ABSTRACT
Hyperspectral remote sensing has tremendous potential for monitoring land cover and water bodies from the rich spatial and spectral information contained in the images. It is a time and resource consuming task to obtain groundtruth data for these images by field sampling. A semi-supervised method for labeling and classification of hyperspectral images is presented. The unsupervised stage consists of image enhancement by feature extraction, followed by clustering for labeling and generating the groundtruth image. The supervised stage for classification consists of a preprocessing stage involving normalization, computation of principal components, and feature extraction. An ensemble of machine learning models takes the extracted features and groundtruth data from the unsupervised stage as input and a decision block then combines the output of the machines to label the image based on majority voting. The ensemble of machine learning methods includes support vector machines, gradient boosting, Gaussian classifier, and linear perceptron. Overall, the gradient boosting method gives the best performance for supervised classification of hyperspectral images. The presented ensemble method is useful for generating labeled data for hyperspectral images that do not have groundtruth information. It gives an overall accuracy of 93.74% for the Jasper hyperspectral image, 100% accuracy for the HSI2 Lake Erie images, and 99.92% for the classification of cyanobacteria or harmful algal blooms and surface scum. The method distinguishes well between blue green algae and surface scum. The full pipeline ensemble method for classifying Lake Erie images in a cloud server runs 24 times faster than a workstation.
Subject(s)
Supervised Machine Learning , Support Vector Machine , Cluster Analysis , Machine Learning , Neural Networks, ComputerABSTRACT
This article presents a dataset for thermal characterization of photovoltaic systems to identify snail trails and hot spot failures. This dataset has 277 thermographic aerial images that were acquired by a Zenmuse XT IR camera (7-13 µ m wavelength) from a DJI Matrice 100 1drone (quadcopter). Additionally, our dataset includes the next environmental measurements: temperature, wind speed, and irradiance. The experimental set up consisted in a photovoltaic array of 4 serial monocrystalline Si panels (string) and an electronic equipment emulating a real load. The conditions for images acquisition were stablished in a flight protocol in which we defined altitude, attitude, and weather conditions.
ABSTRACT
Antecedentes: Se requiere analizar la situación de salud bucal en grupos vulnerables desde la perspectiva de los determinantes sociales para establecer estrategias de intervención efectivas. Objetivo: Describir el estado de salud bucal y factores relacionados en un grupo de mujeres en situación de prostitución en la ciudad de Medellin (Colombia). Métodos: Este fue un estudio descriptivo en una muestra por conveniencia de 53 mujeres que ejercen la prostitución. Se aplicó encuesta y examen clínico y se analizaron variables de autopercepción de salud bucal, índice COP-D (cariados, obturados y perdidos), índice de caries significativa (SiC), problemas de articulación temporomandibular (ATM) y estado protésico. Resultados: 88,2 % de las mujeres encuestadas reportaron un mal estado de salud bucal, 81 % se sentían insatisfechas con su estado bucal y 60 % reportó problemas bucales. La prevalencia de caries dental fue del 64 %, con un COP-D de 15,6 (±8,4), y un SiC de 25,5 (±3,6). Se presentaron diferencias en el estado de salud bucal en indicadores clínicos y subjetivos según factores sociodemográficos. Más de tres cuartas partes requerían cambia o realizar nuevas prótesis superiores o inferiores. En casi la mitad se hallaron ruidos articulares en la ATM según evaluación clínica. Conclusiones: El estado de salud bucal según los indicadores analizados es reflejo de las condiciones sociales en que se encuentran estas mujeres. Se encontraron diferencias en los indicadores de salud bucal de acuerdo con diferentes factores sociodemográficos, lo cual sugiere la influencia de los determinantes sociales en las desigualdades en salud bucal.
Background: The analysis of the oral health situation in vulnerable groups from a perspective of social determinants is required to implement effective intervention strategies. Purpose: To describe the oral health status and its related factors in a group of women in situation of prostitution in Medellin (Colombia). Methods: A descriptive study was conducted with a convenience sample of 53 women. A survey and clinical exanimation was earned out. The study analyzed variables related to self-perceived oral health, DTMF Index, Significant Caries Index (SiC), temporomandibular joint problems (TMJ), and the status of fixed/removable prosthesis. Results: 88.2 % of the sun-eyed women reported their oral health status was poor, 81 % of them felt unsatisfied with their mouth, and 60 % reported oral problems. The prevalence of dental caries was 64 %, with a DTMF of 15.6 (± 8.4), and a SiC of 25.5 (± 3.6). There were differences in oral health status in clinical and subjective indicators accordmg to sociodemographic factors. More than three-quarters required changing or making new upper and/or lower partial or fixed dentures. In almost half, articular noises were found in TMJ according to the clinical evaluation. Conclusions: The oral health status, from the basis of the indicators analyzed, reflects the social conditions found in these women. Differences in the oral health indicators were in accordance to sociodemographic factors. This situation suggests that there is an influence of social determinants on oral health inequalities.
Subject(s)
Health Profile , Health Surveys/statistics & numerical data , Dental Caries/diagnosis , Sex WorkersABSTRACT
High-quality colostrum is an important factor influencing neonatal calf health, and quality assessment is essential to obtain good health results. This research evaluated the effects of the calf's sex, the parity of the cow and the hour of colostrum harvest after parity on the fat, nonfat solids, protein and Ig contents in Holstein colostrum for cows under high grazing conditions in the tropics. The effects of the calf's sex and parity on somatic cell count (SCC) at the first milking postpartum were determined. A comparison was made between a laboratory method and a farm method for the estimation of the fat and protein content of colostrum. Thirty-three cows were sampled in the study. The calf's sex was shown to have an effect on the amount of colostrum, on the concentration of fat, and on the amount of milk produced by lactating Holstein cows; all were higher in cows that gave birth to a female calf. Colostrum protein decreased after the first hour postpartum, and the Ig concentration had a tendency to decrease after 4 h. The cows that had parity 1-2 had lower Ig concentrations and total production of Igs, and higher SCC at the first milking postpartum. Ekomilk was a reliable method to measure the colostrum fat on the farm.
