Search

This paper presents a comparison between the electroencephalogram (EEG) channels during scoliosis correction surgeries. Surgeons use many hand tools and electronic devices that directly affect the EEG channels. These noises do not affect the EEG channels uniformly. This research provides a complete system to find the least affected channel by the noise. The presented system consists of five stages: filtering, wavelet decomposing (Level 4), processing the signal bands using four different criteria (mean, energy, entropy and standard deviation), finding the useful channel according to the criteria's value and, finally, generating a combinational signal from Channels 1 and 2. Experimentally, two channels of EEG data were recorded from six patients who underwent scoliosis correction surgeries in the Pusat Perubatan Universiti Kebangsaan Malaysia (PPUKM) (the Medical center of National University of Malaysia). The combinational signal was tested by power spectral density, cross-correlation function and wavelet coherence. The experimental results show that the system-outputted EEG signals are neatly switched without any substantial changes in the consistency of EEG components. This paper provides an efficient procedure for analyzing EEG signals in order to avoid averaging the channels that lead to redistribution of the noise on both channels, reducing the dimensionality of the EEG features and preparing the best EEG stream for the classification and monitoring stage.

Biosignal analysis is one of the most important topics that researchers have tried to develop during the last century to understand numerous human diseases. Electroencephalograms (EEGs) are one of the techniques which provides an electrical representation of biosignals that reflect changes in the activity of the human brain. Monitoring the levels of anesthesia is a very important subject, which has been proposed to avoid both patient awareness caused by inadequate dosage of anesthetic drugs and excessive use of anesthesia during surgery. This article reviews the bases of these techniques and their development within the last decades and provides a synopsis of the relevant methodologies and algorithms that are used to analyze EEG signals. In addition, it aims to present some of the physiological background of the EEG signal, developments in EEG signal processing, and the effective methods used to remove various types of noise. This review will hopefully increase efforts to develop methods that use EEG signals for determining and classifying the depth of anesthesia with a high data rate to produce a flexible and reliable detection device.

Electroencephalogram (EEG) signals immensely suffer from several physiological artifacts, including electrooculogram (EOG), electromyogram (EMG), and electrocardiogram (ECG) artifacts, which must be removed to ensure EEG's usability. This paper proposes a novel one-dimensional convolutional neural network (1D-CNN), i.e., MultiResUNet3+, to denoise physiological artifacts from corrupted EEG. A publicly available dataset containing clean EEG, EOG, and EMG segments is used to generate semi-synthetic noisy EEG to train, validate and test the proposed MultiResUNet3+, along with four other 1D-CNN models (FPN, UNet, MCGUNet, LinkNet). Adopting a five-fold cross-validation technique, all five models' performance is measured by estimating temporal and spectral percentage reduction in artifacts, temporal and spectral relative root mean squared error, and average power ratio of each of the five EEG bands to whole spectra. The proposed MultiResUNet3+ achieved the highest temporal and spectral percentage reduction of 94.82% and 92.84%, respectively, in EOG artifacts removal from EOG-contaminated EEG. Moreover, compared to the other four 1D-segmentation models, the proposed MultiResUNet3+ eliminated 83.21% of the spectral artifacts from the EMG-corrupted EEG, which is also the highest. In most situations, our proposed model performed better than the other four 1D-CNN models, evident by the computed performance evaluation metrics. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (η). The proposed MLMRS-Net model has shown the best denoising performance, producing an average ΔSNR, η, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of average η improvement. [ABSTRACT FROM AUTHOR]

In this study, we considered HT ht , as in an ideal situation, the "reference ground truth" and the motion corrupted signal over the artifacts-free epochs would always be completely correlated. Hence, the following equation was used to estimate HT ht : (16) HT ht 4. On the other hand, general assumptions regarding the artifact signal HT ht includes temporal localization, not normally distributed with high local variance. [Extracted from the article]

Epileptic seizures are temporary episodes of convulsions, where approximately 70 percent of the diagnosed population can successfully manage their condition with proper medication and lead a normal life. Over 50 million people worldwide are affected by some form of epileptic seizures, and their accurate detection can help millions in the proper management of this condition. Increasing research in machine learning has made a great impact on biomedical signal processing and especially in electroencephalogram (EEG) data analysis. The availability of various feature extraction techniques and classification methods makes it difficult to choose the most suitable combination for resource-efficient and correct detection. This paper intends to review the relevant studies of wavelet and empirical mode decomposition-based feature extraction techniques used for seizure detection in epileptic EEG data. The articles were chosen for review based on their Journal Citation Report, feature selection methods, and classifiers used. The high-dimensional EEG data falls under the category of '3N' biosignals—nonstationary, nonlinear, and noisy; hence, two popular classifiers, namely random forest and support vector machine, were taken for review, as they are capable of handling high-dimensional data and have a low risk of over-fitting. The main metrics used are sensitivity, specificity, and accuracy; hence, some papers reviewed were excluded due to insufficient metrics. To evaluate the overall performances of the reviewed papers, a simple mean value of all metrics was used. This review indicates that the system that used a Stockwell transform wavelet variant as a feature extractor and SVM classifiers led to a potentially better result. [ABSTRACT FROM AUTHOR]