The metasurface refractive index sensor has a high degree of tunability and flexibility, providing excellent performance for high precision refractive index sensing applications. The metasurface absorber with metallic structure has been hindered in further sensor applications due to the inherent Ohmic loss of the metallic material. In this study, a dual nanorod metasurface structure based on semiconductor Si was designed, introducing a symmetry‐breaking structure to excite dual ultra‐narrow q‐BIC resonance peaks with Fano line shapes. Both peaks are located in the near‐infrared region, and multipole analysis shows that this strong field enhancement effect is induced by a magnetic dipole. Experimental results demonstrate the potential of this sensor to provide dual‐channel detection while achieving high sensitivity and high Q‐factor. We believe that this device exhibits outstanding performance and high practicality, providing a reference for the development and application of biological and environmental sensors.

Micro-expressions, which are spontaneous and difficult to suppress, reveal a person’s true emotions. They are characterized by short duration and low intensity, making the task of micro-expression recognition challenging in the field of emotion computing. In recent years, deep learning-based feature extraction and fusion techniques have been widely used for micro-expression recognition, particularly methods based on Vision Transformer that have gained popularity. However, the Vision Transformer-based architecture used in micro-expression recognition involves a significant amount of invalid computation. Additionally, in the traditional two-stream architecture, although separate streams are combined through late fusion, only the output features from the deepest level of the network are utilized for classification, thus limiting the network’s ability to capture subtle details due to the lack of fine-grained information. To address these issues, we propose a new two-level spatio-temporal feature fused with a two-stream architecture. This architecture includes a spatial encoder (modified ResNet) for learning texture features of the face, a temporal encoder (Swin Transformer) for learning facial muscle motor features, a feature fusion algorithm for integrating multi-level spatio-temporal features, a classification head, and a weighted average operator for temporal aggregation. The two-stream architecture has the advantage of extracting richer features compared to the single-stream architecture, leading to improved performance. The shifted window scheme of Swin Transformer restricts self-attention computation to non-overlapping local windows and allows cross-window connections, significantly improving the performance and reducing the computation compared to Vision Transformer. Moreover, the modified ResNet is computationally less intensive. Our proposed feature fusion algorithm leverages the similarity in output feature shapes at each stage of the two streams, enabling the effective fusion of multi-level spatio-temporal features. This algorithm results in an improvement of approximately 4% in both the F1 score and the UAR. Comprehensive evaluations conducted on three widely used spontaneous micro-expression datasets (SMIC-HS, CASME II, and SAMM) consistently demonstrate the superiority of our approach over comparative methods. Notably, our approach achieves a UAR exceeding 0.905 on CASME II, making it one of the few frameworks in the published micro-expression recognition literature to achieve such high performance.

Hyperspectral unmixing (HU) aims to decompose mixed pixels into a set of endmembers and corresponding abundances. Deep learning-based HU methods are currently a hot research topic, but most existing unmixing methods still rely on per-pixel training or employ convolutional neural networks (CNNs), which overlook the non-local correlations of materials and spectral characteristics. Furthermore, current research mainly focuses on linear mixing models, which limits the feature extraction capability of deep encoders and further improvement in unmixing accuracy. In this paper, we propose a nonlinear unmixing network capable of extracting global spatial-spectral features. The network is designed based on an autoencoder architecture, where a dual-stream CNNs is employed in the encoder to separately extract spectral and local spatial information. The extracted features are then fused together to form a more complete representation of the input data. Subsequently, a linear projection-based multi-head self-attention mechanism is applied to capture global contextual information, allowing for comprehensive spatial information extraction while maintaining lightweight computation. To achieve better reconstruction performance, a model-free nonlinear mixing approach is adopted to enhance the model’s universality, with the mixing model learned entirely from the data. Additionally, an initialization method based on endmember bundles is utilized to reduce interference from outliers and noise. Comparative results on real datasets against several state-of-the-art unmixing methods demonstrate the superior of the proposed approach.

As a noninvasive and label‐free optical technique, Raman spectroscopy offers significant advantages in studying the structure and properties of biomacromolecules, as well as real‐time changes in cellular molecular structure. However, its practical applications are hindered by weak scattering responses, low signal intensity, and poor spectral uniformity, which affect the subsequent accuracy of spectral analysis. To address these issues, we report a novel surface‐enhanced Raman scattering (SERS) substrate based on a pyramidal pitted silicon (PPSi) array structure adhered with Au‐shell Ag‐core nanospheres (Au@Ag NSs). By preparing a highly uniform PPSi array substrate with controllable size and arrangement, and constructing SERS‐active Au@Ag NSs on this substrate, a three‐dimensional (3D) composite SERS substrate is realized. The enhancement performance and spectral uniformity of 3D composite SERS substrate were examined using crystal violet (CV) and Rhodamine 6G (R6G) molecules, achieving a minimum detectable concentration of R6G at 10 ⁻⁹ M and the analytical enhancement factor (AEF) of 4.2 × 10 ⁸ . Moreover, SERS detection of biological samples with varying concentrations of Staphylococcus aureus demonstrated excellent biocompatibility of the SERS substrate and enabled quantitative analysis of bacterial concentration ( R ² = 99.7 %). Theoretical simulations using finite‐difference time‐domain (FDTD) analysis were conducted to examine the electromagnetic field distribution of the three‐dimensional SERS composite substrate, confirming its local electric field enhancement effect. These experimental and theoretical results indicate that the Au@Ag NSs/PPSi substrate with a regulable pyramidal pitted array is a promising candidate for sensitive, label‐free SERS detection in medical and biotechnological applications.