Channel Selection for Multi-class Motor Imagery Based on Common Spatial Pattern / 生物医学工程学杂志

High-density channels are often used to acquire electroencephalogram (EEG) spatial information in different cortical regions of the brain in brain-computer interface (BCI) systems. However, applying excessive channels is inconvenient for signal acquisition, and it may bring artifacts. To avoid these defects, the common spatial pattern (CSP) algorithm was used for channel selection and a selection criteria based on norm-2 is proposed in this paper. The channels with the highest M scores were selected for the purpose of using fewer channels to acquire similar rate with high density channels. The Dataset III a from BCI competition 2005 were used for comparing the classification accuracies of three motor imagery between whole channels and the selected channels with the present proposed method. The experimental results showed that the classification accuracies of three subjects using the 20 channels selected with the present method were all higher than the classification accuracies using all 60 channels, which convinced that our method could be more effective and useful.

Eliminating artifacts of EEG data based on independent component analysis / 生物医学工程学杂志

As a new array processing technique, independent component analysis(ICA) is an effective means to resolve the blind source separation(BSS) problem. Based on the brief introductions of ICA theory and algorithm, we apply ICA to the removal of ocular artifacts from EEG recordings. The EEG data collected from the human scalp is actually the mixtures of some independent components. It is coincident with the basic assumptions of ICA. Compared with the traditional methods of artifacts elimination, ICA, a kind of spatial filter, is not restricted by the case of spectrum overlapping, and it has a good reservation of useful detail signals. In addition, the inverse weight matrix of ICA can be used to reflect the topographic structure of different independent sources of EEG.

Application of complexity sequence in sleep staging based on sleep EEG data / 生物医学工程学杂志

In this paper an approach of time-window complexity sequence is applied to sleep EEG analysis. This approach can reduce the loss of state information due to the nonstationarity of EEG signal and the unevenness of state space, and can overcome certain limitations of the complexity itself to some extent. It will help to extract the state features of EEG in different sleep stages. In addition, we preprocess EEG by adopting ICA and wavelet transform (WT). The results show that some physiological artifact in EEG can be eliminated effectively by these methods, and the sleep staging based on sleep EEG data will be more exact.