Search

Using multimodal fusion method to deal with emotion recognition task has become a trend. The fusion vector can more comprehensively reflect the subject's emotional change state, so as to obtain a more accurate emotion recognition effect. However, different fusion input or feature fusion methods have different effects on the final fusion results. In this paper, we propose a subjective and objective feature fused neural network model (SOFNN) for emotion recognition, which can effectively learn spatial–temporal information from EEG signals and dynamically integrate EEG signals with eye movement signals. Specifically, we extract more abundant spatial and temporal information from the original EEG signal through a series of 1-D convolution kernels of different sizes and we verify the effectiveness of the extracted features through experiments. The size of the 1-D convolution kernels is determined by the characteristics (such as sampling rate and number of channels) of the original EEG signal. Then, we design a subjective and objective feature fusion framework to adjust the proportion of the two features through the dynamic learning of the weight vector, so as to fully exploit their respective advantages. We evaluate the performance of our model on the SEED-IV dataset, which is a common dataset. For the recognition task of four emotions (happy, sad, fear and neutral), our model achieves 86.27% accuracy and 10.16% standard deviation, which are better than the existing methods. In addition, we design a variety of ablation experiments to verify the effectiveness of each module in our model. The experiment results show that our model can make better use of the complementary relationship between subjective and objective features, which can achieve better emotion recognition effect. • Experiments prove that the extraction of salient features and the fusion of subjective and objective features are helpful to improve the performance of emotion recognition model. • Our proposed method of combining subjective and objective signals comprehensively explores the complexity of the emotional change process. • Based on the structure of Inception, several parallel 1-D convolution kernels are used to obtain the temporal and spatial information contained in the original EEG signal. • A new feature fusion method is proposed to give full play to the advantages of various modalities by dynamically distributing the weight of each feature. [ABSTRACT FROM AUTHOR]

The Qinling Orogenic Belt was formed by multi-stage convergence and subsequent collision between the North China Block and South China Block during the Palaeozoic to Late Triassic. Following the collision between the South Qinling Belt and the South China Block in the Late Triassic, the whole Qinling Orogenic Belt evolved into an intracontinental orogeny. However, the exact termination time of the Late Mesozoic intracontinental contractional deformation and the tectonic transformation from compression to extension remains unclear. The extensional shear zone developed in the West Qinling Orogenic Belt provides a crucial clue to revealing the tectonic transformation and uplift and exhumation of the orogenic belt. This study focuses on kinematics, deformation temperature, and geochronology of the shear zone in the West Qinling Orogenic Belt through detailed field structural analysis and laboratory analysis. The Taibai shear zone (TBSZ), located in the West Qinling Orogenic Belt, cuts across the Qinling Orogenic Belt along the NE–NEE direction and separates the Taibai pluton in the east from the Baoji pluton in the west. The NE–NEE-striking TBSZ is an extensional shear zone showing a top-to-the-NW sinistral shear sense. The TBSZ was formed under the high greenschist–low amphibolite facies conditions (300–550°C) in the middle-upper crust level (8–15 km). Zircon U–Pb dating and biotite and muscovite 40Ar/39Ar dating indicate that the TBSZ occurred at 120–113 Ma. The extensional TBSZ and normal faults on its hanging wall indicate the tectonic transformation and the extensional collapse of the Mesozoic intracontinental orogenic belt during the late Early Cretaceous. The Cretaceous extensional collapse of the Qinling Orogenic Belt also led to the rapid uplift and exhumation of the Taibai pluton and the North Qinling Belt in the east. [ABSTRACT FROM AUTHOR]