Wyniki wyszukiwania - BazTech

1

A bi-stage neuro - fuzzy classifier system for object identification

Pantazopoulos D. P., Tzafestas S. G.

Image Processing & Communications

|

2007

|

Vol. 12, no 1

53-65

EN

In this paper a two-stage hybrid system for object recognition, that is needed in artificial vision applications, is presented. For the description of the images, three features, namely geometrical parameters, moments, and internal angles, are used as inputs to the classifier. The first stage of the system consists of three neural classifiers (one for each feature). In the second stage the outputs of the first stage are presented to a fuzzy reasoning system which acts as the final classifier and makes the final decision. The proposed bi-stage hybrid neuro-fuzzy classifier (symbolically bisNFC) was tested with a large set of images. The results and the comparisons with other methods showed that bisNFC is a promising classification system.

2

Integrated fuzzy global path following and obstacle avoidance for mobile robots

Zavlangas P.G., Tzafestas S.G.

Systems Science

|

2001

|

Vol. 27, nr 4

85-96

EN

Motion planning is the process of computing a path, i.e., a sequence of robot configurations, allowing it to move from one place to another. It is a central problem in the development of autonomous mobile robots. This is true indeed, but when the environment of the robot becomes complex, i.e., uncertain, partially known, with moving obstacles or other robots, it takes much more than global motion planning to achieve motion autonomy. In this case, the ability to detect unexpected events and react accordingly becomes essential. Reactivity provides the robot with an important mechanism to immediate respond to unpredicted environmental changes. This paper describes an intelligent path planning system for omnidirectional mobile robots. Our proposed solution to the dual need for global path planning and reactivity is to adopt a two-level model: at the upper level, a planner provides the system with a global path, based on the available knowledge; at the lower level, a reactive controller follows this given global path, while dealing with the environmental contingencies. The control architecture, presented in this paper, relies upon two main complementary modules: a global path planner, that computes a nominal path between the current configuration of the robot and its goal, and a reactive local planner, whose purpose is to generate the appropriate commands for the actuators of the robot, so as to follow the global path as close as possible, while reacting in realtime to unexpected events by locally adapting the robots movements, so as to avoid collisions with unpredicted or moving obstacles. This reactive local planner consists of two separate fuzzy controllers for path following and obstacle avoidance. The functioning of the proposed system with respect to omnidirectional mobile robots and results of simulated experiments will be presented.

3

Intelligent forecasting: Fuzzy/neuro-fuzzy methodologies with case studies

Tzafestas S. G., Tzafestas E. S., Maragos P.

Systems Science

|

2000

|

Vol. 26, nr 4

39-48

EN

A key component of the operation and planning activities in the majority of industrial plants such as electric utilities, refineries, and manufacturers, as well as enterprises and organizations is demand, or sales, forecasting. The aim of this paper is to present the solution of the forecasting problem through the application of the fuzzy/neurofuzzy methodologies. In particular, two very effective techniques are discussed based on the Takagi-Sugeno (functional reasoning) fuzzy model. The first uses the orthogonal least squares (OLS) technique to identify the structure of the fuzzy system (input variables selection and input space partitioning), and the second one uses the adaptive resonance theory (ART) technique for the same purpose. A power load forecast and a refinery product quality forecast case study are included to demonstrate the high accuracy achieved by fuzzy/neurofuzzy forecasting methods.

4

Recent algorithms for fuzzy and neurofuzzy path planning and navigation of autonomous mobile robots.

Tzafestas C.S., Tzafestas S.G.

Systems Science

|

1999

|

Vol. 25, nr 2

25-39

EN

This paper reviews a number of recent algorithms for mobile robot path planning, navigation and motion control, which employ fuzzy logic and neurofuzzy learning and reasoning. Staring with a discussion of the structure of fuzzy and neurofuzzy systems, two fuzzy obstacle avoidance path planning algorithms are presented followed by a 3-level neurofuzzy local and global path planning scheme. Then the motion planning and control problem is considered. A fuzzy path tracking strategy is outlined, followed by a fuzzy navigation algorithm among polygonal obstacles and a learning-by-doing neurofuzzy motion planning scheme. The paper ends with a hybrid robust motion control technique witch combines the minimum interference and sliding mode control principles with fuzzy inference. A representative set of examples are included which illustrate the performance of the algorithms under various realistic conditions.

5

A hybrid pricing expert system based on fuzzy reasoning

Tzafestas S. G., Raptis S., Moschos N.

Foundations of Computing and Decision Sciences

|

1999

|

Vol. 24, No. 4

171-187

6

On the robust stability of linear systems with parametric uncertainty.

Tzafestas S. G., Tzamtzi M. P.

Systems Science

|

1998

|

Vol. 24, nr 3

59-65

EN

This paper is concerned with the robust stability of linear systems in state space form for the case where the system matrix A(p) depends on a vector p.member.P .contained in. IRv of uncertainty, with P being a hyperrectangle. A new parameterization of the uncertainty is proposed which leads to sufficient conditions for the robust stability of the system x`(t)=A(p)x(t), x(t0)=x0 needing a finite number of tests. The number of tests required decreases considerably with respect to a previously proposed sufficient condition, and so the chances of satisfying the sufficient condition generally increase. This is illustrated by two nontrivial examples.

7

Design of facult-tolerant control systems: passive and active approaches.

Tzafestas C. S., Rigatos G.G., Tzafestas S. G.

Systems Science

|

1998

|

Vol. 24, nr 4

5-28

EN

This paper addresses the issue of studying and improving the reliability and fault tolerance of a given dynamic system using appropriate control design methodologies. The attention is focused on reviewing the two basic approaches to fault tolerance/reliability, namely: the passive and the active approaches. In the passive approach a wide description of system failures is adopted, and a robust control is sought that can tolerate failures as perturbations from a nominal model. On the other hand, in the active approach which is based on an accurate description of failures, through a failure diagnostic unit, the control can be reconfigured on-line. The passive approach is often easier to implement, but can cope with minor failures. So in actual systems the passive solution is used to save time until a more sophisticated active algorithm enters into the system. The theoretical results are illustrated with four application examples.