biscainho
Keyword(s):  
Adaptive Filters ◽  
Adaptive Signal Processing ◽  
Recursive Least Squares ◽  
Least Mean Square ◽  
Affine Projection ◽  
Signal Prediction ◽  
Iir Filter ◽  
Adaptive Signal ◽  
Filter Algorithms ◽  
Normalized Lms

This chapter focuses on the main aspects of adaptive signal processing. The basic concepts are introduced in a simple framework, and its main applications (namely system identification, channel equalization, signal prediction, and noise cancellation) are briefly presented. Several adaptive algorithms are presented, and their convergence behaviors are analyzed. The algorithms considered in this chapter include the popular least-mean square (LMS), its normalized-LMS version, the affine-projection with the set-membership variation, the recursive least-squares (RLS), the transform-domain, the sub-band domain, and some IIR-filter algorithms such as the equation-error (EE) and the output-error (OE) algorithms. The main purpose of all this presentation is to give general guidelines for the reader to choose the most adequate technique for the audio application at hand.

Adaptive Signal Processing Techniques: An Application to Raman Spectroscopy

1989 ◽  
Vol 43 (5) ◽  
pp. 750-758 ◽  
Author(s):  
Ramiro Jordan ◽  
Stephen A. Dyer
Keyword(s):  
Raman Spectra ◽  
Adaptive Filtering ◽  
Adaptive Filters ◽  
Adaptive Algorithms ◽  
Adaptive Signal Processing ◽  
Least Square ◽  
Least Mean Square ◽  
Processing Techniques ◽  
Adaptive Signal ◽  
Signal Processing Techniques

In this study, the applicability of adaptive filters and algorithms to the enhancement of Raman spectra is investigated. The two adaptive-filter realizations described are the transversal (tapped-delay) and the lattice. The two adaptive algorithms considered are the least-mean-square and the modified least-square. Experimental results demonstrate that enhancement of Raman spectra obtained at low signal-to-noise ratios can be achieved. Extrapolation is applied to enhance the inherently low resolution of Raman spectra. Adaptive filtering techniques yield results comparable to those obtained from maximum-entropy methods for estimating spectra, with a resolution exceeding that allowed by Fourier procedures.

scholarly journals Adaptive method to predict and track unknown system behaviors using RLS and LMS algorithms

2021 ◽  
Vol 34 (1) ◽  
pp. 133-140
Author(s):  
Teimour Tajdari
Keyword(s):  
Input Signal ◽  
Output Signal ◽  
Adaptive Filters ◽  
Adaptive Method ◽  
Lms Algorithm ◽  
Recursive Least Squares ◽  
Least Mean Square ◽  
Filter Output ◽  
System Output ◽  
Unknown System

This study investigates the ability of recursive least squares (RLS) and least mean square (LMS) adaptive filtering algorithms to predict and quickly track unknown systems. Tracking unknown system behavior is important if there are other parallel systems that must follow exactly the same behavior at the same time. The adaptive algorithm can correct the filter coefficients according to changes in unknown system parameters to minimize errors between the filter output and the system output for the same input signal. The RLS and LMS algorithms were designed and then examined separately, giving them a similar input signal that was given to the unknown system. The difference between the system output signal and the adaptive filter output signal showed the performance of each filter when identifying an unknown system. The two adaptive filters were able to track the behavior of the system, but each showed certain advantages over the other. The RLS algorithm had the advantage of faster convergence and fewer steady-state errors than the LMS algorithm, but the LMS algorithm had the advantage of less computational complexity.

scholarly journals Efficient Adaptive Exon Prediction for DNA study using Proportionate LMS Variants

2018 ◽  
Vol 7 (2.17) ◽  
pp. 116 ◽  
Author(s):  
Srinivasareddy Putluri ◽  
Md Zia Ur Rahman
Keyword(s):  
Signal Processing ◽  
Dna Sequences ◽  
Genomic Sequence ◽  
Adaptive Signal Processing ◽  
Protein Coding ◽  
Exon Prediction ◽  
Gene Database ◽  
Processing Techniques ◽  
Adaptive Signal ◽  
Normalized Lms

In the field of Bio-informatics, locating the exon fragments in a deoxyribonucleic acid (DNA) sequence is an important and vital work. Study of protein coding regions is a wide phenomenon in identification of diseases and design of drugs. The regions of DNA that have the protein coding information are termed as exons. Hence identifying the exon segments in a genomic sequence is a crucial job in bio-informatics. Three base periodicity (TBP) has been observed in the regions of DNA sequences can be easily determined by applying signal processing methods. Adaptive signal processing techniques found to be useful than other available methods. This is due to their unique capability to alter weight coefficients based on genomic sequence. We propose efficient adaptive exon predictors (AEPs) based on these considerations using Proportionate Normalized LMS (PNLMS) algorithm and Maximum Proportionate Normalized LMS (MPNLMS) algorithm to improve exon locating ability and better convergence. To ease the complexity of computations in the denominator during filtering process, proposed AEPs using PNLMS and its maximum variants are combined with signature algorithms. Hybrid variants of proposed AEPs include PNLMS, DCPNLMS, ECPNLMS, SSPNLMS, MPNLMS, MDCPNLMS, MECPNLMS and MSSPNLMS algorithms. It was shown that the AEP based on MDCPNLMS is superior in applications of exon identification depending on performance measures with Sensitivity 0.7346, Specificity 0.7483 and precision 0.7325 for a genomic sequence with accession AF009962 at a threshold of 0.8. Finally the capability of several AEPs in predicting exon locations is verified using different DNA sequences found in National Center for Biotechnology Information (NCBI) gene database.  

scholarly journals Антенная решетка и эквалайзер с обратной связью как единое адаптивное устройство

2021 ◽  
Vol 64 (9) ◽  
pp. 550-562
Author(s):  
Виктор Иванович Джиган
Keyword(s):  
Matrix Inversion ◽  
Mean Square ◽  
Least Mean Square ◽  
Least Mean Squares ◽  
Affine Projection ◽  
Matrix Inversion Lemma ◽  
Normalized Lms

В статье рассмотрена адаптивная антенная решетка (ААР), весовые коэффициенты которой совмещены с весовыми коэффициентами части эквалайзера без обратной связи, а выходной сигнал комбинируется с выходным сигналом части эквалайзера с обратной связью. Такие решетка и распределенный эквалайзер функционируют как единый многоканальный адаптивный фильтр, обеспечивающий прием полезного сигнала в условиях его многолучевости и наличия сигналов источников внешних помех. Представлены архитектура антенной решетки/эквалайзера, математическое описание многоканальных адаптивных алгоритмов его работы: рекурсивного алгоритма по критерию наименьших квадратов RLS (Recursive Least Mean Squares) на основе леммы об обращении матрицы MIL (Matrix Inversion Lemma), QR-разложения и преобразования Хаусхолдера с квадратичной вычислительной сложностью, а также простых алгоритмов по критерию наименьшего квадрата LMS (Least Mean Square), нормализованного LMS-алгоритма NLMS (Normalized LMS) и алгоритма аффинных проекций AP (Affine Projection) с линейной вычислительной сложностью. Результаты моделирования линейной антенной решетки с числом антенн/каналов, равным восьми, принимающей полезный сигнал 16-PSK, прошедший через двухлучевой канал связи, при наличии от одного до четырех источников помех с отношением сигнал–помеха (ОСП) –30 дБ по каждой помехе, при отношении сигнал–шум (ОСШ) в каналах решетки 10–30 дБ, демонстрируют эффективность предлагаемого решения.

Noise Cancellation in ECG Signals with an Unbiased Adaptive Filter

2011 ◽  
pp. 348-366 ◽  
Author(s):  
Yunfeng Wu ◽  
Rangaraj M. Rangayyan
Keyword(s):  
Adaptive Filter ◽  
Adaptive Filters ◽  
Mean Squared Error ◽  
Random Noise ◽  
Recursive Least Squares ◽  
Ecg Signal ◽  
Least Mean Square ◽  
Ecg Signals ◽  
Lms Filter ◽  
Filtered Noise

The electrocardiographic (ECG) signal is a transthoracic manifestation of the electrical activity of the heart and is widely used in clinical applications. This chapter describes an unbiased linear adaptive filter (ULAF) to attenuate high-frequency random noise present in ECG signals. The ULAF does not contain a bias in its summation unit and the filter coefficients are normalized. During the adaptation process, the normalized coefficients are updated with the steepest-descent algorithm to achieve efficient filtering of noisy ECG signals. A total of 16 ECG signals were tested in the adaptive filtering experiments with the ULAF, the least-mean-square (LMS), and the recursive-least-squares (RLS) adaptive filters. The filtering performance was quantified in terms of the root-mean-squared error (RMSE), normalized correlation coefficient (NCC), and filtered noise entropy (FNE). A template derived from each ECG signal was used as the reference to compute the measures of filtering performance. The results indicated that the ULAF was able to provide noise-free ECG signals with an average RMSE of 0.0287, which was lower than the second-best RMSE obtained with the LMS filter. With respect to waveform fidelity, the ULAF provided the highest average NCC (0.9964) among the three filters studied. In addition, the ULAF effectively removed more noise, measured by FNE, in comparison with the LMS and RLS filters in most of the ECG signals tested. The issues of adaptive filter setting for noise reduction in ECG signals are discussed at the end of this chapter.

Bearing Natural Degradation Detection in a Gearbox: A Comparative Study of the Effectiveness of Adaptive Filter Algorithms and Spectral Kurtosis

2014 ◽  
Author(s):  
Faris Elasha ◽  
Cristobal Ruiz-Carcel ◽  
David Mba
Keyword(s):  
Adaptive Filter ◽  
Adaptive Filters ◽  
Vibration Signal ◽  
Lms Algorithm ◽  
Complex Signal ◽  
Least Mean Square ◽  
Bearing Faults ◽  
Spectral Kurtosis ◽  
Bearing Defects ◽  
Filter Algorithms

Bearing faults detection at the earliest stages is vital in avoiding future catastrophic failures. Many traditional techniques have been established and utilized in detecting bearing faults, though, these diagnostic techniques are not always successful when the bearing faults take place in gearboxes where the vibration signal is complex; under such circumstances it may be necessary to separate the bearing signal from the complex signal. The objective of this paper is to assess the effectiveness of an adaptive filter algorithms compared to a Spectral Kurtosis (SK) algorithm in diagnosing a bearing defects in a gearbox. Two adaptive filters have been used for the purpose of bearing signal separation, these algorithms were Least Mean Square (LMS) and Fast Block LMS (FBLMS) algorithms. These algorithms were applied to identify a bearing defects in a gearbox employed for an aircraft control system for which endurance tests were performed. The results show that the LMS algorithm is capable of detecting the bearing fault earlier in comparison to the other algorithms.

Speech and Audio Signal Applications

2002 ◽  
pp. 200-224
Author(s):  
Hector Perez-Meana ◽  
Mariko Nakano-Miyatake ◽  
Luis Nino-de-Rivera-y-Oyarzabal
Keyword(s):  
Signal Processing ◽  
Adaptive Filters ◽  
Audio Signal ◽  
Adaptive Signal Processing ◽  
Basic Principles ◽  
Signal Processing Systems ◽  
Adaptive Signal

This chapter reviews the basic principles of multirate adaptive filters together with some of their most successful applications, as well as some recently proposed schemes that improve the subband adaptive signal processing systems.

An Unbiased Linear Adaptive Filter with Normalized Coefficients for the Removal of Noise in Electrocardiographic Signals

2009 ◽  
Vol 3 (4) ◽  
pp. 73-90 ◽  
Author(s):  
Yunfeng Wu ◽  
Rangaraj M. Rangayyan
Keyword(s):  
Adaptive Filter ◽  
Adaptive Filters ◽  
Mean Squared Error ◽  
Random Noise ◽  
Recursive Least Squares ◽  
Least Mean Square ◽  
Ecg Signals ◽  
Squared Error ◽  
Lms Filter ◽  
Filtered Noise

The authors propose an unbiased linear adaptive filter (ULAF) to eliminate high-frequency random noise in electrocardiographic (ECG) signals. The ULAF does not contain a bias in its summation unit, and the filter coefficients are normalized. During the adaptation process, the normalized coefficients are updated with the steepest-descent algorithm in order to achieve efficient filtering of noisy ECG signals. The authors tested the ULAF with ECG signals recorded from 16 subjects, and compared the performance of the ULAF with that of the least-mean-square (LMS) and recursive-least-squares (RLS) adaptive filters. The filtering performance was quantified in terms of the root-mean-squared error (RMSE), normalized correlation coefficient (NCC), and filtered noise entropy (FNE). A template derived from each ECG signal was used as the reference to compute the measures of filtering performance. The results indicated that the ULAF was able to provided noise-free ECG signals with an average RMSE of 0.0287, which was lower than the second best RMSE (0.0365) obtained with the LMS filter. With respect to waveform fidelity, the proposed ULAF provided the highest average NCC (0.9964) among the three filters studied. In addition, the ULAF effectively removed more noise measured by FNE versus the LMS and RLS filters in most of the ECG signals tested.

Sign in / Sign up

Export Citation Format

Share Document