Search

Electroencephalogram (EEG) is a crucial and widely utilized technique in neuroscience research. In this paper, we introduce a novel graph neural network called the spatial-temporal graph attention network with a transformer encoder (STGATE) to learn graph representations of emotion EEG signals and improve emotion recognition performance. In STGATE, a transformer-encoder is applied for capturing time-frequency features which are fed into a spatial-temporal graph attention for emotion classification. Using a dynamic adjacency matrix, the proposed STGATE adaptively learns intrinsic connections between different EEG channels. To evaluate the cross-subject emotion recognition performance, leave-one-subject-out experiments are carried out on three public emotion recognition datasets, i.e., SEED, SEED-IV, and DREAMER. The proposed STGATE model achieved a state-of-the-art EEG-based emotion recognition performance accuracy of 90.37% in SEED, 76.43% in SEED-IV, and 76.35% in DREAMER dataset, respectively. The experiments demonstrated the effectiveness of the proposed STGATE model for cross-subject EEG emotion recognition and its potential for graph-based neuroscience research.

Deep learning has recently been applied to automatically classify the modulation categories of received radio signals without manual experience. However, training deep learning models requires massive volume of data. An insufficient training data will cause serious overfitting problem and degrade the classification accuracy. To cope with small dataset, data augmentation has been widely used in image processing to expand the dataset and improve the robustness of deep learning models. However, in wireless communication areas, the effect of different data augmentation methods on radio modulation classification has not been studied yet. In this paper, we evaluate different data augmentation methods via a state-of-the-art deep learning-based modulation classifier. Based on the characteristics of modulated signals, three augmentation methods are considered, i.e., rotation, flip, and Gaussian noise, which can be applied in both training phase and inference phase of the deep learning-based classifier. Numerical results show that all three augmentation methods can improve the classification accuracy. Among which, the rotation augmentation method outperforms the flip method, both of which achieve higher classification accuracy than the Gaussian noise method. Given only 12.5% of training dataset, a joint rotation and flip augmentation policy can achieve even higher classification accuracy than the baseline with initial 100% training dataset without augmentation. Furthermore, with data augmentation, radio modulation categories can be successfully classified using shorter radio samples, leading to a simplified deep learning model and a shorter classification response time.

Wrought AZ (Mg−Al−Zn) series alloys have attracted lots of researches, due to low cost, high strength and good formability. Few researches focus on creep characteristics of wrought AZ series alloys, which might be of significance to extensive use of low-cost wrought Mg−Al based alloy at elevated temperature. The microstructures, tensile properties and creep characteristics of as-extruded Mg-9Al-Zn-0.5RE-0.5Ca-0.5Si (wt.%, named AZXSE91000) alloy were investigated by optical microscopy (OM), scanning electron microscopy (SEM), X-ray diffractometer (XRD), TEM (transmission electron microscopy), tensile tests and tensile creep tests (40−100 MPa, 125−150 °C). The as-extruded AZXSE91000 alloy exhibited good tensile strength both at room temperature and elevated temperature. The co-addition of Si, Ca and rare earth elements can improve the heat resistance of as-extruded AZ91 alloy resulting from fragmented heat-resistant particles hindering grain boundaries sliding. The steady creep rates of as-extruded AZXSE91000 alloy can be comparable with that of as-cast AZ91 alloy under similar experimental conditions. Dislocation climbing and grain boundary slip should dominantly contribute to the creep of as-extruded AZXSE91000 alloy. The asymmetric discontinuous precipitation in crept samples revealed that diffusion played an unneglected role during the creep process.

Carbon nitride nanocrystals were synthesized on Co/Ni-covered Si(100) wafers using a nitrogen-atom-beam-assisted pulsed laser ablation deposition method. Transmission electron miscroscopy, x-ray diffraction, and Raman spectroscopy showed that as-deposited films were constructed primarily from nanometer-sized β-C[sub3]N[sub4] and CN[subx] crystallites. The co-catalyzation by the cobalt and nickel in the synthesis process is considered to play an important role in the formation of nanocrystalline β-C[sub3]N[sub4]. The reasons for the formation of carbon nitride nanocrystals were analyzed. [ABSTRACT FROM AUTHOR]