Background: Efficient decoding of motor imagery (MI) electroencephalogram (EEG) signals is essential for the precise control and practical deployment of brain-computer interface (BCI) systems. Owing to the complex nonlinear characteristics of EEG signals across spatial, spectral, and temporal dimensions, efficiently extracting multidimensional discriminative features remains a key challenge to improving MI-EEG decoding performance. Methods: To address the challenge of capturing complex spatial, spectral, and temporal features in MI-EEG signals, this study proposes a multi-branch deep neural network, which jointly models these dimensions to enhance classification performance. The network takes as inputs both a three-dimensional power spectral density tensor and two-dimensional time-domain EEG signals and incorporates four complementary feature extraction branches to capture spatial, spectral, spatial-spectral joint, and temporal dynamic features, thereby enabling unified multidimensional modeling. The model was comprehensively evaluated on two widely used public MI-EEG datasets: EEG Motor Movement/Imagery Database (EEGMMIDB) and BCI Competition IV Dataset 2a (BCIIV2A). To further assess interpretability, gradient-weighted class activation mapping (Grad-CAM) was employed to visualize the spatial and spectral features prioritized by the model. Results: On the EEGMMIDB dataset, it achieved an average classification accuracy of 86.34% and a kappa coefficient of 0.829 in the five-class task. On the BCIIV2A dataset, it reached an accuracy of 83.43% and a kappa coefficient of 0.779 in the four-class task. Conclusions: These results demonstrate that the network outperforms existing state-of-the-art methods in classification performance. Furthermore, Grad-CAM visualizations identified the key spatial channels and frequency bands attended to by the model, supporting its neurophysiological interpretability.

The nasal cavity three-dimensional structure reconstruction is significant for the diagnosis and treatment of nasal and nasopharynx diseases. Currently, most systems for nasal cavity three-dimensional structure reconstruction are based on a long-source acoustic tube. However, the long-source acoustic tube has the weaknesses of low portability and high cost. To address these issues, a nasal cavity three-dimensional structure reconstruction system based on a short-source acoustic tube was designed in this research. The designed system comprises the lower computer of a nasal acoustic signal acquisition device and the upper computer of nasal acoustic signal analysis software. The lower computer of a nasal acoustic signal acquisition device consists of a signal processing unit, a detection unit, a microcontroller, and a USB communication interface. It is used to collect the original acoustic signal in the nasal cavity. The upper computer of nasal acoustic signal analysis software consists of the nasal cavity acoustic signal preprocessing method and the nasal cavity three-dimensional structure hierarchical reconstruction method. The nasal cavity acoustic signal preprocessing method is used to eliminate the DC offset component and suppress the high-frequency noise. Then, the nasal cavity three-dimensional structure hierarchical reconstruction method is used to establish the relationship between the cross-sectional area of the nasal cavity and the depth of the nasal cavity. In order to verify the effectiveness of the system designed in this research, the straight tube model and the simulated nasal cavity model were selected as test subjects, and the depth–cross-sectional area was selected as the evaluation indicator of the accuracy of the nasal cavity three-dimensional structure reconstruction result. The experimental results show that the root mean squared error and the mean relative error of the depth–cross-sectional area were reduced from 0.6284 cm${}^2$ to 0.0201 cm${}^2$ and 47.6467% to 1.8248%, respectively, under the straight tube model by using the nasal cavity acoustic signal preprocessing method. The root mean squared error and the mean relative error of the depth–cross-sectional area were reduced from 4.7730 cm${}^2$ to 0.1510 cm${}^2$ and 107.8128% to 3.3096%, respectively, under the simulated nasal cavity model. Meanwhile, this system can increase the effective measurement depth of the nasal cavity from 7 cm to 13 cm based on the preprocessing method. The results demonstrated that the designed system can not only reconstruct and visualize a nasal cavity three-dimensional structure with high precision but also generate comprehensive test reports. Therefore, this system can provide a basis for further auxiliary diagnosis of the disease and facilitate doctors in explaining the physiological structure of the nasal cavity to patients.

With the rapid evolution of Large Language Models (LLMs) in natural language understanding and generation, Relation Extraction (RE) has achieved substantial milestones in low-resource and open-domain scenarios. However, prevailing LLM-based RE methodologies predominantly rely on one-shot prompting or static workflows, which lack autonomous evaluation and iterative optimization mechanisms. Consequently, these approaches are prone to issues such as missing relations, type confusion, and factual hallucinations when navigating complex relational contexts. To address these limitations, this paper proposes DyFIRER (Dynamic Feedback Iterative Relation Extraction Framework), a multi-agent framework characterized by dynamic feedback. By constructing three functionally complementary agents—Extraction, Verification, and Optimization—the framework models the RE task as a closed-loop iterative process consisting of “extraction-verification-feedback-optimization,” thereby enabling dynamic adjustment and continuous refinement of extraction strategies. Experimental results on the DuIE 2.0 open relation extraction extension subset demonstrate that DyFIRER achieves an F1-score of 80.5%, modestly but statistically significantly outperforms GPT-4 (p = 0.014), a result that holds on both the augmented and non-augmented test sets and mainstream static methods (yielding a 10.3% improvement over Qwen-7B). Ablation studies further substantiate the critical role of the dynamic feedback iterative mechanism and the strategy retrieval module in mitigating complex relation omissions and factual hallucinations. The framework requires no additional annotated data or fine-tuning, suggesting potential applicability to low-resource settings, though this was not directly evaluated in the current study.