Automated Seizure Classification Using Deep Neural Network Based on Autoencoder

2020 ◽  
pp. 1-19 ◽  
Author(s):  
Rahul Sharma ◽  
Pradip Sircar ◽  
Ram Bilas Pachori
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Eeg Signals ◽  
Linear Dynamics ◽  
Softmax Classifier ◽  
Domain Expertise ◽  
Electroencephalogram Eeg ◽  
The Brain ◽  
Seizure Classification

A neurological abnormality in the brain that manifests as a seizure is the prime risk of epilepsy. The earlier and accurate detection of the epileptic seizure is the foremost task for the diagnosis of epilepsy. In this chapter, a nonlinear deep neural network is used for seizure classification. The proposed network is based on the autoencoder that significantly explores the non-linear dynamics of the electroencephalogram (EEG) signals. It involves the traditional deep neural domain expertise to extract the features from the raw data in order to fit a deep neural network-based learning model and predicts the class of the unknown seizures. The EEG signals are subjected to an autoencoder-based neural network that unintendedly extracts the significant attributes that are applied to the softmax classifier. The achieved classification accuracy is up to 100% on different publicly available Bonn University database classes. The proposed algorithm is suitable for real-time implementation.

scholarly journals EEG Emotion Classification Using an Improved SincNet-Based Deep Learning Model

2019 ◽  
Vol 9 (11) ◽  
pp. 326 ◽  
Author(s):  
Hong Zeng ◽  
Zhenhua Wu ◽  
Jiaming Zhang ◽  
Chen Yang ◽  
Hua Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Speaker Recognition ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Signal To Noise Ratio ◽  
Single Subject ◽  
Emotion Classification ◽  
Eeg Signals ◽  
Electroencephalogram Eeg ◽  
Deep Learning Model

Deep learning (DL) methods have been used increasingly widely, such as in the fields of speech and image recognition. However, how to design an appropriate DL model to accurately and efficiently classify electroencephalogram (EEG) signals is still a challenge, mainly because EEG signals are characterized by significant differences between two different subjects or vary over time within a single subject, non-stability, strong randomness, low signal-to-noise ratio. SincNet is an efficient classifier for speaker recognition, but it has some drawbacks in dealing with EEG signals classification. In this paper, we improve and propose a SincNet-based classifier, SincNet-R, which consists of three convolutional layers, and three deep neural network (DNN) layers. We then make use of SincNet-R to test the classification accuracy and robustness by emotional EEG signals. The comparable results with original SincNet model and other traditional classifiers such as CNN, LSTM and SVM, show that our proposed SincNet-R model has higher classification accuracy and better algorithm robustness.

PRIOR FORECASTING OF EPILEPTIC SEIZURE AND LOCALIZATION OF EPILEPTOGENIC REGION

2017 ◽  
Vol 29 (02) ◽  
pp. 1750012 ◽  
Author(s):  
Aarti Sharma ◽  
J. K. Rai ◽  
R. P. Tewari
Keyword(s):  
Neural Network ◽  
Epileptic Seizure ◽  
Brain Disorders ◽  
Eeg Signals ◽  
Beta Band ◽  
Signal Average ◽  
Trained Neural Network ◽  
Scalp Electroencephalogram ◽  
Electroencephalogram Eeg ◽  
The Brain

Forecasting of an epileptic seizure and localization of the epileptogenic region is a challenging task. Scalp electroencephalogram (EEG) is the most commonly used signal for studying various brain disorders. This paper presents an algorithm for seizure forecast and detection of epileptogenic region by analyzing EEG signals from frontal, temporal, central and parietal region of the brain. Eight features have been extracted from each EEG signal. Average of features extracted from different regions of brain is computed for each region. An artificial neural network is trained to predict an epileptic seizure by identifying the pre-ictal duration. The trained neural network is tested and found to have an accuracy of 92.3%, sensitivity of 100% and specificity, of 83.3%. Two prominent features, accumulated energy and power in beta band, have been identified to identify the epileptogenic region. The result shows that the region corresponding to temporal lobe has maximum variation in these two features for pre-ictal and inter-ictal duration. The result validates the proposed algorithm to identify the pre-ictal state and predict the seizure in advance and identification of the epileptogenic region.

Intelligent Models to Predict the Prognosis of Premature Neonates According to Their EEG Signals

2017 ◽  
Vol 6 (1) ◽  
pp. 57-66 ◽  
Author(s):  
Yasser Al Hajjar ◽  
Abd El Salam Ahmad Al Hajjar ◽  
Bassam Daya ◽  
Pierre Chauvet
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Decision Tree ◽  
Eeg Signals ◽  
Linear Discriminant ◽  
Premature Newborns ◽  
Intelligent Models ◽  
Intelligent Model ◽  
Electroencephalogram Eeg ◽  
The Brain

The aim of this paper is to find the best intelligent model that allows predicting the future of premature newborns according to their electroencephalogram (EEG). EEG is a signal that measures the electrical activity of the brain. In this paper, the authors used a dataset of 397 EEG records detected at birth of premature newborns and their classification by doctors two years later: normal, sick or risky. They executed machine learning on this dataset using several intelligent models such as multiple linear regression, linear discriminant analysis, artificial neural network and decision tree. They used 14 parameters concerning characteristics extracted from EEG records that affect the prognosis of the newborn. Then, they presented a complete comparative study between these models in order to find who gives best results. Finally, they found that decision tree gave best result with performance of 100% for sick records, 76.9% for risky and 69.1% for normal ones.

Information-based analysis of the coupling between brain and heart reactions to olfactory stimulation

2021 ◽  
pp. 1-11
Author(s):  
Najmeh Pakniyat ◽  
Mohammad Hossein Babini ◽  
Vladimir V. Kulish ◽  
Hamidreza Namazi
Keyword(s):  
Time Series ◽  
Biomedical Science ◽  
Strongly Correlated ◽  
Eeg Signals ◽  
Ecg Signals ◽  
Olfactory Stimuli ◽  
Electrocardiogram Ecg ◽  
First Time ◽  
Electroencephalogram Eeg ◽  
The Brain

BACKGROUND: Analysis of the heart activity is one of the important areas of research in biomedical science and engineering. For this purpose, scientists analyze the activity of the heart in various conditions. Since the brain controls the heart’s activity, a relationship should exist among their activities. OBJECTIVE: In this research, for the first time the coupling between heart and brain activities was analyzed by information-based analysis. METHODS: Considering Shannon entropy as the indicator of the information of a system, we recorded electroencephalogram (EEG) and electrocardiogram (ECG) signals of 13 participants (7 M, 6 F, 18–22 years old) in different external stimulations (using pineapple, banana, vanilla, and lemon flavors as olfactory stimuli) and evaluated how the information of EEG signals and R-R time series (as heart rate variability (HRV)) are linked. RESULTS: The results indicate that the changes in the information of the R-R time series and EEG signals are strongly correlated (ρ=-0.9566). CONCLUSION: We conclude that heart and brain activities are related.

scholarly journals Context-Based Filtering for Assisted Brain-Actuated Wheelchair Driving

2007 ◽  
Vol 2007 ◽  
pp. 1-12 ◽  
Author(s):  
Gerolf Vanacker ◽  
José del R. Millán ◽  
Eileen Lew ◽  
Pierre W. Ferrez ◽  
Ferran Galán Moles ◽  
...  
Keyword(s):  
Control System ◽  
Shared Control ◽  
Eeg Signals ◽  
Intelligent Processing ◽  
Intelligent Wheelchair ◽  
Brain Signals ◽  
Brain Interface ◽  
The Subject ◽  
Electroencephalogram Eeg ◽  
The Brain

Controlling a robotic device by using human brain signals is an interesting and challenging task. The device may be complicated to control and the nonstationary nature of the brain signals provides for a rather unstable input. With the use of intelligent processing algorithms adapted to the task at hand, however, the performance can be increased. This paper introduces a shared control system that helps the subject in driving an intelligent wheelchair with a noninvasive brain interface. The subject's steering intentions are estimated from electroencephalogram (EEG) signals and passed through to the shared control system before being sent to the wheelchair motors. Experimental results show a possibility for significant improvement in the overall driving performance when using the shared control system compared to driving without it. These results have been obtained with 2 healthy subjects during their first day of training with the brain-actuated wheelchair.

scholarly journals Alternative Form of Ordinary Differential Equation of Electroencephalography Signals During an Epileptic Seizure

2021 ◽  
Vol 17 (2) ◽  
pp. 109-113
Author(s):  
Ameen Omar Barja
Keyword(s):  
Differential Equation ◽  
Ordinary Differential Equation ◽  
Epileptic Seizure ◽  
Essential Role ◽  
Clinical Neurophysiology ◽  
Alternative Form ◽  
Eeg Signals ◽  
Seizure Disorders ◽  
Electroencephalogram Eeg ◽  
The Brain

One of the most important fields in clinical neurophysiology is an electroencephalogram (EEG). It is a test used to detect problems related to the brain electrical activity, and it can track and records patterns of brain waves. EEG continues to play an essential role in diagnosis and management of patients with epileptic seizure disorders. Nevertheless, the outcome of EEG as a tool for evaluating epileptic seizure is often interpreted as a noise rather than an ordered pattern. The mathematical modelling of EEG signals provides valuable data to neurologists, and is heavily utilized in the diagnosis and treatment of epilepsy. EEG signals during the seizure can be modeled as ordinary differential equation (ODE). In this study we will present an alternative form of ODE of EEG signals through the seizure.

Signal Processing and Classification for Electroencephalography Based Motor Imagery Brain Computer Interface

2021 ◽  
Vol 11 (12) ◽  
pp. 2918-2927
Author(s):  
A. Shankar ◽  
S. Muttan ◽  
D. Vaithiyanathan
Keyword(s):  
Neural Network ◽  
Signal Processing ◽  
Motor Imagery ◽  
Classification Accuracy ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Discrete Wavelet ◽  
Feature Sets ◽  
Evaluation Of Performance ◽  
The Brain

Brain Computer Interface (BCI) is a fast growing area of research to enable communication between our brains and computers. EEG based motor imagery BCI involves the user imagining movement, the subsequent recording and signal processing on the electroencephalogram signals from the brain, and the translation of those signals into specific commands. Ultimately, motor imagery BCI has the potential to be applied to helping those with special abilities recover motor control. This paper presents an evaluation of performance for EEG based motor imagery BCI with a classification accuracy of 80.2%, making use of features extracted using the Fast Fourier Transform and the Discrete Wavelet Transform, and classification is done using an Artificial Neural Network. It goes on to conclude how the performance is affected by the particular feature sets and neural network parameters.

scholarly journals A Multi-Column CNN Model for Emotion Recognition from EEG Signals

Sensors ◽  
2019 ◽  
Vol 19 (21) ◽  
pp. 4736 ◽  
Author(s):  
Heekyung Yang ◽  
Jongdae Han ◽  
Kyungha Min
Keyword(s):  
Neural Network ◽  
Emotion Recognition ◽  
Deep Neural Network ◽  
Weighted Sum ◽  
Eeg Signals ◽  
Structured Model ◽  
Feature Based ◽  
Improved Accuracy

We present a multi-column CNN-based model for emotion recognition from EEG signals. Recently, a deep neural network is widely employed for extracting features and recognizing emotions from various biosignals including EEG signals. A decision from a single CNN-based emotion recognizing module shows improved accuracy than the conventional handcrafted feature-based modules. To further improve the accuracy of the CNN-based modules, we devise a multi-column structured model, whose decision is produced by a weighted sum of the decisions from individual recognizing modules. We apply the model to EEG signals from DEAP dataset for comparison and demonstrate the improved accuracy of our model.

scholarly journals An Optimized Channel Selection Method Based on Multifrequency CSP-Rank for Motor Imagery-Based BCI System

2019 ◽  
Vol 2019 ◽  
pp. 1-10 ◽  
Author(s):  
Jian Kui Feng ◽  
Jing Jin ◽  
Ian Daly ◽  
Jiale Zhou ◽  
Yugang Niu ◽  
...  
Keyword(s):  
Motor Imagery ◽  
Classification Accuracy ◽  
Channel Selection ◽  
Selection Method ◽  
Selection Methods ◽  
Eeg Signals ◽  
Common Spatial Pattern ◽  
Linear Discriminant ◽  
Novel Method ◽  
Electroencephalogram Eeg

Background. Due to the redundant information contained in multichannel electroencephalogram (EEG) signals, the classification accuracy of brain-computer interface (BCI) systems may deteriorate to a large extent. Channel selection methods can help to remove task-independent electroencephalogram (EEG) signals and hence improve the performance of BCI systems. However, in different frequency bands, brain areas associated with motor imagery are not exactly the same, which will result in the inability of traditional channel selection methods to extract effective EEG features. New Method. To address the above problem, this paper proposes a novel method based on common spatial pattern- (CSP-) rank channel selection for multifrequency band EEG (CSP-R-MF). It combines the multiband signal decomposition filtering and the CSP-rank channel selection methods to select significant channels, and then linear discriminant analysis (LDA) was used to calculate the classification accuracy. Results. The results showed that our proposed CSP-R-MF method could significantly improve the average classification accuracy compared with the CSP-rank channel selection method.

Sign in / Sign up

Export Citation Format

Share Document