ABSTRACT
Total Suspended Solids (TSS) and chlorophyll-a concentration are two critical parameters to monitor water quality. Since directly collecting samples for laboratory analysis can be expensive, this paper presents a methodology to estimate this information through remote sensing and Machine Learning (ML) techniques. TSS and chlorophyll-a are optically active components, therefore enabling measurement by remote sensing. Two study cases in distinct water bodies are performed, and those cases use different spatial resolution data from Sentinel-2 spectral images and unmanned aerial vehicles together with laboratory analysis data. In consonance with the methodology, supervised ML algorithms are trained to predict the concentration of TSS and chlorophyll-a. The predictions are evaluated separately in both study areas, where both TSS and chlorophyll-a models achieved R-squared values above 0.8.
Subject(s)
Chlorophyll A/chemistry , Machine Learning , Remote Sensing Technology/methods , Algorithms , Environmental Monitoring , Geographic Information Systems , Image Processing, Computer-Assisted , Water QualityABSTRACT
Spectral information provided by multispectral and hyperspectral sensors has a great impact on remote sensing studies, easing the identification of carbonate outcrops that contribute to a better understanding of petroleum reservoirs. Sensors aboard satellites like Landsat series, which have data freely available usually lack the spatial resolution that suborbital sensors have. Many techniques have been developed to improve spatial resolution through data fusion. However, most of them have serious limitations regarding application and scale. Recently Super-Resolution (SR) convolution neural networks have been tested with encouraging results. However, they require large datasets, more time and computational power for training. To overcome these limitations, this work aims to increase the spatial resolution of multispectral bands from the Landsat satellite database using a modified artificial neural network that uses pixel kernels of a single spatial high-resolution RGB image from Google Earth as input. The methodology was validated with a common dataset of indoor images as well as a specific area of Landsat 8. Different downsized scale inputs were used for training where the validation used the ground truth of the original size images, obtaining comparable results to the recent works. With the method validated, we generated high spatial resolution spectral bands based on RGB images from Google Earth on a carbonated outcrop area, which were then properly classified according to the soil spectral responses making use of the advantage of a higher spatial resolution dataset.
ABSTRACT
We compared the effect of oral glucose versus oral glucose combined with glycerol (glucose + glycerol) in promoting glucose recovery during hypoglycemia. These studies were carried out in two series of experiments. In the first series of experiments, 16 overnight fasted rats received an intraperitoneal injection of lispro insulin (1 IU/kg), and 25 min later, they received oral water (control), glucose (0.25 g/kg), glycerol (2.5 g/kg), or glucose (0.25 g/kg) + glycerol (2.5 g/kg). In the second series of experiments on 164 eligible type 1 diabetic (T1D) patients, 30 individuals with a history of hypoglycemia were recruited. Five volunteers did not meet the inclusion criteria and two subjects were excluded after starting the clinical investigation; 23 patients concluded the study. All patients with symptoms of hypoglycemia ingested oral glucose (15 g) or glucose (15 g) + glycerol (9.45 g). To treat hypoglycemia in T1D patients, preparations containing glucose alone or glucose + glycerol were used alternately (2 weeks/2 weeks) in a double-blind crossover scheme. Throughout the clinical research (4 weeks), glucose concentrations were assessed with a continuous glucose monitoring device and the results after the use of glucose alone or glucose + glycerol preparations were compared. Oral glucose combined with glycerol was more effective in promoting glucose recovery in comparison with glucose alone, not only in rats but also in T1D patients. Taken together, our experimental and clinical investigations reported the best performance of oral administration of glucose + glycerol in comparison with isolated glucose.
Subject(s)
Diabetes Mellitus, Type 1 , Hypoglycemia , Animals , Blood Glucose , Blood Glucose Self-Monitoring , Diabetes Mellitus, Type 1/drug therapy , Glucose , Glycerol , Humans , Hypoglycemia/drug therapy , Hypoglycemic Agents , Insulin , RatsABSTRACT
Global suicide rates have increased in recent decades becoming a serious social and public health problem. In Brazil, rates have been increasing annually. We aimed to analyze the correlation between suicide mortality rates and global economic and political crisis periods of 2008 and 2014 in Brazil. The analysis of suicide mortality in Brazil was done using a time-series segmented linear regression model that estimated the trend of rates over time. To obtain the model, changes in the trend of both abrupt and gradual suicide rates were investigated. The results indicate statistically significant changes showing an upward trend of suicide rates during the world economic crisis (2008-2013) and during the economic and political crisis in Brazil (2014-2017) compared to previous periods, especially at the extremes of schooling (3 < years and > 8 years). Among white and parda, there were significant trend rates increases in both periods and in different regions. In the Northeast and South regions, we observed a significant increase in the trend rate for males after the Brazilian economic and political crisis (2014 to 2017). We can conclude that the national suicide rates were influenced by the economic and political instability that our country has been going through since 2008, affecting each region differently. Further studies are needed to explore the reasons for interregional differences and the relation of suicide with unemployment rates and possible economic predictors.
ABSTRACT
The relationship between the fires occurrences and diseases is an essential issue for making public health policy and environment protecting strategy. Thanks to the Internet, today, we have a huge amount of health data and fire occurrence reports at our disposal. The challenge, therefore, is how to deal with 4 Vs (volume, variety, velocity and veracity) associated with these data. To overcome this problem, in this paper, we propose a method that combines techniques based on Data Mining and Knowledge Discovery from Databases (KDD) to discover spatial and temporal association between diseases and the fire occurrences. Here, the case study was addressed to Malaria, Leishmaniasis and respiratory diseases in Brazil. Instead of losing a lot of time verifying the consistency of the database, the proposed method uses Decision Tree, a machine learning-based supervised classification, to perform a fast management and extract only relevant and strategic information, with the knowledge of how reliable the database is. Namely, States, Biomes and period of the year (months) with the highest rate of fires could be identified with great success rates and in few seconds. Then, the K-means, an unsupervised learning algorithms that solves the well-known clustering problem, is employed to identify the groups of cities where the fire occurrences is more expressive. Finally, the steps associated with KDD is perfomed to extract useful information from mined data. In that case, Spearman's rank correlation coefficient, a nonparametric measure of rank correlation, is computed to infer the statistical dependence between fire occurrences and those diseases. Moreover, maps are also generated to represent the distribution of the mined data. From the results, it was possible to identify that each region showed a susceptible behaviour to some disease as well as some degree of correlation with fire outbreak, mainly in the drought period.