SVM CLASSIFIER FOR EPILEPTIC SEIZURE PREDICTION USING SUB-BANDING OF IEEG SIGNALS

Epileptic seizure in the brain affects the day-to-day life of any individual due to its unexpected nature of occurrence. It has affected more than 50 million people worldwide. Drug resistance of patients is an important factor which leads to failure of epilepsy treatments using medications in 30% of patients. Surgery is also not a viable option in a substantial number of patients. In such cases, a new kind of seizure forecasting system is necessary to help those people. In our work, various sub-frequency bands of EEG signals are produced from the originally recorded Intracranial Electroencephalogram (IEEG) signals of five canines and two persons to identify possible low complex and less intense EEG features from each sub-band of the entire spectrum. Support Vector Machine (SVM) with different Kernel-based classifiers are used to categorize features into preictal and interictal data. Epileptic Seizures forecasting accuracy of 99% has been achieved for data from canine and human. Employed wavelet filter for noise removal and found that it improved the seizure prediction accuracy in some subjects and reduced the accuracy in some subjects. Similarly, the feature selection technique also improved the preictal detection accuracy in some patients/subjects and reduced the accuracy in some data. From this work, we identified that seizure prediction is possible in at least one sub-frequency band especially in high gamma sub-band generated from the originally recorded signal using a high-pass filter. This work demonstrates an algorithm for seizure forecasting or identifying the preictal region which identifies the suitable best sub-frequency band for predicting the seizure of the originally recorded EEG data by using the computationally less intense EEG features and employing the best classifying SVM kernel.

Download Full-text

Epileptic Seizure Prediction over EEG Data using Hybrid CNN-SVM Model with Edge Computing Services

MATEC Web of Conferences ◽

10.1051/matecconf/201821003016 ◽

2018 ◽

Vol 210 ◽

pp. 03016 ◽

Cited By ~ 2

Author(s):

Punjal Agarwal ◽

Hwang-Cheng Wang ◽

Kathiravan Srinivasan

Keyword(s):

Epileptic Seizure ◽

Life Support ◽

Real Life ◽

Prediction Method ◽

Edge Computing ◽

Support Vector ◽

Seizure Prediction ◽

Computing Services ◽

Svm Model ◽

Epileptic Seizure Prediction

Epilepsy is one of the most common neurological disorders, which is characterized by unpredictable brain seizure. About 30% of the patients are not even aware that they have epilepsy and many have to undergo surgeries to relieve the pain. Therefore, developing a robust brain-computer interface for seizure prediction can help epileptic patients significantly. In this paper, we propose a hybrid CNN-SVM model for better epileptic seizure prediction. A convolutional neural network (CNN) consists of a multilayer structure, which can be adapted and modified according to the requirement of different applications. A support vector machine is a discriminative classifier which can be described by a separating optimal hyperplane used for categorizing new samples. The combination of CNN and SVM is found to provide an effective way for epileptic prediction. Furthermore, the resulting model is made autonomous using edge computing services and is shown to be a viable seizure prediction method. The results can be beneficial in real-life support of epilepsy patients.

Download Full-text

A Novel Permutation Entropy-Based EEG Channel Selection for Improving Epileptic Seizure Prediction

Sensors ◽

10.3390/s21237972 ◽

2021 ◽

Vol 21 (23) ◽

pp. 7972

Author(s):

Jee S. Ra ◽

Tianning Li ◽

Yan Li

Keyword(s):

Sensitivity And Specificity ◽

Epileptic Seizure ◽

Epileptic Seizures ◽

Optimization Method ◽

Channel Selection ◽

Permutation Entropy ◽

Patient Specific ◽

Support Vector ◽

Seizure Prediction ◽

Epileptic Seizure Prediction

The key research aspects of detecting and predicting epileptic seizures using electroencephalography (EEG) signals are feature extraction and classification. This paper aims to develop a highly effective and accurate algorithm for seizure prediction. Efficient channel selection could be one of the solutions as it can decrease the computational loading significantly. In this research, we present a patient-specific optimization method for EEG channel selection based on permutation entropy (PE) values, employing K nearest neighbors (KNNs) combined with a genetic algorithm (GA) for epileptic seizure prediction. The classifier is the well-known support vector machine (SVM), and the CHB-MIT Scalp EEG Database is used in this research. The classification results from 22 patients using the channels selected to the patient show a high prediction rate (average 92.42%) compared to the SVM testing results with all channels (71.13%). On average, the accuracy, sensitivity, and specificity with selected channels are improved by 10.58%, 23.57%, and 5.56%, respectively. In addition, four patient cases validate over 90% accuracy, sensitivity, and specificity rates with just a few selected channels. The corresponding standard deviations are also smaller than those used by all channels, demonstrating that tailored channels are a robust way to optimize the seizure prediction.

Download Full-text

Evaluation of Features in Detection of Dislike Responses to Audio–Visual Stimuli from EEG Signals

Computers ◽

10.3390/computers9020033 ◽

2020 ◽

Vol 9 (2) ◽

pp. 33 ◽

Cited By ~ 3

Author(s):

Firgan Feradov ◽

Iosif Mporas ◽

Todor Ganchev

Keyword(s):

Visual Stimuli ◽

Decomposition Methods ◽

Automated Detection ◽

Support Vector ◽

Svm Classifier ◽

Discrete Wavelet ◽

K Nearest Neighbors ◽

Eeg Activity ◽

Rbf Kernel ◽

Eeg Features

There is a strong correlation between the like/dislike responses to audio–visual stimuli and the emotional arousal and valence reactions of a person. In the present work, our attention is focused on the automated detection of dislike responses based on EEG activity when music videos are used as audio–visual stimuli. Specifically, we investigate the discriminative capacity of the Logarithmic Energy (LogE), Linear Frequency Cepstral Coefficients (LFCC), Power Spectral Density (PSD) and Discrete Wavelet Transform (DWT)-based EEG features, computed with and without segmentation of the EEG signal, on the dislike detection task. We carried out a comparative evaluation with eighteen modifications of the above-mentioned EEG features that cover different frequency bands and use different energy decomposition methods and spectral resolutions. For that purpose, we made use of Naïve Bayes classifier (NB), Classification and regression trees (CART), k-Nearest Neighbors (kNN) classifier, and support vector machines (SVM) classifier with a radial basis function (RBF) kernel trained with the Sequential Minimal Optimization (SMO) method. The experimental evaluation was performed on the well-known and widely used DEAP dataset. A classification accuracy of up to 98.6% was observed for the best performing combination of pre-processing, EEG features and classifier. These results support that the automated detection of like/dislike reactions based on EEG activity is feasible in a personalized setup. This opens opportunities for the incorporation of such functionality in entertainment, healthcare and security applications.

Download Full-text

Power Transformer Partial Discharge Fault Diagnosis Based on Multidimensional Feature Region

Mathematical Problems in Engineering ◽

10.1155/2016/4835694 ◽

2016 ◽

Vol 2016 ◽

pp. 1-11 ◽

Cited By ~ 3

Author(s):

Rong Jia ◽

Yongtao Xie ◽

Hua Wu ◽

Jian Dang ◽

Kaisong Dong

Keyword(s):

Frequency Band ◽

Power Transformer ◽

Partial Discharge ◽

Extraction Methods ◽

Sample Entropy ◽

Support Vector ◽

Band Pass Filter ◽

Pass Filter ◽

Hilbert Huang Transform ◽

Frequency Band Energy

Effectively extracting power transformer partial discharge (PD) signals feature is of great significance for monitoring power transformer insulation condition. However, there has been lack of practical and effective extraction methods. For this reason, this paper suggests a novel method for the PD signal feature extraction based on multidimensional feature region. Firstly, in order to better describe differences in each frequency band of fault signals, empirical mode decomposition (EMD) and Hilbert-Huang transform (HHT) band-pass filter wave for raw signal is carried out. And the component of raw signals on each frequency band can be obtained. Secondly, the sample entropy value and the energy value of each frequency band component are calculated. Using the difference of each frequency band energy and complexity, signals feature region is established by the multidimensional energy parameters and the multidimensional sample entropy parameters to describe PD signals multidimensional feature information. Finally, partial discharge faults are classified by sphere-structured support vector machines algorithm. The result indicates that this method is able to identify and classify different partial discharge faults.

Download Full-text

Identification of Natural Images and Computer Generated Graphics Based on Hybrid Features

International Journal of Digital Crime and Forensics ◽

10.4018/jdcf.2012010101 ◽

2012 ◽

Vol 4 (1) ◽

pp. 1-16 ◽

Cited By ~ 10

Author(s):

Fei Peng ◽

Juan Liu ◽

Min Long

Keyword(s):

Classification Accuracy ◽

Fractal Dimensions ◽

Natural Images ◽

Identification Accuracy ◽

Support Vector ◽

Svm Classifier ◽

Grayscale Image ◽

Hybrid Features ◽

Pass Filter ◽

Noise Characteristics

Examining the identification of natural images (NI) and computer generated graphics (CG), a novel method is proposed based on hybrid features. Since the image acquisition pipelines are different, some differences exist in statistical, visual, and noise characteristics between natural images and computer generated graphics. Firstly, the mean, variance, kurtosis, skew-ness, and median of the histograms of grayscale image in the spatial and wavelet domain are selected as statistical features. Secondly, the fractal dimensions of grayscale image and wavelet sub-bands are extracted as visual features. Thirdly, considering the shortage of the photo response non-uniformity noise (PRNU) acquired from wavelet based de-noising filter, a pre-processing of Gaussian high pass filter is applied to the image before the extraction of PRNU, and the physical features are calculated from the enhanced PRNU. In the identification, a support vector machine (SVM) classifier is used in experiments and an average classification accuracy of 94.29% is achieved, where the classification accuracy for computer generated graphics is 97.3% and for natural images is 91.28%. Analysis and discussion show that the method is suitable for the identification of natural images and computer generated graphics and can achieve better identification accuracy than the existing methods with fewer dimensions of features.

Download Full-text

Fault Diagnosis of Automobile Rear Axle Based on Wavelet Packet and Support Vector Machine

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.211-212.1021 ◽

2011 ◽

Vol 211-212 ◽

pp. 1021-1026 ◽

Cited By ~ 1

Author(s):

Yong Chen ◽

Bao Qiang Wang ◽

Jin Yao

Keyword(s):

Support Vector Machine ◽

Fault Diagnosis ◽

Frequency Band ◽

Rear Axle ◽

Wavelet Packet ◽

Support Vector ◽

Svm Classifier ◽

Failure State ◽

Diagnosis Method ◽

Specific Frequency

This paper presents a fault diagnosis method of automobile rear axle based on wavelet packet analysis (WPA) and support vector machine (SVM) classifier. By Fourier transformation we find out the frequency band that can mostly reflect the rear axle failure state and use wavelet packet to decompose and reconstruct the vibration signals of rear axle, then extract each band’s energy and the variance, standard deviation, skewness, kurtosis of the specific frequency band to constitute a feature vector. We use the feature vectors which are come from some pieces of normal and abnormal samples to train support vector machine classifier for obtaining the best classification，at the same time, discuss the optimization of SVM parameters. Application shows that the method is effective in real time fault diagnosis for the automobile rear axle and has a strong anti-interference ability in different working conditions.

Download Full-text