Electroencephalogram (EEG) classification for brain-computer interface (BCI) is a new way of realizing human-computer interreaction. In this paper the application of semi-supervised sparse representation classifier algorithms based on help training to EEG classification for BCI is reported. Firstly, the correlation information of the unlabeled data is obtained by sparse representation classifier and some data with high correlation selected. Secondly, the boundary information of the selected data is produced by discriminative classifier, which is the Fisher linear classifier. The final unlabeled data with high confidence are selected by a criterion containing the information of distance and direction. We applied this novel method to the three benchmark datasets, which were BCIⅠ, BCIⅡ_Ⅳ and USPS. The classification rate were 97%,82% and 84.7%, respectively. Moreover the fastest arithmetic rate was just about 0.2 s. The classification rate and efficiency results of the novel method are both better than those of S3VM and SVM, proving that the proposed method is effective.
ObjectiveTo analyze the relevant factors for surgical site infection. MethodsA total of 677 cases of surgery in one hospital from July 1 to December 31 in 2012 were surveyed (not including implant and cardiac intervention surgeries), which were divided into different groups according to the preoperative incision contamination level, and the postoperative healing of incisions were observed closely. After the patients were discharged, we investigated the situation of incisions by phone or periodic review, and forms were filled in on schedule. ResultsBy follow-up evaluation of the 677 cases, the incisions in 12 cases were infected and the infection rate was 1.77%. Polluted and infected (14.28%, 30.76%) incisions caused more infection than the clean and clean-polluted incisions (0.00%, 0.59%). The patients who stayed in hospital for 4 or more than 4 days before surgeries (infection rate was 4.55%) took more risk of infection than the patients whose preoperative time in hospital were 2-3 days (infection rate was 0.60%) and 1 or shorter than 1 day (0.68%). Perioperative use of antibiotics for longer than 72 hours will increase the risk of incision infection than those within 48 hours (7.69%, 0.00%; P=0.002). ConclusionSurgical site infection is related to the incision type. Shortening the preoperative in-hospital time will reduce the risk of infection. Long time use of antibiotics in perioperative period cannot prevent the postoperative infection effectively, but may increase the risk of infection.