Emotion plays an important role in people's cognition and communication. By analyzing electroencephalogram (EEG) signals to identify internal emotions and feedback emotional information in an active or passive way, affective brain-computer interactions can effectively promote human-computer interaction. This paper focuses on emotion recognition using EEG. We systematically evaluate the performance of state-of-the-art feature extraction and classification methods with a public-available dataset for emotion analysis using physiological signals (DEAP). The common random split method will lead to high correlation between training and testing samples. Thus, we use block-wise K fold cross validation. Moreover, we compare the accuracy of emotion recognition with different time window length. The experimental results indicate that 4 s time window is appropriate for sampling. Filter-bank long short-term memory networks (FBLSTM) using differential entropy features as input was proposed. The average accuracy of low and high in valance dimension, arousal dimension and combination of the four in valance-arousal plane is 78.8%, 78.4% and 70.3%, respectively. These results demonstrate the advantage of our emotion recognition model over the current studies in terms of classification accuracy. Our model might provide a novel method for emotion recognition in affective brain-computer interactions.
ObjectiveTo investigate the effect of Masquelet technique combined with artificial dermis on repairing bone and soft tissue defects in rabbits, and to observe the microstructure and vascularization of induced membrane, so as to guide the clinical treatment of Gustilo-Anderson type Ⅲ open fracture with large bone defect and soft tissue defect.MethodsEighty male rabbits, weighing 2.03-2.27 kg (mean, 2.11 kg), were selected. The bilateral thighs of 64 rabbits were randomly divided into experimental group and control group, the remaining 16 rabbits were sham operation group. Bone and soft tissue defect models of femur were made in all rabbits. In the experimental group, the first stage of Masquelet technique was used [polymethyl methacrylate bone cement was filled in bone defect area] combined with artificial dermis treatment; in the control group, the first stage of Masquelet technique was used only; in the sham operation group, the wound was sutured directly without any treatment. Four rabbits in sham operation group and 16 rabbits in the experimental group and control group were sacrificed at 2, 4, 6, and 8 weeks after operation, respectively. The induced membranes and conjunctive membranes were observed on both sides of the femur. The membrane structure was observed by HE staining, and the microvessel density (MVD) was counted by CD34 immunohistochemical staining.ResultsGross observation showed that the spongy layer of collagen in the artificial dermis of the experimental group disappeared completely at 4 weeks after operation, and the induced membrane structure of the experimental group and the control group was complete; the membrane structure of the control group was translucent, and the membrane structure of the experimental group was thicker, light red opaque, accompanied by small vessel proliferation. The membrane structure of the experimental group and the control group increased gradually from 6 to 8 weeks after operation. In the sham operation group, only scar tissue proliferation was observed over time. HE staining showed that a large number of muscle fibers and a small amount of collagen fibers proliferation with inflammatory cell infiltration could be seen in the experimental group and the control group at 2 weeks after operation; most of the sham operation group were muscle fibers with a small amount of interfibrous vessels. At 4 weeks after operation, collagen fibers increased and some blood vessels formed in the experimental group. The nuclei of collagen fibers in the control group were round-like, while those in the experimental group were flat-round. At 6 and 8 weeks after operation, the collagen fibers in the experimental group and the control group increased. The nuclei of the collagen fibers in the control group were still round-like. The nuclei of the collagen fibers in the experimental group were fusiformis and deeply stained compared with those in the control group. The proliferation of blood vessels was observed in both groups, and the number of proliferation vessels in the experimental group was increased compared with that in the control group. In the sham operation group, a large number of fibroblasts still appeared, but no significant proliferation of blood vessels with time was observed. CD34 immunohistochemical staining showed that MVD in each group increased gradually with the prolongation of time after operation. MVD in the sham operation group was significantly higher than that in the experimental group and the control group at 2 weeks after operation, and significantly smaller than that in the experimental group and the control group at 4, 6, and 8 weeks after operation (P<0.05). MVD in the experimental group was significantly higher than that in the control group at 4 and 6 weeks after operation (P<0.05), but there was no significant difference in MVD between the two groups at 2 and 8 weeks (P>0.05).ConclusionMasquelet technique combined with artificial dermis in the treatment of femoral bone defect and soft tissue defect in rabbits can significantly promote the vascularization of membrane structure at 4-6 weeks after operation. The combination of these two methods has guiding significance for the treatment of Gustilo-Anderson type Ⅲ open fracture with bone and soft tissue defects.