Search results for "data set"
showing 10 items of 154 documents
Accurate estimation of retinal vessel width using bagged decision trees and an extended multiresolution Hermite model.
2012
We present an algorithm estimating the width of retinal vessels in fundus camera images. The algorithm uses a novel parametric surface model of the cross-sectional intensities of vessels, and ensembles of bagged decision trees to estimate the local width from the parameters of the best-fit surface. We report comparative tests with REVIEW, currently the public database of reference for retinal width estimation, containing 16 images with 193 annotated vessel segments and 5066 profile points annotated manually by three independent experts. Comparative tests are reported also with our own set of 378 vessel widths selected sparsely in 38 images from the Tayside Scotland diabetic retinopathy scre…
Quantitative assessment of aortic stenosis by three-dimensional echocardiography
1997
The purpose of this study was to assess the feasibility of three-dimensional echocardiography in aortic stenosis. Planimetric determination of valve area and dynamic volume-rendered display were performed. Three-dimensional echocardiography permits display of any desired plane of the cardiac structure. Thus in the case of aortic stenosis, the plane used for planimetric evaluation can be positioned exactly through the valve orifice. Dynamic volume-rendered display may provide a spatial demonstration of the stenotic valve. In 48 patients aortic valve area was measured by planimetry. The three-dimensional data set was acquired by a workstation in the course of a multiplane transesophageal exam…
Resident care needs and work stressors in special care units versus non-specialized long-term care units
2006
Differences in how elderly residents' care needs affect staff's experiences of work stressors between special care units (SCUs) for dementia and psychiatric residents and non-SCUs were investigated. The data were drawn from 390 staff members in 38 long-term care SCUs, and 587 staff in 53 non-SCUs in Finland. Residents' care needs were based on the Resident Assessment Instrument (RAI) system measured by the Minimum Data Set 2.0. Work stressors (time-pressure and role-conflicts) were assessed with a staff survey questionnaire. Multiple-group regression analysis showed that residents' dependency in activities of daily living (ADL) was related to increased work stressors only in SCUs. A high pr…
Distribution and categorization of left ventricular measurements in the general population: results from the population-based Gutenberg Heart Study.
2010
Background— Echocardiography, the dominant imaging modality for quantification of left ventricular metrics, has undergone continuing development in the past few decades. However, given the lack of population-based data, current guidelines are still based on restricted and small data sets analyzed with methods including expert opinion. This work presents empirically derived reference values from a large-scale, epidemiologic study conducted with state-of-the-art imaging technology and methods. Methods and Results— The distribution of echocardiographic measurements of the left ventricle was analyzed in a population-based sample of 5000 mid-Europeans from the Gutenberg Heart Study in Germany. …
Predicting maximum annual values of event soil loss by USLE-type models
2017
Abstract Previous experimental investigations showed that a large proportion of total plot soil erosion over a long time period is generally due to relatively few, large storms. Consequently, erosion models able to accurately predict the highest plot soil loss values have practical importance since they could allow to improve the design of soil conservation practices in an area of interest. At present USLE-based models are attractive from a practical point of view, since the input data are generally easy to obtain. The USLE was developed with specific reference to the mean annual temporal scale but it was also applied at the event scale. Other models, such as the USLE-M and the USLE-MM, app…
Contribution to modeling the viscosity Arrhenius-type equation for some solvents by statistical correlations analysis
2014
Abstract Estimation and knowledge of transport properties of fluids are essential for heat and mass flow. Viscosity is one of the important properties which are affected by temperature and pressure. In the present work, based on the use of econometric and statistical techniques for parametric and non-parametric regression analysis and statistical correlation tests, we propose an equation modeling the relationship between the two parameters of viscosity Arrhenius-type equation, such as the Arrhenius energy ( E a ) or the pre-exponential factor ( A s ). In addition, we introduce a third interesting parameter called Arrhenius temperature ( T A ), to enrich the discussion. Empirical validation …
A Multi-layer Feed Forward Neural Network Approach for Diagnosing Diabetes
2018
Diabetes is one of the worlds major health problems according to the World Health Organization. Recent surveys indicate that there is an increase in the number of diabetic patients resulting in an increase in serious complications such as heart attacks and deaths. Early diagnosis of diabetes, particularly of type 2 diabetes, is critical since it is vital for patients to get insulin treatments. However, diagnoses could be difficult especially in areas with few medical doctors. It is, therefore, a need for practical methods for the public for early detection and prevention with minimal intervention from medical professionals. A promising method for automated diagnosis is the use of artificial…
Challenges of automatic processing of large amount of skin lesion multispectral data
2020
This work will describe the challenges involved in setting up automatic processing for a large differentiated data set. In this study, a multispectral (skin diffuse reflection images using 526nm (green), 663nm (red), and 964nm (infrared) illumination and autofluorescence (AF) image using 405 nm excitation) data set with 756 lesions (3024 images) was processed. Previously, using MATLAB software, finding markers, correctly segmenting images with dark edges and image alignment were the main causes of the problems in automatic data processing. To improve automatic processing and eliminate the use of licensed software, the latter was substituted with the open source Python environment. For more …
An optical water type framework for selecting and blending retrievals from bio-optical algorithms in lakes and coastal waters.
2014
Bio-optical models are based on relationships between the spectral remote sensing reflectance and optical properties of in-water constituents. The wavelength range where this information can be exploited changes depending on the water characteristics. In low chlorophyll-a waters, the blue/green region of the spectrum is more sensitive to changes in chlorophyll-a concentration, whereas the red/NIR region becomes more important in turbid and/or eutrophic waters. In this work we present an approach to manage the shift from blue/green ratios to red/NIR-based chlorophyll-a algorithms for optically complex waters. Based on a combined in situ data set of coastal and inland waters, measures of over…
BED: A new dataset for EEG-based biometrics
2021
Various recent research works have focused on the use of electroencephalography (EEG) signals in the field of biometrics. However, advances in this area have somehow been limited by the absence of a common testbed that would make it possible to easily compare the performance of different proposals. In this work, we present a data set that has been specifically designed to allow researchers to attempt new biometric approaches that use EEG signals captured by using relatively inexpensive consumer-grade devices. The proposed data set has been made publicly accessible and can be downloaded from https://doi.org/10.5281/zenodo.4309471 . It contains EEG recordings and responses from 21 individuals…