Extraction of numerical data from ophthalomological images and building a glaucoma prediction model

Real-time neural network based predictor for cov19 virus spread

PLoS ONE ◽

10.1371/journal.pone.0243189 ◽

2020 ◽

Vol 15 (12) ◽

pp. e0243189

Author(s):

Michał Wieczorek ◽

Jakub Siłka ◽

Dawid Połap ◽

Marcin Woźniak ◽

Robertas Damaševičius

Keyword(s):

Prediction Model ◽

Real Time ◽

Prediction Models ◽

Numerical Data ◽

Real Data ◽

Future Trend ◽

World Health ◽

Number Of Patients ◽

The World ◽

Health Organization

Since the epidemic outbreak in early months of 2020 the spread of COVID-19 has grown rapidly in most countries and regions across the World. Because of that, SARS-CoV-2 was declared as a Public Health Emergency of International Concern (PHEIC) on January 30, 2020, by The World Health Organization (WHO). That’s why many scientists are working on new methods to reduce further growth of new cases and, by intelligent patients allocation, reduce number of patients per doctor, what can lead to more successful treatments. However to properly manage the COVID-19 spread there is a need for real-time prediction models which can reliably support various decisions both at national and international level. The problem in developing such system is the lack of general knowledge how the virus spreads and what would be the number of cases each day. Therefore prediction model must be able to conclude the situation from past data in the way that results will show a future trend and will possibly closely relate to the real numbers. In our opinion Artificial Intelligence gives a possibility to do it. In this article we present a model which can work as a part of an online system as a real-time predictor to help in estimation of COVID-19 spread. This prediction model is developed using Artificial Neural Networks (ANN) to estimate the future situation by the use of geo-location and numerical data from past 2 weeks. The results of our model are confirmed by comparing them with real data and, during our research the model was correctly predicting the trend and very closely matching the numbers of new cases in each day.

Download Full-text

A Critical Re-analysis of the Series 64 Performance Data

10.5957/fast-2015-015 ◽

2015 ◽

Author(s):

Donald MacPherson

Keyword(s):

Prediction Model ◽

High Speed ◽

Original Work ◽

Numerical Data ◽

Computational Prediction ◽

Test Results ◽

Data Set ◽

Family Of Curves ◽

Resistance Prediction ◽

Hull Forms

The Series 64 has been an oft-cited resource for the resistance prediction of high-speed transom-stern round-bilge hull forms since publication of Yeh’s paper (1965). Its range of parameters is extensive, making it one of only a few sets of test data for long and slender hulls. In the course of this author’s planned development of a computational prediction model based on the Series 64 data, significant outliers in the expected series family of curves were revealed and it became evident that there were inconsistencies in the relative relationships between hulls in the series. This prompted a re-analysis of the series to identify potentially erroneous test results and conclusions in the original work, so as to remove them from the numerical data set for a proposed computational model.

Download Full-text

The mensuration of interfaces

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s042482010012148x ◽

1992 ◽

Vol 50 (1) ◽

pp. 216-217

Author(s):

W.M. Stobbs

Keyword(s):

Electron Microscopy ◽

50Th Anniversary ◽

Numerical Data ◽

Industrial Applications ◽

Dynamical Theory ◽

Large Strains ◽

Reasonable Approach ◽

Lattice Resolution ◽

Analogue To Digital ◽

The Way

I do not have access to the abstracts of the first meeting of EMSA but at this, the 50th Anniversary meeting of the Electron Microscopy Society of America, I have an excuse to consider the historical origins of the approaches we take to the use of electron microscopy for the characterisation of materials. I have myself been actively involved in the use of TEM for the characterisation of heterogeneities for little more than half of that period. My own view is that it was between the 3rd International Meeting at London, and the 1956 Stockholm meeting, the first of the European series , that the foundations of the approaches we now take to the characterisation of a material using the TEM were laid down. (This was 10 years before I took dynamical theory to be etched in stone.) It was at the 1956 meeting that Menter showed lattice resolution images of sodium faujasite and Hirsch, Home and Whelan showed images of dislocations in the XlVth session on “metallography and other industrial applications”. I have always incidentally been delighted by the way the latter authors misinterpreted astonishingly clear thickness fringes in a beaten (”) foil of Al as being contrast due to “large strains”, an error which they corrected with admirable rapidity as the theory developed. At the London meeting the research described covered a broad range of approaches, including many that are only now being rediscovered as worth further effort: however such is the power of “the image” to persuade that the above two papers set trends which influence, perhaps too strongly, the approaches we take now. Menter was clear that the way the planes in his image tended to be curved was associated with the imaging conditions rather than with lattice strains, and yet it now seems to be common practice to assume that the dots in an “atomic resolution image” can faithfully represent the variations in atomic spacing at a localised defect. Even when the more reasonable approach is taken of matching the image details with a computed simulation for an assumed model, the non-uniqueness of the interpreted fit seems to be rather rarely appreciated. Hirsch et al., on the other hand, made a point of using their images to get numerical data on characteristics of the specimen they examined, such as its dislocation density, which would not be expected to be influenced by uncertainties in the contrast. Nonetheless the trends were set with microscope manufacturers producing higher and higher resolution microscopes, while the blind faith of the users in the image produced as being a near directly interpretable representation of reality seems to have increased rather than been generally questioned. But if we want to test structural models we need numbers and it is the analogue to digital conversion of the information in the image which is required.

Download Full-text

The Added Value of Graphical Input and Display for Electron Lens Design

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100179701 ◽

1990 ◽

Vol 48 (1) ◽

pp. 190-191

Author(s):

B. Lencova ◽

G. Wisselink

Keyword(s):

Flux Density ◽

Numerical Data ◽

Added Value ◽

Lens Design ◽

Step Size ◽

Magnetic Lens ◽

Flux Lines ◽

Fine Mesh ◽

Electron Lens ◽

User Friendly

Recent progress in computer technology enables the calculation of lens fields and focal properties on commonly available computers such as IBM ATs. If we add to this the use of graphics, we greatly increase the applicability of design programs for electron lenses. Most programs for field computation are based on the finite element method (FEM). They are written in Fortran 77, so that they are easily transferred from PCs to larger machines.The design process has recently been made significantly more user friendly by adding input programs written in Turbo Pascal, which allows a flexible implementation of computer graphics. The input programs have not only menu driven input and modification of numerical data, but also graphics editing of the data. The input programs create files which are subsequently read by the Fortran programs. From the main menu of our magnetic lens design program, further options are chosen by using function keys or numbers. Some options (lens initialization and setting, fine mesh, current densities, etc.) open other menus where computation parameters can be set or numerical data can be entered with the help of a simple line editor. The "draw lens" option enables graphical editing of the mesh - see fig. I. The geometry of the electron lens is specified in terms of coordinates and indices of a coarse quadrilateral mesh. In this mesh, the fine mesh with smoothly changing step size is calculated by an automeshing procedure. The options shown in fig. 1 allow modification of the number of coarse mesh lines, change of coordinates of mesh points or lines, and specification of lens parts. Interactive and graphical modification of the fine mesh can be called from the fine mesh menu. Finally, the lens computation can be called. Our FEM program allows up to 8000 mesh points on an AT computer. Another menu allows the display of computed results stored in output files and graphical display of axial flux density, flux density in magnetic parts, and the flux lines in magnetic lenses - see fig. 2. A series of several lens excitations with user specified or default magnetization curves can be calculated and displayed in one session.

Download Full-text