Search

Urban traffic demand forecasting is an important component in the implementation of intelligent transport systems (ITS). Urban traffic demand data is a spatiotemporal data, describing the amount of traffic demand generated by different areas or stations within a city along the time dimension. Although there has been considerable research work, researchers still face several challenges in predicting accurately, including the capture of hidden features in the temporal dimension of such spatiotemporal data, and the capture of dynamic dependent changes in the spatial dimension. These are even more difficult for long‐time series prediction tasks. This paper designs a multivariate temporal forecasting model specifically adapted to traffic demand to address these challenges, called the Gated Spatiotemporal Graph Attention Network (GSTGAT). GSTGAT is based on the Transformer framework and the whole model is used in an end‐to‐end manner. First of all, it uses the gated self‐attention to extract temporal features in the sequence. Secondly, graph attention is used to capture the spatial dependencies among different variables in the unstructured space. Finally, the use of gated recurrent units in combination with hidden spatial states is proposed to capture multiple levels of spatial dependencies. Experimental results on the taxi dataset in New York and the bicycle dataset in San Francisco Bay Area show that the authors' proposed model outperforms other state‐of‐the‐art models and improves the prediction accuracy. [ABSTRACT FROM AUTHOR]

This paper proposes an alternative feminist understanding of maintenance by investigating the artistic practices and lived experiences of feminist artist Mierle Laderman Ukeles (b. 1939). Our main theoretical and empirical focus lies on maintenance, and we show how art and motherhood as productive connection points proffer different ways of perceiving, understanding, and practicing maintenance. By contextualizing our case within the historical backdrop of New York between the late 1960s and 1980s, we demonstrate how Ukeles's maintenance art proposes novel ways of perceiving the value of maintenance, from the maintenance performed by mothers to considerations of the broader societal implications of maintenance. Such alternative political understanding aligns with critiques of postfeminist societal discourse. We contend that Ukeles's art inspires a political shift in our thinking about maintenance, where maintenance is valued not solely for its indispensable and utilitarian attributes but also it's relational, emotional, and embodied qualities. This nuanced understanding requests visibility for maintenance and foregrounds “more‐than‐I,” agency, and continuity of life, thereby acknowledging the inherent value of the political dimensions of maintenance. [ABSTRACT FROM AUTHOR]

Background: More than 20 million children in the United States lack access to primary health care. Practice Learning: Research shows that students with regular access to physical and mental health services have fewer absences, are more social, less likely to participate in risky behaviors, have improved focus and higher test scores. Implication For School Health Policy, Practice, And Equity: School‐based health centers (SBHCs) can be an important, valuable and viable health care delivery option to meet the full‐range of primary health care needs of students where they spend the majority of their wake hours, ie, in school. Children in rural and other underserved communities, as well as those underinsured, non‐insured, economically challenged, underserved, and the most vulnerable among us are especially at risk. Conclusions: This paper discusses the history, value, and importance of SBHCs from myriad perspectives, including physical and emotional wellbeing, academic and social success, and the promotion of a positive transition to adulthood. In addition, the authors' experiences that resulted in building the first SBHC in the Mid‐Hudson Valley Region of New York State are shared. These experiences form the foundation for creating an important roadmap for individuals and school leaders that are interested in bringing a SBHC to their school and district. [ABSTRACT FROM AUTHOR]

Background: Malnutrition is associated with increased morbidity, mortality, and healthcare costs. Early detection is important for timely intervention. This paper assesses the ability of a machine learning screening tool (MUST‐Plus) implemented in registered dietitian (RD) workflow to identify malnourished patients early in the hospital stay and to improve the diagnosis and documentation rate of malnutrition. Methods: This retrospective cohort study was conducted in a large, urban health system in New York City comprising six hospitals serving a diverse patient population. The study included all patients aged ≥ 18 years, who were not admitted for COVID‐19 and had a length of stay of ≤ 30 days. Results: Of the 7736 hospitalisations that met the inclusion criteria, 1947 (25.2%) were identified as being malnourished by MUST‐Plus‐assisted RD evaluations. The lag between admission and diagnosis improved with MUST‐Plus implementation. The usability of the tool output by RDs exceeded 90%, showing good acceptance by users. When compared pre‐/post‐implementation, the rate of both diagnoses and documentation of malnutrition showed improvement. Conclusion: MUST‐Plus, a machine learning‐based screening tool, shows great promise as a malnutrition screening tool for hospitalised patients when used in conjunction with adequate RD staffing and training about the tool. It performed well across multiple measures and settings. Other health systems can use their electronic health record data to develop, test and implement similar machine learning‐based processes to improve malnutrition screening and facilitate timely intervention. Key points/Highlights: Malnutrition is prevalent among hospitalised patients and frequently goes unrecognised, with the potential for severe sequelae. Accurate diagnosis, documentation and treatment of malnutrition have the potential of having a positive impact on morbidity rate, mortality rate, length of inpatient stay, readmission rate and hospital revenue. The tool's successful application highlights its potential to optimise malnutrition screening in healthcare systems, offering potential benefits for patient outcomes and hospital finances. [ABSTRACT FROM AUTHOR]

Whole lake residence time has been associated with various water quality parameters, including harmful algal blooms. Despite observations of spatial variability in commonly measured lake water quality parameters, little attention is given to the spatial variability of residence time in lakes. In this paper we use water age as a surrogate for residence time and we examine its spatial and temporal distribution in 10 bays of varying size in Lake George, New York (USA). Using a validated hydrodynamic model against observations of water temperature and water currents, and using simulated water age, we show that the average residence time in most of the bays is less than 3 days. Timeseries of bay‐average water age shows that it can sharply decrease within 1 day due to a strong wind event. The average spatial distribution is shown to be non‐uniform, with only a small section of the bottom layer of the bays having a substantially greater age, which may be more than 1 week in certain bays. Snapshots of water age transects indicate that strong wind events substantially change the vertical distribution of water age in some bays, even to the extent of inverting the distribution. The substantial decreases of water age in the bays were associated with the shallowing and deepening of the thermocline. Our results highlight how variations in water residence times within lakes could introduce substantial variation in water quality attributes. Whole lake residence times may serve as a poor proxy to understand the dynamics of water masses, especially in large and morphologically complex waterbodies. Key Points: Simulation of water age with a validated hydrodynamic model against temperature and currentsAverage water age (surrogate to residence time) in bays is smaller than 6 daysSpatial distribution of water age within bays is not uniform and strong wind events lead to lower water age within 1 day [ABSTRACT FROM AUTHOR]