Functional movement screening (FMS) is a crucial testing method that evaluates fundamental movement patterns in the human body and identifies functional limitations. However, due to the inherent complexity of human movements, the automated assessment of FMS poses significant challenges. Prior methodologies have struggled to effectively capture and model critical human features in video data. To address this challenge, this paper introduces an automatic assessment approach for FMS by leveraging deep learning techniques. The proposed method harnesses an I3D network to extract spatiotemporal video features across various scales and levels. Additionally, an attention mechanism (AM) module is incorporated to enable the network to focus more on human movement characteristics, enhancing its sensitivity to diverse location features. Furthermore, the multilayer perceptron (MLP) module is employed to effectively discern intricate patterns and features within the input data, facilitating its classification into multiple categories. Experimental evaluations conducted on publicly available datasets demonstrate that the proposed approach achieves state-of-the-art performance levels. Notably, in comparison to existing state-of-the-art (SOTA) methods, this approach exhibits a marked improvement in accuracy. These results corroborate the efficacy of the I3D-AM-MLP framework, indicating its significance in extracting advanced human movement feature expressions and automating the assessment of functional movement screening.
Functional Movement Screening (FMS) is a movement pattern quality assessment system used to assess basic movement capabilities such as flexibility, stability, and pliability. Movement impairments and abnormal postures can be identified through peculiar movements and postures of the body. The reliability, validity, and accuracy of functional movement screening are difficult to test due to the subjective nature of the assessment. In this sense, this paper presents an automatic evaluation method for functional movement screening based on a dual-stream network and feature fusion. First, the RAFT algorithm is used to estimate the optical flow of a video, generating a set of optical flow images to represent the motion between consecutive frames. By inputting optical flow images and original video frames separately into the I3D model, it can better capture spatiotemporal features compared to the single-stream method. Meanwhile, this paper introduces a simple but effective attention fusion method that combines features extracted from optical flow with the original frames, enabling the network to focus on the most relevant parts of the input data, thereby improving prediction accuracy. The prediction of the four categories of FMS results was performed. It produced better correlation results compared to other more complex fusion protocols, with an accuracy improvement of 3% over the best-performing fusion method. Tests on public datasets showed that the evaluation metrics of the method proposed in this paper were the most advanced, with an accuracy improvement of approximately 4% compared to the currently superior methods. The use of deep learning methods makes it more objective and reliable to identify human movement impairments and abnormal postures.
This study aims to explore the interplay between parent-child communication, social support, physical exercise and non-cognitive abilities among adolescents. Using data from the China Education Panel Survey (2014–2015) with a nationally representative sample of 5,055 eighth-grade students. Analyses were conducted via Stata 17.0 and SPSS 26, employing chain mediation tests and bootstrap analysis. The results were as follows:1) parent-child communication directly contributes to the enhancement of adolescents’ non-cognitive abilities, facilitates their access to social support, and promotes their participation in physical exercise; 2) parent-child communication indirectly improves adolescents’ non-cognitive abilities through the chain mediating effect of social support and physical exercise; 3) the positive effect of parent-child communication on non-cognitive abilities is stronger among urban adolescents compared to rural adolescents, and more pronounced among only children than non-only children. In conclusion, parent-child communication not only directly and positively predicts adolescents’ non-cognitive abilities but also exerts indirect effects via two single mediators (social support and physical exercise) and a chain mediation mechanism combining both mediators.
Small-scale rural sports events are increasingly used as tools for regional regeneration, yet counterfactual evidence on whether they generate sustained tourism benefits at the county level remains limited. This study examines the rapid rise of “Village BA” in Taijing County, Guizhou, China, as a quasi-experimental setting. Using county-level panel data from 2015 to 2024, we estimate tourism responses associated with the post-2022 Village BA-centered expansion by combining the synthetic control method, synthetic difference-in-differences, and a matching-weighted two-way fixed-effects model. Across the baseline specifications, the estimated effects are positive for both outcomes, although their inferential profiles differ across estimators and robustness settings. First, the estimated effects in 2023–2024 are generally larger than those in the 2022 breakout stage, indicating a sustained post-breakout tourism response. Second, tourist-visitor estimates are comparatively more directionally stable across estimators and sensitivity specifications, whereas baseline tourism-revenue effects become more pronounced and more precisely estimated during the later institutional-expansion stage, a pattern broadly consistent with a relative “flows first, returns later” interpretation. SCM placebo rankings do not reach conventional significance levels, while SDID and matching-weighted TWFE provide alternative assessments of statistical precision. Sensitivity analyses further show that tourism-revenue estimates are more sensitive to estimator choice and the treatment of the COVID-affected pre-treatment years. These findings provide counterfactual evidence of county-level tourism gains associated with the Village BA-centered expansion, while the underlying mechanisms remain theory-grounded rather than directly identified.