ABSTRACT
Performance of motor imagery based brain-computer interfaces (MI BCIs) greatly depends on how to extract the features. Various versions of filter-bank based common spatial pattern have been proposed and used in MI BCIs. Filter-bank based common spatial pattern has more number of features compared with original common spatial pattern. As the number of features increases, the MI BCIs using filter-bank based common spatial pattern can face overfitting problems. In this study, we used eigenvector centrality feature selection method, wavelet packet decomposition common spatial pattern, and kernel extreme learning machine to improve the performance of MI BCIs and avoid overfitting problems. Furthermore, the computational speed was improved by using kernel extreme learning machine.
Subject(s)
Electroencephalography , Algorithms , Brain-Computer Interfaces , Imagery, Psychotherapy , ImaginationABSTRACT
To investigate the therapeutic effect of ciprofloxacin for the treatment of endophthalmitis, we used 18 rabbits with Staphylococcus aureus induce dendophthalmitis. The rabbits were assigned into three groups according to the treatment regimen; those who were not given any drug into group I, those who were given 100 microgram/ml ciprofloxacin intrvitreally into group II, and those who were given 2 mg/ml ciprofloxacin subconjunctivaly for 5 days into group III. We assessed clinical score, culture result of vitreous aspirate and pathologic finding of various ocular tissue. We found clinically significant decrease in clinical score in group II, but there were no significant differences in the vitreous culture and in the histologic findings among the study groups. In conclusion, we assume that intravitreal injection of ciprofloxacin may be the better treatment modality to treat endophthalmitis by S.aureus. In addition we still think there ought to be more studies as to the determination the dosage of ciprofloxacin and the use of steroid in combination.
