Classify Motor Imagery by a Novel CNN with Data Augmentation.

The brain-computer interface (BCI) based on electroencephalography (EEG) converts the subject's intentions into control signals. For the BCI, the study of motor imagery has been widely used. In recent years, a classification method based on a convolutional neural network (CNNs) has been proposed. However, most of the existing methods use a single convolution scale on CNN, and another problem that affects the results is limited training data. To solve these problems, we propose a mixed-scale CNN architecture, and a data augmentation method is used to classify the EEG of motor imagery. After classifying the BCI competition IV dataset 2b, the average classification accuracy is 81.52%. Compared with the existing methods, our method has a better classification result. This method effectively solves the problems existing in the existing CNN-based motor imagery classification methods, and it improves the classification accuracy.

The effect of Bt Cry9Ee toxin on honey bee brood and adults reared in vitro, Apis mellifera (Hymenoptera: Apidae).

The effects of Bt Cry9Ee toxin on honey bee, Apis mellifera L., survival, developmental rate, larval weight, pollen consumption, and midgut bacterial diversity were tested in the laboratory. Honey bee larvae and adults were reared in vitro and fed a diet that contained Cry9Ee toxin at 0.01, 0.1, 1, and 10 mg/L. Cry9Ee toxin 0.01, 0.1, and 1 mg/L in diet used in this study may represent a value closer to field relevance and the highest concentration is unlikely to be encountered in the field and thus represent a worst case scenario. The dependent variables were compared for groups of honey bees feeding on treated diet and those feeding on negative control (no addition of a test substance), solvent control (0.01 mM Na2CO3), and positive control diet (dimethoate 45 mg/L). Bt Cry9Ee toxin did not affect survival or larval weight, and the result was great confidence in accepting the null hypothesis by power analysis. The effect on development rates and pollen consumption were the inconclusive results because the post-hoc power was less than 0.8. Furthermore, the midgut bacterial structure and compositions were determined using high-throughput sequencing targeting the V3-V4 regions of the 16S rDNA. All core honey bee intestinal bacterial class such as γ-Proteobacteria, Actinobacteria, α-Proteobacteria, Bacilli, ß-Proteobacteria, and Bacteroidia were detected, and no significant changes were found in the species diversity and richness between Cry9Ee treatments and laboratory control.