In this paper, we propose a novel neural network model, called bi-hemispheres domain adversarial neural network (BiDANN), for EEG emotion recognition. BiDANN is motivated by the neuroscience findings, i.e., the emotional brain's asymmetries between left and right hemispheres. The basic idea of BiDANN is to map the EEG feature data of both left and right hemispheres into discriminative feature spaces separately, in which the data representations can be classified easily. For further precisely predicting the class labels of testing data, we narrow the distribution shift between training and testing data by using a global and two local domain discriminators, which work adversarially to the classifier to encourage domain-invariant data representations to emerge. After that, the learned classifier from labeled training data can be applied to unlabeled testing data naturally. We conduct two experiments to verify the performance of our BiDANN model on SEED database. The experimental results show that the proposed model achieves the state-of-the-art performance.
To expand the usage of endophytes in agriculture and in forestry, the insecticidal gene cry218 of Bacillus thuringiensis was introduced into a poplar bacterial endophyte Burkholderia pyrrocinia JK-SH007. The cry218 gene was cloned by polymerase chain reaction (PCR) and was inserted into a PHKT 2 expression vector that was introduced into the bacterial endophyte JK-SH007. By using sodium dodecyl sulphate polyacryl amide gel electrophoresis (SDS-PAGE) and western blotting, we confirmed that the engineered bacterial endophyte was successfully constructed, and it harboured insecticidal function after the bioassay in planta. The toxicity of the expressed insecticidal protein was analysed on second instar silkworm. The regression equation showed that the median lethal concentration (LC 50) of the insecticidal protein was 0.77 (0.57-1.04) g/L at 72 h. The insecticidal bacteria genetically modified in this study have laid the foundation for further exploitation of biocontrol bacteria.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.