Search Results (177)

Tiny Machine Learning (TinyML) extends edge AI capabilities to resource-constrained devices, offering a promising solution for real-time, low-power intelligence in smart cities. This review systematically analyzes 66 peer-reviewed studies from 2019 to 2024, covering applications across urban mobility, environmental monitoring, public safety, waste management, and infrastructure health. We examine hardware platforms and machine learning models, with particular attention to power-efficient deployment and data privacy. We review the approaches employed in published studies for deploying machine learning models on resource-constrained hardware, emphasizing the most commonly used communication technologies—while noting the limited uptake of low-power options such as Low Power Wide Area Networks (LPWANs). We also discuss hardware–software co-design strategies that enable sustainable operation. Furthermore, we evaluate the alignment of these deployments with the United Nations Sustainable Development Goals (SDGs), highlighting both their contributions and existing gaps in current practices. This review identifies recurring technical patterns, methodological challenges, and underexplored opportunities, particularly in the areas of hardware provisioning, usage of inherent privacy benefits in relevant applications, communication technologies, and dataset practices, offering a roadmap for future TinyML research and deployment in smart urban systems. Among the 66 studies examined, 29 focused on mobility and transportation, 17 on public safety, 10 on environmental sensing, 6 on waste management, and 4 on infrastructure monitoring. TinyML was deployed on constrained microcontrollers in 32 studies, while 36 used optimized models for resource-limited environments. Energy harvesting, primarily solar, was featured in 6 studies, and low-power communication networks were used in 5. Public datasets were used in 27 studies, custom datasets in 24, and the remainder relied on hybrid or simulated data. Only one study explicitly referenced SDGs, and 13 studies considered privacy in their system design. Full article

Rapid global urbanization poses complex challenges that demand advanced data-driven forecasting solutions for smart cities. Traditional statistical and standalone Long Short-Term Memory (LSTM) models often struggle to capture non-linear dynamics and long-term dependencies in urban time-series data. This review critically examines hybrid LSTM models that integrate LSTM with complementary algorithms, including CNN, GRU, ARIMA, and SVM. These hybrid architectures aim to enhance prediction accuracy, integrate diverse data sources, and improve computational efficiency. This study systematically reviews principles, trends, and real-world applications, quantitatively evaluating hybrid LSTM models using performance metrics such as mean absolute error (MAE), root mean square error (RMSE), and the coefficient of determination (R²), while identifying key study limitations. The case studies considered include traffic management, environmental monitoring, energy forecasting, public health, infrastructure assessment, and urban waste management. For example, hybrid models have achieved substantial accuracy improvements in traffic congestion forecasting, reducing their mean absolute error by up to 29%. Despite the inherent challenges related to structural complexity, interpretability, and data requirements, ongoing research on attention mechanisms, model compression, and explainable AI has significantly mitigated these limitations. Thus, hybrid LSTM models have emerged as vital analytical tools capable of robust spatiotemporal prediction, effectively supporting sustainable urban development and data-driven decision-making in evolving smart city environments. Full article

Objectives: The present study evaluated anthropometry Z-scores of exclusively breastfed infants aged 0~6 months and examined their associations with various parent–infant factors. Methods: This cross-sectional study included 383 mother–infant dyads from 10 Chinese cities in the final analyses, under strict inclusion and exclusion criteria. Data were collected by trained investigators using questionnaires covering demographic characteristics, perinatal health, maternal and infant factors during lactation. Nutrient intake was assessed and calculated by 24 h recall. Anthropometric measurements of parents and infants were taken using calibrated instruments, with infant growth assessed via Chinese growth standards. Statistical analyses included correlation and linear mixed-effect models accounting for regional clustering, with variable selection guided by backward elimination step regression. Nonlinear relationships were explored using spline and piecewise regression methods. Results: Over 60% of the mothers had inadequate energy and protein intake. Approximately two-thirds of the participants had fat intakes exceeding the upper limit. Inadequate or excessive gestational weight gain, poor maternal sleep quality, lactational mastitis, higher maternal fat intake and infant gastrointestinal symptoms were associated with lower infant anthropometry Z-scores. A threshold effect was detected between maternal fat intake and infant WAZ, BMI Z, and WLZ. Conclusions: This study found that anthropometry Z-scores of exclusively breastfed infants aged 0–6 months were significantly associated with certain maternal–infant factors and maternal fat intake, emphasizing the need for early intervention on adverse factors and balanced maternal diet nutrition during lactation. Full article

Addressing the economic–ecological imbalance within urban agglomeration integration and sustainable development is crucial, particularly in the context of achieving the Sustainable Development Goals of sustainable cities and communities. This study examines this imbalance using a unique ecosystem services (ESs) balance index that evaluates “supply” and “demand” tradeoffs. It emphasizes localization, mobility, and cooperation as regionalization strategies, utilizing multisource datasets. To address gaps from endogeneity and heterogeneity, the study regresses these strategies on ESs balance values, incorporating landscape patterns as endogenous variables across 214 YRDCA counties or districts in 2020, using a multilevel geographically weighted instrumental variable regression model. Employing the patch-generating land use simulation method, three scenarios were explored: non-intervened development (ND), mobility priority (MD), and localization priority (LP). These scenarios were assessed for their 2025 mitigation effects and health benefits to optimize balanced development strategies. Key findings include (1) a severe ecological–economic imbalance in supply and demand patterns; (2) localization boosts economic development, mobility enhances ecological development, and cooperation promotes both; and (3) LP and MP strategies, compared to ND, show promising potential to reduce the imbalance and generate health benefits, although the extent of the impact may depend on the implementation scale and regional context. By promoting inclusive urbanization and participatory and integrated planning, and enhancing urban resilience through targeted risk-reduction strategies, this study provides insights into fostering balanced development among cities. Full article

Urban green spaces are integral components of city ecosystems, supporting essential belowground microbial communities such as arbuscular mycorrhizal fungi (AMF). Understanding how green space types influence AMF communities is key to promoting urban ecological function. This study examines AMF diversity, community assembly, and co-occurrence network structures in two urban green space types—park and roadside—in Kaifeng, Henan Province, China. Soil samples were collected from both sites, and AMF community composition was assessed using high-throughput sequencing. Environmental variables, including total nitrogen (TN), available phosphorus (AP), available potassium (AK), water content, and pH, were measured to evaluate their influence on AMF communities. The results indicate marked differences between the two green space types. Park soils support significantly greater AMF species richness and more complex co-occurrence networks than roadside soils. These differences are correlated with higher nutrient levels in park soils. By contrast, AMF communities in roadside soils are more strongly associated with soil water content and pH, resulting in reduced diversity and more homogeneous community structures. Stochastic processes predominantly govern community assembly in both green space types, with roadside green spaces being more influenced by stochastic processes than park green spaces. These findings highlight the influence of urban landscape type on AMF communities and provide guidance for enhancing urban biodiversity through targeted landscape planning and soil management. In future work, we will implement long-term AMF monitoring across different green-space types and evaluate specific management practices to optimize soil health and ecosystem resilience. Full article

Introduction: Gentrification, commonly defined as low-socioeconomic-status (SES) neighborhoods experiencing rapid increases in rental value, can lead to changes in the built and social neighborhood environment. Schools are an important location for pollutant exposure and child opportunities because children spend significant time in school. Given their central role in both environmental and social contexts, we examined the relationship between gentrification, pollutants, and child opportunity near schools in New York City. Methods: School locations (N_total = 1482) were classified into gentrifying (n = 624), non-gentrifying (n = 198), and higher-SES (ineligible for gentrification; n = 660) neighborhoods. Annual average pollutant levels (black carbon (BC), fine particulates (PM_2.5), nitrogen dioxide (NO₂)) were assessed near schools. Child opportunity index (COI 2.0) was used to evaluate overall opportunity and three domains: education; health/environment; social/economic. Results: On average, pollution was highest in gentrifying neighborhoods compared to non-gentrifying (5–8.6% difference) and higher-SES (4.8–14.8% difference) neighborhoods. Average air pollution levels remained consistently higher in gentrifying neighborhoods both before and after gentrification compared to non-gentrifying and higher-SES neighborhoods. Regarding childhood opportunity, education, and social/economic opportunities were better and health/environment opportunities were worse in gentrifying compared to non-gentrifying neighborhoods. Conclusions: Gentrifying neighborhoods are at risk for higher exposure to pollutants and lower health/environment childhood opportunities compared to other neighborhoods. Full article

Public transportation in cities is negatively affected by reliance on petroleum-based fuels, leading to emissions and poor air quality. Although the environmental evaluation of alternative buses in terms of sustainability has been extensively studied, the social dimensions have not received as much attention. In this regard, this research examines the social implications of alternative urban buses through life cycle impact assessment (LCIA) methods, including Eco-Indicator 99, Impact 2002+, and ReCiPe Endpoint. The results indicate that diesel buses significantly impact health, while hybrid, fuel cell, and electric buses can decrease emissions by 50%. These results underscore the necessity of zero-emission technologies to enhance urban air quality and promote better public health. Full article

This study examines variations in personal exposure to PM_2.5 and NO₂ while commuting by bicycle, vehicle, and walking during heating and non-heating seasons in Gliwice, an industrial city in Upper Silesia, Poland. Understanding these variations is crucial for assessing health risks and developing effective mitigation strategies. Personal exposure was measured using low-cost sensors, while stationary measurements provided comparative background concentrations. The results indicate statistically significant seasonal differences in pollutant concentrations. NO₂ levels were higher during the heating season (mean: 30.84 µg/m³, median: 25.60 µg/m³) than in the non-heating season (mean: 22.61 µg/m³, median: 20.37 µg/m³; p = 0.025). In contrast, PM_2.5 concentrations were higher in the non-heating season (mean: 12.1 µg/m³) compared to the heating season (mean: 9.5 µg/m³; p = 0.032). Inhaled doses instead of concentrations evaluated the exposure of participants. The inhaled doses of NO₂ and PM_2.5 per km were significantly higher for walking (mean: 141.3 and 30.7 µg/km for the male participant; 77.9 and 31.6 µg/km for the female participant) than for bicycle and walking (p < 0.05). These findings underscore the impact of transport mode and seasonality on air pollution exposure, highlighting the necessity for targeted mitigation strategies to reduce commuters’ exposure to traffic-related pollutants. Full article

Background/Objectives: Acute pancreatitis (AP) remains a pressing clinical challenge, largely due to its potential to lead to life-threatening complications and increased mortality. Over the years, numerous tools have been proposed to evaluate the intensity of AP and estimate likely health outcomes. Despite their usefulness, many of these assessment models are complex and rely on a wide array of clinical inputs, making them less practical in everyday healthcare settings. In contrast, the Aggregate Systemic Inflammation Index (AISI), which is calculated using routine blood count parameters, provides a simpler and more inclusive approach to measuring systemic inflammation. This research focuses on examining how effectively AISI can be used to gauge disease severity and project clinical trajectories in individuals affected by pancreatitis. Methods: This retrospective study reviewed the medical records of 412 individuals diagnosed with acute pancreatitis, all of whom received care at the Internal Medicine Clinic of Ankara Bilkent City Hospital between 1 April 2019 and 1 September 2024. The investigation encompassed a thorough analysis of patients’ demographic characteristics, lab parameters, and clinical findings, with special attention given to inflammatory markers, including the Aggregate Systemic Inflammation Index (AISI), its revised version, the Platelet-to-Lymphocyte Ratio (PLR), the Neutrophil-to-Lymphocyte Ratio (NLR), and the Systemic Inflammatory Response Index (SIRI). Comparative analyses between groups were performed using independent sample t-tests and one-way ANOVA, complemented by Tukey’s post hoc tests where appropriate. Correlations among continuous variables were determined through Pearson’s analysis, and the prognostic accuracy of both AISI and its modified form was assessed using Receiver Operating Characteristic (ROC) curve methodology. Results: The mean age among participants was 63.47 ± 17.92 years, while the average AISI value was calculated as 1183.89 ± 1067.42. Both the original and modified versions of the AISI index showed strong positive correlations with several key clinical measures, including prolonged hospitalization, a Glasgow score of 2 or above, BISAP, Ranson scoring, the revised Atlanta classification, and APACHE II. AISI was also significantly linked to the presence of complications and overall mortality (p < 0.01). Analysis through ROC curves demonstrated that an AISI level above 236.626 effectively predicted hospital stays exceeding 10 days, with a sensitivity of 94.40% and a specificity of 91.00%. Moreover, both AISI and its modified form reliably distinguished patients who had a Ranson score of zero, with high diagnostic accuracy. Conclusions: AISI and its modified version demonstrate a strong association with both the intensity and clinical course of acute pancreatitis. Thanks to their simplicity, low cost, and broad usability in healthcare settings, these indices hold considerable promise as practical and dependable tools for assessing the severity and likely outcomes of this increasingly prevalent disease. Full article

This paper examines the potential economic benefits of biological pest control in urban forests by evaluating its effectiveness in controlling these pests and assessing its economic benefits. It also analyzes the advantages and disadvantages of using biological pest control as a sustainable method for managing specific pest populations. Urban forests improve the quality of life in cities, leading to more sustainable communities. Urban trees are more vulnerable to insect excursions, and pest infestations are increasingly threatening urban forests. Pest control methods are necessary to confront this threat, which risks tree health and vitality. However, traditional chemical pest control methods pose significant environmental and human health risks, highlighting the need for more sustainable solutions. Biological pest control methods have many advantages and few disadvantages compared with traditional chemical methods. Biological pest control is an environmentally friendly method that, as an investment, could lead to long-term economic benefits in terms of return on the initial investment, reducing costs over time, and a high benefit-to-cost ratio. Full article

This study evaluates the progress of Korea’s National Strategic Smart City Program (NSSCP), a flagship R&D initiative, in advancing sustainable and intelligent urban development on a global scale. Utilizing the United Nations’ United for Smart Sustainable Cities (U4SSC) framework, which integrates both sustainability and smartness in city development, this research examines the program’s alignment with global standards. The findings reveal that the NSSCP contributes to the attainment of the Sustainable Development Goals (SDGs) in areas such as health, energy, innovation, and sustainable communities. It also effectively addresses key dimensions of smart cities, including smart living, environmental stewardship, mobility, and economic vitality. Despite these achievements, this study identifies critical challenges, such as the absence of robust evaluation tools and an overemphasis on quantitative targets. This research is important in advancing the discourse on smart city development, offering insights into the efficacy of smart services and systems through the lens of the NSSCP’s cloud-based open data hub model. Full article

This study examines the mediating effect of subjective housing quality between housing conditions and mental health, using survey data from ten Chinese mega-cities. The results from multi-level linear regression models show that housing areas are highly associated with subjective housing quality and that renters have lower levels of subjective housing quality than homeowners. At the community level, the age of housing tends to diminish its subjective quality, while a lower plot ratio is associated with more favorable evaluations of housing conditions. Surprisingly, educational resources in proximity to housing are negatively associated with subjective housing quality. Subjective housing quality is closely linked to mental health. Additionally, the results show that home ownership significantly strengthens the association between subjective housing quality and mental health. Namely, the mediating effect of subjective housing quality on the relationship between housing conditions and mental health is stronger for homeowners than for renters. Full article

South Asia, a rapidly urbanizing and industrializing region, faces critical air quality challenges, with transportation emissions becoming a major source of urban pollution. These emissions contribute significantly to public health issues, including respiratory and cardiovascular diseases, while imposing substantial economic burdens on affected populations. This study aims to examine regional trends, evaluate the economic impact of transportation-driven air pollution, and offer actionable insights for policy development. Using a narrative review approach, the study synthesizes evidence on air quality, transportation emissions, and public health in major South Asian cities. Key findings reveal that in Sri Lanka, transportation emissions, driven by traffic congestion and industrial activity, worsen respiratory conditions, especially in Colombo. In India, cities like Delhi suffer from severe health risks linked to pollution from the growing transportation sector. Pakistan’s expanding transportation sector increases energy consumption and emissions, particularly in Lahore, which experiences significant health impacts. In Bangladesh, Dhaka faces intense pollution due to urbanization and vehicle growth, while Kathmandu in Nepal struggles with diesel vehicle emissions. The economic burden of transportation-driven air pollution is considerable, with rising healthcare costs and productivity losses in major cities. The study recommends cleaner transportation technologies, enhanced public transit, and regional cooperation to address pollution, urging a comprehensive approach to urban planning and sustainable transport infrastructure for improved air quality and economic resilience in South Asia’s cities. Full article

Background/Objectives: Cancer is a chronic and serious disease that has a wide range of effects on patients, some of which extend to family members and primary caregivers (PCs), thereby affecting their quality of life (QOL). The aim of this study was to evaluate the QOL of PCs of patients with cancer and to investigate the sociodemographic and other factors that impact PCs’ QOL. Methods: This cross-sectional study was conducted at the Princess Noura Oncology Center, King Abdulaziz Medical City, Jeddah, and included 235 PCs. A short-form health survey—the SF-36, which includes eight domains—was used to measure the QOL of patients’ PCs. Results: The relationship between the QOL of PCs and the characteristics of patients and PCs was examined. The QOL of PCs was associated with several variables. Multiple regression analysis showed that older age, female sex, and caring for patients with hematological malignancies were independent, significant variables associated with lower PCs’ QOL, whereas PCs caring for female patients experienced a better QOL. Conclusions: These findings highlight the essential aspects of caregivers’ QOL and their influencing factors. To better understand the implications of these factors, future studies are required to demonstrate the effects of patient- and disease-related factors on PCs’ QOL. Full article

This study examines the health resource networks across China’s 31 provinces and cities (excluding Hong Kong, Macao, and Taiwan) between 2012 and 2021. We construct an evaluation system for health resources using the entropy weight method and analyze the structural evolution of the health resource network through a complex network perspective. Furthermore, a spatial econometric model is employed to investigate the impact of health resource network positions on resident health. Our findings show that communication between nodes in the health resource network increased initially and then decreased, with core communication regions shifting from Central China to East China. The network position of health resources has a significant positive impact on residents’ health and exhibits spatial spillover effects. The impact of network positions is more significant in core regions compared to peripheral areas. This study highlights the importance of optimizing health resource distribution and improving health outcomes by focusing on network positions within China’s health system. These findings contribute to policy development for enhancing public health at both local and regional levels and offer valuable insights for countries facing similar health system challenges. Full article