► The green space coverage in Chinese cities increased steadily from 1991 to 2009. ► Cities in the same region exhibited long-term similar trends of development. ► Population, land area and GDP significantly affected green space coverage. ► Per capita GDP had the highest independent contribution to green space coverage. ► A linear model to predict variance in green space was constructed. a b s t r a c t a r t i c l e i n f o Irrespective of which side is taken in the densification-sprawl debate, insights into the relationship between urban green space coverage and urbanization have been recognized as essential for guiding sustainable urban development. However, knowledge of the relationships between socio-economic variables of urbanization and long-term green space change is still limited. In this paper, using simple regression, hierarchical partitioning and multi-regression, the temporal trend in green space coverage and its relationship with urbanization were investigated using data from 286 cities between 1989 and 2009, covering all provinces in mainland China with the exception of Tibet. We found that: [1] average green space coverage of cities investigated increased steadily from 17.0% in 1989 to 37.3% in 2009; [2] cities with higher recent green space coverage also had relatively higher green space coverage historically; [3] cities in the same region exhibited similar long-term trends in green space coverage; [4] eight of the nine variables characterizing urbanization showed a significant positive linear relationship with green space coverage, with 'per capita GDP' having the highest independent contribution (24.2%);[5] among the climatic and geographic factors investigated, only mean elevation showed a significant effect; and [6] using the seven largest contributing individual factors, a linear model to predict variance in green space coverage was constructed. Here, we demonstrated that green space coverage in built-up areas tended to reflect the effects of urbanization rather than those of climatic or geographic factors. Quantification of the urbanization effects and the characteristics of green space development in China may provide a valuable reference for research into the processes of urban sprawl and its relationship with green space change.
Nowadays, metro systems play an important role in meeting the urban transportation demand in large cities. The understanding of passenger route choice is critical for public transit management. The wide deployment of Automated Fare Collection(AFC) systems opens up a new opportunity. However, only each trip's tap-in and tap-out timestamp and stations can be directly obtained from AFC system records; the train and route chosen by a passenger are unknown, which are necessary to solve our problem. While existing methods work well in some specific situations, they don't work for complicated situations. In this paper, we propose a solution that needs no additional equipment or human involvement than the AFC systems. We develop a probabilistic model that can estimate from empirical analysis how the passenger flows are dispatched to different routes and trains. We validate our approach using a large scale data set collected from the Shenzhen metro system. The measured results provide us with useful inputs when building the passenger path choice model.
a b s t r a c tSocio-economic factors have significant influences on air quality and are commonly used to guide environmental planning and management. Based on data from 85 long-term daily monitoring cities in China, air quality as evaluated by AOFDAQ-A (Annual Occurrence Frequency of Daily Air Quality above Level III), was correlated to socio-economic variable groups of urbanization, pollution and environmental treatment by variation partitioning and hierarchical partitioning methods. We found: (1) the three groups explained 43.5% of the variance in AOFDAQ-A; (2) the contribution of "environmental investment" to AOFDAQ-A shown a time lag effect; (3) "population in mining sector" and "coverage of green space in built-up area" were respectively the most significant negative and positive explanatory socioeconomic variables; (4) using eight largest contributing individual factors, a linear model to predict variance in AOFDAQ-A was constructed. Results from our study provide a valuable reference for the management and control of air quality in Chinese cities.
Background: As the booming of deep learning era, especially the advances in convolutional neural networks (CNNs), CNNs have been applied in medicine fields like radiology and pathology. However, the application of CNNs in dermatology, which is also based on images, is very limited. Inflammatory skin diseases, such as psoriasis (Pso), eczema (Ecz), and atopic dermatitis (AD), are very easily to be mis-diagnosed in practice. Methods: Based on the EfficientNet-b4 CNN algorithm, we developed an artificial intelligence dermatology diagnosis assistant (AIDDA) for Pso, Ecz & AD and healthy skins (HC). The proposed CNN model was trained based on 4,740 clinical images, and the performance was evaluated on experts-confirmed clinical images grouped into 3 different dermatologist-labelled diagnosis classifications (HC, Pso, Ecz & AD).
Results:The overall diagnosis accuracy of AIDDA is 95.80%±0.09%, with the sensitivity of 94.40%±0.12% and specificity 97.20%±0.06%. AIDDA showed accuracy for Pso is 89.46%, with sensitivity of 91.4% and specificity of 95.48%, and accuracy for AD & Ecz 92.57%, with sensitivity of 94.56% and specificity of 94.41%.Conclusions: AIDDA is thus already achieving an impact in the diagnosis of inflammatory skin diseases, highlighting how deep learning network tools can help advance clinical practice.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.