Wavelet neural network classification of EEG signals by using AR model with MLE preprocessing

Neural networks are trained to classify half-second segments of six-channel, EEG data into one of five classes corresponding to five cognitive tasks performed by four subjects. Two and three-layer feedforward neural networks are trained using 10-fold cross-validation and early stopping to control over-fitting. EEG signals were represented as autoregressive (AR) models. The average percentage of test segments correctly classified ranged from 71% for one subject to 38% for another subject. Cluster analysis of the resulting neural networks’ hidden-unit weight vectors identifies which EEG channels are most relevant to this discrimination problem.

https://sce.uhcl.edu/boetticher/CSCI5931%20Computer%20Human%20Interaction/Classification%20of%20EEG%20signals%20from%20four%20subjects%20during%20five%20mental%20tasks.pdf

Classification of EEG Signals from Four Subjects During Five Mental Tasks

This paper presents an enhanced particle filter (PF) approach for predicting remaining useful life (RUL) of rolling bearings. In the presented approach, particles in each recursive step are used to determine an alterable importance density function and the backpropagation neutral network is utilized to improve the particle diversity before resampling. Based on the enhanced PF, the framework of online rolling bearing RUL prediction is designed and a multiorder autoregressive model is used to construct the dynamic model for PF. Case studies performed on a simulation example and two test-to-failure experiments indicate that the presented approach can accurately predict the RUL of rolling bearings and it can achieve better performance than the traditional PF-based approach and commonly used support vector regression approach.

Remaining Useful Life Prediction of Rolling Bearings Using an Enhanced Particle Filter

This paper presents an integrated approach, which combines recurrence quantification analysis (RQA) with the Kalman filter, for bearing degradation evaluation. The RQA, a nonlinear signal processing method, is applied to extracting recurrence plot entropy features from vibration signals as input to build an autoregression (AR) model. This AR model is used to estimate parameters of the dynamic model of the bearing, and the Kalman filter is then utilized to obtain optimal prediction results on the bearing degradation state from its dynamic model. Case studies performed on two test-to-failure experiments indicate that the presented approach can predict occurrence of the bearing failure 50 min in advance.

Bearing Degradation Evaluation Using Recurrence Quantification Analysis and Kalman Filter

Current trends in clinical applications demand automation in electrocardiogram (ECG) signal processing and heart beat classification. This paper examines the design of an effective recognition method to diagnose heart diseases. The proposed method consists of three main modules: de-noising module, feature extraction module, and classifier module. In the de-noising module, multiscale principal component analysis (MSPCA) is used for noise reduction of the ECG signals. In the feature extraction module, autoregressive (AR) modeling is used for extracting features. In the classifier module, different classifiers are examined such as simple logistic, k-nearest neighbor, multilayer perceptron, radial basis function networks, and support vector machines. Different experiments are carried out using the MIT-BIH arrhythmia database to classify different ECG heart beats and the performance of the proposed method is evaluated in terms of several standard metrics. The experimental results show that the proposed method is able to reduce noise from the noisy ECG signals more accurately in comparison to previous methods. The numerical results indicated that the proposed algorithm achieved 99.93 % of the classification accuracy using MSPCA de-noising and AR modeling.

Effect of Multiscale PCA De-noising in ECG Beat Classification for Diagnosis of Cardiovascular Diseases

A new method for on-line spectral estimation of nonstationary time series via autoregressive (AR) model construction is proposed. The method consists of on-line parameter estimation based on the recursive least squares ladder estimation algorithm with a forgetting factor and on-line order determination based on AIC with some modifications. The effectiveness of the proposed method is demonstrated by computer simulation study and applying to the actual data of electroencephalogram (EEG). >

K. Uosaki

Papers

On-line spectral estimation of nonstationary time series based on AR model parameter estimation and order selection with a forgetting factor