Land cover mapping in complex environments can be challenging due to their landscape heterogeneity. With the increasing availability of various open-access remotely sensed datasets, more images ...acquired by different sensors and on different dates tend to be used to improve land cover classification accuracy. Selecting an appropriate feature domain with the best landscape separability is therefore crucial in meeting the requirement of computational efficiency and model interpretability. Variable selection is widely used in pattern recognition to enhance model parsimony. This study focused on the variable selection process and proposed a series of methods to select the optimal feature domain to improve land cover classification in a complex urbanized coastal area. Two decision tree models (CART-Classification and Regression Tree and CIT-Conditional Inference Tree) and five variable importance measures (GINI, PVIM-Permutated Variable Importance Measure, MD- Minimum Depth, IPM-Intervention of Prediction Measure, and CPVIM-Conditional Permutation Variable Importance Measure) based on random forests were considered. Variable importance measures were applied to a set of spectral, spatial and temporal features derived from medium-resolution satellite images. Backward elimination methods were used to select the optimal feature subset. It is found that compared to the traditional band-only model, the variable selection process can significantly improve the model parsimony and computational efficiency. The CPVIM based on CIT decision tree model was more reliable in selecting relevant features regardless their correlations, but CART tended to generate higher classification accuracy. Therefore, the combination of the CART model and the ranking from the CPVIM variable measure is recommended to achieve higher classification accuracy and better data interpretability. The novelty of our work is with the insight into the merits of integrating variable selection in the land cover classification process over complex environments.
•Variable selection can significantly improve coastal land cover classification.•The selection of variable importance measures may vary by data types.•Conditional permutated variable importance measure was reliable for correlated data.•Conditional Inference Tree took more time but did not necessarily improve accuracy.
In this paper, we present evidence from a lab-in-the-field experiment of the effects of the Chinese one-child policy on adults in China who were born just before and after the introduction of the ...policy. We measure risk, uncertainty, and time preferences, as well as subjects’ preferences in the social domain, i.e., concerning competitiveness, cooperation, and bargaining. We sampled people from three Chinese provinces born both before and after the introduction of the policy in 1979. We utilize the fact that the one-child policy was introduced at different times and with different degrees of strictness in different provinces. Overall, we find a statistically significant effect only on risk and uncertainty aversion and not on any other preferences in the experiments: Those born after the introduction of the one-child policy are less risk and uncertainty averse. These results hold for various robustness checks and heterogeneity tests. Hence, our results do not confirm the general wisdom and stereotype of only-children in China being “little emperors.”
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The support vector machine is a group of relatively novel statistical learning algorithms that have not been extensively exploited in the remote sensing community. In previous studies they have been ...found to generally outperform some popular classifiers. Several recent studies found
that training samples and input data dimensionalities can affect image classification accuracies by those popular classifiers and support vector machines alike. The current study extends beyond these recent research frameworks and into another important inquiry area addressing the impacts
of internal parameterization on the performance of support vector machines for land-cover classification. A set of support vector machines with different combinations of kernel types, parameters, and error penalty are carefully constructed to classify a Landsat Thematic Mapper image into eight
major land-cover categories using identical training data. The accuracy of each classified map is further evaluated using identical reference data. The results reveal that kernel types and error penalty can substantially affect the classification accuracy, and that a careful selection of parameter
settings can help improve the performance of the support vector classification. These findings reported here can help establish a practical guidance on the use of support vector machines for land-cover classification from remote sensor data.
The locality preserving projections (LPP) algorithm is a recently developed linear dimensionality reduction algorithm that has been frequently used in face recognition and other applications. ...However, the projection matrix in LPP is not orthogonal, thus creating difficulties for both reconstruction and other applications. As the orthogonality property is desirable, orthogonal LPP (OLPP) has been proposed so that an orthogonal projection matrix can be obtained based on a step by step procedure; however, this makes the algorithm computationally more expensive. Therefore, in this paper, we propose a fast and orthogonal version of LPP, called FOLPP, which simultaneously minimizes the locality and maximizes the globality under the orthogonal constraint. As a result, the computation burden of the proposed algorithm can be effectively alleviated compared with the OLPP algorithm. Experimental results on two face recognition data sets and two hyperspectral data sets are presented to demonstrate the effectiveness of the proposed algorithm.
The aim of this study was to evaluate a combination diet of organic acids and essential oils on epithelial restitution, intestinal microflora, and volatile fatty acids in broiler chickens. A total of ...144 1-day-old male chicks (Cobb 500) were allotted to 3 treatment groups consisting of 6 replicates with 8 birds per replicate. The dietary treatments were as follows: control group (CON, basal diet), antibiotics group (ANT, control + 0.15 g/kg enramycin), and addition group (EOA, control + 0.30 g/kg encapsulated organic acids and essential oils). Compared to the CON group, the EOA group showed a higher feed conversion ratio (FCR) (P < 0.05) at day 42. The ANT group showed the lowest count of Lactobacillus spp. (P < 0.05) and the highest count of Escherichia coli (P < 0.05) in the ileal digesta. Birds that were fed the EOA-supplemented diet had decreased populations of E. coli (P < 0.05). Compared with the ANT group, supplementation with EOA tended to reduce the pH of jejunal digesta (P = 0.079) and ileal digesta (P = 0.078) but significantly increased the concentration of butyric acid (P < 0.05) and tended to increase the concentrations of acetic acid (P = 0.087) and total short-chain fatty acids (SCFA; P = 0.098) in the ileal digesta. The EOA group showed higher sucrase and maltase activities of jejunal mucosa (P < 0.05) than those in the other groups. The EOA supplementation increased (P < 0.05) claudin-1 mRNA expression in the jejunum. Compared with the other groups, enramycin supplementation significantly reduced jejunal mucosa sIgA (P < 0.05) and down-regulated Mucin-2 and TLR2 mRNA relative expression (P < 0.05) in the jejunal mucosa of broiler chickens. Both EOA and enramycin contribute beneficially to FCR because of their antimicrobial action. EOA may reduce harmful bacteria and promote digestive enzyme activity and higher concentrations of SCFA. In contrast, enramycin may inhibit the growth of beneficial bacteria and reduce the need for intestinal mucosal barrier function.
Environmental sustainability research is dependent on accurate land cover information. Even with the increased number of satellite systems and sensors acquiring data with improved spectral, spatial, ...radiometric and temporal characteristics and the new data distribution policy, most existing land cover datasets are derived from a pixel-based, single-date multi-spectral remotely sensed image with an unacceptable accuracy. One major bottleneck for accuracy improvement is how to develop an accurate and effective image classification protocol. By incorporating and utilizing multi-spectral, multi-temporal and spatial information in remote sensing images and considering the inherit spatial and sequential interdependence among neighboring pixels, we propose a new patch-based recurrent neural network (PB-RNN) system tailored for classifying multi-temporal remote sensing data. The system is designed by incorporating distinctive characteristics of multi-temporal remote sensing data. In particular, it uses multi-temporal–spectral–spatial samples and deals with pixels contaminated by clouds/shadow present in multi-temporal data series. Using a Florida Everglades ecosystem study site covering an area of 771 square kilometers, the proposed PB-RNN system has achieved a significant improvement in the classification accuracy over a pixel-based recurrent neural network (RNN) system, a pixel-based single-image neural network (NN) system, a pixel-based multi-image NN system, a patch-based single-image NN system, and a patch-based multi-image NN system. For example, the proposed system achieves 97.21% classification accuracy while the pixel-based single-image NN system achieves 64.74%. By utilizing methods like the proposed PB-RNN one, we believe that much more accurate land cover datasets can be produced over large areas.
Climate change adaptation in urban areas is among the biggest challenges humanity faces partly because of the combined effects of urban heating and global warming. The variability of urban heat ...islands (VUHIs) is known to influence the effectiveness of climate adaptation strategies; however, the understanding of VUHIs is still limited. Here, we quantified the diurnal and seasonal VUHIs in 245 Chinese cities that varied in population and physical size based on the remotely sensing data from 2002 to 2012. Taking the 2012 VUHIs as an example, we examined the relationships between VUHIs and underlying drivers of background climate and urbanization. The results showed that: (1) the VUHIs from 2002 to 2012 had obvious periodicity in different years while significant diurnal and seasonal variability; (2) the explanation rates of local background climate for the diurnal VUHIs were 30% (spring), 19% (summer), 29% (autumn), and 25% (winter), respectively; (3) the explanation rates of urbanization for the diurnal VUHIs were 13% (spring), 22% (summer), 11% (autumn), and 21% (winter), respectively; (4) these two variables also accounted for 32% and 12% of the seasonal VUHIs during the daytime, and 25% and 23% during the nighttime, respectively. Our research suggests that the improvement of urban climate-change adaptation necessitates local “climate-smart” strategies, a reduction in local anthropogenic heat emissions, and rational use of green planning for sustainable urban development.
Display omitted
•Variability of urban heat islands (VUHI) was investigated in 245 Chinese cities.•The average diurnal VUHI is positive in summer but negative in other seasons.•Hot and humid climate amplify VUHI while strong wind mitigates VUHI.•Vehicles affect VUHI in summer and energy is significant in autumn and winter.
Recently, necroptosis, as a programmed cell death pathway, has drawn much attention as it has been implicated in multiple pathologies, especially in the field of inflammatory diseases. Pseudokinase ...mixed lineage kinase domain-like protein (MLKL) serves as a terminal-known obligate effector in the process of necroptosis. To date, the majority of research on MLKL has focused on its role in necroptosis, and the prevailing view has been that the sole function of MLKL is to mediate necroptosis. However, increasing evidence indicates that MLKL can serve as a regulator of many diseases via its non-necroptotic functions. These functions of MLKL shed light on its functional complexity and diversity. In this review, we briefly introduce the current state of knowledge regarding the structure of MLKL, necroptosis signaling, as well as cross-linkages among necroptosis and other regulated cell death pathways, and we particularly highlight recent progress related to newly identified functions and inhibitors of MLKL. These discussions promote a better understanding of the role of MLKL in diseases, which will foster efforts to pharmacologically target this molecule in clinical treatments.
Porous metals are very popular functional materials that have been used for various fields due to their attractive properties such as high porosity, controllable permeability, and high specific ...surface area, etc. This study provides an overall review of the fabrication, characterization and application of the porous metal materials (PMMs) for polymer electrolyte membrane fuel cell (PEMFC) applications. Metal foams, porous metal sinters, metal meshes and perforated metals are included. Such materials have been used as flow distributor/flow field, current collector, gas diffusion backing and also catalyst support. Different applications require different dominant characteristics of the PMMs. Although the feasibility of using the PMMs for PEMFC applications have been comprehensively validated by both modeling and experimental investigations, there still exists plenty of scope to explore the in-depth mechanisms concerning how and how much the PMMs contribute to the fuel cell performance. This work not only summarizes the development of this subject, but also analyzes the challenges that must be overcome in the future. Moreover, a systematical optimization link for active functional design (AFD) of PEMFC-oriented PMMs is also presented.
Vegetation is a fundamental element in urban ecosystems, and vegetation mapping is critical for urban and landscape planning and management. While remote sensing has increasingly been used for ...vegetation mapping, this spatially explicit approach can be challenging due to the spectral similarity between various vegetation types and the presence of complex features in the urban environment. The objective of this study is to develop a method that can help improve vegetation mapping in urban areas from medium-resolution remote sensor imagery. Central to our method is the combined use of stratified classification and multiple endmember spectral mixture analysis (MESMA) techniques. Specifically, we firstly partition the entire landscape into rural and urban subsets using road network density so that each subset can be processed independently to minimize the spectral confusion between some urban features and agricultural land covers. Secondly, we carefully extract all vegetation covers at the sub-pixel level for the urban subset by using the MESMA technique in order to account for small, fragmented vegetation patches that would be classified as non-vegetated classes otherwise. Thirdly, we adopt a separate supervised classification protocol to the rural subset and the vegetation covers extracted from the urban subset. Finally, we combine the classified outcomes from the two subsets to produce a complete map. We have implemented this method to produce a land cover map including various vegetation types from a Landsat Thematic Mapper (TM) image covering a large metropolitan area. It is found that this method has substantially outperformed two related ones that use the same supervised protocol to the entire area directly or to the rural subset and the urban subset without being MESMA processed. The advantage of our method is that it has extended the capability of sub-pixel analysis beyond vegetation abundance estimation and into the area of mapping thematic vegetation types in urban areas.
•We develop a method to help improve vegetation mapping in urban areas.•Landscape partition and multiple endmember spectral mixture analysis are used.•Sub-pixel information can support mapping thematic vegetation types in urban areas.