Motor imagery electroencephalogram (MI-EEG) decoding algorithms face multiple challenges. These include incomplete feature extraction, susceptibility of attention mechanisms to distraction under low signal-to-noise ratios, and limited capture of long-range temporal dependencies. To address these issues, this paper proposes a multi-branch differential attention temporal network (MDAT-Net). First, the method constructed a multi-branch feature fusion module to extract and fuse diverse spatio-temporal features from different scales. Next, to suppress noise and stabilize attention, a novel multi-head differential attention mechanism was introduced to enhance key signal dynamics by calculating the difference between attention maps. Finally, an adaptive residual separable temporal convolutional network was designed to efficiently capture long-range dependencies within the feature sequence for precise classification. Experimental results showed that the proposed method achieved average classification accuracies of 85.73%, 90.04%, and 96.30% on the public datasets BCI-IV-2a, BCI-IV-2b, and HGD, respectively, significantly outperforming several baseline models. This research provides an effective new solution for developing high-precision motor imagery brain-computer interface systems.
Due to the significant non-stationarity and feature distribution discrepancies in surface electromyography (sEMG) signals during muscle fatigue monitoring, traditional fixed-parameter Transformer models often struggle to accurately capture the complex evolution of time-frequency characteristics across different fatigue stages. To address this limitation, this paper proposes a K-means clustering-guided neural architecture search method (CG-NAS) to achieve adaptive optimization of Transformer architectures based on data distribution characteristics. The method first classified input EMG features using the K-means clustering algorithm and constructed Gaussian distributions characterized by mean and variance to quantify the complexity of each cluster. These distribution priors then guided the neural architecture search process, enabling dynamic alignment between the architecture search space and data characteristics: for low-complexity data clusters with small mean and variance, lightweight Transformer architectures were selected, whereas for high-complexity clusters, architectures with greater width and depth were allocated. Experimental results demonstrated the superior performance of CG-NAS in muscle fatigue index prediction tasks, achieving a mean absolute error of 0.098 2 and a coefficient of determination of 0.957 3, significantly outperforming multiple benchmark models. The study shows that CG-NAS effectively aligns with the nonlinear evolution of time-frequency features during the fatigue process and provides an efficient and robust solution for fatigue monitoring.
ObjectiveTo investigate the clinical anatomy and application of free profunda femoral artery pedicled chimeric myocutaneous perforator flap in the defect reconstruction after radical resection of tongue carcinoma. MethodsBetween April 2011 and January 2016, 44 cases of tongue carcinoma underwent radical resection, and tongue defects were reconstructed by free profunda femoral artery pedicled chimeric myocutaneous perforator flaps at the same stage. There were 40 males and 4 females, with a mean age of 46.3 years (range, 32-71 years). The pathologic type was squamous cell carcinoma, which involved the lingual margin in 24 cases, the ventral tongue in 17 cases, and the mouth floor in 3 cases. According to Union for International Cancer Control (UICC) TNM staging, 16 cases were rated as T4N0M0, 11 cases as T4N1M0, 9 cases as T3N1M0, and 8 cases as T3N2M0. The course of disease ranged from 1 to 22 months (mean, 8.6 months). The size of perforator flap ranged from 8.5 cm×4.0 cm to 12.0 cm×6.5 cm, and the size of muscle flap ranged from 4.0 cm×3.0 cm to 7.5 cm×5.0 cm. The adductor magnus myocutaneous flap with a pedicle of (8.3±0.5) cm was used in 11 cases, and the gracilis muscle myocutaneous flap with a pedicle of (8.1±0.8) cm was used in 33 cases. The donor sites were sutured directly. ResultsAll 44 perforator flaps survived uneventfully, and the donor site healed well. The patients were followed up for 12 to 40 months (mean, 23.8 months). The reconstructed tongue had good appearance and function in swallowing and language. No local recurrence was found. Only linear scar was left at the donor sites. ConclusionThe free profunda femoral artery pedicled chimeric myocutaneous perforator flap can be harvested in various forms, and is an ideal choice to reconstruct defect after radical resection of tongue carcinoma.