Jiaxuan Lu

Introduction: Electroencephalography (EEG) based emotion recognition is pivotal for advancing mobile health monitoring and real-time affective interaction. However, current methodologies face a critical trade-off between modeling the complex, multi-scale dynamics of brain activity and maintaining the computational efficiency necessary for edge deployment. Existing approaches often rely on fixed temporal scales and neglect hierarchical spatial connectivity, which limits both classification robustness and scalability in practical settings. Methods: To address these challenges, we propose the Multi-Scale Spatiotemporal Graph Mamba (MSGM). Specifically, it employs multi-window temporal segmentation to extract relative power spectral density (rPSD) features, mimicking the brain's multi-scale processing to capture both transient emotional fluctuations and sustained mood. Spatially, it constructs bimodal global and local graphs refined by multi-depth Graph Convolutional Networks (GCNs), intuitively modeling hierarchical brain connectivity rather than isolated sensors. These features are synthesized via a token embedding fusion module and processed by a single-layer MSST-Mamba module, which leverages state-space modeling to ensure linear computational complexity, avoiding Transformer latency bottlenecks to facilitate real-time clinical monitoring. Results: Assessed on the SEED, THU-EP, and FACED datasets under subject-independent protocols, MSGM outperforms baseline approaches, attaining competitive accuracy and F1 scores (e.g., 83.43% accuracy and 85.03% F1 score on SEED). Leveraging a single MSST-Mamba layer, MSGM demonstrates robust generalization and efficiency, achieving millisecond-level inference (151 ms) on the NVIDIA Jetson Xavier NX edge device, confirming its suitability for real-time applications. Discussion: The capability of MSGM to capture complex spatiotemporal dynamics with low computational overhead highlights its suitability for real-time monitoring and interactive interfaces. By integrating neuroanatomical priors into the selective state-space modeling, the framework effectively maintains spatial intelligence and topological consistency throughout the classification process. This approach not only improves recognition accuracy but also ensures neurophysiologically grounded interpretability. Future research will focus on multimodal integration and further optimization of hierarchical spatial modeling to address the challenges of cross-subject variability. To support research reproducibility, the source code of MSGM will be made available at https://github.com/liuguangyunjizero/MSGM .

EEG-based emotion recognition struggles with capturing multi-scale spatiotemporal dynamics and ensuring computational efficiency for real-time applications. Existing methods often oversimplify temporal granularity and spatial hierarchies, limiting accuracy. To overcome these challenges, we propose the Multi-Scale Spatiotemporal Graph Mamba (MSGM), a novel framework integrating multi-window temporal segmentation, bimodal spatial graph modeling, and efficient fusion via the Mamba architecture. By segmenting EEG signals across diverse temporal scales and constructing global-local graphs with neuroanatomical priors, MSGM effectively captures fine-grained emotional fluctuations and hierarchical brain connectivity. A multi-depth Graph Convolutional Network (GCN) and token embedding fusion module, paired with Mamba's state-space modeling, enable dynamic spatiotemporal interaction at linear complexity. Notably, with just one MSST-Mamba layer, MSGM surpasses leading methods in the field on the SEED, THU-EP, and FACED datasets, outperforming baselines in subject-independent emotion classification while achieving robust accuracy and millisecond-level inference on the NVIDIA Jetson Xavier NX.

Device recognition is vital for security in wireless communication systems, particularly for applications like access control. Radio Frequency Fingerprint Identification (RFFI) offers a non-cryptographic solution by exploiting hardware-induced signal distortions. This paper proposes HyDRA, a Hybrid Dual-mode RF Architecture that integrates an optimized Variational Mode Decomposition (VMD) with a novel architecture based on the fusion of Convolutional Neural Networks (CNNs), Transformers, and Mamba components, designed to support both closed-set and open-set classification tasks. The optimized VMD enhances preprocessing efficiency and classification accuracy by fixing center frequencies and using closed-form solutions. HyDRA employs the Transformer Dynamic Sequence Encoder (TDSE) for global dependency modeling and the Mamba Linear Flow Encoder (MLFE) for linear-complexity processing, adapting to varying conditions. Evaluation on public datasets demonstrates state-of-the-art (SOTA) accuracy in closed-set scenarios and robust performance in our proposed open-set classification method, effectively identifying unauthorized devices. Deployed on NVIDIA Jetson Xavier NX, HyDRA achieves millisecond-level inference speed with low power consumption, providing a practical solution for real-time wireless authentication in real-world environments.

Event cameras, as an emerging imaging technology, offer distinct advantages over traditional RGB cameras, including reduced energy consumption and higher frame rates. However, the limited quantity of available event data presents a significant challenge, hindering their broader development. To alleviate this issue, we introduce a tailored U-shaped State Space Model Knowledge Transfer (USKT) framework for Event-to-RGB knowledge transfer. This framework generates inputs compatible with RGB frames, enabling event data to effectively reuse pre-trained RGB models and achieve competitive performance with minimal parameter tuning. Within the USKT architecture, we also propose a bidirectional reverse state space model. Unlike conventional bidirectional scanning mechanisms, the proposed Bidirectional Reverse State Space Model (BiR-SSM) leverages a shared weight strategy, which facilitates efficient modeling while conserving computational resources. In terms of effectiveness, integrating USKT with ResNet50 as the backbone improves model performance by 0.95%, 3.57%, and 2.9% on DVS128 Gesture, N-Caltech101, and CIFAR-10-DVS datasets, respectively, underscoring USKT's adaptability and effectiveness. The code will be made available upon acceptance.

With the advent of the era of foundation models, pre-training and fine-tuning have become common paradigms. Recently, parameter-efficient fine-tuning has garnered widespread attention due to its better balance between the number of learnable parameters and performance. However, some current parameter-efficient fine-tuning methods only model a single modality and lack the utilization of structural knowledge in downstream tasks. To address this issue, this paper proposes a multi-modal parameter-efficient fine-tuning method based on graph networks. Each image is fed into a multi-modal large language model (MLLM) to generate a text description. The image and its corresponding text description are then processed by a frozen image encoder and text encoder to generate image features and text features, respectively. A graph is constructed based on the similarity of the multi-modal feature nodes, and knowledge and relationships relevant to these features are extracted from each node. Additionally, Elastic Weight Consolidation (EWC) regularization is incorporated into the loss function to mitigate the problem of forgetting during task learning. The proposed model achieves test accuracies on the OxfordPets, Flowers102, and Food101 datasets that improve by 4.45%, 2.92%, and 0.23%, respectively. The code is available at https://github.com/yunche0/GA-Net/tree/master.