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.

Nasal obstruction is a common symptom of nasal conditions, with nasal resistance being a crucial physiological indicator for assessing severity. However, traditional rhinomanometry faces challenges with interference, limited automation, and unstable measurement results. To address these issues, this research designed a nasal resistance measurement system based on multi-sensor fusion of pressure and flow. The system comprises lower computer hardware for acquiring raw pressure–flow signals in the nasal cavity and upper computer software for segmenting and filtering effective respiratory cycles and calculating various nasal resistance indicators. Meanwhile, the system’s anti-interference capability was assessed using recall, precision, and accuracy rates for respiratory cycle recognition, while stability was evaluated by analyzing the standard deviation of nasal resistance indicators. The experimental results demonstrate that the system achieves recall and precision rates of 99% and 86%, respectively, for the recognition of effective respiratory cycles. Additionally, under the three common interference scenarios of saturated or weak breaths, breaths when not worn properly, and multiple breaths, the system can achieve a maximum accuracy of 96.30% in identifying ineffective respiratory cycles. Furthermore, compared to the measurement without filtering for effective respiratory cycles, the system reduces the median within-group standard deviation across four types of nasal resistance measurements by 5 to 18 times. In conclusion, the nasal resistance measurement system developed in this research demonstrates strong anti-interference capabilities, significantly enhances the automation of the measurement process and the stability of the measurement results, and offers robust technical support for the auxiliary diagnosis of related nasal conditions.