Classification of EEG signals based on AR model and approximate entropy
Citations Over Time
Abstract
The analysis of electroencephalogram (EEG) signal is a low-cost and effective technique to examine electrical activity of the brain and diagnose brain diseases in the Brain Computer Interface (BCI) applications. Classification of EEG signals is an important task in BCI applications. This paper investigates two common methods of feature extraction on EEG signals, autoregressive (AR) model and approximate entropy. AR coefficients of each segment of each channel are calculated by AR model and entropies of each channel are also calculated by approximate entropy. A combination strategy of feature extraction, where each feature vector consists of AR coefficients and approximate entropies, is proposed in this paper. Extreme learning machine is employed as a classifier for evaluating the classification performance. The classification of five different mental tasks is evaluated by the proposed method. It can be observed from experimental results that the proposed method can effectively improve the classification performance, and achieve a good compromise between classification accuracy and computational cost.
Related Papers
- → Physiological time-series analysis using approximate entropy and sample entropy(2000)7,644 cited
- → Range Entropy: A Bridge between Signal Complexity and Self-Similarity(2018)67 cited
- → Comparative study of approximate entropy and sample entropy robustness to spikes(2011)95 cited
- [The sample entropy and its application in EEG based epilepsy detection].(2007)
- → Range Entropy: A Bridge Between Signal Complexity and Self-Similarity(2018)