Explore the vast range of titles available.

The main goal of this study was to use the synthetic minority oversampling technique (SMOTE) to expand the quantity of landslide samples for machine learning methods (i.e., support vector machine (SVM), logistic regression (LR), artificial neural network (ANN), and random forest (RF)) to produce high-quality landslide susceptibility maps for Lishui City in Zhejiang Province, China. Landslide-related factors were extracted from topographic maps, geological maps, and satellite images. Twelve factors were selected as independent variables using correlation coefficient analysis and the neighborhood rough set (NRS) method. In total, 288 soil landslides were mapped using field surveys, historical records, and satellite images. The landslides were randomly divided into two datasets: 70% of all landslides were selected as the original training dataset and 30% were used for validation. Then, SMOTE was employed to generate datasets with sizes ranging from two to thirty times that of the training dataset to establish and compare the four machine learning methods for landslide susceptibility mapping. In addition, we used slope units to subdivide the terrain to determine the landslide susceptibility. Finally, the landslide susceptibility maps were validated using statistical indexes and the area under the curve (AUC). The results indicated that the performances of the four machine learning methods showed different levels of improvement as the sample sizes increased. The RF model exhibited a more substantial improvement (AUC improved by 24.12%) than did the ANN (18.94%), SVM (17.77%), and LR (3.00%) models. Furthermore, the ANN model achieved the highest predictive ability (AUC = 0.98), followed by the RF (AUC = 0.96), SVM (AUC = 0.94), and LR (AUC = 0.79) models. This approach significantly improves the performance of machine learning techniques for landslide susceptibility mapping, thereby providing a better tool for reducing the impacts of landslide disasters.

The sponge city is a new concept of stormwater management for ecological city construction, which aims to restore water-cycle processes and reduce runoff. Cities in coastal districts are suffering from serious instability due to high population density, urbanization, and land-use changes. However, previous research contains few evaluations of balancing urban ecological indicators of sponge city performance, including geographical, environmental, economic, and social factors, and their effect on resilience at a macro level to develop low-impact development schemes. In this study, we developed an integrated framework using factor analysis, geographical statistics, multi-objective analysis, and remote sensing methods to extract the factors influencing sponge city resilience and to establish spatial pattern schemes. The results indicated that the urbanization degree and plant adaptability had the greatest impact on sponge city performance, with weights of 45 and 27%, respectively. Sponge city spatial pattern schemes performed the best in the combination scenario of 14.8–46.8% green roofs (by area ratio) supported by grooves and rain barrels +10% herbaceous basins divided into units by ecological tree pools +10% permeable pavements and sidewalks. This scenario balanced facilities and cost to optimize the spatial pattern, which improved sponge city adaptability and urban ecological conditions.

Haemonchus contortus is a species of gastrointestinal strongyles of primary concern for sheep. This highly pathogenic, blood-feeding helminth negatively influences animal health, welfare and productivity. In order to elucidate the current scenario in terms of prevalence and intensity of H. contortus infection in sheep farms across Europe, a standardized crosssectional survey was conducted in three pilot areas in Ireland, Switzerland and Italy, all part of the EU funded GLOWORM project. Two consecutive field surveys (in 2012 and 2013) were conducted in the three countries in the same period (August-October) in 259 sheep farms in total. Harmonized, diagnostic procedures (from farm to laboratory) based on pooled samples, the FLOTAC technique and coproculture were used. The georeferenced parasitological results were modelled (at the pilot area level) following a Bayesian geostatistical approach with correction for preferential sampling and accounting for climatic and environmental covariates. The observed H. contortus prevalence rates did vary between the countries showing high values in Switzerland (77%) and Italy (73%) compared to Ireland (4%). Spatial patterns of H. contortus distribution were detected in Switzerland and Italy with a north-south gradient. The latent factor analysis highlighted the importance of seasonality and annual cyclicity within country (particularly in southern Italy), while mean temperature and rainfall dominated between country variations in the prevalence of H. contortus infection.

Background Getting a random household sample during a survey can be expensive and very difficult especially in urban area and non-specialist. This study aimed to test an alternative method using freely available aerial imagery. Methods A gridded map and random selection method was used to select households for interviews. A hundred numbered of points were put along the edges of an updated map of Maroua. Then two numbers were randomly draw at a time and a line was drawn between those two numbers. A lot of different kinds of shapes of different sizes obtained were numbered. Ten shapes were randomly draw and the one selected were considered as ‘neighbourhoods’. A grid of 30 m × 30 m was drawn over each and then numbered. 202 grids considered here as households were randomly selected from the ten neighbourhoods for interviews. Results Out of 202 households visited, only 4 were found to be something other than a house. In addition, 30 sampled households (14.85%) were abandoned or the occupants had relocated elsewhere. This method resulted in an accuracy level of 72%, its advantage is the ability to generate efficient random sample at relatively low cost as well the time required. Conclusions The method proposed in this study was efficient and cost-effective when compared to the infield generation of a household inventory or Global Positioning System (GPS) tracking of households. It can then be used by researchers in low-incomes countries where funding for research is a challenge. However, this method needs to train the investigators on how to use the GPS.

To achieve powerful infringement retrieval for reference images in digital publications, a new improved Scale Invariant Feature Transformation (SIFT) algorithm has been proposed in this paper. The retrieval process in the improved algorithm is innovatively divided into two stages to achieve coarse retrieval and fine retrieval respectively. In coarse retrieval, Geographical Statistics (GeoStat) is creatively used to describe the global spatial relationship of key-points in different orientations in an image and then generate a 144-dimensional feature vector to represent each image. In fine retrieval, only partial images, which are highly similar to the query image obtained from results of coarse retrieval, need to be considered. And the indexing and matching process in the improved algorithm is improved by adding a judgment process to improve the matching speed and reduce the mistaken matching rate. Experimental results show that the proposed algorithm has more advantages in retrieval speed and higher retrieval accuracy than the original SIFT algorithm. And the proposed algorithm is also more suitable for infringement retrieval of reference images in digital publications than the original one.

We estimate a measure of segregation, experienced isolation, that captures individuals’ exposure to diverse others in the places they visit over the course of their days. Using Global Positioning System (GPS) data collected from smartphones, we measure experienced isolation by race. We find that the isolation individuals experience is substantially lower than standard residential isolation measures would suggest but that experienced isolation and residential isolation are highly correlated across cities. Experienced isolation is lower relative to residential isolation in denser, wealthier, more educated cities with high levels of public transit use and is also negatively correlated with income mobility.

Ensuring access to healthcare in emergency health situations is a persistent concern for health system planners. Emergency services, including critical care units for severe burns and coronary events, are amongst those for which travel time is the most crucial, potentially making a difference between life and death. Although it is generally assumed that access to healthcare is not an issue in densely populated urban areas due to short distances, we prove otherwise by applying improved methods of assessing accessibility to emergency services by the urban poor that take traffic variability into account. Combining unique data on emergency health service locations, traffic flow variability and informal settlements boundaries, we generated time-cost based service areas to assess the extent to which emergency health services are reachable by urban slum dwellers when realistic traffic conditions and their variability in time are considered. Variability in traffic congestion is found to have significant impact on the measurement of timely access to, and availability of, healthcare services for slum populations. While under moderate traffic conditions all slums in Dhaka City are within 60-minutes travel time from an emergency service, in congested traffic conditions only 63% of the city's slum population is within 60-minutes reach of most emergency services, and only 32% are within 60-minutes reach of a Burn Unit. Moreover, under congested traffic conditions only 12% of slums in Dhaka City Corporation comply with Bangladesh's policy guidelines that call for access to 1 health service per 50,000 population for most emergency service types, and not a single slum achieved this target for Burn Units. Emergency Obstetric Care (EmOC) and First Aid & Casualty services provide the best coverage, with nearly 100% of the slum population having timely access within 60-minutes in any traffic condition. Ignoring variability in traffic conditions results in a 3-fold overestimation of geographic coverage and masks intra-urban inequities in accessibility to emergency care, by overestimating geographic accessibility in peripheral areas and underestimating the same for central city areas. The evidence provided can help policy makers and urban planners improve health service delivery for the urban poor. We recommend that taking traffic conditions be taken into account in future GIS-based analysis and planning for healthcare service accessibility in urban areas.

Background Human mobility is fundamental to understanding global issues in the health and social sciences such as disease spread and displacements from disasters and conflicts. Detailed mobility data across spatial and temporal scales are difficult to collect, however, with movements varying from short, repeated movements to work or school, to rare migratory movements across national borders. While typical sources of mobility data such as travel history surveys and GPS tracker data can inform different typologies of movement, almost no source of readily obtainable data can address all types of movement at once. Methods Here, we collect Google Location History (GLH) data and examine it as a novel source of information that could link fine scale mobility with rare, long distance and international trips, as it uniquely spans large temporal scales with high spatial granularity. These data are passively collected by Android smartphones, which reach increasingly broad audiences, becoming the most common operating system for accessing the Internet worldwide in 2017. We validate GLH data against GPS tracker data collected from Android users in the United Kingdom to assess the feasibility of using GLH data to inform human movement. Results We find that GLH data span very long temporal periods (over a year on average in our sample), are spatially equivalent to GPS tracker data within 100 m, and capture more international movement than survey data. We also find GLH data avoid compliance concerns seen with GPS trackers and bias in self-reported travel, as GLH is passively collected. We discuss some settings where GLH data could provide novel insights, including infrastructure planning, infectious disease control, and response to catastrophic events, and discuss advantages and disadvantages of using GLH data to inform human mobility patterns. Conclusions GLH data are a greatly underutilized and novel dataset for understanding human movement. While biases exist in populations with GLH data, Android phones are becoming the first and only device purchased to access the Internet and various web services in many middle and lower income settings, making these data increasingly appropriate for a wide range of scientific questions.

Recent studies of human mobility largely focus on displacements patterns and power law fits of empirical long-tailed distributions of distances are usually associated to scale-free superdiffusive random walks called Lévy flights. However, drawing conclusions about a complex system from a fit, without any further knowledge of the underlying dynamics, might lead to erroneous interpretations. Here we show, on the basis of a data set describing the trajectories of 780,000 private vehicles in Italy, that the Lévy flight model cannot explain the behaviour of travel times and speeds. We therefore introduce a class of accelerated random walks, validated by empirical observations, where the velocity changes due to acceleration kicks at random times. Combining this mechanism with an exponentially decaying distribution of travel times leads to a short-tailed distribution of distances which could indeed be mistaken with a truncated power law. These results illustrate the limits of purely descriptive models and provide a mechanistic view of mobility. Many human mobility studies have shown empirically long-tailed distance distributions, which are usually associated to Lévy flights. Here, the authors show that the behavior of private vehicles could be misinterpreted as Lévy flights but is fully captured by a class of accelerated random walks.

Background The World Health Organization recommends strategies to improve urban design, public transportation, and recreation facilities to facilitate physical activity for non-communicable disease prevention for an increasingly urbanized global population. Most evidence supporting environmental associations with physical activity comes from single countries or regions with limited variation in urban form. This paper documents variation in comparable built environment features across countries from diverse regions. Methods The International Physical Activity and the Environment Network (IPEN) study of adults aimed to measure the full range of variation in the built environment using geographic information systems (GIS) across 12 countries on 5 continents. Investigators in Australia, Belgium, Brazil, Colombia, the Czech Republic, Denmark, China, Mexico, New Zealand, Spain, the United Kingdom, and the United States followed a common research protocol to develop internationally comparable measures. Using detailed instructions, GIS-based measures included features such as walkability (i.e., residential density, street connectivity, mix of land uses), and access to public transit, parks, and private recreation facilities around each participant’s residential address using 1-km and 500-m street network buffers. Results Eleven of 12 countries and 15 cities had objective GIS data on built environment features. We observed a 38-fold difference in median residential densities, a 5-fold difference in median intersection densities and an 18-fold difference in median park densities. Hong Kong had the highest and North Shore, New Zealand had the lowest median walkability index values, representing a difference of 9 standard deviations in GIS-measured walkability. Conclusions Results show that comparable measures can be created across a range of cultural settings revealing profound global differences in urban form relevant to physical activity. These measures allow cities to be ranked more precisely than previously possible. The highly variable measures of urban form will be used to explain individuals’ physical activity, sedentary behaviors, body mass index, and other health outcomes on an international basis. Present measures provide the ability to estimate dose–response relationships from projected changes to the built environment that would otherwise be impossible.