engleski

Rule-Based EEG Classifier Utilizing Local Entropy of Time-Frequency Distributions

Electroencephalogram (EEG) signals are known to contain signatures of stimuli, which induce brain activities. However, detecting these signatures to classify captured EEG waveforms is one of the most challenging tasks of EEG analysis. This paper proposes a novel time- frequency based method for EEG analysis and characterization implemented in a computer-aid decision support system, which can be used to assist medical experts in interpreting EEG patterns. The computerized method utilizes EEG spectral non- stationarity, which is clearly revealed in multicomponent signal time- frequency distributions (TFDs). The proposed algorithm, based on the modification of the Rényi entropy, called local or short-term Rényi entropy (STRE), has been upgraded with a blind components separation procedure and instantaneous frequency (IF) estimation. The method is applied to both forward and backward left and right hand movement EEGs, as well as to imagined hand movement EEGs captured by a 19-channel EEG recording system. The obtained results show that the proposed methods, in a given virtual instrument, efficiently distinguishes between real and imagined limb movements by considering their signatures in terms of the dominant EEG component IFs at the specified subset of EEG channels (namely, F3, F4, F7, F8, T3 and T4). Furthermore, computing the number of EEG signal components, their extraction and IF estimation provides an important information that shows potentials to enhance existing clinical diagnostic techniques for detecting intensity, location, and type of brain function abnormalities in patients with motor control neurological disorders.

Rényi entropy ; Short-term Rényi entropy ; Instantaneous frequency (IF) estimation ; EEG signals ; Time-frequency signal analysis

nije evidentirano