Albertmarquez7658

Large-scale data sources, remote sensing technologies, and superior computing power have tremendously benefitted to environmental health study. Recently, various machine-learning algorithms were introduced to provide mechanistic insights about the heterogeneity of clustered data pertaining to the symptoms of each asthma patient and potential environmental risk factors. However, there is limited information on the performance of these machine learning tools. In this study, we compared the performance of ten machine-learning techniques. Using an advanced method of imbalanced sampling (IS), we improved the performance of nine conventional machine learning techniques predicting the association between exposure level to indoor air quality and change in patients' peak expiratory flow rate (PEFR). We then proposed a deep learning method of transfer learning (TL) for further improvement in prediction accuracy. Our selected final prediction techniques (TL1_IS or TL2-IS) achieved a balanced accuracy median (interquartile range) of 66(56~76) % for TL1_IS and 68(63~78) % for TL2_IS. Precision levels for TL1_IS and TL2_IS were 68(62~72) % and 66(62~69) % while sensitivity levels were 58(50~67) % and 59(51~80) % from 25 patients which were approximately 1.08 (accuracy, precision) to 1.28 (sensitivity) times increased in terms of performance outcomes, compared to NN_IS. Our results indicate that the transfer machine learning technique with imbalanced sampling is a powerful tool to predict the change in PEFR due to exposure to indoor air including the concentration of particulate matter of 2.5 μm and carbon dioxide. This modeling technique is even applicable with small-sized or imbalanced dataset, which represents a personalized, real-world setting.In this age of rapid biodiversity loss, we must continue to refine our approaches to describing variation in life on Earth. Combining knowledge and research tools from multiple disciplines is one way to better describe complex natural systems. Understanding plant community diversity requires documenting both pattern and process. We must first know which species exist, and where (i.e., taxonomic and biogeographic patterns), before we can determine why they exist there (i.e., ecological and evolutionary processes). Floristic botanists often use collections-based approaches to elucidate biodiversity patterns, while plant ecologists use hypothesis-driven statistical approaches to describe underlying processes. Because of these different disciplinary histories and research goals, floristic botanists and plant ecologists often remain siloed in their work. Here, using a case study from an urban greenway in Colorado, USA, we illustrate that the collections-based, opportunistic sampling of floristic botanists is highlf plant cover along the highly modified urban greenway. We suggest that actively fostering collaborations between floristic botanists and ecologists can create new insights into the maintenance of species diversity at the community scale.Spotting is thought to increase wildfire rate of spread (ROS) and in some cases become the main mechanism for spread. The role of spotting in wildfire spread is controlled by many factors including fire intensity, number of and distance between spot fires, weather, fuel characteristics and topography. Through a set of 30 laboratory fire experiments on a 3 m x 4 m fuel bed, subject to air flow, we explored the influence of manually ignited spot fires (0, 1 or 2), the presence or absence of a model hill and their interaction on combined fire ROS (i.e. ROS incorporating main fire and merged spot fires). During experiments conducted on a flat fuel bed, spot fires (whether 1 or 2) had only a small influence on combined ROS. Slowest combined ROS was recorded when a hill was present and no spot fires were ignited, because the fires crept very slowly downslope and downwind of the hill. This was up to, depending on measurement interval, 5 times slower than ROS in the flat fuel bed experiments. However, ignition of 1 or 2 spot fires (with hill present) greatly increased combined ROS to similar levels as those recorded in the flat fuel bed experiments (depending on spread interval). The effect was strongest on the head fire, where spot fires merged directly with the main fire, but significant increases in off-centre ROS were also detected. Our findings suggest that under certain topographic conditions, spot fires can allow a fire to overcome the low spread potential of downslopes. Current models may underestimate wildfire ROS and fire arrival time in hilly terrain if the influence of spot fires on ROS is not incorporated into predictions.Public health policies to contain the spread of COVID-19 rely mainly on non-pharmacological measures. Those measures, especially social distancing, are a challenge for developing countries, such as Brazil. In São Paulo, the most populous state in Brazil (45 million inhabitants), most COVID-19 cases up to April 18th were reported in the Capital and metropolitan area. However, the inner municipalities, where 20 million people live, are also at risk. As governmental authorities discuss the loosening of measures for restricting population mobility, it is urgent to analyze the routes of dispersion of COVID-19 in São Paulo territory. We hypothesize that urban hierarchy is the main responsible for the disease spreading, and we identify the hotspots and the main routes of virus movement from the metropolis to the inner state. In this ecological study, we use geographic models of population mobility to check for patterns for the spread of SARS-CoV-2 infection. We identify two patterns based on surveillance data one by contiguous diffusion from the capital metropolitan area, and the other hierarchical with long-distance spread through major highways that connects São Paulo city with cities of regional relevance. This knowledge can provide real-time responses to support public health strategies, optimizing the use of resources in order to minimize disease impact on population and economy.Using the economic complexity methodology on data for disease prevalence in 195 countries during the period of 1990-2016, we propose two new metrics for quantifying the disease space of countries. 3-O-Acetyl-11-keto-β-boswellic With these metrics, we analyze the geography of diseases and empirically investigate the effect of economic development on the health complexity of countries. We show that a higher income per capita increases the complexity of countries' diseases. We also show that complex diseases tend to be non-ubiquitous diseases that are prevalent in disease-diversified (complex) countries, while non-complex diseases tend to be non-ubiquitous diseases that are prevalent in non-diversified (non-complex) countries. Furthermore, we build a disease-level index that links a disease to the average level of GDP per capita of the countries in which the disease is prevalent. With this index, we highlight the link between economic development and the complexity of diseases and illustrate how increases in income per capita are associated with more complex diseases.