Sleep quality is closely related to human health. It is very important to correctly discriminate the sleep stages for evaluating sleep quality, diagnosing and analyzing the sleep-related disorders. Polysomnography (PSG) signals are commonly used to record and analyze sleep stages. Effective feature extraction and representation is one of the most important steps to improve the performance of sleep stage classification. In this work, a collaborative representation (CR) algorithm was adopted to re-represent the original extracted features from electroencephalogram signal, and then the kernel entropy component analysis (KECA) algorithm was further used to reduce the feature dimension of CR-feature. To evaluate the performance of CR-KECA, we compared the original feature, CR feature and readied CR feature (CR-PCA) after principal component analysis (PCA). The experimental results of sleep stage classification indicated that the CR-KECA method achieved the best performance compared with the original feature, CR feature, and CR-PCA feature with the classification accuracy of 68.74±0.46%, sensitivity of 68.76±0.43% and specificity of 92.19±0.11%. Moreover, CR algorithm had low computational complexity, and the feature dimension after KECA was much smaller, which made CR-KECA algorithm suitable for the analysis of large-scale sleep data.
This research was to study the regulation of intravenous administration of human umbilical cord blood mesenchymal stem cells (HUCBMSCs) on secretion of neural specific protein in rats after traumatic brain injury (TBI), and to explore its mechanisms promoting the recovery of neurological function. The TBI models of rats were established. We then injected HUCBMSCs, labelled by Brdu (5-bromo-2-deoxyuridine), into the TBI rats via the tail vein using modified Feeney free-falling method. The levels of neural biochemical indicators (serum S100βprotein, NSE, LDH, CK) of rats were detected in shamed group, injury group and HUCBMSCs-transplanted group. And the morphological changes of brain tissue of rats in the three groups were observed by using HE staining under light microscope. During the whole experiment no immunosuppressant was used for the four groups. From the research, transplant-related death of the rats was not found in transplantation group. In the injury group, rises were found in contents of serum S100βprotein, NSE, LDH, CK in the early stage after the rats were injured, which were much higher than those in shamed group at correspondent time point(P < 0.01). In HUCBMSCs-transplanted group, although these biochemistry indexes were found rising for a short period in the early stage, along with the time, these indexes were obviously lower than in those injury group (P < 0.05). Under light microscopy pathological changes of rats in HUCBMSCs-transplanted group were much slighter than those in injury group. It was well concluded that in the situation of no immuno-suppressants, the intravenous-injected HUCBMSCs could reduce the secretion of serum S100βprotein, NSE, LDH, CK, promote the repair of tissue injury effectively, and promote the functional recovery of neurons.