An automated diagnosis of depression using three-channel bandwidth-duration localized wavelet filter bank with EEG signals

2018 ◽  
Vol 52 ◽  
pp. 508-520 ◽  
Author(s):  
Manish Sharma ◽  
P.V. Achuth ◽  
Dipankar Deb ◽  
Subha D. Puthankattil ◽  
U. Rajendra Acharya
Keyword(s):  
Filter Bank ◽  
Wavelet Filter ◽  
Automated Diagnosis ◽  
Eeg Signals ◽  
Channel Bandwidth ◽  
Wavelet Filter Bank

Three Channel Wavelet Filter Banks With Minimal Time Frequency Spread for Classification of Seizure-Free and Seizure EEG Signals

2020 ◽  
pp. 220-236
Author(s):  
Dinesh Bhati ◽  
Akruti Raikwar ◽  
Ram Bilas Pachori ◽  
Vikram M. Gadre
Keyword(s):  
Classification Accuracy ◽  
Filter Bank ◽  
Optimality Criteria ◽  
Wavelet Filter ◽  
Eeg Signals ◽  
Time Frequency ◽  
Minimal Time ◽  
Frequency Spread ◽  
Band Filter ◽  
Wavelet Filter Bank

The authors compute the classification accuracy of minimal time-frequency spread wavelet filter bank with three channels in discriminating seizure-free and seizure electroencephalogram (EEG) signals. Wavelet filter bank with three channels generates two wavelet functions and one scaling function at the first level of wavelet decomposition. A time-frequency localized filter bank can be generated by minimizing the time spread and frequency spread of any one or all the functions simultaneously. The minimal time-frequency spread wavelet filter bank with three channels of regularity order, one designed with several different time-frequency optimality criteria and length six, are chosen, and the effect of each optimality criterion on the discrimination of seizure-free and seizure EEG signals is computed. The classification accuracy for five different optimality criteria are computed. Time-frequency localized three-band filter bank of length six classifies, the seizure-free and seizure EEG signals of Bonn University EEG database, with 98.25% of accuracy.

scholarly journals Automatic Sleep-Stage Scoring in Healthy and Sleep Disorder Patients Using Optimal Wavelet Filter Bank Technique with EEG Signals

2021 ◽  
Vol 18 (6) ◽  
pp. 3087 ◽  
Author(s):  
Manish Sharma ◽  
Jainendra Tiwari ◽  
U. Rajendra Acharya
Keyword(s):  
Machine Learning ◽  
Filter Bank ◽  
Sleep Stage ◽  
Normal Subjects ◽  
Kappa Coefficient ◽  
Sleep Stages ◽  
Wavelet Filter ◽  
Eeg Signals ◽  
Wavelet Filter Bank ◽  
Sleep Stage Scoring

Sleep stage classification plays a pivotal role in effective diagnosis and treatment of sleep related disorders. Traditionally, sleep scoring is done manually by trained sleep scorers. The analysis of electroencephalogram (EEG) signals recorded during sleep by clinicians is tedious, time-consuming and prone to human errors. Therefore, it is clinically important to score sleep stages using machine learning techniques to get accurate diagnosis. Several studies have been proposed for automated detection of sleep stages. However, these studies have employed only healthy normal subjects (good sleepers). The proposed study focuses on the automated sleep-stage scoring of subjects suffering from seven different kind of sleep disorders such as insomnia, bruxism, narcolepsy, nocturnal frontal lobe epilepsy (NFLE), periodic leg movement (PLM), rapid eye movement (REM) behavioural disorder and sleep-disordered breathing as well as normal subjects. The open source physionet’s cyclic alternating pattern (CAP) sleep database is used for this study. The EEG epochs are decomposed into sub-bands using a new class of optimized wavelet filters. Two EEG channels, namely F4-C4 and C4-A1, combined are used for this work as they can provide more insights into the changes in EEG signals during sleep. The norm features are computed from six sub-bands coefficients of optimal wavelet filter bank and fed to various supervised machine learning classifiers. We have obtained the highest classification performance using an ensemble of bagged tree (EBT) classifier with 10-fold cross validation. The CAP database comprising of 80 subjects is divided into ten different subsets and then ten different sleep-stage scoring tasks are performed. Since, the CAP database is unbalanced with different duration of sleep stages, the balanced dataset also has been created using over-sampling and under-sampling techniques. The highest average accuracy of 85.3% and Cohen’s Kappa coefficient of 0.786 and accuracy of 92.8% and Cohen’s Kappa coefficient of 0.915 are obtained for unbalanced and balanced databases, respectively. The proposed method can reliably classify the sleep stages using single or dual channel EEG epochs of 30 s duration instead of using multimodal polysomnography (PSG) which are generally used for sleep-stage scoring. Our developed automated system is ready to be tested with more sleep EEG data and can be employed in various sleep laboratories to evaluate the quality of sleep in various sleep disorder patients and normal subjects.

Measurement of reverberation time of a passenger car utilizing the wavelet filter bank

2005 ◽  
Vol 219 (3) ◽  
pp. 329-336 ◽  
Author(s):  
Sang-Kwon Lee ◽  
Dong-June Yu
Keyword(s):  
Filter Bank ◽  
Bandpass Filter ◽  
Wavelet Filter ◽  
Reverberation Time ◽  
Passenger Cars ◽  
Passenger Car ◽  
Concert Hall ◽  
Low Level ◽  
Wavelet Filter Bank

A few researchers have tried to find the measurement of the reverberation time of a passenger car. However, this has proved to be extremely difficult because the reverberation time of a passenger car is too short to measure using the traditional bandpass filter. If the reverberation time is very short, the product of the reverberation time ( T) and the bandwidth ( B) of the traditional bandpass filter is very small. The low level of the product BT required for the measurement of the reverberation time using the traditional bandpass filter is 16. In order to overcome this problem, the wavelet filter bank has been developed. In the paper, this new wavelet filter is employed to measure the reverberation times of five different classes of passenger car. The low level of the product BT required for the measurement of reverberation time using the wavelet filter is 4. Therefore, it was possible to measure the reverberation times of five passenger cars successfully using the new wavelet filter bank. It is found that the reverberation times measured in most passenger cars are around 0.04. It is a very short reverberation time compared with those of general acoustic rooms like a concert hall.

Sign in / Sign up

Export Citation Format

Share Document