How to detect the P300 component in EEG accurately and instantly is a hot problem in the research field of Brain-Computer Interface. In this paper, an algorithm based on F-score feature selection and support vector machines was introduced for P300 detection. Using F-score feature selection method, we reduced input features to overcome the shortcoming of support vector machines in terms of low detection speed, and then implemented the detection of P300 component with support vector machines, which have good classification performance. The algorithm was tested with a P300 dataset from the BCI competition 2003. The results showed that the algorithm achieved an accuracy of 100% in P300 detection within five repetitions, and the detection speed of this algorithm was 2 times higher than that of the traditional support vector machines algorithm without F-score feature selection.
Algorithms ; Electroencephalography ; methods ; Event-Related Potentials, P300 ; physiology ; Humans ; Pattern Recognition, Automated ; methods ; Principal Component Analysis ; Signal Processing, Computer-Assisted

Objective To investigate the relationships of nutritional status and length of stay(LOS)with phase angle(PA)in patients with severe craniocerebral injury.Methods A total of 100 patients[Glasgow Coma Scale(GCS)score ≤8 points]admitted outside the department of neurology were selected as study objects.Body composition analysis and blood samples were used to determine the intracellular and extracellular water content,skeletal muscle,PA,prognostic nutritional index(PNI)and LOS.Patients were divided into low PA group(n=42)and normal PA group(n=58)based on PA values.Body composition related indexes,PNI and LOS were compared between the two groups.The correlation between PA and each index was analyzed.The influencing factors of malnutri-tion were analyzed.The influencing factors of malnutrition were analyzed.Results Intracellular wa-ter,total body water,body cell content and PNI in the low PA group were significantly lower,and LOS was significantly longer than that in the normal PA group(P＜0.05).PA was positively correlated with intracellular water,extracellular water,total body water,skeletal muscle,body cell content,bone mineral content,basal metabolic rate and PNI(P＜0.05),while PA was negatively correlated with LOS(P＜0.05).PA(OR=5.441,P=0.001,95％CI,2.011 to 14.719)and LOS(OR=8.373,P＜0.001,95％CI,3.079 to 22.765)were the influential factors in the occurrence of malnutrition.Conclusion PA is significantly correlated with nutritional status and LOS in patients with severe craniocerebral injury.

Objective To investigate the relationships of nutritional status and length of stay(LOS)with phase angle(PA)in patients with severe craniocerebral injury.Methods A total of 100 patients[Glasgow Coma Scale(GCS)score ≤8 points]admitted outside the department of neurology were selected as study objects.Body composition analysis and blood samples were used to determine the intracellular and extracellular water content,skeletal muscle,PA,prognostic nutritional index(PNI)and LOS.Patients were divided into low PA group(n=42)and normal PA group(n=58)based on PA values.Body composition related indexes,PNI and LOS were compared between the two groups.The correlation between PA and each index was analyzed.The influencing factors of malnutri-tion were analyzed.The influencing factors of malnutrition were analyzed.Results Intracellular wa-ter,total body water,body cell content and PNI in the low PA group were significantly lower,and LOS was significantly longer than that in the normal PA group(P＜0.05).PA was positively correlated with intracellular water,extracellular water,total body water,skeletal muscle,body cell content,bone mineral content,basal metabolic rate and PNI(P＜0.05),while PA was negatively correlated with LOS(P＜0.05).PA(OR=5.441,P=0.001,95％CI,2.011 to 14.719)and LOS(OR=8.373,P＜0.001,95％CI,3.079 to 22.765)were the influential factors in the occurrence of malnutrition.Conclusion PA is significantly correlated with nutritional status and LOS in patients with severe craniocerebral injury.