Epileptic seizure detection from EEG signals with phase–amplitude cross-frequency coupling and support vector machine

2018 ◽  
Vol 32 (08) ◽  
pp. 1850086 ◽  
Author(s):  
Yang Liu ◽  
Jiang Wang ◽  
Lihui Cai ◽  
Yingyuan Chen ◽  
Yingmei Qin
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Epileptic Seizures ◽  
Classification Performance ◽  
Support Vector ◽  
Svm Classifier ◽  
Eeg Signals ◽  
Frequency Coupling ◽  
Phase Amplitude ◽  
Cross Frequency Coupling

As a pattern of cross-frequency coupling (CFC), phase–amplitude coupling (PAC) depicts the interaction between the phase and amplitude of distinct frequency bands from the same signal, and has been proved to be closely related to the brain’s cognitive and memory activities. This work utilized PAC and support vector machine (SVM) classifier to identify the epileptic seizures from electroencephalogram (EEG) data. The entropy-based modulation index (MI) matrixes are used to express the strength of PAC, from which we extracted features as the input for classifier. Based on the Bonn database, which contains five datasets of EEG segments obtained from healthy volunteers and epileptic subjects, a 100% classification accuracy is achieved for identifying seizure ictal from healthy data, and an accuracy of 97.67% is reached in the classification of ictal EEG signals from inter-ictal EEGs. Based on the CHB–MIT database which is a group of continuously recorded epileptic EEGs by scalp electrodes, a 97.50% classification accuracy is obtained and a raising sign of MI value is found at 6[Formula: see text]s before seizure onset. The classification performance in this work is effective, and PAC can be considered as a useful tool for detecting and predicting the epileptic seizures and providing reference for clinical diagnosis.

scholarly journals Landscape Perception Identification and Classification Based on Electroencephalogram (EEG) Features

2022 ◽  
Vol 19 (2) ◽  
pp. 629
Author(s):  
Yuting Wang ◽  
Shujian Wang ◽  
Ming Xu
Keyword(s):  
Support Vector Machine ◽  
Random Forest ◽  
Classification Accuracy ◽  
Support Vector ◽  
Svm Classifier ◽  
Eeg Signals ◽  
Landscape Perception ◽  
Landscape Types ◽  
Electroencephalogram Eeg ◽  
Eeg Features

This paper puts forward a new method of landscape recognition and evaluation by using aerial video and EEG technology. In this study, seven typical landscape types (forest, wetland, grassland, desert, water, farmland, and city) were selected. Different electroencephalogram (EEG) signals were generated through different inner experiences and feelings felt by people watching video stimuli of the different landscape types. The electroencephalogram (EEG) features were extracted to obtain the mean amplitude spectrum (MAS), power spectrum density (PSD), differential entropy (DE), differential asymmetry (DASM), rational asymmetry (RASM), and differential caudality (DCAU) in the five frequency bands of delta, theta, alpha, beta, and gamma. According to electroencephalogram (EEG) features, four classifiers including the back propagation (BP) neural network, k-nearest neighbor classification (KNN), random forest (RF), and support vector machine (SVM) were used to classify the landscape types. The results showed that the support vector machine (SVM) classifier and the random forest (RF) classifier had the highest accuracy of landscape recognition, which reached 98.24% and 96.72%, respectively. Among the six classification features selected, the classification accuracy of MAS, PSD, and DE with frequency domain features were higher than those of the spatial domain features of DASM, RASM and DCAU. In different wave bands, the average classification accuracy of all subjects was 98.24% in the gamma band, 94.62% in the beta band, and 97.29% in the total band. This study identifies and classifies landscape perception based on multi-channel EEG signals, which provides a new idea and method for the quantification of human perception.

Shape-restricted support vector machine (SR-SVM): a SVM classifier taking supplementary shape information of input

2021 ◽  
Vol 40 (1) ◽  
pp. 1481-1494
Author(s):  
Geng Deng ◽  
Yaoguo Xie ◽  
Xindong Wang ◽  
Qiang Fu
Keyword(s):  
Support Vector Machine ◽  
Classification Performance ◽  
Research Literature ◽  
Support Vector ◽  
Svm Classifier ◽  
Classification Problems ◽  
Active Set ◽  
Shape Information ◽  
Convex Optimization Problem ◽  
Shape Restrictions

Many classification problems contain shape information from input features, such as monotonic, convex, and concave. In this research, we propose a new classifier, called Shape-Restricted Support Vector Machine (SR-SVM), which takes the component-wise shape information to enhance classification accuracy. There exists vast research literature on monotonic classification covering monotonic or ordinal shapes. Our proposed classifier extends to handle convex and concave types of features, and combinations of these types. While standard SVM uses linear separating hyperplanes, our novel SR-SVM essentially constructs non-parametric and nonlinear separating planes subject to component-wise shape restrictions. We formulate SR-SVM classifier as a convex optimization problem and solve it using an active-set algorithm. The approach applies basis function expansions on the input and effectively utilizes the standard SVM solver. We illustrate our methodology using simulation and real world examples, and show that SR-SVM improves the classification performance with additional shape information of input.

Feature Selection Method Based on Mutual Information and Support Vector Machine

2021 ◽  
pp. 2150021
Author(s):  
Gang Liu ◽  
Chunlei Yang ◽  
Sen Liu ◽  
Chunbao Xiao ◽  
Bin Song
Keyword(s):  
Support Vector Machine ◽  
Feature Selection ◽  
Mutual Information ◽  
Classification Accuracy ◽  
Feature Selection Method ◽  
Selection Method ◽  
Support Vector ◽  
Svm Classifier ◽  
Standard Data ◽  
Feature Dimension

A feature selection method based on mutual information and support vector machine (SVM) is proposed in order to eliminate redundant feature and improve classification accuracy. First, local correlation between features and overall correlation is calculated by mutual information. The correlation reflects the information inclusion relationship between features, so the features are evaluated and redundant features are eliminated with analyzing the correlation. Subsequently, the concept of mean impact value (MIV) is defined and the influence degree of input variables on output variables for SVM network based on MIV is calculated. The importance weights of the features described with MIV are sorted by descending order. Finally, the SVM classifier is used to implement feature selection according to the classification accuracy of feature combination which takes MIV order of feature as a reference. The simulation experiments are carried out with three standard data sets of UCI, and the results show that this method can not only effectively reduce the feature dimension and high classification accuracy, but also ensure good robustness.

scholarly journals Eye-Tracking Analysis for Emotion Recognition

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Paweł Tarnowski ◽  
Marcin Kołodziej ◽  
Andrzej Majkowski ◽  
Remigiusz Jan Rak
Keyword(s):  
Support Vector Machine ◽  
Eye Movements ◽  
Eye Tracking ◽  
Emotion Recognition ◽  
Classification Accuracy ◽  
Pupil Diameter ◽  
Support Vector ◽  
Svm Classifier ◽  
High Arousal ◽  
Validation Method

This article reports the results of the study related to emotion recognition by using eye-tracking. Emotions were evoked by presenting a dynamic movie material in the form of 21 video fragments. Eye-tracking signals recorded from 30 participants were used to calculate 18 features associated with eye movements (fixations and saccades) and pupil diameter. To ensure that the features were related to emotions, we investigated the influence of luminance and the dynamics of the presented movies. Three classes of emotions were considered: high arousal and low valence, low arousal and moderate valence, and high arousal and high valence. A maximum of 80% classification accuracy was obtained using the support vector machine (SVM) classifier and leave-one-subject-out validation method.

scholarly journals Sentiment polarity classification of tweets using a extended dictionary

2018 ◽  
Vol 21 (62) ◽  
pp. 1
Author(s):  
Jorge E. Camargo ◽  
Vladimir Vargas-Calderon ◽  
Nelson Vargas ◽  
Liliana Calderón-Benavides
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Classification Performance ◽  
Semantic Relations ◽  
Support Vector ◽  
The Real ◽  
Polarity Classification ◽  
Real Academia ◽  
Word Definitions

With the purpose of classifying text based on its sentiment polarity (positive or negative), we proposed an extension of a 68,000 tweets corpus through the inclusion of word definitions from a dictionary of the Real Academia Espa\~{n}ola de la Lengua (RAE). A set of 28,000 combinations of 6 Word2Vec and support vector machine parameters were considered in order to evaluate how positively would affect the inclusion of a RAE's dictionary definitions classification performance. We found that such a corpus extension significantly improve the classification accuracy. Therefore, we conclude that the inclusion of a RAE's dictionary increases the semantic relations learned by Word2Vec allowing a better classification accuracy.

scholarly journals Feature Extraction and Classification of MRI Using Hybrid RBF Kernel and SVM

2021 ◽  
pp. 418-426
Author(s):  
Suhas S ◽  
Dr. C. R. Venugopal
Keyword(s):  
Support Vector Machine ◽  
Image Retrieval ◽  
Classification Accuracy ◽  
Kernel Functions ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Svm Classifier ◽  
Mr Images ◽  
Rbf Kernel

An enhanced classification system for classification of MR images using association of kernels with support vector machine is developed and presented in this paper along with the design and development of content-based image retrieval (CBIR) system. Content of image retrieval is the process of finding relevant image from large collection of image database using visual queries. Medical images have led to growth in large image collection. Oriented Rician Noise Reduction Anisotropic Diffusion filter is used for image denoising. A modified hybrid Otsu algorithm termed is used for image segmentation. The texture features are extracted using GLCM method. Genetic algorithm with Joint entropy is adopted for feature selection. The classification is done by support vector machine along with various kernels and the performance is validated. A classification accuracy of 98.83% is obtained using SVM with GRBF kernel. Various features have been extracted and these features are used to classify MR images into five different categories. Performance of the MC-SVM classifier is compared with different kernel functions. From the analysis and performance measures like classification accuracy, it is inferred that the brain and spinal cord MRI classification is best done using MC- SVM with Gaussian RBF kernel function than linear and polynomial kernel functions. The proposed system can provide best classification performance with high accuracy and low error rate.

Spectral-Spatial Classification of Hyperspectral Image Based on Support Vector Machine

2021 ◽  
Vol 16 (1) ◽  
pp. 56-74
Author(s):  
Weiwei Yang ◽  
Haifeng Song
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Support Vector ◽  
Svm Classifier ◽  
Spatial Classification ◽  
Homogeneous Regions

Recent research has shown that integration of spatial information has emerged as a powerful tool in improving the classification accuracy of hyperspectral image (HSI). However, partitioning homogeneous regions of the HSI remains a challenging task. This paper proposes a novel spectral-spatial classification method inspired by the support vector machine (SVM). The model consists of spectral-spatial feature extraction channel (SSC) and SVM classifier. SSC is mainly used to extract spatial-spectral features of HSI. SVM is mainly used to classify the extracted features. The model can automatically extract the features of HSI and classify them. Experiments are conducted on benchmark HSI dataset (Indian Pines). It is found that the proposed method yields more accurate classification results compared to the state-of-the-art techniques.

Classifying Electroencephalogram (EEG) Signals Using BAT-SVM Classifier for Detecting Epilepsy

2021 ◽  
Vol 12 (3) ◽  
pp. 96-115
Author(s):  
Manal Tantawi ◽  
Aya Naser ◽  
Howida Shedeed ◽  
Mohammed Fahmy Tolba
Keyword(s):  
Support Vector Machines ◽  
Epileptic Seizures ◽  
Bat Algorithm ◽  
Line Length ◽  
Support Vector ◽  
Svm Classifier ◽  
Eeg Signals ◽  
Vector Machines ◽  
Electroencephalogram Eeg ◽  
Source Of Information

Electroencephalogram (EEG) signals are a valuable source of information for detecting epileptic seizures. However, monitoring EEG for long periods of time is very exhausting and time consuming. Thus, detecting epilepsy in EEG signals automatically is highly appreciated. In this study, three classes, namely normal, interictal (out of seizure time), and ictal (during seizure), are considered. Moreover, a comparative study is provided for the efficient features in literature resulting in a suggested combination of only three discriminative features, namely R'enyi entropy, line length, and energy. These features are calculated from each of the EEG sub-bands. Finally, support vector machines (SVM) classifier optimized using BAT algorithm (BAT-SVM) is introduced by this study for discriminating between the three classes. Experiments were conducted using Andrzejak database. The accomplished experiments and comparisons in this study emphasize the superiority of the proposed BAT-SVM along with the suggested feature set in achieving the best results.

scholarly journals AGNES-SMOTE: An Oversampling Algorithm Based on Hierarchical Clustering and Improved SMOTE

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Xin Wang ◽  
Yue Yang ◽  
Mingsong Chen ◽  
Qin Wang ◽  
Qin Qin ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Hierarchical Clustering ◽  
Classification Accuracy ◽  
Classification Performance ◽  
Support Vector ◽  
Seed Sample ◽  
Imbalanced Datasets ◽  
Centroid Method ◽  
Svm Classification ◽  
Sampling Process

Aiming at low classification accuracy of imbalanced datasets, an oversampling algorithm—AGNES-SMOTE (Agglomerative Nesting-Synthetic Minority Oversampling Technique) based on hierarchical clustering and improved SMOTE—is proposed. Its key procedures include hierarchically cluster majority samples and minority samples, respectively; divide minority subclusters on the basis of the obtained majority subclusters; select “seed sample” based on the sampling weight and probability distribution of minority subcluster; and restrict the generation of new samples in a certain area by centroid method in the sampling process. The combination of AGNES-SMOTE and SVM (Support Vector Machine) is presented to deal with imbalanced datasets classification. Experiments on UCI datasets are conducted to compare the performance of different algorithms mentioned in the literature. Experimental results indicate AGNES-SMOTE excels in synthesizing new samples and improves SVM classification performance on imbalanced datasets.

scholarly journals Multiple graph fusion based on Riemannian geometry for motor imagery classification

2022 ◽  
Author(s):  
Xiaofeng Xie ◽  
Xiaokun Zou ◽  
Tianyou Yu ◽  
Rongnian Tang ◽  
Yao Hou ◽  
...  
Keyword(s):  
Riemannian Manifold ◽  
Motor Imagery ◽  
Classification Performance ◽  
Support Vector ◽  
Svm Classifier ◽  
Classification Problems ◽  
Eeg Signals ◽  
Spatial Covariance ◽  
Bilinear Mapping ◽  
Subject Specific

AbstractIn motor imagery-based brain-computer interfaces (BCIs), the spatial covariance features of electroencephalography (EEG) signals that lie on Riemannian manifolds are used to enhance the classification performance of motor imagery BCIs. However, the problem of subject-specific bandpass frequency selection frequently arises in Riemannian manifold-based methods. In this study, we propose a multiple Riemannian graph fusion (MRGF) model to optimize the subject-specific frequency band for a Riemannian manifold. After constructing multiple Riemannian graphs corresponding to multiple bandpass frequency bands, graph embedding based on bilinear mapping and graph fusion based on mutual information were applied to simultaneously extract the spatial and spectral features of the EEG signals from Riemannian graphs. Furthermore, with a support vector machine (SVM) classifier performed on learned features, we obtained an efficient algorithm, which achieves higher classification performance on various datasets, such as BCI competition IIa and in-house BCI datasets. The proposed methods can also be used in other classification problems with sample data in the form of covariance matrices.

Sign in / Sign up

Export Citation Format

Share Document