Peiliang Gong

Accurate Remaining Useful Life prediction is critical for industrial predictive maintenance. However, real-world deployment is challenging due to the irregular nature of sensor observations, characterized by asynchronous sampling, burst missingness, and temporal jitter. Compounding this issue, purely data-driven models often generate physically implausible degradation trajectories that violate the irreversible nature of damage accumulation. To address this, we propose PC-MambaSDE, a unified continuous-time framework for robust RUL prediction under irregular observations. Specifically, we design a Mask-Aware Continuous Mamba Encoder that explicitly leverages observation masks to extract context-rich control signals. Furthermore, we introduce a Physics-Guided Latent SDE with parametrically rectified hybrid drift, superimposing a global physical bias to enforce monotonic degradation even amid severe observation gaps. Additionally, we formulate RUL prediction as a boundary value problem via a Terminal Degradation Penalty, which decouples a Health Index dimension and applies a penalty loss to guide trajectories toward the failure state. Theoretically, we prove that our variational objective is mathematically equivalent to minimizing the KL divergence via Girsanov's theorem, and we guarantee the global asymptotic stability of the learned dynamics through Lyapunov analysis. To enable rigorous evaluation, we develop a Hybrid Irregularity Generation Scheme that simulates realistic industrial imperfections. Extensive experiments on public benchmarks demonstrate that PC-MambaSDE significantly outperforms state-of-the-art methods, particularly under extreme observation scarcity, validating the efficacy of embedding physical priors into continuous-time latent dynamics. Our code is available at https://github.com/KylinToeFish/PC-MambaSDE.

Despite the remarkable success of foundation models in single-modal EEG analysis, their extension to multimodal affective tasks remains constrained by pervasive modality gaps and the prohibitive computational overhead of conventional fine-tuning. This paper presents Frequency-domain Informed Prompt Tuning (FIPT), a parameter-efficient framework designed to adapt pre-trained EEG backbones (e.g., LaBraM, CBraMod) to multimodal emotion recognition. By freezing the backbone's core weights, we introduce a Spectral-Rhythmic Alignment Module (SRAM) that synchronizes heterogeneous physiological signals in a unified frequency space, effectively mitigating cross-modal discrepancies. To further bridge the representation gap, we employ a Knowledge-Augmented Hybrid Prompting strategy, which injects Power Spectral Density (PSD) priors to anchor the model’s attention on biologically significant oscillatory features.Extensive evaluations on four diverse public datasets demonstrate that FIPT consistently achieves state-of-the-art performance. Our sensitivity analysis reveals that the framework effectively leverages spectral priors for guided adaptation, providing a robust, interpretable, and scalable paradigm for multimodal affective computing.

Time-Series (TS) data has grown in importance with the rise of Internet of Things devices like sensors, but its labeling remains costly and complex. While Unsupervised Domain Adaptation (UDAs) offers an effective solution, growing data privacy concerns have led to the development of Source-Free UDA (SFUDAs), enabling model adaptation to target domains without accessing source data. Despite their potential, applying existing SFUDAs to TS data is challenging due to the difficulty of transferring temporal dependencies-an essential characteristic of TS data-particularly in the absence of source samples. Although prior works attempt to address this by specific source pretraining designs, such requirements are often impractical, as source data owners cannot be expected to adhere to particular pretraining schemes. To address this, we propose Temporal Source Recovery (TemSR), a framework that leverages the intrinsic properties of TS data to generate a source-like domain and recover source temporal dependencies. With this domain, TemSR enables dependency transfer to the target domain without accessing source data or relying on source-specific designs, thereby facilitating effective and practical TS-SFUDA. TemSR features a masking-recovery-optimization process to generate a source-like distribution with restored temporal dependencies. This distribution is further refined through local context-aware regularization to preserve local dependencies, and anchor-based recovery diversity maximization to promote distributional diversity. Together, these components enable effective temporal dependency recovery and facilitate transfer across domains using standard UDA techniques. Extensive experiments across seven TS tasks demonstrate the effectiveness of TemSR, which even surpasses existing TS-SFUDA methods that require source-specific designs.

Functional brain connectivity networks capture complex relationships and temporal evolution between brain regions, which have become increasingly important for diagnosing neurological disorders. However, existing methods, which are primarily based on vector or graph representations, struggle to adequately characterize the intricate spatio-temporal topological architecture of functional brain networks. Additionally, they predominantly rely on data-driven paradigms and lack priors pertaining to cross-windows network interactions. To address these issues, we propose a spatio-temporal hypergraph attention network framework for brain network analysis. Specifically, we first propose a temporal attention network architecture embedded with temporal similarity-driven prior knowledge, which effectively extracts long-range dependency information from fMRI by combining multi-head self-attention mechanisms and cross-window temporal prior knowledge. Second, we design a hierarchical hypergraph generation module that fuses local and global brain topological information to achieve multi-scale modeling of high-order spatio-temporal structures. Additionally, the spatial attention network, developed based on transformer architecture, employs hypergraph message passing mechanisms to effectively construct multi-level spatial interaction relationships between brain regions. Finally, a multi-layer perceptron (MLP) is adopted for classification. Experiments on the ADNI and PD datasets demonstrate that our method outperforms several state-of-the-art approaches in diagnostic performance and provides discriminative graph features for relevant brain disease diagnosis.

Electromyography (EMG) signals are widely applied in prosthetic control, rehabilitation training, and human-machine interaction. This places stringent requirements on gesture recognition algorithms to balance long-range temporal modeling with local pose invariance. Existing approaches typically trade off between local and global features and lack causally consistent interpretability, resulting in insufficient generalization across subjects and sessions. To address these shortcomings, we propose a novel dual-stream causal Capsule-Transformer network (CapsFormer). In the Transformer stream, we employ a “causal attention” in the self-attention mechanism to explicitly block all future information, ensuring that each time-step representation depends solely on itself and prior signals; in the Capsule stream, we leverage dynamic routing to capture local part-whole pose vectors, enhancing robustness against electrode shifts and muscle deformations. The two streams' features are then integrated in a fusion module and trained end-to-end. To validate the model's effectiveness, we evaluate it on a multi-subject dataset; results demonstrate that CapsFormer outperforms state-of-the-art models in recognition accuracy, cross-subject robustness, and interpretability. This work not only offers a new paradigm for efficient EMG signal representation but also supports causally consistent temporal signal analysis and interpretable deep learning methods, bearing significant implications for intelligent prosthetic control and human-machine interfaces.

Graph Neural Networks (GNNs) have emerged as a fundamental class of models for analyzing graph-structured data, with broad applications spanning social networks, computational neuroscience, and intelligent transportation systems. In contrast to Euclidean data, graphs pose distinctive challenges due to their irregular topology, permutation invariance, and multi-scale nature. GNNs address these issues through message-passing mechanisms that facilitate efficient representation learning by propagating and aggregating node-level information across the network. This survey offers a timely and systematic review of recent progress in GNNs, with a particular focus on methodological advances since 2022. We provide a structured synthesis of the rapidly expanding literature, categorizing and analyzing key innovations across architectural design, optimization strategies, and structural adaptations. The review also highlights impactful applications of GNNs in diverse domains and identifies critical open challenges in scalability, dynamic graph processing, interpretability, and integration with other artificial intelligence paradigms. We conclude by outlining promising research avenues to guide future developments in graph representation learning.