Enhancing local representation learning through global-local integration with functional connectivity for EEG-based emotion recognition.

Emotion recognition based on electroencephalogram (EEG) signals is crucial in understanding human affective states. Current research has limitations in extracting local features. The representation capabilities of local features are limited, making it difficult to comprehensively capture emotional information. In this study, a novel approach is proposed to enhance local representation learning through global-local integration with functional connectivity for EEG-based emotion recognition. By leveraging the functional connectivity of brain regions, EEG signals are divided into global embeddings that represent comprehensive brain connectivity patterns throughout the entire process and local embeddings that reflect dynamic interactions within specific brain functional networks at particular moments. Firstly, a convolutional feature extraction branch based on the residual network is designed to extract local features from the global embedding. To further improve the representation ability and accuracy of local features, a multidimensional collaborative attention (MCA) module is introduced. Secondly, the local features and patch embedded local embeddings are integrated into the feature coupling module (FCM), which utilizes hierarchical connections and enhanced cross-attention to couple region-level features, thereby enhancing local representation learning. Experimental results on three public datasets show that compared with other methods, this method improves accuracy by 4.92% on the DEAP, by 1.11% on the SEED, and by 7.76% on the SEED-IV, demonstrating its superior performance in emotion recognition tasks.

Real-Time EEG-Based Emotion Recognition.

Most studies have demonstrated that EEG can be applied to emotion recognition. In the process of EEG-based emotion recognition, real-time is an important feature. In this paper, the real-time problem of emotion recognition based on EEG is explained and analyzed. Secondly, the short time window length and attention mechanisms are designed on EEG signals to follow emotion change over time. Then, long short-term memory with the additive attention mechanism is used for emotion recognition, due to timely emotion updates, and the model is applied to the SEED and SEED-IV datasets to verify the feasibility of real-time emotion recognition. The results show that the model performs relatively well in terms of real-time performance, with accuracy rates of 85.40% and 74.26% on SEED and SEED-IV, but the accuracy rate has not reached the ideal state due to data labeling and other losses in the pursuit of real-time performance.

Mechanism for Topology Selection of Isomeric Two-Dimensional Covalent Organic Frameworks.

The mechanism of growth of one of the competitive topologies for covalent organic frameworks with constitutional isomers is poorly understood. Herein, we employ molecular dynamics to study the isoenergetic assembly of the rhombic square (sql) and Kagome lattice (kgm). The concentration, solvent conditions, and the reversibility of chemical reactions are considered by means of an Arrhenius two-state model to describe the reactions. High concentrations and poor solvent both result in sql, agreeing well with recent experiments. Moreover, the high reversibility of reactions gives rise to sql, while the low reversibility leads to kgm, suggesting a new way of regulating the topology. Our analyses support that the nucleation of isomers influenced by experimental conditions is responsible for the selection of topologies, which improves understanding of the control of topology. We also propose a strategy in which a two-step growth can be exploited to greatly improve the crystallinity of kgm.

Flower-like NiO/ZnO hybrid coated with N-doped carbon layer derived from metal-organic hybrid frameworks as novel anode material for high performance sodium-ion batteries.

Metal-organic hybrid frameworks are considered as the promising precursor to prepare high performance anode materials for sodium-ion batteries (SIBs). In the present work, flower-like NiO/ZnO@NC with hollow and porous structure was prepared via a facile solvothermal and calcination process. The hollow and porous structure not only improve the electron transport capability, and but also inhibits the aggregation and accommodates the volume change of NiO/ZnO@NC. Meanwhile, the coated amorphous carbon layer could also increase the electron conductivity and buffer the huge volume expansion of active material NiO/ZnO. When used as anode for SIBs, NiO/ZnO@NC demonstrates a high specific capacity of 300 mAh g-1 with good cycling stability for 150 cycles, fast charge and discharge capability (154 mAh g-1 at 2500 mA g-1) and superior long cycling life at high current density for 2500 cycles. The strategy in this work should provide a new insight into fabrication novel structural anode materials for high performance SIBs.