Sleep electroencephalogram (EEG) is an important index in diagnosing sleep disorders and related diseases. Manual sleep staging is time-consuming and often influenced by subjective factors. Existing automatic sleep staging methods have high complexity and a low accuracy rate. A sleep staging method based on support vector machines (SVM) and feature selection using single channel EEG single is proposed in this paper. Thirty-eight features were extracted from the single channel EEG signal. Then based on the feature selection method F-Score's definition, it was extended to multiclass with an added eliminate factor in order to find proper features, which were used as SVM classifier inputs. The eliminate factor was adopted to reduce the negative interaction of features to the result. Research on the F-Score with an added eliminate factor was further accomplished with the data from a standard open source database and the results were compared with none feature selection and standard F-Score feature selection. The results showed that the present method could effectively improve the sleep staging accuracy and reduce the computation time.
Databases, Factual ; Electroencephalography ; Humans ; Sleep Stages ; Support Vector Machine

0.05,respectively).The effect of test groups on the bacteria and fungi compared with that of control groups in dynamically monitoring showed significance(P

Adult ; Dinitrobenzenes ; poisoning ; Emergency Treatment ; Humans ; Male ; Middle Aged ; Occupational Exposure

Objective To summary the clinical experience of ECMO for failure to separate from bypass after arterial switch operation of TGA.Methods 8 TGA patients (6 boys and 2 girls,aged 1 day to 3.5 years and weighing 2.7-11.0 kg,3 VSD intact and 5 with VSD,others complicated malformation including COA,left ventricular outtract stenosis) were treated with VA ECMO owing to failure to separate from bypass caused by low output syndrome after ASO between July 2007 and June 2016.We collected the medical records and analyzed the indication,management and complication of ECMO for this patient population.There were two stages of ECMO supporting for low output after ASO,The first stage was to improve tissue perfusion and correct inner environment by high flow supporting,and the second stage was ventricular function training.ECMO was weaned when the blood pressure was more than 60 mmHg and the difference value of systolic pressure and diastolic pressure was 15-20 mmHg under medium dose inotropics supporting.Volume infusion was limited strictly during ECMO.Results The running time were 22-300 h.5 patients were weaned from ECMO successfully and 4 patients discharged to home.The long-term follow-up of echocardiography indicated normal cardiac function in 3 patients.1 older child had left cardiac failure again after weaning from ECMO 12 days later;he was supported by LVAD subsequently.LVAD was weaned after 236h supporting,unfortunately,He died from cardiac failure 50 days after LVAD weaning.3 patients could not wean from ECMO and died.The main complications were bleeding and pericardial tamponade.Conclusion VA ECMO was effective treatment for failure to separate from bypass after switch operation of TGA.The high mortality was seen in patients with intramural coronary arterial.The myocardial structure perhaps changed secondary in older TGA children,ECMO and LVAD can be used as short-term circulatory transition to artificial heart or transplant.Bleeding was the main complication of this population;surgical hemostasis and accurate coagulation management were the guarantee for successful ECMO running.