Multivariate time series imputation is fundamental to downstream analysis, yet modeling inter-variable dependencies with incomplete observations remains challenging. Existing methods learn global dependencies across samples or dynamic local dependencies per sample. Global dependencies are stable but adapt poorly to sample variations and temporal non-stationarity, whereas local dependencies are adaptive yet unreliable when observations are insufficient, causing erroneous information propagation. To address these limitations, we propose GLAIM, a Global-Local Adaptive Inter-variable Dependency Modeling framework for multivariate time series imputation. GLAIM comprises two complementary components. The Stable Global Dependency Constructor derives robust global inter-variable dependencies from complementary temporal representations, providing a stable backbone less affected by sample-specific missingness and noise. The Sample-Conditioned Dependency Refiner adapts this backbone to each sample and time step using its temporal state and available observations, enabling reliable local refinement under incomplete observations. Extensive experiments on nine real-world datasets demonstrate that GLAIM achieves state-of-the-art performance under random and block missingness, remains robust to missing-rate shifts, and benefits from its complementary global and local components. Code is available at https://github.com/LuRenjias/GLAIM.
Mingyang Wang, Rong Li, Xiao Wang et al.· 0 citations
The accurate assessment of movement quality in rehabilitation training is a critical challenge in both clinical and home-based settings. Traditional methods often rely on subjective evaluations or limited sensor data, which can lead to inconsistent and inaccurate assessments. This paper introduces a novel methodology that integrates surface electromyography (sEMG) signals with RGB-D video data to provide a comprehensive, real-time analysis of rehabilitation movement quality. The proposed framework leverages the Manifold-driven Event Forecaster, a sophisticated model that captures the intricate biomechanical and neuromuscular aspects of human motion. The methodology is composed of three primary components: a Nonlinear Constraint Optimizer that aligns multimodal data onto a shared manifold, an Agent-based Temporal Segmenter that partitions data into meaningful temporal segments, and a Probabilistic Quality Predictor that quantifies movement quality with an uncertainty-aware approach. The framework employs advanced strategies such as manifold alignment refinement and uncertainty-aware modeling to enhance robustness and interpretability. These innovations enable the system to make accurate, real-time predictions of movement quality, effectively addressing challenges such as variability in patient performance and sensor noise. Experimental results demonstrate the efficacy of the proposed approach, showing significant improvements in the precision and reliability of movement quality assessments. This comprehensive solution has the potential to transform rehabilitation practices by providing objective, data-driven insights into patient progress and therapy effectiveness, ultimately contributing to improved patient outcomes and more personalized rehabilitation programs.
Xiaolu Li, Rong Li, Ruisheng Wu· International Journal of Ima...· 0 citations
The Continuous-time Squared Error (CSE) is proposed, which employs importance weighting to eliminate the influence of the timestamp sampling distributions and theoretically proves that CSE's asymptotic estimation error with respect to continuous-time risk is no greater than that of MSE.
Rong Li, Haixin Xie, Xiao Wang et al.· 0 citations
Irregular time series forecasting is crucial in many domains, such as healthcare and meteorological observation. However, due to the inherent characteristics of irregular time series, including sparse observations and non-uniform sampling, accurately predicting future dynamics remains challenging. In light of these two characteristics, many existing methods aggregate irregular observations into fixed-dimensional estimated response coefficients through predefined basis functions and use these coefficients as sequence representations. Nevertheless, this modeling paradigm still suffers from two key limitations: (i) a potential non-vanishing asymptotic bias caused by ignoring the sampling density of timestamps; and (ii) the limited adaptability of predefined basis functions to diverse temporal patterns. In this study, we propose a Debiased Neural Basis-Function Network (DNBNet) to address these challenges. Its core is a debiased neural basis-function response mechanism, which corrects asymptotic bias through importance sampling while parameterizing basis functions with neural networks to adapt to diverse temporal patterns. In addition, considering the sparsity of irregular data, we design a novel multi-scale decomposition module based on average pooling, together with a mass-aware fusion mechanism, to obtain richer representations. Finally, a dual-branch decoder is employed for forecasting. Extensive experiments on multiple real-world datasets demonstrate the effectiveness of DNBNet and its strong generalizability across diverse irregular time series scenarios. Our code can be obtained at https://github.com/hnu-vis/DNBNet.
Rong Li, Changjian Chen· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
