An introduction to support Vector Machines: and other kernel-based learning methods
An introduction to support Vector Machines: and other kernel-based learning methods
Applied Soft Computing
Expert Systems with Applications: An International Journal
Lyapunov exponents/probabilistic neural networks for analysis of EEG signals
Expert Systems with Applications: An International Journal
Review article: Human scalp EEG processing: Various soft computing approaches
Applied Soft Computing
A Neuro-Fuzzy Inference System Through Integration of Fuzzy Logic and Extreme Learning Machines
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
| Hi-index | 0.00 |
Diagnosing pain mechanisms is one of the main approaches to improve clinical treatments. Especially, the detection of existence and/or level of pain can be vital when verbal information is not present for instant for neonates, disabled persons, anesthetized patients and also animals. Various researches have been performed to locate and classify pain, however, no consistent result has been achieved. The aim of this study is to show a strict relation between electroencephalogram (EEG) signal features and perceptual pain levels and to clarify the relation of classified signal to pain origin. Cortical regions on scalp were assigned based on an evolutional method for optimized alignment of electrodes that improve the clinical monitoring results. The EEG signals were recorded during relax condition and variety of pain conditions. Specific spectral features which are studied to show consistency with dynamical characteristic of EEG signals were combined with non-linear features including approximate entropy and Lyapunov exponent to provide the feature vector. Evolutionary optimization method was used to reduce the features space dimension and computational costs. A hybrid adaptive network fuzzy inference system (ANFIS) and support vector machine (SVM) scheme was used for classification of pain levels. ANFIS optimizer is used to fine tune the non-linear alignment of kernels of SVM. The results show that pain levels can be differentiated with high accuracy and robustness even for few recording electrodes. This research verifies the hypothesis that electrical variations of brain patterns can be used for determination of pain levels. The proposed classification method provided up to 95% accuracy.