The use of wavelet transform as a preprocessor for the neural network detection of EEG spikes

Kalaycı, T.; Özdamar, Özcan; Erdöl, Nurgün

doi:10.1109/secon.1994.324252

Cited by 13 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is based on the idea that wavelet analysis can provide accurate and specific time-frequency decomposition of neurologic signals. This method has already been applied to EEG denoising [18,24,25], ERP component separation [26], spindle and spike detection [27,28,29], etc. It allowed an automatic processing of the signal and provided both qualitative and quantitative information.…”

Section: Discussionmentioning

confidence: 99%

Development of Wavelet-Based Tools for Event Related Potentials’ N400 Detection: Application to Visual and Auditory Vowelling and Semantic Priming in Arabic Language

Mountaj¹,

Hamzaoui²,

Himmi³

et al. 2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Neurological signals are generally very weak in amplitude and strongly noisy. As a result, one of the major challenges in neuroscience is to be able to eliminate noise and thus exploit the maximum amount of information contained in neurological signals (EEG...). In this paper, we aimed at studying the N400 wave of the Event-Related Potentials (ERPs) that may reflect the effects of vowelling and semantic priming in Arabic language. To improve the quality of the recorded ERP signals, we considered a nonlinear filtering method based on 10th order Daubechies discrete wavelet transform combined to principal component analysis (PCA). Among all tested wavelets, the Daubechies one showed high values of the used signal processing metrics. Thus, it allowed a significant enhancement of the signal to noise ratio while using only 10 ERP trials. In addition, we confirm its effectiveness while comparing the filtered outputs to those obtained using the averaging technique implemented in the conventional EEGLab toolbox. In a second step, the Mexican Hat function was used to achieve continuous wavelet analysis of the filtered signals. This timescale analysis method permitted to get an alternative representation of the ERPs and to detect the N400 wave with significantly greater accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Development of Wavelet-Based Tools for Event Related Potentials’ N400 Detection: Application to Visual and Auditory Vowelling and Semantic Priming in Arabic Language

Mountaj¹,

Hamzaoui²,

Himmi³

et al. 2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…A study introducing the use of WT as preprocessor for neural network detection of EEG spikes [4] involved a 16 channel recording of 4 patients sampled at a rate of 100 Hz. EEG experts labelled the recordings as spikes and non-spikes.…”

Section: Feature Extractionmentioning

confidence: 99%

A Proposal to Automate Seizure Detection based on a Comparative Study of EEG Signal Analysis

Telang¹,

More²,

Modi³

et al. 2017

IJCA

View full text Add to dashboard Cite

Epilepsy is a chronic neurological disorder which is characterized by recurrent and sudden seizures. People with epilepsy suffer from multiple types of seizures and Electroencephalography is an important clinical tool for diagnosing, monitoring and managing neurological disorders related to epilepsy. EEG signals are most often used to diagnose epilepsy, as seizures cause anomalies in EEG readings. In today's world where adult life expectancy is rising and humans are living longer than ever before, the healthcare system generates vast amounts of data, including EEG signals. This paper examines the prospects and challenges faced in utilizing this data in order to optimize seizure detection in order to improve the patients' quality of life. This paper also explores how Machine Learning can be applied to extract features and analyze the EEG signals and propose methods to achieve high classification accuracy.

show abstract

“…Wavelet analysis of EEG has also been extensively used for signal processing applications in intelligent detection systems for use in clinical settings [137,138]. Wavelet transform has also been used for compression EEG signals, Wavelet compression techniques have been shown to improve neuroelectric data compression ratios with little loss of signal information [136,139,140].…”

Section: Applying Discrete Wavelet Transform On Eegmentioning

confidence: 99%

A physiological signal processing system for optimal engagement and attention detection

Belle

Hobson

Najarian

2011

2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW)

View full text Add to dashboard Cite

The use of wavelet transform as a preprocessor for the neural network detection of EEG spikes

Cited by 13 publications

References 9 publications

Development of Wavelet-Based Tools for Event Related Potentials’ N400 Detection: Application to Visual and Auditory Vowelling and Semantic Priming in Arabic Language

Development of Wavelet-Based Tools for Event Related Potentials’ N400 Detection: Application to Visual and Auditory Vowelling and Semantic Priming in Arabic Language

A Proposal to Automate Seizure Detection based on a Comparative Study of EEG Signal Analysis

A physiological signal processing system for optimal engagement and attention detection

Contact Info

Product

Resources

About