This paper proposes a motor imagery recognition algorithm based on feature fusion and transfer adaptive boosting (TrAdaboost) to address the issue of low accuracy in motor imagery (MI) recognition across subjects, thereby increasing the reliability of MI-based brain-computer interfaces (BCI) for cross-individual use. Using the autoregressive model, power spectral density and discrete wavelet transform, time-frequency domain features of MI can be obtained, while the filter bank common spatial pattern is used to extract spatial domain features, and multi-scale dispersion entropy is employed to extract nonlinear features. The IV-2a dataset from the 4th International BCI Competition was used for the binary classification task, with the pattern recognition model constructed by combining the improved TrAdaboost integrated learning algorithm with support vector machine (SVM), k nearest neighbor (KNN), and mind evolutionary algorithm-based back propagation (MEA-BP) neural network. The results show that the SVM-based TrAdaboost integrated learning algorithm has the best performance when 30% of the target domain instance data is migrated, with an average classification accuracy of 86.17%, a Kappa value of 0.723 3, and an AUC value of 0.849 8. These results suggest that the algorithm can be used to recognize MI signals across individuals, providing a new way to improve the generalization capability of BCI recognition models.
Objective To study the efficacy and adverse events of adjunctive perampanel in children with refractory epilepsy. Methods A prospective study was carried out in 45 children with refractory epilepsy, who were treated in our hospital from January 2020 to February 2021 using perampanel as an add-on treatment, with a criteria for enrollment and the starting dose of perampanel. Follow-up would be taken at once a month. Afte 3 months would check blood routine, liver function, kidney function and humoral immunity. The EEG was reviewed after 6 months. The initial dose of perampanel was 0.04 mg/(kg·d) (the maximum didn't exceed 2 mg/d), increasing by 0.04 mg/(kg·d) every two weeks, and the maximum maintenance dose didn't exceed 6 mg/d. The efficacy and adverse reactions of perampanel were evaluated by comparing the seizure frequency and EEG results before and after a 6-month add-on therapy.ResultsAmong the 45 children,complete seizure control was achieved in 7 cases after the therapy, and the seizure attacks were reduced in 26 cases, showing a total response rate of 73.3%. After the treatment, the epileptiform discharge of 28 children was reduced, and the effective rate was 62.22%. During the observation period, all the blood routine, liver function, kidney function,and humoral immunity of the children were normal.10 cases of adverse reactions occurred after the additional treatment of perampanel, and the adverse reaction rate was 22.22%. Conclusions Perampanel has good efficacy and safety in the add-on treatment of refractory epilepsy.