Traditional methods for plan path prediction have low accuracy and stability. In this paper, we propose a novel approach for plan path prediction based on relative motion between positions (RMBP) by...

Accurate and interpretable delay predictions are vital for decision-making in the aviation industry. However, effectively incorporating spatiotemporal dependencies and external factors related to delay propagation remains a challenge. To address this challenge, we propose the SpatioTemporal Propagation Network (STPN), a novel space-time separable graph convolutional network that models delay propagation by considering both spatial and temporal factors. STPN uses a multi-graph convolution model that considers both geographic proximity and airline schedules from a spatial perspective, while employing a multi-head self-attention mechanism that can be learned end-to-end and explicitly accounts for various types of temporal dependencies in delay time series from a temporal perspective. Experiments on two real-world delay datasets show that STPN outperforms state-of-the-art methods for multi-step ahead arrival and departure delay prediction in large-scale airport networks. Additionally, the counterfactuals generated by STPN provide evidence of its ability to learn explainable delay propagation patterns. Comprehensive experiments also demonstrate that STPN sets a robust benchmark for general spatiotemporal forecasting. The code for STPN is available at https://github.com/Kaimaoge/STPN .

The special processing conditions of micro-injection moulding will affect the micro-structure of polymer microparts processed by micro-injection moulding. In this article, two-dimensional wide-angle X-ray diffraction (2D-WAXD) and differential scanning calorimetry (DSC) were used to study the influence of nucleating agent concentration, mould temperature and injection pressure on content of the β-phase in isotactic polypropylene (iPP) with β-nucleating agent in micro-injection moulding. It was found that the high shear stress during micro-injection moulding could induce the formation of β-phase crystals in pure iPP, but which could restrain the formation of β-phase crystals in iPP with β-nucleating agent. The β-crystal content in micro-injection moulded samples decreased continuously with increasing the mould temperature from 130°C to 160°C. Besides, the shear stress that could restrain the nucleating efficiency of β-nucleating agent in β-nucleated iPP increased with the rise of the injection pressure and resulted in the decrease of β-phase crystals in the sample.

Haptic temporal signal recognition plays an important supporting role in robot perception. This paper investigates how to improve classification performance on multiple types of haptic temporal signal datasets using a Transformer model structure. By analyzing the feature representation of haptic temporal signals, a Transformer-based two-tower structural model, called Touchformer, is proposed to extract temporal and spatial features separately and integrate them using a self-attention mechanism for classification. To address the characteristics of small sample datasets, data augmentation is employed to improve the stability of the dataset. Adaptations to the overall architecture of the model and the training and optimization procedures are made to improve the recognition performance and robustness of the model. Experimental comparisons on three publicly available datasets demonstrate that the Touchformer model significantly outperforms the benchmark model, indicating our approach's effectiveness and providing a new solution for robot perception.

Background: Nutrient deficiency disorders (NDs) harm growth, causing economic losses. Addressing NDs is a global priority, yet recent data is limited. This study examines latest NDs data across 204 countries and 21 regions from 1990 to 2021.Methods: Data from the 2021 Global Burden of Disease (GBD) study were used to analyze NDs-related incidence, prevalence, deaths, and disability-adjusted life years (DALYs) at global, national, and regional levels. Joinpoint regression analysis was applied to evaluate temporal trends, with Estimated Annual Percentage Change (EAPC) assessing long-term patterns.Results: In 2021, the global burden of NDs remained substantial, with a total of 1,845,246,558 cases with an ASPR of 23,858.99 cases per 100,000 individuals (95% UI: 23,445.77–24,320.82). The ASIR was 7,725.1 per 100,000 people (95% UI: 7,404.01–8,109.01), while the ASMR was 3.03 per 100,000 persons (95% UI: 2.69–3.4). Additionally, age-standardized DALYs rate was 657.62 per 100,000 individuals (95% UI: 489.93–869.58). Regionally, areas with low SDI exhibited the greatest ASPR, ASIR, ASDR, and age-standardized DALYs rates, whereas high SDI regions had the lowest rates.Conclusions: Although global NDs burden has declined from 1990 to 2021, regional and demographic disparities remain. Enhanced healthcare access in high-risk SDI regions is essential to further mitigate NDs's global impact.