Fish Swarm Optimized Deep Hopfield Neural Network-Assisted HCI System for Augmentative Communication Using a Visual Feedback System

2021 ◽  
Author(s):  
Shuo Li ◽  
Jianjun Li ◽  
Priyan Malarvizhi Kumar ◽  
Ashish Kr. Luhach
Keyword(s):  
Neural Network ◽  
Visual Feedback ◽  
Feedback System ◽  
Hopfield Neural Network ◽  
Augmentative Communication ◽  
Human Computer Interface ◽  
Eeg Signals ◽  
Portable Monitor ◽  
Communication Approach ◽  
Electroencephalogram Eeg

In this context, the uses of computers, the Human-computer interface (HCI) system, can assist interaction on-demand services. HCI method facilitates ventilated patients to interact with computers about their needs using their brain’s electrical activity. To accomplish this, an HCI framework is developed in this research to facilitate visual feedback system (VFS) using an augmentative communication approach. Augmentative communication (AC.) or icon-based services are incorporated with a portable monitor placed in front of a patient; they can look at the screen to select (ask) their appropriate needs-related icons. The services have been achieved by capturing and processing patients’ electromagnetic brain activates during the icon selection by their eye flickering moment recording using wearable Electroencephalogram (EEG). The flickering icons on the screen conveying an appropriate message to the monitoring unit computer, and the monitoring unit can respond to the patient’s request using VFS. The HCI system is comprised of the following methodologies to achieve augmentative communication-based services such as EEG signals acquisition, filtering, partition-based feature extraction, and fusion and fish swarm optimized Deep Hopfield neural network FSODHNN based classifier. The evolution results of the VSF based HCI framework are demonstrated successfully. It obtained the highest accuracy of 99.11%, specificity of 99.05%, the sensitivity of 99.09%, and the lowest RMSE of 0.98, MSE of 0.92 in icon identification/selection.

Identification of Epileptic Electroencephalograms Signals Using an Integrated Transfer Radius Basis Function Neural Network

2020 ◽  
Vol 10 (7) ◽  
pp. 1584-1589
Author(s):  
Chi Hua ◽  
Li Liu ◽  
Liang Kuang ◽  
Dechang Pi
Keyword(s):  
Neural Network ◽  
Basis Function ◽  
Signal Recognition ◽  
Physical And Mental Health ◽  
Eeg Signals ◽  
Integration Strategy ◽  
Training Samples ◽  
Number Of Patients ◽  
Electroencephalogram Eeg

As a common brain disease, epilepsy is rapidly increasing in terms of the number of patients. Long-term repeated sudden seizures seriously affect the physical and mental health of patients. Epileptic electroencephalogram (EEG) signals are an effective tool in the hands of clinicians for diagnosing epilepsy, and how to use computer technology to automatically analyze and detect epileptic EEG signals has become very meaningful. This article proposes a method for effectively identifying epileptic EEGs for further diagnosis of epilepsy. The traditional modeling method default is to train on training samples and test samples that obey the same distribution, which usually does not match the actual situation. Therefore, a transfer learning (TL) mechanism is introduced to a classical radial basis function neural network (RBFNN). Considering the limited stability of a single classifier, this article introduces an integration strategy and proposes an integrated transfer RBFNN (ITRBFNN) algorithm. Experimental results of EEG signal recognition for epilepsy show that the algorithm has better adaptability of scene transfer and stability.

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.

Research of Classification Methods of EEG Signal Based on Wavelet Packet Transform and LVQ Neural

2014 ◽  
Vol 1049-1050 ◽  
pp. 1626-1630
Author(s):  
Xue Yan Pang ◽  
Shi Nin Yin ◽  
Hong Zhou Li ◽  
Jian Ming Zhu ◽  
Zhen Cheng Chen
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Wavelet Packet ◽  
Recognition Rate ◽  
Signal Recognition ◽  
Eeg Signals ◽  
Specific Frequency ◽  
Correct Recognition Rate ◽  
Electroencephalogram Eeg

In order to improve the correct recognition rate of EEG(Electroencephalogram,EEG) signals to meet the needs of Brain-Computer Interface system,this paper put forward a new method of signal recognition which combines wavelet packet decomposition and LVQ neural network.First,using the method of wavelet packet to analyze the signal,and then extract the specific frequency band’s energy of wavelet packet as characteristics.Then using the LVQ neural network model to study the distinguishing between the two EEG datas of Motor Imagery.The simulation experiment uses Matlab software to design LVQ neural network model to judge the two kinds of Motor Imagery task.In the process of judgment,respecti-vely to classify the data by using BP neural network and LVQ neural network.Experimental results show that the LVQ neural network can have a higher correct accuracy to recognize the motor imaginary task than BP neural.

scholarly journals A multiplex visibility graph motif‐based convolutional neural network for characterizing sleep stages using EEG signals

2020 ◽  
Vol 6 (4) ◽  
pp. 355-363
Author(s):  
Qing Cai ◽  
Jianpeng An ◽  
Zhongke Gao
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Sleep Stage ◽  
Network Motif ◽  
Visibility Graph ◽  
Sleep Stages ◽  
Dynamic Features ◽  
Eeg Signals ◽  
Graph Motif ◽  
Electroencephalogram Eeg

Sleep is an essential integrant in everyone’s daily life; therefore, it is an important but challenging problem to characterize sleep stages from electroencephalogram (EEG) signals. The network motif has been developed as a useful tool to investigate complex networks. In this study, we developed a multiplex visibility graph motif‐based convolutional neural network (CNN) for characterizing sleep stages using EEG signals and then introduced the multiplex motif entropy as the quantitative index to distinguish the six sleep stages. The independent samples t‐test shows that the multiplex motif entropy values have significant differences among the six sleep stages. Furthermore, we developed a CNN model and employed the multiplex motif sequence as the input of the model to classify the six sleep stages. Notably, the classification accuracy of the six‐state stage detection was 85.27%. Results demonstrated the effectiveness of the multiplex motif in characterizing the dynamic features underlying different sleep stages, whereby they further provide an essential strategy for future sleep‐stage detection research.

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.

scholarly journals Classification of EEG Signals Using Quantum Neural Network and Cubic Spline

2016 ◽  
Vol 62 (4) ◽  
pp. 401-408
Author(s):  
Mariam Abdul-Zahra Raheem ◽  
Ehab AbdulRazzaq Hussein
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Cubic Spline ◽  
Eeg Signals ◽  
Quantum Neural Network ◽  
Average Accuracy ◽  
Three Stages ◽  
Simulation Results ◽  
Electroencephalogram Eeg

Abstract The main aim of this paper is to propose Cubic Spline-Quantum Neural Network (CS-QNN) model for analysis and classification of Electroencephalogram (EEG) signals. Experimental data used here were taken from seven different electrodes. The work has been done in three stages, normalization of the signals, extracting the features by Cubic Spline Technique (CST) and classification using Quantum Neural Network (QNN). The simulation results showed that five types of EEG signals were classified with an average accuracy for seven electrodes that is 94.3% when training 70% of the features while with an average accuracy of 92.84% when training 50% of the features.

Sign in / Sign up

Export Citation Format

Share Document