Human emotions are intricate psychological phenomena that reflect an individual’s current physiological and psychological state.Emotions have a pronounced influence on human behavior,cognition,communication,and decis...Human emotions are intricate psychological phenomena that reflect an individual’s current physiological and psychological state.Emotions have a pronounced influence on human behavior,cognition,communication,and decision-making.However,current emotion recognition methods often suffer from suboptimal performance and limited scalability in practical applications.To solve this problem,a novel electroencephalogram(EEG)emotion recognition network named VG-DOCoT is proposed,which is based on depthwise over-parameterized convolutional(DO-Conv),transformer,and variational automatic encoder-generative adversarial network(VAE-GAN)structures.Specifically,the differential entropy(DE)can be extracted from EEG signals to create mappings into the temporal,spatial,and frequency information in preprocessing.To enhance the training data,VAE-GAN is employed for data augmentation.A novel convolution module DO-Conv is used to replace the traditional convolution layer to improve the network.A transformer structure is introduced into the network framework to reveal the global dependencies from EEG signals.Using the proposed model,a binary classification on the DEAP dataset is carried out,which achieves an accuracy of 92.52%for arousal and 92.27%for valence.Next,a ternary classification is conducted on SEED,which classifies neutral,positive,and negative emotions;an impressive average prediction accuracy of 93.77%is obtained.The proposed method significantly improves the accuracy for EEG-based emotion recognition.展开更多
GaN power electronic devices,such as the lateral AlGaN/GaN Schottky barrier diode(SBD),have received significant attention in recent years.Many studies have focused on optimizing the breakdown voltage(BV)of the device...GaN power electronic devices,such as the lateral AlGaN/GaN Schottky barrier diode(SBD),have received significant attention in recent years.Many studies have focused on optimizing the breakdown voltage(BV)of the device,with a particular emphasis on achieving ultra-high-voltage(UHV,>10 kV)applications.However,another important question arises:can the device maintain a BV of 10 kV while having a low turn-on voltage(V_(on))?In this study,the fabrication of UHV AlGaN/GaN SBDs was demonstrated on sapphire with a BV exceeding 10 kV.Moreover,by utilizing a doublebarrier anode(DBA)structure consisting of platinum(Pt)and tantalum(Ta),a remarkably low Von of 0.36 V was achieved.This achievement highlights the great potential of these devices for UHV applications.展开更多
基金supported by the National Key Research and Development Program of China(No.2022YFE0122700)the National Natural Science Foundation of China(No.61971230)。
文摘Human emotions are intricate psychological phenomena that reflect an individual’s current physiological and psychological state.Emotions have a pronounced influence on human behavior,cognition,communication,and decision-making.However,current emotion recognition methods often suffer from suboptimal performance and limited scalability in practical applications.To solve this problem,a novel electroencephalogram(EEG)emotion recognition network named VG-DOCoT is proposed,which is based on depthwise over-parameterized convolutional(DO-Conv),transformer,and variational automatic encoder-generative adversarial network(VAE-GAN)structures.Specifically,the differential entropy(DE)can be extracted from EEG signals to create mappings into the temporal,spatial,and frequency information in preprocessing.To enhance the training data,VAE-GAN is employed for data augmentation.A novel convolution module DO-Conv is used to replace the traditional convolution layer to improve the network.A transformer structure is introduced into the network framework to reveal the global dependencies from EEG signals.Using the proposed model,a binary classification on the DEAP dataset is carried out,which achieves an accuracy of 92.52%for arousal and 92.27%for valence.Next,a ternary classification is conducted on SEED,which classifies neutral,positive,and negative emotions;an impressive average prediction accuracy of 93.77%is obtained.The proposed method significantly improves the accuracy for EEG-based emotion recognition.
基金supported by National Key R&D Project grant No.2022YFE0122700)National High-Tech R&D Project(grant No.2015AA033305)+2 种基金Jiangsu Provincial Key R&D Program(grant No.BK2015111)China Postdoctoral Science Foundation(grant No.2023M731583)Jiangsu Provincial Innovation and Entrepreneurship Doctor Program,the Research and Development Funds from State Grid Shandong Electric Power Company and Electric Power Research Institute.
文摘GaN power electronic devices,such as the lateral AlGaN/GaN Schottky barrier diode(SBD),have received significant attention in recent years.Many studies have focused on optimizing the breakdown voltage(BV)of the device,with a particular emphasis on achieving ultra-high-voltage(UHV,>10 kV)applications.However,another important question arises:can the device maintain a BV of 10 kV while having a low turn-on voltage(V_(on))?In this study,the fabrication of UHV AlGaN/GaN SBDs was demonstrated on sapphire with a BV exceeding 10 kV.Moreover,by utilizing a doublebarrier anode(DBA)structure consisting of platinum(Pt)and tantalum(Ta),a remarkably low Von of 0.36 V was achieved.This achievement highlights the great potential of these devices for UHV applications.
