Experience in Performing Analytical Calculations Using Algebraic Model of Constructive Logic in Medicine and Biology

10.12737/2717 ◽  
2013 ◽  
Vol 20 (4) ◽  
pp. 7-12
Author(s):  
Хромушин ◽  
Oleg Khromushin ◽  
Хромушин ◽  
Viktor Khromushin ◽  
Китанина ◽  
...  
Keyword(s):  
Neural Network ◽  
Hidden Variables ◽  
Joint Effect ◽  
Algebraic Model ◽  
Constructive Logic ◽  
Network Algorithms ◽  
Dead End ◽  
Determining Factors ◽  
Small Set ◽  
The Impact

This paper describes the experience of analytical calculations in medicine and biology using the mathematical apparatus of algebraic model of constructive logic, created with Russia in 1983. Basically it is a model intuitionism calculus, displaying the inductive part of the thinking - formulation of a relatively small set of summary of the information arrays of large dimension. The initial data to build the model is a table. Each row in this table is treated as a case in which the values of the factors are listed in the form of any numeric value, and the result of their exposure. The resulting model is represented by a set of the resulting components as factors indicating the detection limits, combined mark conjunction (pointing to the joint effect). Each resulting component characterized by the capacity, which is the essence of the number of rows in the table that meet the specified limits of the determining factors in their joint action defined by algebraic model of constructive logic. Optimality is demonstrated by a comparison with a dead-end disjunctive form, as not allowing further simplification in the synthesis of combinational logical schema. The algorithm has the potential partial avoidance of the impact of hidden variables that are slowly evolve over time. The stages of the analysis, including the building of the expert system, are demonstrated and also the ways of further improvement of the algorithm are specified. An algebraic model of constructive logic of their capabilities is not inferior to neural network algorithms for analytical capabilities, convenient in use and doesn´t require the training phase. An algebraic model of constructive logic is fundamentally different from many well-known algorithms including neural network algorithms. Its use along with other allows to reach greater confidence in the assessment of the results.

scholarly journals A new spatio-temporal graph neural network method for the analysis of GNSS geodetic data

2021 ◽  
Author(s):  
Mostafa Kiani Shahvandi ◽  
Benedikt Soja
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Time Series ◽  
Time Series Prediction ◽  
Temporal Correlation ◽  
Machine Learning Algorithms ◽  
Network Algorithms ◽  
Graph Neural Networks ◽  
The Impact ◽  
Gnss Networks

<p>Graph neural networks are a newly established category of machine learning algorithms dealing with relational data. They can be used for the analysis of both spatial and/or temporal data. They are capable of modeling how time series of nodes, which are located at different spatial positions, change by the exchange of information between nodes and their neighbors. As a result, time series can be predicted to future epochs.</p><p>GNSS networks consist of stations at different locations, each producing time series of geodetic parameters, such as changes in their positions. In order to successfully apply graph neural networks to predict time series from GNSS networks, the physical properties of GNSS time series should be taken into account. Thus, we suggest a new graph neural network algorithm that has both a physical and a mathematical basis. The physical part is based on the fundamental concept of information exchange between nodes and their neighbors. Here, the temporal correlation between the changes of time series of the nodes and their neighbors is considered, which is computed by geophysical loading and/or climatic data. The mathematical part comes from the time series prediction by mathematical models, after the removal of trends and periodic effects using the singular spectrum analysis algorithm. In addition, it plays a role in the computation of the impact of neighboring nodes, based on the spatial correlation computed according to the pair-wise node-neighbor distance. The final prediction is the simple weighted summation of the predicted values of the time series of the node and those of its neighbors, in which weights are the multiplication of the spatial and temporal correlations.</p><p>In order to show the efficiency of the proposed algorithm, we considered a global network of more than 18000 GNSS stations and defined the neighbors of each node as stations that are located within the range of 10 km. We performed several different analyses, including the comparison between different machine learning algorithms and statistical methods for the time series prediction part, the impact of the type of data used for the computation of temporal correlation (climatic and/or geophysical loading), and comparison with other state-of-the-art graph neural network algorithms. We demonstrate the superiority of our method to the current graph neural network algorithms when applied to time series of geodetic networks. In addition, we show that the best machine learning algorithm to use within our graph neural network architecture is the multilayer perceptron, which shows an average of 0.34 mm in prediction accuracy. Furthermore, we find that the statistical methods have lower accuracies than machine learning ones, as much as 44 percent.</p>

scholarly journals Towards Physics-Based Generalizable Convolutional Neural Network Models for Indoor Propagation

2021 ◽  
Author(s):  
Aristeidis Seretis
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Network Models ◽  
Radiowave Propagation ◽  
Indoor Propagation ◽  
Neural Network Models ◽  
Small Set ◽  
The Impact

A fundamental challenge for machine learning models for electromagnetics is their ability to predict output quantities of interest (such as fields and scattering parameters) in geometries that the model has not been trained for. Addressing this challenge is a key to fulfilling one of the most appealing promises of machine learning for computational electromagnetics: the rapid solution of problems of interest just by processing the geometry and the sources involved. The impact of such models that can "generalize" to new geometries is more profound for large-scale computations, such as those encountered in wireless propagation scenarios. We present generalizable models for indoor propagation that can predict received signal strengths within new geometries, beyond those of the training set of the model, for transmitters and receivers of multiple positions, and for new frequencies. We show that a convolutional neural network can "learn" the physics of indoor radiowave propagation from ray-tracing solutions of a small set of training geometries, so that it can eventually deal with substantially different geometries. We emphasize the role of exploiting physical insights in the training of the network, by defining input parameters and cost functions that assist the network to efficiently learn basic and complex propagation mechanisms.

Database optimization for multi-factor analysis by means of the algebraic model of constructive logic

10.12737/3863 ◽  
2014 ◽  
Vol 8 (1) ◽  
pp. 1-9 ◽  
Author(s):  
Лукина ◽  
T. Lukina ◽  
Хромушин ◽  
Oleg Khromushin ◽  
Хромушин ◽  
...  
Keyword(s):  
Factor Analysis ◽  
Model Building ◽  
Limit Of Detection ◽  
Algebraic Model ◽  
Target Line ◽  
Constructive Logic ◽  
Determining Factors ◽  
Connective Tissue Dysplasia ◽  
Singular Numbers ◽  
Table Data

The paper considers the stage of preparing the database for multi-factor analysis by means of the algebraic model of constructive logic that has been used successfully since 1999 to perform the analysis in medicine and biology. Initial data for model building is a table. Each line in this table is treated as a case where the values of factors and their impacts are marked. The resulting model is represented by a set of result components in the form of factors indicating the limit of detection combined by conjunction sing (pointing to the combined effect). Each resulting component is characterized by the capacity is the essence of the number of lines in the table, which correspond to the specified limits of determining factors in their joint action. The resulting logical expression is characterized by a combination of factors (indicating the detection limits of each of them) in their capacity as the degree of influence on the result. The initial table data should not have contradictions (when the aim is achieved and isn´t achieved by the same values of the factors). To this aim, the program envisages the exception of those targeted lines of which coincide with non-target strings. However, this isn´t always acceptable in cases of a large number of matching target lines and the singular numbers of non-target strings. Then a large number of cases due to the single non-target line are excluded. The analysis of the coincidences of target and non-target lines to select a single non-target line, to remove them from the database on the example of connective tissue dysplasia with magnesium therapy has been proposed. Comparative analysis of the obtained mathematical models was carried out. The effect of improvement of mathematical model on the basis of algebraic model of constructive logic was demonstrated.

scholarly journals Towards Physics-Based Generalizable Convolutional Neural Network Models for Indoor Propagation

2021 ◽  
Author(s):  
Aristeidis Seretis
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Network Models ◽  
Radiowave Propagation ◽  
Indoor Propagation ◽  
Neural Network Models ◽  
Small Set ◽  
The Impact

A fundamental challenge for machine learning models for electromagnetics is their ability to predict output quantities of interest (such as fields and scattering parameters) in geometries that the model has not been trained for. Addressing this challenge is a key to fulfilling one of the most appealing promises of machine learning for computational electromagnetics: the rapid solution of problems of interest just by processing the geometry and the sources involved. The impact of such models that can "generalize" to new geometries is more profound for large-scale computations, such as those encountered in wireless propagation scenarios. We present generalizable models for indoor propagation that can predict received signal strengths within new geometries, beyond those of the training set of the model, for transmitters and receivers of multiple positions, and for new frequencies. We show that a convolutional neural network can "learn" the physics of indoor radiowave propagation from ray-tracing solutions of a small set of training geometries, so that it can eventually deal with substantially different geometries. We emphasize the role of exploiting physical insights in the training of the network, by defining input parameters and cost functions that assist the network to efficiently learn basic and complex propagation mechanisms.

Research on behavior recognition based on feature fusion of automatic coder and recurrent neural network

2020 ◽  
Vol 39 (6) ◽  
pp. 8927-8935
Author(s):  
Bing Zheng ◽  
Dawei Yun ◽  
Yan Liang
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Behavior Pattern ◽  
Rapid Development ◽  
Video Data ◽  
Support Vector ◽  
Behavior Recognition ◽  
Learning Methods ◽  
The Impact ◽  
Internet Of Things Technology

Under the impact of COVID-19, research on behavior recognition are highly needed. In this paper, we combine the algorithm of self-adaptive coder and recurrent neural network to realize the research of behavior pattern recognition. At present, most of the research of human behavior recognition is focused on the video data, which is based on the video number. At the same time, due to the complexity of video image data, it is easy to violate personal privacy. With the rapid development of Internet of things technology, it has attracted the attention of a large number of experts and scholars. Researchers have tried to use many machine learning methods, such as random forest, support vector machine and other shallow learning methods, which perform well in the laboratory environment, but there is still a long way to go from practical application. In this paper, a recursive neural network algorithm based on long and short term memory (LSTM) is proposed to realize the recognition of behavior patterns, so as to improve the accuracy of human activity behavior recognition.

European Economies Stability Faced With Potential Outburst of Sovereign Debt Crisis. An Empirical Study Using Neural Network

2013 ◽  
Vol 12 (2) ◽  
pp. 3255-3260
Author(s):  
Stelian Stancu ◽  
Alexandra Maria Constantin
Keyword(s):  
Neural Network ◽  
Sovereign Debt ◽  
Debt Crisis ◽  
Banking System ◽  
Sovereign Debt Crisis ◽  
European Level ◽  
Continuous Growth ◽  
Economic Context ◽  
European Economies ◽  
The Impact

Instilment, on a European level, of a state incompatible with the state of stability on a macroeconomic level and in the financial-banking system lead to continuous growth of vulnerability of European economies, situated at the verge of an outburst of sovereign debt crises. In this context, the current papers main objective is to produce a study regarding the vulnerability of European economies faced with potential outburst of sovereign debt crisis, which implies quantitative analysis of the impact of sovereign debt on the sensitivity of the European Unions economies. The paper also entails the following specific objectives: completing an introduction in the current European economic context, conceptualization of the notion of “sovereign debt crisis, presenting the methodology and obtained empirical results, as well as exposition of the conclusions.

Sign in / Sign up

Export Citation Format

Share Document