Search

Aircraft ducts play an indispensable role in various systems of an aircraft. The regular inspection and maintenance of aircraft ducts are of great significance for preventing potential failures and ensuring the normal operation of the aircraft. Traditional manual inspection methods are costly and inefficient, especially under low-light conditions. To address these issues, we propose a new defect detection model called LESM-YOLO. In this study, we integrate a lighting enhancement module to improve the accuracy and recognition of the model under low-light conditions. Additionally, to reduce the model's parameter count, we employ space-to-depth convolution, making the model more lightweight and suitable for deployment on edge detection devices. Furthermore, we introduce Mixed Local Channel Attention (MLCA), which balances complexity and accuracy by combining local channel and spatial attention mechanisms, enhancing the overall performance of the model and improving the accuracy and robustness of defect detection. Finally, we compare the proposed model with other existing models to validate the effectiveness of LESM-YOLO. The test results show that our proposed model achieves an mAP of 96.3%, a 5.4% improvement over the original model, while maintaining a detection speed of 138.7, meeting real-time monitoring requirements. The model proposed in this paper provides valuable technical support for the detection of dark defects in aircraft ducts. [ABSTRACT FROM AUTHOR]

Understanding the determinants of elderly people's public transport usage patterns can offer new insights into elderly mobility issues and provide policy implications for planning toward an aging-friendly and sustainable city. However, few studies have examined the impact of the built environment on the trip time of the elderly using big data. Moreover, the elderly's trip time has been mostly investigated by the multivariate linear regression model (MLR), ignoring the non-linear association between explanatory variables and trip time. Using smart card data from Nanjing in 2019, this study employs a gradient boosting regression trees (GBRT) model to probe into the correlations between the built environment and the elderly's trip time. The results show that significant non-linear relationships exist between trip time and the selected explanatory variables, which cannot be captured by the MLR model. It suggests that relevant policy implementations should be carried out in conjunction with the elderly's travel environment by regarding their threshold effects. Besides, interaction effects of spatial attributes on trip time are identified in our study. For example, elderly people living in the exurban area are more likely to take long-distance metro travel for their physical exercise. These findings demonstrate that planners and policymakers should not only consider one single built-environment factor, but also the interactions of various factors to enhance elderly mobility., Author(s): Zhuangbin Shi [1]; Yang Liu [1]; Mingwei He (corresponding author) [1]; Qiyang Liu [2] 1. Introduction Due to the accelerating global aging process, the social life and well-being of [...]

In remote sensing image retrieval task, deep metric learning loss is an effective method for learning semantic similarity relationships between images. However, most deep metric learning losses treat different ranked images equally. Therefore, we propose a novel score-ranking smooth average precision (SRSAP) loss to improve the retrieval performance. Firstly, the score-ranking (SR) loss builds an ensemble-based similarity structure by using all images. Secondly, we utilize smooth AP to assign more weight to higher-ranked images. Finally, the joint loss function is utilized to fine-tune the network. The experiments show that SRSAP loss is distinctly superior to usual deep metric losses. [ABSTRACT FROM AUTHOR]

In this study, we applied an explainable machine learning technique based on the LightGBM method, a category of gradient boosting decision tree algorithm, to conduct a quantitative radar precipitation estimation and move to understand the underlying reasons for excellent estimations. By introducing 3D grid radar reflectivity data into the LightGBM algorithm, we constructed three LightGBM models, including 2D and 3D LightGBM models. Ten groups of experiments were carried out to compare the performances of the LightGBM models with traditional Z–R relationship methods. To further assess the performances of the LightGBM models, rainfall events with 11,483 total samples during August-September of 2022 were used for statistical analysis, and two heavy rainfall events were specifically chosen for the spatial distribution evaluation. The results from both the statistical analysis and spatial distribution demonstrate that the performance of the LightGBM 3D model with nine points is the best method for quantitative precipitation estimation in this study. Through analyzing the explainability of the LightGBM models from Shapley additive explanations (SHAP) regression values, it can be inferred that the superior performance of the LightGBM 3D model is mainly attributed to its consideration of the rain gauge station attributes, diurnal variation characteristics, and the influence of spatial offset. [ABSTRACT FROM AUTHOR]

On the evening of 30 April 2021, a severe hailstorm swept across eastern China, causing catastrophic gale and damaging hailstones. This hailstorm event was directly caused by two mesoscale convective systems associated with strong squall lines, with mid-level cold advection from the northeast cold vortex, and strong low-level convergence associated with the low-level vortex and wind shear line. Double nesting of the high-resolution weather research and forecasting model (9–1 km) is utilized to simulate this hailstorm with five microphysics schemes. The radar-based maximum estimated size of hail (MESH) algorithm, differential reflectivity and fractions skill scores were used to quantitatively evaluate the precision. All schemes basically captured the two squall lines that swept through eastern China, although they appeared one or two hours earlier than observation. Particularly, Goddard and Thompson performed better in the MESH swath and fractions skill scores among the five different schemes. However, Thompson most realistically captured the reflectivity pattern, intensity and vertical structure of mesoscale convective systems. Its high-reflectivity column corresponded to the maximum center of the hail mixing ratio within the updraft region, which is consistent with the characteristics of a pulse-type hailstorm in its mature phase. [ABSTRACT FROM AUTHOR]

Public acceptability is a major concern for road pricing schemes in Western countries but has not yet been sufficiently studied in the context of Chinese cities, a number of which are considering the introduction of such travel constraint measures. This study explores factors influencing public acceptability of a proposed congestion charge in the City of Beijing. In so doing, the study focuses on understanding the appropriateness of Western frameworks for assessing public acceptability in the Chinese context. Through literature review and focus groups a survey to test different public acceptability constructs was developed (N = 1104). A Structural Equation Model was used to analyze relationships that exist among the different aspects of public acceptability. The results demonstrate that public acceptability is dominantly influenced by the level of trust toward the Government and experts. Various determinants in the Western context, such as access to information and perceived effectiveness were not found to have a significant impact on public acceptability. The results imply that public acceptability of congestion charging in the Chinese context has a stronger resonance with wider social issues such as equity than more specific transport problems such as congestion. As such, attempting to present evidence on the anticipated effectiveness of the policy in alleviating congestion and smog may not make the policy more acceptable to the public. The overall inference of the study is that contextual factors are more important than has been previously considered within public acceptability studies. [ABSTRACT FROM AUTHOR]

Pulmonary thromboembolism (PTE) is a fatal clinical syndrome that usually occurs in elderly individuals. The present study aimed to identify functional and key genes involved in the early diagnosis of PTE using bioinformatics analysis. The GSE84738 dataset was retrieved from the Gene Expression Omnibus database. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analyses were subsequently performed. In addition, Cytoscape software v.3.7.2 was used to construct a protein-protein interaction (PPI) network. Serum samples from patients with PTE and healthy individuals were collected and the expression levels of Toll-like receptor (TLR)4, TLR2, IL-1β, JUN, prostaglandin-endoperoxide synthase 2 (PTGS2), osteopontin (SPP1) and endothelin-1 (ET-1) were analyzed by reverse transcription-quantitative PCR. A total of 160 upregulated and 159 downregulated differentially expressed genes were identified between patients with PTE and healthy individuals. TNF, IL-1β, JUN, TLR4, PTGS2, vascular cell adhesion molecule 1, SPP1, ryanodine receptor 2, TLR2 and ET-1 were considered as hub genes, which are defined as the genes with the highest degree of interaction in the enrichment and PPI network analyses. The top 10 common genes with the highest degree in the PPI network and the top 10 genes in modules 1 and 2 were TLR4, TLR2, IL-1β, JUN, PTGS2, SPP1 and ET-1. Taken together, the present study suggested that TLR4, TLR2, IL-1β and SPP1 were enriched in patients with PTE, thus providing novel potential biomarkers for the diagnosis of PTE. [ABSTRACT FROM AUTHOR]

Understanding the spatiotemporal variation of high-efficiency ride-hailing orders (HROs) is helpful for transportation network companies (TNCs) to balance the income of drivers through reasonable order dispatch, and to alleviate the imbalance between supply and demand by improving the pricing mechanism, so as to promote the sustainable and healthy development of the ride-hailing industry and urban transportation. From the perspective of TNCs for order management, this study investigates the spatiotemporal variation of HROs and common ride-hailing orders (CROs) for ride-hailing services using the trip data of Didi Chuxing in Haikou, China. Ordinary least squares (OLS) and geographically weighted regression (GWR) models are established to examine the factors that affect the densities of HROs and CROs during different time periods, such as morning, evening, afternoon and night, with considering various built environment variables. The OLS models show that factors including road density, average travel time rate, companies and enterprises and transportation facilities have significant impacts on HROs and CROs for most periods. The results of the GWR models are consistent with the global regression results and show the local effects of the built environment on HROs and CROs in different regions. [ABSTRACT FROM AUTHOR]

Due to the coupling of different energy systems, optimization of different energy complementarities, and the realization of the highest overall energy utilization rate and environmental friendliness of the energy system, distributed energy system has become an important way to build a clean and low-carbon energy system. However, the complex topological structure of the system and too many coupling devices bring more uncertain factors to the system which the calculation of the interval power flow of distributed energy system becomes the key problem to be solved urgently. Affine power flow calculation is considered as an important solution to solve uncertain steady power flow problems. In this paper, the distributed energy system coupled with cold, heat, and electricity is taken as the research object, the influence of different uncertain factors such as photovoltaic and wind power output is comprehensively considered, and affine algorithm is adopted to calculate the system power flow of the distributed energy system under high and low load conditions. The results show that the system has larger operating space, more stable bus voltage and more flexible pipeline flow under low load condition than under high load condition. The calculation results of the interval power flow of distributed energy systems can provide theoretical basis and data support for the stability analysis and optimal operation of distributed energy systems. [ABSTRACT FROM AUTHOR]

In order to explore the factors affecting users’ behaviors in a free-floating bike sharing (FFBS) system in China, a survey was conducted in Jiangsu province, China in 2017, and the travel characteristics of FFBS users were analyzed. A binary logistic model was applied to quantify the impact of various variables regarding residents’ usage preference based on 30401 valid questionnaires. The findings show that (1) FFBS was mainly used for short-distance travel in cities, especially for commuting and schooling, and the time period of travel in FFBS coincided with the rush-hour in urban areas; (2) a higher level of education, a higher daily transportation cost, the convenience of picking up and parking, and the contribution to users’ health could promote the usage of FFBS, while malfunctioning bicycles and limited regulations were major obstacles restricting the development of FFBS; (3) interestingly, people with high-incomes rather than those with low-incomes showed an inclination for FFBS owing to the charge mode. This research provides empirical evidence to facilitate the formulation of urban transportation policies and to improve the management of FFBS for the operators. [ABSTRACT FROM AUTHOR]

The weak and sustained tropical cyclone (TC) Rumbia (2018) and its associated heavy precipitation after landfall are simulated by the Weather Research and Forecasting model using three microphysics parameterizations (MP) and two planetary boundary layer (PBL) schemes. Key factors regulating the heavy rainfall distribution of landed TC at three stages (landfall, inland slow-moving and recurving stage) and their sensitivities to multi-physics parameterizations are examined. Results show that heavy rainfall distribution is largely regulated by the intensity of TC itself at landfall, but more affected by environmental factors at the two inland stages, including the environmental vertical wind shear, the associated upper-level wind divergence and low-level moisture convergence. Different MP and PBL schemes mainly affect the simulation of TC thermodynamic structure and key environmental factors, leading to their different forecast skills at three stages. Specifically, the Yonsei University (YSU) PBL scheme systematically outperforms the Mellor-Yamada-Nakanishi-Niino (MYNN) scheme in simulating stronger TC and heavy rainfall intensity. With the advantageous YSU PBL scheme, the Ferrier MP scheme only shows a slight advantage in simulating the intensity of TC and heavy rainfall at landfall. However, the WRF single-moment 6-class (WSM6) and Thompson scheme produce more graupel or snow, and better simulate the key environmental factors, showing their respective advantages in simulating the heavy rainfall structure and location at the two inland stages. This implies that the use of nonlocal YSU PBL scheme and the MP schemes with sophisticated ice processes shows superiority in simulating the postlandfall heavy rainfall induced by weak TCs. • Postlandfall rainfall of weak TC is highly affected by environmental factors. • Ice species and radial distribution of diabatic heating affect TC structures and rainfall. • The MYNN PBL scheme underestimates TC intensity and heavy rainfall compared to YSU. [ABSTRACT FROM AUTHOR]