Márta Takács

Conjunction and disjunction operators in neuro-fuzzy risk calculation model simplification

In this paper a possible simplification of a risk level calculation models neuro-fuzzy subsystem will be studied. The basic model has a hierarchical multilevel structure and uses fuzzy logic based decision making for some groups of risk factors and neuro-fuzzy subsystem is based on ANFIS model structure for the other. The simplification of neuro-fuzzy subsystem is based on disjunction fuzzy operator where the operator selection is application-dependent. This is because the three basic operations of crisp sets (negation, conjunction, and disjunction) can be generalized for fuzzy sets in an infinite number of ways. In this work the effect of different conjunction and disjunction operators on the result of simplified structure was compared and analyzed.

Risk level calculation for body physical exercise with different fuzzy based methods

In this paper two types of hierarchical multilevel models will be introduced for the calculation of risk of physical exercise in fuzzy environment. One of them is the Analytic Hierarchy Process with Fuzzy Comprehensive Evaluation based model and the other was made in Simulink-Fuzzy Toolbox environment with Mamdani-type fuzzy evaluation. The two methods were tested on several input data and the result of them has been compared and analyzed.

Minnesota code: A fuzzy logic-based approach

The advances in computer science and informatics provide the basis for creating modern health diagnostics algorithms and instruments. One of the evaluation methods of reference ECG signals is based on the Minnesota code. This is a rule based system, which provides a value based criteria for specific ECG parameters. There are several studies which have tried to determine the effectiveness of the computer based Minnesota code compared to human usage of the code system. The results showed that computers are as effective in the evaluation of ECG signal with the Minnesota code as humans are with visual analysis. The code system is sensitive to waveform changes, but is not affected by conduction disturbances and arrhythmic events. An additional downside is that the values predefined in the tree-based rule system are crisp values, which means that any noise or a minor delay can cause the rest of the Minnesota code to be ignored. In this paper the authors propose a fuzzy-based approach to bypass these known issues.

Fuzzy rule base construction for Minnesota Code

The Minnesota Code is the evaluation method of reference ECG signals. The experimental studies compare the effectiveness of the computer based Minnesota Code applications to human usage of the code system, and the results showed that computers are as effective in the evaluation of ECG signal with the Minnesota Code as humans are with visual analysis. In this paper the authors propose a fuzzy-based approach to bypass known imperfections and imprecision of the existing Minnesota Code rules. The first step for the possible comprehensive fuzzy implementation of the Minnesota Code is the structural building of the fuzzy decision system for one rule group of the Minnesota Code. For this code group an ECG signal has been tested, containing the necessary beat information. The same input signal has been tested with a standard crisp based and fuzzy based solution. The fuzzy environment provides more information for the medical expert or for the further levels of the whole hierarchically organized diagnostic structure.∗

Application of fuzzy logic in hemodialysis equipment

In hemodialysis machines peristaltic pumps are responsible for the transfer of fluids. These pumps can only deliver the solutions with significant error, due to the deviation of the pump head and due to production errors. Previous work focused on system identification and fluid flow control by a PID controller. In this paper the goal is to replace the PID controller with an adaptive fuzzy controller. Furthermore, the use of integral component for error signal rejection is examined as input to the fuzzy logic system. The mentioned controllers are compared through appropriate aspects and the paper ends with discussion of the behavior of the adaptive fuzzy controller on the real system.

The effect of aggregation and defuzzification method selection on the risk level calculation

In this paper a fuzzy logic-based hierarchical multilevel risk calculation model will be introduced with different model parameters. On each occasion when a fuzzy-based simulation model is constructed, the appropriate aggregation and defuzzification method must be chosen. It is very difficult because it cannot be said generally, which is the best method, its depends on the current application. The model presented in the paper is a model for risk calculation of physical exercise, and it was constructed in Simulink - Fuzzy Logic Toolbox environment with Mamdani-type fuzzy evaluation and different aggregation and defuzzification operators. The test was performed for several typical groups of the patients. The results are compared with a previously implemented Analytic Hierarchy Process with Fuzzy Comprehensive Evaluation based model with similar purposes. The result of the comparison has been analyzed and the best methods have been selected.

Content representation structure for product system modeling

Product model based engineering long history of which started with computer aided design, manufacturing, and engineering (CAD/CAM/CAE) solutions recently utilizes product model which represents product as a system. In this new generation of product model, parts and units of product are modeled on the physical level as formerly. However, this level is supported by three higher abstraction levels of product concept model. The physical and concept levels are typically organized in the requirements, functions, logical, and physical (RFLP) structure. In this way, high abstraction is available for enhanced and theoretically grounded engineering utilizing achievements from systems engineering (SE) and requirements engineering (RE). In this paper, three recent results are introduced from a long-term research in high abstraction based product definition at the Laboratory of Intelligent Engineering Systems (LIES), Óbuda University. These contributions are driving generation of RFLP elements, product features, model creation structures, and product realization model structures by organized contextual knowledge background in content structures, multilevel content structures in case of their pure contextual creation and application, and driving product model generation by restricted human initiative. Finally, placing of the proposed content structure processing units in PLM system is outlined.

A fast fuzzy decision tree for color filtering

Fuzzy decision trees have been gaining popularity in the past two decades. They are the fuzzy extensions of crisp decision trees, introducing fuzzy logic into the nodes of the tree, thus making their generalization capabilities more robust. This paper presents a fuzzy decision tree architecture that is optimized for quick inference, in order to make the classification process as fast as possible. Furthermore, two training algorithms are presented to incrementally train fuzzy decision trees for realtime classification applications.

Fuzzy Cognitive Map for student evaluation model

In the paper a novel Fuzzy Cognitive Map based algorithm was introduced for the calculation of the values of the interrelation levels between the factors in a system for the student grade evaluation. Furthermore using the calculated edge weights between the factors, and differences of the stored and filtered dates for students from the Neptun education IT system, a learning algorithm was presented, with the learning cycles and states related for successive known semesters. Continuing the learning process, we can predict, make the forecast for the factors and states for the forthcoming semesters, with the unknown factor values.

Minnesota code: A neuro-fuzzy-based decision tuning

The Minnesota Code is the evaluation method of reference ECG signals. The experimental studies compare the effectiveness of the computer based Minnesota Code applications to human usage of the code system, and the results showed that computers are as effective in the evaluation of ECG signal with the Minnesota Code as humans are with visual analysis. A fuzzy-based approach can be used to bypass known imperfections and imprecision of the existing Minnesota Code rules. A fuzzy-based approach also has issues with corner case inputs, which can lead to incorrect partial results and incorrect diagnostics outputs. The fuzzy environment provides more information for the medical expert or for the further levels of the whole hierarchically organized diagnostic structure. The authors of the paper present a possible solution for fine-tuning the diagnostic rules using neural networks. In this paper, the standard fuzzy-based approach is extended to a neuro-fuzzy solution.