scholarly journals Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

2021 ◽  
Vol 15 ◽  
Author(s):  
Afshin Shoeibi ◽  
Delaram Sadeghi ◽  
Parisa Moridian ◽  
Navid Ghassemi ◽  
Jónathan Heras ◽  
...  
Keyword(s):  
Activation Function ◽  
Brain Regions ◽  
Support Vector ◽  
Eeg Signals ◽  
Convolutional Networks ◽  
Conventional Machine ◽  
Intelligent Methods ◽  
Time Frames ◽  
The Brain

Schizophrenia (SZ) is a mental disorder whereby due to the secretion of specific chemicals in the brain, the function of some brain regions is out of balance, leading to the lack of coordination between thoughts, actions, and emotions. This study provides various intelligent deep learning (DL)-based methods for automated SZ diagnosis via electroencephalography (EEG) signals. The obtained results are compared with those of conventional intelligent methods. To implement the proposed methods, the dataset of the Institute of Psychiatry and Neurology in Warsaw, Poland, has been used. First, EEG signals were divided into 25 s time frames and then were normalized by z-score or norm L2. In the classification step, two different approaches were considered for SZ diagnosis via EEG signals. In this step, the classification of EEG signals was first carried out by conventional machine learning methods, e.g., support vector machine, k-nearest neighbors, decision tree, naïve Bayes, random forest, extremely randomized trees, and bagging. Various proposed DL models, namely, long short-term memories (LSTMs), one-dimensional convolutional networks (1D-CNNs), and 1D-CNN-LSTMs, were used in the following. In this step, the DL models were implemented and compared with different activation functions. Among the proposed DL models, the CNN-LSTM architecture has had the best performance. In this architecture, the ReLU activation function with the z-score and L2-combined normalization was used. The proposed CNN-LSTM model has achieved an accuracy percentage of 99.25%, better than the results of most former studies in this field. It is worth mentioning that to perform all simulations, the k-fold cross-validation method with k = 5 has been used.

scholarly journals Best Feature Extraction and Classification Algorithms for EEG Signals in Neuromarketing

2020 ◽  
Author(s):  
Jafar Zamani ◽  
Ali Boniadi Naieni
Keyword(s):  
Feature Extraction ◽  
Brain Activity ◽  
Support Vector ◽  
High Temporal Resolution ◽  
Discrete Wavelet ◽  
Eeg Signal ◽  
Eeg Signals ◽  
High Efficient ◽  
The Brain

Purpose: There are many methods for advertisements of products and neuromarketing is new area in this field. In neuromarketing, we use neuroscience information for revealing Consumer behavior by extracting brain activity. Functional Magnetic Resonance Imaging (fMRI), Magnetoencephalography (MEG), and Electroencephalography (EEG) are high efficient tools for investigating the brain activity in neuromarketing. EEG signal is a high temporal resolution and a cheap method for examining the brain activity. Materials and Methods: 32 subjects (16 males and 16 females) aging between 20-35 years old participated in this study. We proposed neuromarketing method exploit EEG system for predicting consumer preferences while they view E-commerce products. We apply some important preprocessing steps for noise and artifacts elimination of the EEG signal. In next step feature extraction methods are applied on the EEG data such as Discrete Wavelet Transform (DWT) and statistical features. The goal of this study is classification of analyzed EEG signal to likes and dislikes using supervised algorithms. We use Support Vector Machine (SVM), Artificial Neural Network (ANN) and Random Forest (RF) for data classification. The mentioned methods were used for whole and lobe brain data. Results: The results show high efficacy for SVM algorithms than other methods. Accuracy, sensitivity, specificity and precision parameters were used for evaluation of the model performance. The results show high performance of SVM algorithms for classification of the data with accuracy more than 87% and 84% for whole and parietal lobe data. Conclusion: We designed a tool with EEG signals for extraction brain activity of consumers using neuromarketing methods. We investigated the effects of advertising on brain activity of consumers by EEG signals measures.

scholarly journals Identification and Research of Adhd and Healthy Controls using Fmri

2019 ◽  
Vol 8 (6S) ◽  
pp. 370-372
Keyword(s):  
Brain Regions ◽  
Healthy Controls ◽  
Hyperactivity Disorder ◽  
Network Activation ◽  
Healthy Control ◽  
Temporal And Spatial ◽  
The Individual ◽  
The Brain ◽  
Coronal View

Analyzing the brain regions for different activations corresponding to the activation input for an experimental setup of task functional MRI or a resting state functional Magnetic Resonance Imaging(fMRI) for a diagnosed or healthy control is a challenging issue as the processing data is voluminous 4D data with nearly 1,51,552 voxels for a single volume of 261 scans fMRI. The data considered for analysis consists of 10 healthy controls and 10 Attention Deficit Hyperactivity Disorder(ADHD) fMRI. The workflow starts with preprocessing the individual scan for realignment, coregistration and Normalisation to Montreal Neurological Institute (MNI) space. Single site scan visit consists of 64x64x37 voxels. Seventy independent components are obtained from processed data by data reduction, Independent Component Analysis (ICA) calculation, Back reconstruction and Component Calibration. ICA performs satisfactorily well on temporal and spatial localization. Visual medial network activation is pronounced in ADHD Controls than in healthy people. Sagittal, Axial and Coronal view of ADHD controls is obtained as component number 42.The analysis is further used for the automatic classification of healthy controls and ADHD people.

Tumor Classification Based on Regional Heterogeneity Using Pixel Level Feature Descriptors

2021 ◽  
Vol 11 (5) ◽  
pp. 1481-1488
Author(s):  
C. Gunasundari ◽  
K. Selva Bhuvaneswari
Keyword(s):  
Texture Analysis ◽  
Early Stage ◽  
Pituitary Tumors ◽  
Brain Regions ◽  
Regional Heterogeneity ◽  
Gradient Based ◽  
Classification Of Tumors ◽  
Effective Diagnosis ◽  
The Brain

Brain tumor is considered to be widely analyzed disease for effective diagnosis and treatment planning. Several approaches were framed to detect and diagnose tumor at early stage. In this work, texture analysis is carried out to analyze the nature of tumor and categorize it. Around 3064 images were analyzed during this study consisting of meningioma, glioma and pituitary tumors. Intensity and gradient pixel based texture analysis is carried out in this analysis. Results confirm that the tumors can be classified and categorized based on the intensity and gradient pixel information. A total of 2216 feature vector is extracted it is observed that the gradient based information aids for better classification of tumors. Localized binary patterns are found to provide detailed information about the subtle variation in the brain regions due to the presence of abnormality in brain tissues. It is further observed that the normalized feature vectors show better differentiation between tumor categories. The ROC and PRC curves exhibit the high classification ability using the extracted features to differentiate tumor grades.

Classification Algorithms for EEG-Based Brain-Computer Interface

2019 ◽  
pp. 52-73
Author(s):  
Sravanth Kumar Ramakuri ◽  
Chinmay Chakraboirty ◽  
Anudeep Peddi ◽  
Bharat Gupta
Keyword(s):  
Brain Activity ◽  
Biomedical Signal Processing ◽  
Computer Interface ◽  
Eeg Signals ◽  
Large Sets ◽  
Eeg Data ◽  
Important Measurement ◽  
The Brain

In recent years, a vast research is concentrated towards the development of electroencephalography (EEG)-based human-computer interface in order to enhance the quality of life for medical as well as nonmedical applications. The EEG is an important measurement of brain activity and has great potential in helping in the diagnosis and treatment of mental and brain neuro-degenerative diseases and abnormalities. In this chapter, the authors discuss the classification of EEG signals as a key issue in biomedical research for identification and evaluation of the brain activity. Identification of various types of EEG signals is a complicated problem, requiring the analysis of large sets of EEG data. Representative features from a large dataset play an important role in classifying EEG signals in the field of biomedical signal processing. So, to reduce the above problem, this research uses three methods to classify through feature extraction and classification schemes.

Automatic Detection and Classification of Ischemic Stroke Using K-Means Clustering and Texture Features

2016 ◽  
pp. 441-461
Author(s):  
N. Hema Rajini ◽  
R. Bhavani
Keyword(s):  
Ischemic Stroke ◽  
Life Support ◽  
Texture Features ◽  
Support Vector ◽  
Clustering Technique ◽  
Computed Tomography Images ◽  
Brain Extraction ◽  
Third Stage ◽  
The Brain

Computed tomography images are widely used in the diagnosis of ischemic stroke because of its faster acquisition and compatibility with most life support devices. This chapter presents a new approach to automated detection of ischemic stroke using k-means clustering technique which separates the lesion region from healthy tissues and classification of ischemic stroke using texture features. The proposed method has five stages, pre-processing, tracing midline of the brain, extraction of texture features and feature selection, classification and segmentation. In the first stage noise is suppressed using a median filtering and skull bone components of the images are removed. In the second stage, midline shift of the brain is calculated. In the third stage, fourteen texture features are extracted and optimal features are selected using genetic algorithm. In the fourth stage, support vector machine, artificial neural network and decision tree classifiers have been used. Finally, the ischemic stroke region is extracted by using k-means clustering technique.

scholarly journals A Comprehensive Analysis of 2D&3D Video Watching of EEG Signals by Increasing PLSR and SVM Classification Results

2019 ◽  
Vol 63 (3) ◽  
pp. 425-434 ◽  
Author(s):  
Negin Manshouri ◽  
Temel Kayikcioglu
Keyword(s):  
3D Video ◽  
Support Vector ◽  
Least Squares Regression ◽  
Eeg Signals ◽  
3D Technology ◽  
Svm Classification ◽  
Brain Signals ◽  
Short Period ◽  
The Impact ◽  
The Brain

Abstract Despite the development of two- and three-dimensional (2D&3D) technology, it has attracted the attention of researchers in recent years. This research is done to reveal the detailed effects of 2D in comparison with 3D technology on the human brain waves. The impact of 2D&3D video watching using electroencephalography (EEG) brain signals is studied. A group of eight healthy volunteers with the average age of 31 ± 3.06 years old participated in this three-stage test. EEG signal recording consisted of three stages: After a bit of relaxation (a), a 2D video was displayed (b), the recording of the signal continued for a short period of time as rest (c), and finally the trial ended. Exactly the same steps were repeated for the 3D video. Power spectrum density (PSD) based on short time Fourier transform (STFT) was used to analyze the brain signals of 2D&3D video viewers. After testing all the EEG frequency bands, delta and theta were extracted as the features. Partial least squares regression (PLSR) and Support vector machine (SVM) classification algorithms were considered in order to classify EEG signals obtained as the result of 2D&3D video watching. Successful classification results were obtained by selecting the correct combinations of effective channels representing the brain regions.

scholarly journals Motor Imagery EEG Classification Using Capsule Networks

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2854 ◽  
Author(s):  
Kwon-Woo Ha ◽  
Jin-Woo Jeong
Keyword(s):  
Motor Imagery ◽  
Learning Approaches ◽  
Eeg Signals ◽  
Left Hand ◽  
Computer Interfaces ◽  
Conventional Machine ◽  
Short Time ◽  
Electroencephalogram Eeg ◽  
Target Data

Various convolutional neural network (CNN)-based approaches have been recently proposed to improve the performance of motor imagery based-brain-computer interfaces (BCIs). However, the classification accuracy of CNNs is compromised when target data are distorted. Specifically for motor imagery electroencephalogram (EEG), the measured signals, even from the same person, are not consistent and can be significantly distorted. To overcome these limitations, we propose to apply a capsule network (CapsNet) for learning various properties of EEG signals, thereby achieving better and more robust performance than previous CNN methods. The proposed CapsNet-based framework classifies the two-class motor imagery, namely right-hand and left-hand movements. The motor imagery EEG signals are first transformed into 2D images using the short-time Fourier transform (STFT) algorithm and then used for training and testing the capsule network. The performance of the proposed framework was evaluated on the BCI competition IV 2b dataset. The proposed framework outperformed state-of-the-art CNN-based methods and various conventional machine learning approaches. The experimental results demonstrate the feasibility of the proposed approach for classification of motor imagery EEG signals.

Sign in / Sign up

Export Citation Format

Share Document