LMS Adaptive Algorithm Research Articles

Secure multiple adaptive kernel diffusion LMS algorithm for distributed estimation over sensor networks

Secure multiple adaptive kernel diffusion LMS algorithm for distributed estimation over sensor networks

A novel approach to geometric algebra-based variable step-size LMS adaptive filtering algorithm

A novel approach to geometric algebra-based variable step-size LMS adaptive filtering algorithm

Modified LMS Adaptive Algorithm for the determination of Maximum SNR using Self-Adaptation Technique of Noise Factor for Communication System

The most often used adaptive filter (AF) is the least-mean-square (LMS) filter. This filter has many applications in the area of communication and signal processing. System identification represents a significant use case for adaptive filters. This paper represents a new structure/model of system identification and adaptive noise cancellation (ANC) using state-of-the-art LMS-AF. The paper expressed the algorithm of updated LMS-AF. The major parts of the proposed model are- two adaptive filters, one LMS filter, one correlation function, and one auto-correlation function. The research investigation for the proposed model is based on the self-adaptation or self-learning method to obtain the maximum signal to noise ratio (SNR) based on the real-time inputs. The proposed structure/model converges towards the ideal LMS-ANC system. This paper also includes mathematical analysis, simulation, results, and discussion. The most important comparison parameters are the SNR and mean-square-error (MSE).

An empirical analysis of the evolution of piano performance skills based on big data

Abstract The current hotspots of empirical analysis of piano performance skills mainly focus on the recognition of single notes, and there are some limitations in recognition accuracy and noise resistance performance. In this paper, to address this problem, firstly, on the basis of big data, we propose to realize the segmentation of the music section and noise section based on the single-port limit energy difference method and perform note onset and stop detection for the music section based on LMS adaptive filtering algorithm, using the musical characteristics of piano to identify the energy jumping point, which effectively improves the accuracy of note onset and stop detection and avoids the situation of missing and wrong diagnosis. Then the piano piece was played as an example, and the scientific evaluation of the piano performance skills was made based on the results of the determination of note types. The results showed that the errors of the eight notes of the piece were 0.9%, 0.30%, 0.24%, 0.28%, 0.34%, 0.11%, 0.63% and 0.28%. The correct rate of determining the types of notes in the performance technique of the music was 100%, and the error of determining all notes was controlled within 1%. This study provides a reference standard for evaluating the quality of music performance and has broad application prospects in the fields of family leisure, music tutoring, etc.

Transmission loss measurement of recycled granular material using wave decomposition by impulse response extraction based on deconvolution

A simplified method for measuring transmission loss with a single fixed microphone inside an impedance tube is proposed. The separation of the incident wave from the reflected wave is achieved by deconvolving the loudspeaker driver voltage signal with the microphone signal to extract the impulse response. Random noise and a sinusoidal sweep signal were used as excitation signals for extraction of the impulse response, and two deconvolution methods were employed: linear deconvolution based on the adaptive LMS algorithm and simple spectral division. To avoid the overlap of incident and reflected pulses, a long impedance tube was used. Using a long impedance tube eliminates the need for an anechoic tube termination and the need to calibrate microphones. It is found that a reflective tube termination provides more accurate results compared to an approximately anechoic termination. The approximately anechoic termination shortens the available time window of the reflected pulse because it reflects some of the low-frequency sound. The standard deviation of the results and the dynamic range of the proposed method were determined experimentally. The applicability of the new method was tested on samples of unconsolidated granular material recycled from construction sites. The measured transmission losses of the different granular fractions were compared with a theoretical model for transmission losses at low frequencies. Samples consisting of smaller granule fractions were found to have surprisingly high transmission loss values. The design of the extended vertical impedance tube in combination with the proposed method is cost effective, speeds up the measurement procedure and provides reliable results.

Active noise reduction analysis and experimental research on electromagnetic vibration noise of transformer

Active noise reduction system is widely used in production and life because of its good noise reduction effect in low frequency band, easy installation, high practicability and good economy. This paper focused on the compilation of active noise reduction algorithms and the overall system debugging, and explored the factors that affected the active noise reduction. In order to realize the software part of the active noise reduction system, the LMS adaptive filtering algorithm was written and non-linearity function and auxiliary machine learning algorithm was used. Then the hardware system was built for the overall joint debugging of software and hardware. Combined with the practical application background of electrical equipment engineering, the influence of the angle, number of speakers and the distance from electrical equipment on the noise reduction effect were studied. The results showed the overall noise reduction in the experiment was about 6 dB, which proved that the active noise reduction system proposed in this paper is effective.

Noise reduction in speech signal of Parkinson’s Disease (PD) patients using optimal variable stage cascaded adaptive filter configuration

In hands-free communications, including mobile phones, teleconferencing, and video conferencing, the ultimate aim is to obtain a noise-free signal. The adaptive filters that utilize the LMS adaptation algorithm are the best suited for speech signal de-noising among the existing speech signal enhancement techniques. LMS adaptive filter is preferred due to its low computational complexity and robustness, but it fails to simultaneously achieve a faster convergence speed and minimum steady-state MSE. This work introduces a novel cascaded adaptive filter structure for speech signal de-noising wherein the objective is to estimate the noise-free signal with high accuracy. The proposed optimal variable stage cascaded adaptive filter model utilizes a variable stage cascaded adaptive filter structure to estimate the noise-free signal, which is then employed to recover the clean signal with high accuracy. The proposed filter model is tested for reducing the noise from a normal speech signal taken from the NOIZEUS database and an impaired speech signal of Parkinson’s Disease affected patients taken from the MDVR-KCL dataset. The signals are corrupted by various stationary and non-stationary noise signals of different input SNR levels. The noisy signal is used to test the performance of the proposed optimal filter model. The signal de-noising performance of the proposed filter is evaluated in MSE, SNR, and ANR. The results have shown that the proposed filter model provides remarkable performance and an output SNR of 10–15 dB higher than the existing cascaded filter structures. Further, the proposed filter model employs LMS adaptive algorithm, offering a cost-effective and straightforward hardware implementation of ANC with improved accuracy.

Implementation of Least Mean Square Adaptive Algorithm on Covid-19 Prediction

This study used Corona Virus Disease-19 (Covid-19) data in Indonesia from June to August 2021, consisting of data on people who were infected or positive Covid-19, recovered from Covid-19, and passed away from Covid-19. The data were processed using the adaptive LMS algorithm directly without pre-processing cause calculation errors, because covid-19 data was not balanced. Z-score and min-max normalization were chosen as pre-processing methods. After that, the prediction process can be carried out using the LMS adaptive method. The analysis was done by observing the error prediction that occurred every month per case. The results showed that data pre-processing using min-max normalization was better than with Z-score normalization because the error prediction for pre-processing using min-max and z-score were 18% and 47%, respectively.

Micro-Jitter Control of Magnetically Suspended Control Moment Gyro Using Adaptive LMS Algorithm

Imbalanced vibration generated during the operation of a high-speed rotor inside a gyro is transmitted to the magnetically suspended control moment gyro through a magnetic bearing stator, resulting in micro-jitter. This greatly affects the control accuracy of the spacecraft attitude. In order to effectively suppress micro-jitter, the dynamic model of the magnetically suspended rotor with imbalanced mass is established in this article, and the imbalanced characteristics of the high-speed rotor are analyzed. Finally, a double-channel adaptive least mean square error algorithm is proposed. By utilizing that the radial X- and Y- displacement signals from the rotor displacement sensor are orthogonal to each other, a feedforward correction is applied to adaptively compensate the residual displacement stiffness of the magnetically suspended rotor system due to mass imbalance. While eliminating this synchronous current, the proposed algorithm also offsets the adverse effects of the low-pass characteristics of the power amplifier. Simulation and experimental results show that the method compensates the synchronous displacement stiffness force generated by the system with high precision, and realizes the micro-jitter control of the magnetically suspendedcontrol moment gyro.

Application of a New CO₂ Prediction Method Within Family House Occupancy Monitoring

The article describes the application of Python for verification of a newly designed method of CO2 prediction from measurements of indoor parameters of temperature and relative humidity within occupancy monitoring in real conditions of a family home. The article describes the implementation of non-electric quantities (indoor CO2 concentration, indoor temperature, indoor relative humidity) measurement in five rooms of a family home (living room, kitchen, children’s room, bathroom, bedroom) using Loxone technology sensors. The IBM IoT (Internet Of Things) was used for storing and subsequent processing of the measured values within the time interval of December 22, 2018, to December 31, 2018. The devised method used radial basis function (artificial neural networks (ANN)) mathematical method (implementation in Python environment) to perform accurate predictions. For further increase of the accuracy and reduction of prediction noise from the obtained course of the predicted signal, multiple variations of the LMS adaptive filter algorithm (Sign, Sign-Sign, Sign-Regressor) were used (implemented in the MATLAB SW tool). The accuracy of the newly proposed CO2 concentration prediction method exceeds 95% in the selected experiments.

Investigating the Effectiveness of Adaptive Step Size LMS Algorithms for the Use with VOIP Applications

Investigating the Effectiveness of Adaptive Step Size LMS Algorithms for the Use with VOIP Applications

Mud Pulse Signal Extraction and Noise Cancellation based on Adaptive LMS and NLMS Algorithms Performance

Mud Pulse Signal Extraction and Noise Cancellation based on Adaptive LMS and NLMS Algorithms Performance - written by Saleh M. Mwachaka published on 2020/05/27 download full article with reference data and citations

An Artifact Elimination in Cardiac Signal using Circular Leaky Normalized LMS Adaptive Algorithm through Iot

In distant cardiac care observing purposes, Electrocardiogram (ECG) waves are infected by artifacts while gaining data and broadcast of signals. The elimination of the noise is a predominant mission for accurate analysis. In this paper, an effort has been made to eliminate the artifacts, mainly baseline wander (BW), muscle artifacts (MA), power line interface (PLI), and Electrode motion (EM) using a Normalized Least mean square error (NLMS) algorithm. Later on to recover the filtering capacity and speed up the convergence process, data normalization is used. The above algorithm is normalized with reference to maximum data normalization which results in lessened computational difficulty in the denominator. Based on the above algorithms, a variety of adaptive signal enhancers (ASE’s) are improved. To decrease the computational difficulty of the signal enhancer, the designed ASE’s are united with sign-based algorithms. The designed ASE’s are analyzed on original ECG signals gained from the MIT-BIH database to evaluate the performance. The reproduction outcomes gained demonstrates that the block based algorithms are finer than NLMS in terms of the signal to noise ratio (SNR), excess mean square error and computational difficulty. Among the NLMS alternatives, the VSS-CLNLMS (Variable Stepsize Circular Leaky Normalized Least Mean Square error) based ASE’s have fine filtering capacity with a lessened number of computations. The development of the SNR obtained in the progression with the use of VSS-CLNLMS-based ASE’s are calculated as 13.2945 dBs, 12.4589 dBs, 15.6179 dBs and 14.0881 dBs respectively for BW, MA, PLI and EM artifacts.

Set-Membership LMS Adaptive Algorithms Based on an Error-Estimation Time-Varying Bound Method

To reduce the computational complexity and enhance the convergence rate, this article presents set-membership least mean square adaptive algorithms based on an error-estimation time-varying bound method. The bound is constituted by the estimation error for the previous iteration and a time-varying error adjustment factor. The set-membership (SM) method utilizes the estimation error for the current iteration and the bound to determine whether to update the weight vector. When the estimation error is larger than the bound, the weight vector is updated; otherwise, no updating is required. Then, by utilizing a nonlinear function between the step size and the estimation error, the step size is modified to further enhance the convergence rate. Compared to the traditional set-membership normalized least mean square algorithms, the simulation results show that the proposed algorithms have the following advantages: (1) fast convergence with low computational costs, (2) maintaining low, steady-state mean square error, (3) enhancing noise resistance in low-SNR environments and (4) estimating the SM bound in noisy environments without requiring noise power estimation.

Comparative study for Active Noise Cancellation using Adaptive filtering and Standing wave pattern

Noise pollution is one of the most fundamental challenges facing our environment, causes health problem, communication inefficiency and degrade the performance of works due to lack of concentration, thus, mitigating this impact becomes an unavoidable requirement of time to protect people's health and the environment. This noise may originate from several sources including industrial machinery, system parts wear out, and adjacent environmental acoustics. To mitigate this noise effect, an Active Noise Cancellation (ANC) headphone is achieved by two effective techniques; Adaptive filtering and Standing wave phenomenon. In this work, an ANC system is designed using both adaptive filtering and standing wave techniques, the former one basically utilizes single-channel feedforward whereas the latter one utilizes both single-channel feedforward and feedback control. LMS adaptive filter algorithm is the basic component of the designed ANC headphone. For simulation, a noise-free signal will be used as the desired audio signal and a gaussian distributed noise as the unwanted noise signal, these are combined to form noise corrupted speech signal. Propose algorithms performance were evaluated based on the ability to mitigate effects of different frequency broad-band noise signals and of different Noise to Signal ratio. Evaluation measures used are; convergence rate and noise reduction in dB. Result reveals ANC headphone using standing wave technique has better performance at mitigating noise frequency below 800Hz, with low SNR than Adaptive filtering. However, at higher frequencies above 1000Hz, ANC headphone using Adaptive filtering has good performance of masking high frequencies up to 22dB.

Application of IIR Digital Filter with A New LMS Adaptive Algorithm

Any system will be inevitably disturbed by noise. The existence of noise affects the processing and application of real signals. How to effectively suppress and eliminate noise has always been a hot spot in the industrial field. In order to design a filter which can properly adjust its parameters according to different environments to obtain the optimal value, this paper designs an adaptive IIR digital filter, and studies as well as improves the adaptive algorithm. A new variable step size LMS algorithm based on multi-scale wavelet transform is proposed in this paper. The wavelet transform domain algorithm belongs to LMS transform domain algorithm and is a new time-frequency analysis method developed, so it has the characteristics of multi-resolution analysis. This adaptive IIR filter designed is applied to suppression and cancellation of noise, and simulation experiments are performed on the MATLAB software platform, so that better illustrating the superiority of this improved algorithm.

Modelling and simulation of KHLMS algorithm‐based DSTATCOM

The assessment of the shunt compensation allied power quality glitches bounds the design and modelling of a controller for the d-FACTS (Distribution Flexible Alternating current Transmission System) device. So, Kernel Hebbian least mean square (KHLMS) is proposed for controlling the distributed static compensator (DSTATCOM) in this study. The KHLMS is the improved version of an adaptive LMS (ALMS), which is designed by using a suitable pattern of learning mechanism. Both the controller algorithms are formulated on the basis of mathematical equations using MATLAB/Simulink. In accordance with the system variation adaptability and experimental application, each phase controller is configured as an independent neural network structure. The objective of control algorithms is used for the extraction of fundamental active and reactive components from load currents for the generation of the reference source currents. In comparison with the ALMS algorithm, the KHLMS demonstrates more effective in improving the voltage regulation at DC link capacitor, voltage balancing, source current harmonic reduction, and power factor correction under the disturbance influences caused by even and uneven loading.

A Novel Adaptive LMS Algorithm with Genetic Search Capabilities for System Identification of Adaptive FIR and IIR Filters

In this paper we introduce a novel adaptation algorithm for adaptive filtering of FIR and IIR digital filters within the context of system identification. The standard LMS algorithm is hybridized with GA (Genetic Algorithm) to obtain a new integrated learning algorithm, namely, LMS-GA. The main aim of the proposed learning tool is to evade local minima, a common problem in standard LMS algorithm and its variants and approaching the global minimum by calculating the optimum parameters of the weights vector when just estimated data are accessible. In the proposed LMS-GA technique, first, it works as the standard LMS algorithm and calculates the optimum filter coefficients that minimize the mean square error, once the standard LMS algorithm gets stuck in local minimum, the LMS-GA switches to GA to update the filter coefficients and explore new region in the search space by applying the cross-over and mutation operators. The proposed LMS-GA is tested under different conditions of the input signal like input signals with colored characteristics, i.e., correlated input signals and investigated on FIR adaptive filter using the power spectral density of the input signal and the Fourier-transform of the input’s correlation matrix. Demonstrations via simulations on system identification of IIR and FIR adaptive digital filters revealed the effectiveness of the proposed LMS-GA under input signals with different characteristics.

Analysis of incremental LMS adaptive algorithm over wireless sensor networks with delayed-links

Wireless sensor networks (WSN) are used for many delay-sensitive applications, e.g. military surveillance, emergency response, city management, etc. Therefore, modeling of delay is very important. This paper presents a study of the impact of sensors' sensing delay, process delay and transmission delay in the estimation of the desired unknown parameter in the WSN. Recently proposed wireless sensor networks, in the literature, assume perfect nodes and links, in view of delay. It means that no consideration has been made about the delay in the sensing, processing and, transmission procedures. The proposed method in this paper analyzes the behavior of the distributed incremental estimation algorithm in the presence of delay in wireless sensor networks. Weighted spatio-temporal energy conservation method is used to evaluate the transient and steady state behavior of the wireless sensor networks with delay without putting any restriction on regressor's distribution. The equations that illustrate mean square deviation (MSD), excess mean square error (EMSE) and mean square error (MSE) behavior of individual nodes, are driven. Also, simulations show that overall delay could be calculated to turn off nodes in some iterations without affecting the performance of the distributed estimation algorithm or adding extra latency to the network, which can improve power management strategies by modifying sleep-wake scheduling protocols. Eventually, it is shown that simulation results have a good match with derived theoretical expressions.

A Variable Step Size LMS Adaptive Filtering Algorithm Based on Maximum Correntropy Criterion for Identification of Low Frequency Oscillation Modes

In this paper, the adaptive filtering based on LMS algorithm is applied to the recognition of low-frequency oscillation mode. The step factor is improved based on Sinh function to accelerate the convergence speed of the algorithm while ensuring a low steady-state error, and the robustness of the algorithm in identification is improved by combining the maximum correlation entropy rule. The effectiveness of the algorithm for low-frequency oscillation mode identification is verified by simulation of the 10-machine 39-node New-England power system.