DEVELOPMENT OF AN EXPERT SYSTEM FOR DIAGNOSTICS OF LUNG DISEASES BASED ON NEURAL NETWORK MODELING

2021 ◽  
pp. 155-159
Author(s):  
Екатерина Ивановна Новикова ◽  
Екатерина Александровна Андрианова ◽  
Елена Евгеньевна Удодова ◽  
Анастасия Юрьевна Корниенко ◽  
Александр Станиславович Панов
Keyword(s):  
Neural Network ◽  
Lung Diseases ◽  
Network Models ◽  
The Body ◽  
Neural Network Modeling ◽  
Diagnostic Study ◽  
Topological Groups ◽  
Social Significance ◽  
Neural Network Models ◽  
Information Process

В статье рассматриваются вопросы диагностики заболеваний легких, таких как кавернозный, инфильтративный, очаговой, диссеминированный туберкулез, онкология и пневмония. Медико-социальное значение болезней органов дыхания в современных условиях велико и определяется, прежде всего, их крайне высокой частотой среди различных контингентов населения. Учитывая значимость дыхания для организма, необходимо вовремя выявлять различные патологии и применять незамедлительные меры лечения. Одним из средств повышения эффективности диагностики данных патологий является автоматизация обработки диагностических данных с использованием современных технологий, а также создание компьютерной системы поддержки принятия решений, которая принимала бы во внимание большой объем диагностической информации и исключала ошибки субъективного характера. Выделение топологических групп по легочным заболеваниям проводилось с использованием самоорганизующихся карт Кохонена. По результатам классификации было проведено обучения нейронных сетей, используя алгоритм «многослойного персептрона» методом «обратного распространения», и получены математические модели. В медицинской практике постоянно следует учитывать то обстоятельство, что достоверные и адекватные медицинские данные, например, лабораторные анализы, результаты инструментального диагностического исследования, данные опроса больного или физикального исследования, потеряют свою актуальность, если информационный процесс длительно растянут по времени. Разработанные нейросетевые модели, были реализованы в информационно-программном обеспечении, которое позволит повысить эффективность процесса диагностики заболеваний легких The article deals with the diagnosis of lung diseases such as cavernous, infiltrative, focal, disseminated tuberculosis, oncology and pneumonia. The medical and social significance of respiratory diseases in modern conditions is great and is determined, first of all, by their extremely high frequency among various contingents of the population. Given the importance of breathing for the body, it is necessary to timely identify various pathologies and apply immediate treatment measures. One of the means of increasing the efficiency of diagnosing these pathologies is the automation of the processing of diagnostic data using modern technologies, as well as the creation of a computer decision support system that would take into account a large amount of diagnostic information and exclude subjective errors. The selection of topological groups for pulmonary diseases was carried out using self-organizing Kohonen maps. Based on the classification results, neural networks were trained using the "multilayer perceptron" algorithm by the "backpropagation" method and mathematical models were obtained. In medical practice, one should constantly take into account the fact that reliable and adequate medical data, for example, laboratory tests, the results of an instrumental diagnostic study, data from a patient survey or physical examination, will lose their relevance if the information process is prolonged for a long time. The developed neural network models were implemented in information and software that will improve the efficiency of the process of diagnosing lung diseases

scholarly journals Artificial neural network modeling of jatropha oil fueled diesel engine for emission predictions

2009 ◽  
Vol 13 (3) ◽  
pp. 91-102 ◽  
Author(s):  
Thirunavukkarasu Ganapathy ◽  
Parkash Gakkhar ◽  
Krishnan Murugesan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Models ◽  
Neural Network Modeling ◽  
Data Sets ◽  
Nox Emissions ◽  
Jatropha Oil ◽  
Neural Network Models ◽  
Artificial Neural ◽  
Artificial Neural Network Models

This paper deals with artificial neural network modeling of diesel engine fueled with jatropha oil to predict the unburned hydrocarbons, smoke, and NOx emissions. The experimental data from the literature have been used as the data base for the proposed neural network model development. For training the networks, the injection timing, injector opening pressure, plunger diameter, and engine load are used as the input layer. The outputs are hydrocarbons, smoke, and NOx emissions. The feed forward back propagation learning algorithms with two hidden layers are used in the networks. For each output a different network is developed with required topology. The artificial neural network models for hydrocarbons, smoke, and NOx emissions gave R2 values of 0.9976, 0.9976, and 0.9984 and mean percent errors of smaller than 2.7603, 4.9524, and 3.1136, respectively, for training data sets, while the R2 values of 0.9904, 0.9904, and 0.9942, and mean percent errors of smaller than 6.5557, 6.1072, and 4.4682, respectively, for testing data sets. The best linear fit of regression to the artificial neural network models of hydrocarbons, smoke, and NOx emissions gave the correlation coefficient values of 0.98, 0.995, and 0.997, respectively.

Neural network modeling of carcass measurements to predict beef tenderness

2000 ◽  
Vol 80 (2) ◽  
pp. 311-318 ◽  
Author(s):  
B. D. Hill ◽  
S. D. M. Jones ◽  
W. M. Robertson ◽  
I. T. Major
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Large Data ◽  
Research Centre ◽  
Neural Network Modeling ◽  
Marbling Score ◽  
Neural Network Models ◽  
Cooking Method ◽  
Beef Tenderness ◽  
Plant Weight

Neural network (NN) models were developed for predicting and classifying an objective measurement of tenderness using carcass data such as pre-slaughter information (sex, age, kill order), weights, pH, temperatures, lean color readings, lab-determined measurements, grade measurements and organ weights. Tenderness was expressed objectively as Warner-Bratzler shear (WBS) force measured on steaks, aged 6 d, from the longissimus thoracis et lumborum (LTL) muscle. Carcass data from experiments conducted between 1985 and 1995 at the Lacombe Research Centre were combined to form large data sets (n = 775–1177) for modeling. Neural network models to predict actual shear values showed limited potential (R2 = 0.37–0.45) and were only marginally better than a multiple linear regression (MLR) model (R2 = 0.34). Neural network models that classified carcasses into tenderness categories showed better potential (mean accuracy 51–53%). The best four-category (tender, probably tender, probably tough, tough) model classified tender and tough steaks with accuracies of 0.64 and 0.79, respectively. This model reduced tough and probably tough carcasses by 55% in our population. The model required the following 11 inputs, which, except for cooking method, are available by 24 h postmortem: sex, live plant weight, hot carcass weight, 24-h cooler shrink, 24-h pH, 24-h CIE color b*, 24-h CIE lightness L* × hue angle, rib eye area, grader's marbling score (AMSA%), grade, and cooking method. By implementing techniques outlined in this study in a plant situation, the current 23% unacceptable consumer rating for Canadian beef could be reduced to 10–12%. Key words: Neural networks, beef, tenderness, carcass measurements, longissimus muscle

Fine Pitch Stencil Printing Process Modeling and Optimization

1996 ◽  
Vol 118 (1) ◽  
pp. 1-6 ◽  
Author(s):  
Y. Li ◽  
R. L. Mahajan ◽  
N. Nikmanesh
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Design Parameters ◽  
Neural Network Modeling ◽  
Solder Paste ◽  
Neural Network Models ◽  
Height Variation ◽  
Stencil Printing ◽  
Fine Pitch ◽  
Gradient Descent Algorithm

In this paper, we present a statistical-neural network modeling approach to process optimization of fine pitch stencil printing for solder paste deposition on pads of printed circuit boards (PCB). The overall objective was to determine the optimum settings of the design parameters that would result in minimum solder paste height variation for the new board designs with 20-mil, 25-mil, and 50-mil pitch pad patterns. As a first step, a Taguchi orthogonal array, L27, was designed to capture the main effects of the six important printing machinery parameters and the PCBs pad conditions. Some of their interactions were also included. Fifty-four experimental runs (two per setting) were conducted. These data were then used to construct neural network models relating the desired quality characteristics to the input design parameters. Our modular approach was used to select the appropriate architecture for these models. These models in conjunction with the gradient descent algorithm enabled us to determine the optimum settings for minimum solder paste height variation. Confirming experiments on the production line validated the optimum settings predicted by the model. In addition to the combination of all the three pad patterns, i.e., 20, 25, and 50 mil pitch pads, we also built neural network models for individual and dual combinations of the three pad patterns. The simulations indicate different optimum settings for different pad pattern combinations.

Neural Network Modeling for Face Milling Operation

2019 ◽  
Vol 11 (2) ◽  
Author(s):  
B. Sureshkumar ◽  
V. Vijayan ◽  
S. Dinesh ◽  
K. Rajaguru
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Face Milling ◽  
Future Research ◽  
Neural Network Modeling ◽  
Depth Of Cut ◽  
Work Piece ◽  
Neural Network Models ◽  
Feed Force ◽  
Milling Operation

Milling operation is one of the important manufacturing processes in production industry. Study and analysis of milling process parameters such as spindle speed, feed rate and depth of cut are important for process planning engineers. The responses are temperature, surface roughness, machining time, feed force, thrust force and cutting force. The main aim of this study is to find out the effects of these parameters in face milling operation on Monel k 400 work piece materials with tungsten carbide insert. The theoretical investigation is carried out with neural network modelling and the 3-1-6 structure neural network models are considered. Developed neural network models show best agreement with experimental values. For same type of operation, result of these experiments shall be useful for future research purpose.

PREDICTING SOFTWARE QUALITY, DURING TESTING, USING NEURAL NETWORK MODELS: A COMPARATIVE STUDY

1994 ◽  
Vol 01 (03) ◽  
pp. 303-319 ◽  
Author(s):  
TAGHI M. KHOSHGOFTAAR ◽  
ROBERT M. SZABO
Keyword(s):  
Neural Network ◽  
Software Quality ◽  
Principal Components ◽  
Network Modeling ◽  
Network Models ◽  
Neural Nets ◽  
Neural Network Modeling ◽  
Neural Network Models ◽  
Predictive Quality

The application of statistical modeling techniques has been an intensely pursued area of research in the field of software engineering. The goal has been to model software quality and use that information to better understand the software development process. Neural network modeling methods have recently been applied to this field. The results reported indicate that neural network models have better predictive quality than some statistical models when predicting reliability and the number of faults. In this paper, we will investigate the application of principal components analysis to neural network modeling as a way of improving the predictive quality of neural network quality models. Using data we collected from a large commercial software system, we developed a multiple regression model using the principal components. Then, we trained two neural nets, one with raw data, and one with principal components. Then, we compare the predictive quality of the three competing models for a variety of quality measures.

SYSTEM ORIENTED NEURAL NETWORKS — PROBLEM FORMULATION, METHODOLOGY AND APPLICATION

2006 ◽  
Vol 20 (02) ◽  
pp. 143-158 ◽  
Author(s):  
KANG LI ◽  
JIAN-XUN PENG
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Model ◽  
Neural Network Model ◽  
Fitness Function ◽  
A Priori ◽  
Network Models ◽  
Problem Formulation ◽  
Neural Network Modeling ◽  
Neural Network Models

A novel methodology is proposed for the development of neural network models for complex engineering systems exhibiting nonlinearity. This method performs neural network modeling by first establishing some fundamental nonlinear functions from a priori engineering knowledge, which are then constructed and coded into appropriate chromosome representations. Given a suitable fitness function, using evolutionary approaches such as genetic algorithms, a population of chromosomes evolves for a certain number of generations to finally produce a neural network model best fitting the system data. The objective is to improve the transparency of the neural networks, i.e. to produce physically meaningful "white box" neural network model with better generalization performance. In this paper, the problem formulation, the neural network configuration, and the associated optimization software are discussed in detail. This methodology is then applied to a practical real-world system to illustrate its effectiveness.

scholarly journals EXPERIENCE OF NEURAL NETWORK MODELING IN MANAGING THE ACHIEVEMENT OF CRITERIA FOR A NEW MODEL OF A MEDICAL ORGANIZATION THAT USES LEAN TECHNOLOGIES

2020 ◽  
Vol 30 (5) ◽  
pp. 673-678
Author(s):  
S.B. Petrov ◽  
S.D. Mazunina
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
Performance Criteria ◽  
Neural Network Modeling ◽  
Neural Network Models ◽  
Medical Organization ◽  
New Model ◽  
Generalized Regression

Nowadays the scientific developments connected with increase of readiness of the medical institutions, rendering primary medical and sanitary aid, to work with application of methods and tools of lean technologies for increase of level of availability and quality of medical aid to the population of Russia acquire urgency. The aim of the study is to assess the prognostic importance of common neural network models to analyze the value components of the reception of a local therapist, affecting the level of satisfaction with the quality of medical care, from the position of management to achieve the criteria of a new model of a medical organization using lean technologies. The following types of neural network models were studied: based on a multilayer perceptron, a radial basis function, and a generalized regression neural network. Models based on multiple linear regression equations were used as a control group of networks. In total, 50 artificial neural networks were obtained and analyzed. The effectiveness of neural network models was evaluated based on the following parameters: the ratio of standard deviations of the forecast error and the source data, as well as the Pearson correlation between the observed and predicted indicators of the model. Among the studied neural network models, models based on a multi-layer perceptron and generalized regression neural networks have the highest quality of prediction, which makes them promising for use in systems that monitor and predict the structure of the value component of the main processes in medical organizations for patients. The proposed neural network models can become the basis for creating information management systems that monitor the achievement of performance criteria for a new model of a medical organization that uses lean technologies.

scholarly journals Analyzing the relationship between the cytokine profile of invasive breast carcinoma, its histopathological characteristics and metastasis to regional lymph nodes

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Alexander Autenshlyus ◽  
Sergey Arkhipov ◽  
Elena Mikhaylova ◽  
Igor Marinkin ◽  
Valentina Arkhipova ◽  
...  
Keyword(s):  
Neural Network ◽  
Breast Carcinoma ◽  
Lymph Nodes ◽  
Network Models ◽  
Cytokine Profile ◽  
Invasive Breast Carcinoma ◽  
Neural Network Modeling ◽  
Neural Network Models ◽  
Ki 67 ◽  
Regional Lymph Nodes

AbstractThis study was aimed at analyzing the relations of metastasis to regional lymph nodes (RLNs) with histopathological indicators of invasive breast carcinoma of no special type (IC-NST) and its cytokine profile. Enzyme-linked immunosorbent assays were performed to determine concentrations of IL-2, IL-6, IL-8, IL-10, IL-17, IL-18, IL-1β, IL-1Ra, TNF-α, IFN-γ, G-CSF, GM-CSF, VEGF-A, and MCP-1 in the culture supernatant of IC-NST samples from 48 female patients. Histopathological indicators (degree of tumor cell differentiation, mitoses, and others) and ER, PR, Her2/neu, Ki-67, and CD34 expression levels were determined. By means of three types of neural network models, it was shown that for different parameters of the output layer, different groups of parameters are involved that have predictive value regarding metastasis to RLNs. As a result of multi-dimensional cluster analysis, three clusters were formed with different cytokines profiles of IC-NST. Different correlations between indicators of cytokine production by IC-NST and its histopathological parameters were revealed in groups with different cytokine profiles. It was shown that at simultaneous evaluation of the production of even two cytokines, the importance of which relationship with metastasis was revealed by neural network modeling, can increase the probability of determining the presence of metastasis in the RLNs.

scholarly journals Artificial intelligence accuracy assessment in NO2 concentration forecasting of metropolises air

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Seyedeh Reyhaneh Shams ◽  
Ali Jahani ◽  
Saba Kalantary ◽  
Mazaher Moeinaddini ◽  
Nematollah Khorasani
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Green Space ◽  
Accuracy Assessment ◽  
Network Models ◽  
Urban Traffic ◽  
Neural Network Modeling ◽  
Main Concern ◽  
Neural Network Models ◽  
Artificial Neural

AbstractAir quality has been the main concern worldwide and Nitrous oxide (NO2) is one of the pollutants that have a significant effect on human health and environment. This study was conducted to compare the regression analysis and neural network model for predicting NO2 pollutants in the air of Tehran metropolis. Data has been collected during a year in the urban area of Tehran and was analyzed using multi-linear regression (MLR) and multilayer perceptron (MLP) neural networks. Meteorological parameters, urban traffic data, urban green space information, and time parameters are applied as input to forecast the daily concentration of NO2 in the air. The results demonstrate that artificial neural network modeling (R2 = 0.89, RMSE = 0.32) results in more accurate predictions than MLR analysis (R2 = 0.81, RMSE = 13.151). According to the result of sensitivity analysis of the model, the value of park area, the average of green space area and one-day time delay are the crucial parameters influencing NO2 concentration of air. Artificial neural network models could be a powerful, effective and suitable tool for analysis and modeling complex and non-linear relation of environmental variables such as ability in forecasting air pollution. Green spaces establishment has a significant role in NO2 reduction even more than traffic volume.

scholarly journals A Method for Assessing the Retention of Trace Elements in Human Body Using Neural Network Technology

2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
Yulia Tunakova ◽  
Svetlana Novikova ◽  
Aligejdar Ragimov ◽  
Rashat Faizullin ◽  
Vsevolod Valiev
Keyword(s):  
Neural Network ◽  
Trace Elements ◽  
Drinking Water ◽  
Trace Element ◽  
Human Body ◽  
Network Models ◽  
The Body ◽  
Human Organism ◽  
Neural Network Models ◽  
The Many

Models that describe the trace element status formation in the human organism are essential for a correction of micromineral (trace elements) deficiency. A direct trace element retention assessment in the body is difficult due to the many internal mechanisms. The trace element retention is determined by the amount and the ratio of incoming and excreted substance. So, the concentration of trace elements in drinking water characterizes the intake, whereas the element concentration in urine characterizes the excretion. This system can be interpreted as three interrelated elements that are in equilibrium. Since many relationships in the system are not known, the use of standard mathematical models is difficult. The artificial neural network use is suitable for constructing a model in the best way because it can take into account all dependencies in the system implicitly and process inaccurate and incomplete data. We created several neural network models to describe the retentions of trace elements in the human body. On the model basis, we can calculate the microelement levels in the body, knowing the trace element levels in drinking water and urine. These results can be used in health care to provide the population with safe drinking water.

Sign in / Sign up

Export Citation Format

Share Document