scholarly journals On Biomedical Computations in Cluster and Cloud Environment

2021 ◽  
pp. 76-84
Author(s):  
Tamara Bardadym ◽  
Vasyl Gorbachuk ◽  
Natalia Novoselova ◽  
Sergiy Osypenko ◽  
Vadim Skobtsov ◽  
...  
Keyword(s):  
Numerical Experiments ◽  
Complex Diseases ◽  
Real Data ◽  
Software Tools ◽  
Classification Model ◽  
Biomedical Data ◽  
Cloud Environment ◽  
Hybrid Classification ◽  
Analytical System ◽  
Modern Technologies

Introduction. This publication summarizes the experience of the use of applied containerized software tools in cloud environment, which the authors gained during the project “Development of methods, algorithms and intellectual analytical system for processing and analysis of heterogeneous clinical and biomedical data in order to improve the diagnosis of complex diseases”, accomplished by the team from the United Institute of Informatics Problems of the NAS of Belarus and V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine. In parallel, the features of biomedical data and the main approaches to their processing and classification, implemented within the framework of an intelligent analytical system, and the possibility of their implementation as part of a container application are described. The purpose of the paper is to describe modern technologies that ensure the reproducibility of numerical experiments in this field and the tools aimed to integrate several sources of biomedical information in order to improve the diagnostics and prognosis of complex diseases. Special attention is also paid to the methods of handling data received from different sources of biomedical information. Particular attention is paid to methods of processing data obtained from various sources of biomedical information and included to the intelligent analytical system. Results. The experience of the use of applied containerized biomedical software tools in cloud environment is summarized. The reproducibility of scientific computing in relation with modern technologies of scientific calculations is discussed. The main approaches to biomedical data preprocessing and integration in the framework of the intelligent analytical system are described. The developed hybrid classification model presents the basis of the intelligent analytical system and aims to integrate several sources of biomedical information. Conclusions. The experience of using the developed classification module NonSmoothSVC, which is part of the developed intelligent analytical system, gained during its testing on artificial and real data, allows us to conclude about several advantages provided by the containerized form of the created application. Namely: • It permits to provide access to real data located in cloud environment, • It is possible to perform calculations to solve research problems on cloud resources both with the help of developed tools and with the help of cloud services, • Such a form of research organization makes numerical experiments reproducible, i.e. any other researcher can compare the results of their developments on specific data that have already been studied by others, in order to verify the conclusions and technical feasibility of new results, • There exists a universal opportunity to use the developed tools on technical devices of various classes from a personal computer to powerful cluster. The hybrid classification model as a core of the intelligent system will make it possible to integrate multidimensional, heterogeneous biomedical data with the aim to better understand the molecular courses of disease origin and development, to improve the identification of disease subtypes and disease prognosis. Keywords: classifier, cloud service, containerized application, heterogeneous biomedical data

Intelligent analytical system as a tool to ensure the reproducibility of biomedical calculations

2020 ◽  
Vol 25 (3) ◽  
pp. 65-78
Author(s):  
Bardadym T.O. ◽  
◽  
Gorbachuk V.M. ◽  
Novoselova N.A. ◽  
Osypenko C.P. ◽  
...  
Keyword(s):  
Health Care ◽  
Real Data ◽  
Data Preprocessing ◽  
Demographic Variables ◽  
Biomedical Data ◽  
Cloud Environment ◽  
National Academy Of Sciences ◽  
Analytical System ◽  
Academy Of Sciences ◽  
Modern Technologies

The experience of the use of applied containerized biomedical software tools in cloud environment is summarized. The reproducibility of scientific computing in relation with modern technologies of scientific calculations is discussed. The main approaches to biomedical data preprocessing and integration in the framework of the intelligent analytical system are described. At the conditions of pandemic, the success of health care system depends significantly on the regular implementation of effective research tools and population monitoring. The earlier the risks of disease can be identified, the more effective process of preventive measures or treatments can be. This publication is about the creation of a prototype for such a tool within the project «Development of methods, algorithms and intelligent analytical system for processing and analysis of heterogeneous clinical and biomedical data to improve the diagnosis of complex diseases» (M/99-2019, M/37-2020 with support of the Ministry of Education and Science of Ukraine), implementted by the V.M. Glushkov Institute of Cybernetics, National Academy of Sciences of Ukraine, together with the United Institute of Informatics Problems, National Academy of Sciences of Belarus (F19UKRG-005 with support of the Belarussian Republican Foundation for Fundamental Research). The insurers, entering the market, can insure mostly low risks by facilitating more frequent changes of insurers by consumers (policyholders) and mixing the overall health insurance market. Socio-demographic variables can be risk adjusters. Since age and gender have a relatively small explanatory power, other socio-demographic variables were studied – marital status, retirement status, disability status, educational level, income level. Because insurers have an interest in beneficial diagnoses for their policyholders, they are also interested in the ability to interpret relevant information – upcoding: insurers can encourage their policyholders to consult with doctors more often to select as many diagnoses as possible. Many countries and health care systems use diagnostic information to determine the reimbursement to a service provider, revealing the necessary data. For processing and analysis of these data, software implementations of construction for classifiers, allocation of informative features, processing of heterogeneous medical and biological variables for carrying out scientific research in the field of clinical medicine are developed. The experience of the use of applied containerized biomedical software tools in cloud environment is summarized. The reproducibility of scientific computing in relation with modern technologies of scientific calculations is discussed. Particularly, attention is paid to containerization of biomedical applications (Docker, Singularity containerization technology), this permits to get reproducibility of the conditions in which the calculations took place (invariability of software including software and libraries), technologies of software pipelining of calculations, that allows to organize flow calculations, and technologies for parameterization of software environment, that allows to reproduce, if necessary, an identical computing environment. The main approaches to biomedical data preprocessing and integration in the framework of the intelligent analytical system are described. The experience of using the developed linear classifier, gained during its testing on artificial and real data, allows us to conclude about several advantages provided by the containerized form of the created application: it permits to provide access to real data located in cloud environment; it is possible to perform calculations to solve research problems on cloud resources both with the help of developed tools and with the help of cloud services; such a form of research organization makes numerical experiments reproducible, i.e. any other researcher can compare the results of their developments on specific data that have already been studied by others, in order to verify the conclusions and technical feasibility of new results; there exists a universal opportunity to use the developed tools on technical devices of various classes from a personal computer to powerful cluster.

Petrophysical Facies Classification Based on Fuzzy Inference Networks

2013 ◽  
Vol 634-638 ◽  
pp. 4017-4021
Author(s):  
Jun Hui Pan ◽  
Hui Wang ◽  
Xiao Gang Yang
Keyword(s):  
Fuzzy Inference ◽  
Fuzzy Reasoning ◽  
Real Data ◽  
Analysis Data ◽  
Classification Model ◽  
Core Analysis ◽  
Development Zone ◽  
The Real ◽  
Facies Classification ◽  
Quantitative Indicators

Aiming at the petrophysical facies recognition, a novel identification method based on the weighted fuzzy reasoning networks is proposed in the paper. First, the types and indicators are obtained from core analysis data and the results given by experts, and then the standard patterning database of reservoir petrophysical facies is established. Secondly, by integrating expert experiences and quantitative indicators to reflect the change of petrophysical facies, the classification model of petrophysical facies based on the weighted fuzzy reasoning networks is designed. The preferable application results are presented by processing the real data from the Sabei development zone of Daqing oilfield.

scholarly journals Photovoltaic Prediction Software: Evaluation with Real Data from Northern Spain

2021 ◽  
Vol 11 (11) ◽  
pp. 5025
Author(s):  
David González-Peña ◽  
Ignacio García-Ruiz ◽  
Montserrat Díez-Mediavilla ◽  
Mª. Isabel Dieste-Velasco ◽  
Cristina Alonso-Tristán
Keyword(s):  
Energy Production ◽  
Field Data ◽  
Real Data ◽  
Software Tools ◽  
Horizontal Axis ◽  
Real Field ◽  
Tracking Systems ◽  
Northern Spain ◽  
Commercial Software ◽  
Solar Tracking

Prediction of energy production is crucial for the design and installation of PV plants. In this study, five free and commercial software tools to predict photovoltaic energy production are evaluated: RETScreen, Solar Advisor Model (SAM), PVGIS, PVSyst, and PV*SOL. The evaluation involves a comparison of monthly and annually predicted data on energy supplied to the national grid with real field data collected from three real PV plants. All the systems, located in Castile and Leon (Spain), have three different tilting systems: fixed mounting, horizontal-axis tracking, and dual-axis tracking. The last 12 years of operating data, from 2008 to 2020, are used in the evaluation. Although the commercial software tools were easier to use and their installations could be described in detail, their results were not appreciably superior. In annual global terms, the results hid poor estimations throughout the year, where overestimations were compensated by underestimated results. This fact was reflected in the monthly results: the software yielded overestimates during the colder months, while the models showed better estimates during the warmer months. In most studies, the deviation was below 10% when the annual results were analyzed. The accuracy of the software was also reduced when the complexity of the dual-axis solar tracking systems replaced the fixed installation.

scholarly journals Hybrid classification model to detect advanced intrusions using data mining techniques

2018 ◽  
Vol 7 (2.4) ◽  
pp. 10
Author(s):  
V Mala ◽  
K Meena
Keyword(s):  
Data Mining ◽  
Learning Algorithm ◽  
Detection System ◽  
Classification Model ◽  
Detection Methods ◽  
Data Mining Techniques ◽  
Detection Systems ◽  
Intruder Detection ◽  
Hybrid Classification ◽  
Using Data

Traditional signature based approach fails in detecting advanced malwares like stuxnet, flame, duqu etc. Signature based comparison and correlation are not up to the mark in detecting such attacks. Hence, there is crucial to detect these kinds of attacks as early as possible. In this research, a novel data mining based approach were applied to detect such attacks. The main innovation lies on Misuse signature detection systems based on supervised learning algorithm. In learning phase, labeled examples of network packets systems calls are (gave) provided, on or after which algorithm can learn about the attack which is fast and reliable to known. In order to detect advanced attacks, unsupervised learning methodologies were employed to detect the presence of zero day/ new attacks. The main objective is to review, different intruder detection methods. To study the role of Data Mining techniques used in intruder detection system. Hybrid –classification model is utilized to detect advanced attacks.

scholarly journals Stiffness Analysis to Predict the Spread Out of Fake Information

2021 ◽  
Vol 13 (9) ◽  
pp. 222
Author(s):  
Raffaele D'Ambrosio ◽  
Giuseppe Giordano ◽  
Serena Mottola ◽  
Beatrice Paternoster
Keyword(s):  
Numerical Experiments ◽  
Real Data ◽  
Sir Model ◽  
Stiffness Index ◽  
Fake News ◽  
Stiffness Analysis ◽  
Data Support

This work highlights how the stiffness index, which is often used as a measure of stiffness for differential problems, can be employed to model the spread of fake news. In particular, we show that the higher the stiffness index is, the more rapid the transit of fake news in a given population. The illustration of our idea is presented through the stiffness analysis of the classical SIR model, commonly used to model the spread of epidemics in a given population. Numerical experiments, performed on real data, support the effectiveness of the approach.

scholarly journals Nonlinear Dynamics Identification of the Oculo-Motor System based on Eye Tracking Data

2021 ◽  
Vol 15 ◽  
pp. 569-577
Author(s):  
Vitaliy Pavlenko ◽  
Tetiana Shamanina ◽  
Vladislav Chori
Keyword(s):  
Eye Tracking ◽  
Motor System ◽  
Real Data ◽  
Software Tools ◽  
Volterra Model ◽  
Innovative Technology ◽  
Tracking Data ◽  
Nonlinear Dynamic Model ◽  
Nonlinear Properties ◽  
Dynamics Identification

Instrumental computing and software tools have been developed for constructing a nonlinear dynamic model of the human oculo-motor system (OMS) based on the data of input–output experiments using test visual stimuli and innovative technology eye tracking. For identification the Volterra model is used in the form of multidimensional transient functions of the 1st, 2nd and 3rd orders, taking into account the inertial and nonlinear properties of the OMS. Software tools for processing eye tracking data developed in the Matlab environment are tested on real data from an experimental study of OMS.

scholarly journals A Novel Approach of CT Images Feature Analysis and Prediction to Screen for Corona Virus Disease (COVID-19)

2020 ◽  
Author(s):  
Ahmed Abdullah Farid ◽  
Gamal Ibrahim Selim ◽  
Hatem Awad A. Khater
Keyword(s):  
Feature Extraction ◽  
Virus Disease ◽  
Real Data ◽  
Ct Images ◽  
Learning Tools ◽  
Corona Virus ◽  
Novel Approach ◽  
Hybrid Classification ◽  
Hybrid Feature Extraction ◽  
First Time

The paper demonstrates the analysis of Corona Virus Disease based on a probabilistic model. It involves a technique for classification and prediction by recognizing typical and diagnostically most important CT images features relating to Corona Virus. The main contributions of the research include predicting the probability of recurrences in no recurrence (first time detection) cases at applying our proposed approach for feature extraction. The combination of the conventional statistical and machine learning tools is applied for feature extraction from CT images through four images filters in combination with proposed composite hybrid feature extraction (CHFS). The selected features were classified by the stack hybrid classification system(SHC). Experimental study with real data demonstrates the feasibility and potential of the proposed approach for the said cause.

Quality of Life Modeling at the Regional Level

2012 ◽  
pp. 163-186
Author(s):  
Jirí Krupka ◽  
Miloslava Kašparová ◽  
Pavel Jirava ◽  
Jan Mandys
Keyword(s):  
Quality Of Life ◽  
Czech Republic ◽  
Decision Tree ◽  
Decision Rules ◽  
Real Data ◽  
Classification Model ◽  
Data Sets ◽  
The Czech Republic ◽  
First Case

The chapter presents the problem of quality of life modeling in the Czech Republic based on classification methods. It concerns a comparison of methodological approaches; in the first case the approach of the Institute of Sociology of the Academy of Sciences of the Czech Republic was used, the second case is concerning a project of the civic association Team Initiative for Local Sustainable Development. On the basis of real data sets from the institute and team initiative the authors synthesized and analyzed quality of life classification models. They used decision tree classification algorithms for generating transparent decision rules and compare the classification results of decision tree. The classifier models on the basis of C5.0, CHAID, C&RT and C5.0 boosting algorithms were proposed and analyzed. The designed classification model was created in Clementine.

Sign in / Sign up

Export Citation Format

Share Document