Classification of mental task from EEG signals using Immune Feature Weighted Support Vector Machine

2010 ◽  
Author(s):  
Lei Guo ◽  
Youxi Wu ◽  
Ting Cao ◽  
Weili Yan ◽  
Xueqin Shen
Keyword(s):  
Support Vector Machine ◽  
Support Vector ◽  
Mental Task ◽  
Eeg Signals

scholarly journals Wavelet based Extraction of Features from EEG Signals and Classification of Novel Emotion Recognition Using SVM and HMM Classifier and to Measure its Accuracy

2021 ◽  
Vol 36 (1) ◽  
pp. 727-732
Author(s):  
M. Mohanambal ◽  
Dr.P. Vishnu Vardhan
Keyword(s):  
Support Vector Machine ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Mean Value ◽  
Support Vector ◽  
Svm Classifier ◽  
Emotion Detection ◽  
Eeg Signals

Aim: The study aims to extract features from EEG signals and classify emotion using Support Vector Machine (SVM) and Hidden Markov Model (HMM) classifier. Materials and methods: The study was conducted using the Support Vector Machine (SVM) and Hidden Markov Model (HMM) programs to analyze and compare the recognition of emotions classified under EEG signals. The results were computed using the MATLAB algorithm. For each group, ten samples were used to compare the efficiency of SVM and HMM classifiers. Result: The study’s performance exhibits the HMM classifier’s accuracy over the SVM classifier and the emotion detection from EEG signals computed. The mean value of the HMM classifier is 52.2, and the SVM classifier is 22.4. The accuracy rate of 35% with the data features is found in HMM classifier. Conclusion: This study shows a higher accuracy level of 35% for the HMM classifier when compared with the SVM classifier. In the detection of emotions using the EEG signal. This result shows that the HMM classifier has a higher significant value of P=.001 < P=.005 than the SVM classifier.

Epilepsy EEG Classification Based on Convolution Support Vector Machine

2021 ◽  
Vol 11 (1) ◽  
pp. 25-32
Author(s):  
Qi Xin ◽  
Shaohai Hu ◽  
Shuaiqi Liu ◽  
Xiaole Ma ◽  
Hui Lv ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Focal Epilepsy ◽  
Principal Component ◽  
Support Vector ◽  
Eeg Signals ◽  
Eeg Classification ◽  
Eeg Data ◽  
Epilepsy Diagnosis ◽  
Electroencephalogram Eeg

Clinical Electroencephalogram (EEG) data is of great significance to realize automatable detection, recognition and diagnosis to reduce the valuable diagnosis time. To make a classification of epilepsy, we constructed convolution support vector machine (CSVM) by integrating the advantages of convolutional neural networks (CNN) and support vector machine (SVM). To distinguish the focal and non-focal epilepsy EEG signals, we firstly reduced the dimensionality of EEG signals by using principal component analysis (PCA). After that, we classified the epilepsy EEG signals by the CSVM. The accuracy, sensitivity and specificity of our method reach up to 99.56%, 99.72% and 99.52% respectively, which are competitive than the widely acceptable algorithms. The proposed automatic end to end epilepsy EEG signals classification algorithm provides a better reference for clinical epilepsy diagnosis.

Classifying Mental Tasks Using Local Mean Decomposition of Electroencephalogram and Support Vector Machine

2013 ◽  
Vol 330 ◽  
pp. 973-976
Author(s):  
Li Yu Huang ◽  
Jie Niu ◽  
Jia Ning Zheng ◽  
Ying Ju Du
Keyword(s):  
Support Vector Machine ◽  
New Combination ◽  
Support Vector ◽  
Mental Task ◽  
Eeg Signals ◽  
Local Mean Decomposition ◽  
Local Mean ◽  
Task Features ◽  
Optimal Kernel ◽  
Better Than

We present a new combination classification algorithm and test it on the EEG of right and left motor imagery experiment. First, the original EEGs signals are decomposed by Local Mean Decomposition (LMD) and then determine that the first three PFs include the main mental task features. After determining the optimal kernel parameters for support vector machine (SVM), the energy values of the first three PFs of the EEG signals from three electrodes were extracted as the input vectors of SVM. The outputs of SVM were the classification results for different mental task EEG signals. Result shows that mean accuracy of the proposed algorithm is 92.25%, and the best accuracy is 95.00%, which is much better than the present traditional algorithms.

Sign in / Sign up

Export Citation Format

Share Document