Predicting Retinal Diseases using Efficient Image Processing and Convolutional Neural Network (CNN)

Neural networks in image processing are becoming a more crucial and integral part of machine learning as computational technology and hardware systems are advanced. Deep learning is also getting attention from the medical sector as it is a prominent process for classifying diseases. There is a lot of research to predict retinal diseases using deep learning algorithms like Convolutional Neural Network (CNN). Still, there are not many researches for predicting diseases like CNV which stands for choroidal neovascularization, DME, which stands for Diabetic Macular Edema; and DRUSEN. In our research paper, the CNN (Convolutional Neural Networks) algorithm labeled the dataset of OCT retinal images into four types: CNV, DME, DRUSEN, and Natural Retina. We have also done several preprocessing on the images before passing these to the neural network. We have implemented different models for our algorithm where individual models have different hidden layers. At the end of our following research, we have found that our algorithm CNN generates 93% accuracy.

The importance of understanding web frameworks for statisticians

As the web and computational technology carry on growing and huge data are yielded on the web, these technologies are turn into important for a statisticians' work. It is worthy that statistician always gain knowledge of new aspects of computation. A lack of computational reasoning skills gets it hard for statisticians to work in a team. If statistician do not take up this computations challenge more coherently, statistics will be marginalized and take away related at a time when its data science reputation grow up significantly. In addition, people rely on the information on web, for whatever their reason.Since web growth, several major transforms have evolved, from the most rudimentary concept until a new model of interaction between humans and machines. Simple interactivity denotes that users can enter data to the application on a web page, then click on button, and then appears a new web page with the results of the computations. This application has been known as web application with most are built with the utility of web frameworks which is a package of programming tasks that offering services through the Internet. Therefore, this paper gives short overview the importance of Flask web frameworks to assist the lack of computational skill of statistician over web application in the simplest possible way and how web framework is used to create a web page with application form, run the application to compute statistical calculation which has been deployed in local server, and produce a web page with the solutions

Processing and visualization of the results of parametric numerical calculations

In modern problems of mathematical modeling in computational gas dynamics, it is increasingly necessary to implement parametric studies. In these cases, the key factors of the problem under consideration vary with the chosen step within the given ranges. Calculations of this kind can be effectively carried out by constructing a generalized computational experiment. A generalized computational experiment is a computational technology that combines the solution of mathematical modeling problems, parallel technologies, and visual analytics technologies. The results of a generalized computational experiment are multidimensional arrays, where the dimension of the arrays corresponds to the number of key factors. Processing and visual presentation of such arrays requires solving a number of separate tasks. The processing and visual presentation of the results are carried out for target functionals represented as a function of many variables. The report presents an examples of solving specific processing and visualization problems based on the implemented generalized computational experiment for 3D cone in supersonic flow.

Aggregated criterion for estimating the efficiency of functioning of sections of the Ulan-Bator railway

В статье рассматривается проблема разработки (формирования) функции эффективности (агрегированного критерия, свертки критериев) входящих в состав Улан-Баторской железной дороги (УБЖД) участков, которая содержала бы специальным образом взвешенные частные характеристики качества функционирования этих участков. Решение этой проблемы осуществляется на основе разработанной в Иркутском государственном университете путей сообщения информационно-вычислительной технологии (ИВТ) многокритериального оценивания эффективности функционирования сложных социально-экономических и технических систем. ИВТ позволяет на модельном уровне оценивать эту эффективность одним числом (выраженным, например, в процентах), что открывает широкие возможности в управлении этими системами, поскольку позволяет выполнять, в частности, масштабный многофакторный сравнительный анализ деятельности однородных организационных и других структур и принимать на этой основе решения самого различного характера. Построена функция эффективности функционирования участков УБЖД, включающая в свой состав взвешенные частные индикаторы такой эффективности: погрузка, статическая нагрузка, выгрузка, отправление вагонов, перевозка пассажиров, простои вагонов с одной переработкой, простои местных вагонов, простои транзитных вагонов с переработкой, простои транзитных вагонов без переработки. На основе этой функции рассчитана масштабированная на сто процентов эффективность каждого участка. При этом все показатели предпочтения упорядочены по убыванию значимости. Подобная информация, формируемая с годичной периодичностью, может быть весьма полезна руководству УБЖД для принятия широкого спектра управленческих, в том числе кадровых, решений. Аналогичная работа может быть выполнена в интересах РАО РЖД. The article discusses the problem of developing (forming) an efficiency function (aggregated criterion, convolution of criteria) of the sections included in the Ulan Bator Railway (UBZhD), which would contain specially weighted private characteristics of the quality of the functioning of these sections. The solution to this problem is carried out on the basis of the information and computational technology (ICT) developed at the Irkutsk State University of communication lines for multi-criteria assessment of the effectiveness of the functioning of complex socio-economic and technical systems. IWT makes it possible at the model level to evaluate this efficiency by one number (expressed, for example, as a percentage), which opens up ample opportunities in the management of these systems, since it allows performing, in particular, a large-scale multifactorial comparative analysis of the activities of homogeneous organizational and other structures and on this basis solutions of the most varied nature. The function of the effectiveness of the functioning of the UBZhD sections has been built, which includes weighted private indicators of such efficiency: loading, static load, unloading, dispatch of cars, transportation of passengers, idle time of cars with one processing, idle time of local cars, idle time of transit cars with processing, idle time of transit cars without processing. Based on this function, a 100% scaled efficiency is calculated for each site. Moreover, all preference indicators are sorted in descending order of importance. Such information, generated on a yearly basis, can be very useful to the UBZhD leadership for making a wide range of managerial, including personnel, decisions. Similar work can be performed in the interests of RAO Russian Railways.

Less Known Results on the Solar System

For a two half millennium evolution of knowledge from the Democrit’s natural, rational atomized material conception to the Newtonian, Maxwellian, Einsteinian mathematized physics, the research in the most cases has followed a deductive route from observable facts/reality according to the Mach’s rigorous positivism principle. During the last century both experimental and computational technology progress has accumulated a solid factual datum support on the better knowledge of our actual world, so that the research is beginning on inductive route of the hidden/dark detailed processes as a whole. This revolutionary stage of physics, based on a holistic integral approach, is concerned with the relativity-gravity evolution in a quantifiable space-time universe created after the morphogenetic light explosion (or the 4D-BIG BANG). The paper presented herein contains some less known aspects on the work of solar system as a whole, along with the specific activity of the Earth-planet as a part integrated into the solar complex.

Comprehensive Analysis of State-of-the-Art CAD Tools and Technique for Chronic Kidney Disease (CKD)

It has been seen that in the last one decade, AI/ML/DL has been considered a core research area in healthcare as we know that kidney is one among the important internal body organs helps in regulation of the fluid within the body such that it relieves the body from the existence of the waste in the body. it is difficult to detect early on by normal clinical process. Many researchers have focused their work to identify the kidney disease or classify the kidney disease using computational technology because of the mortality rate is very high in kidney patients. Primary focus of this paper is review the current research work based on computational advancement in the area of kidney disease and also identify the gaps or future scope to identify and predict the kidney disease at earlier stage.

A Utilização de Softwares no Ensino e Aprendizagem dos Cursos de Engenharia

ResumoO estudo aqui exposto é parte de uma pesquisa de mestrado em andamento desenvolvida no Programa de Pós-Graduação Stricto Sensu em Metodologias para o Ensino de Linguagens e suas Tecnologias. Trata-se de uma investigação que tem o propósito de retratar a pesquisa acadêmica encontrada no repositório de publicações da Associação Brasileira de Ensino em Engenharia – ABENGE –. Para a realização desta pesquisa bibliográfica buscou-se no repositório. os artigos publicados em um período de 12 anos – a partir de 2006 até 2018. Selecionou-se publicações que tiveram como foco a utilização de softwares para desenvolver processos de ensino e de aprendizagem de disciplinas de cursos de engenharia. Dos 397 artigos encontrados, 25 foram selecionados como instrumento de análise para esta pesquisa, dos quais, 14 deles foram publicados em 2017 e 2018. Analisando as tais publicações, pôde concluir que o método qualitativo se sobressaiu acima do quantitativo e quali-quanti, e ainda 44% dos artigos se basearam em questionários, avaliações ou entrevistas, seguidos de 40% de pesquisas bibliográficas. No tocante aos resultados foi possível identificar que quase a totalidade dos estudos concluiu que a utilização de diferentes metodologias, dentre elas softwares para o ensino, é fundamental para a inserção do futuro engenheiro ao mercado atual. Palavras-chave: Ensino de Engenharia. Processos de Ensino e de Aprendizagem. Tecnologia Computacional. AbstractThe study here presented is part of an ongoing master's research developed at the Stricto Sensu Postgraduate Program in Methodologies for Language Teaching and its Technologies. It is an investigation that has the purpose of portraying the academic research found in the repository of publications of the Brazilian Association of Engineering Teaching - ABENGE. In order to carry out this bibliographical research, the repository was searched for articles published over a period of 12 years - from 2006 to 2018. Publications that focused on the use of software to develop teaching and learning processes for engineering courses were selected. Of the 397 articles found, 25 were selected as analysis tools for this research, 14 of which were published in 2017 and 2018. Analyzing these publications, it was possible to conclude that the qualitative method stood out above the quantitative and quali-quantitative methods, and 44% of the articles were based on questionnaires, evaluations or interviews, followed by 40% of bibliographical research. Regarding the results, it was possible to identify that almost all the studies concluded that the use of different methodologies, including software for teaching, is fundamental for the insertion of the future engineer in the current market. Keyword: Engineering Education. Teaching and Learning Processes. Computational Technology.

Designing a tangible tabletop installation and enacting a socioenactive experience with TangiTime

Contemporary computational technology (tangible and ubiquitous) are still challenging the mainstream systems design methods, demanding new ways of considering the interaction design and its evaluation. In this work, we draw on concepts of enactivism and enactive systems to investigate interaction and experience in the context of the ubiquity of computational systems. Our study is illustrated with the design and usage experience of TangiTime: a tangible tabletop system proposed for an educational exhibit. TangiTime was designed to enable a socioenactive experience of interaction with the concept of “deep time.” In this paper, we present the TangiTime design process, the artifacts designed and implemented, in its conceptual, interactional, and architectural aspects. Besides that, we present and discuss results of an exploratory study within an exhibition context, to observe how socioenactive aspects of the experience potentially emerge from the interaction. Overall, the paper contributes with elements of design that should be considered when designing a socioenactive experience in environments constituted by contemporary computational technology.

Digital/Computational Technology for Molecular Cytology Testing: A Short Technical Note with Literature Review

This short article describes the method of digital cytopathology using Z-stack scanning with or without extended focusing. This technology is suitable to observe such thick clusters as adenocarcinoma on cytologic specimens. Artificial intelligence (AI) has been applied to histological images, but its application on cytologic images is still limited. This article describes our attempt to apply AI technology to cytologic digital images. For molecular analysis, cytologic materials, such as smear, LBC, and cell blocks, have been successfully used for targeted single gene detection and multiplex gene analysis with next-generation sequencing. As a future perspective, the system can be connected to full automation by combining digital cytopathology with AI application to detect target cancer cells and to perform molecular analysis. The literature review is updated according to the subjects.