Vassil Sgurev

Handwritten document image segmentation and analysis

Abstract The paper proposes automatic segmentation of handwritten document binary images. The Hough transform (HT) over the source image is applied and then the slope of handwritten rows is estimated by analyzing the parameter plane. The inverse HT is used for ‘cutting’ the image and forming ‘strips’, containing the respective handwritten rows. Localization of words is a result of convolution with a proper mask. Such segmentation aims at extracting the specific features of handwriting.

TRASY -- An automated system for real-time control of the industrial truck haulage in open-pit mines

Abstract The control of truck haulage in open-pit mines is an essential problem in the production process of the mines. We describe an automated system for real-time control of the haulage vehicles in terms of the underlying models and solution procedures and we report on the experiences with the system in a real industrial environment.

Intelligent Agents Based Non -- Square Plants Control

Generalized approach for non-square plants (NSP) control based on multi agent system (MAS) is proposed. The control system provides relevant reconfiguration and adaptation in case of plant changes, due to manipulated variables (MV) saturation, filature of input and/or output instrumentation, close proximity to ill-conditioning. A big flexibility is reached when objective function, operation properties and constraints are dynamically changed. Simulation results are presented from MAS realized on JADE platform for two inputs two outputs (TITO) plant using stigmergy as an optimizing method. Comparative analysis of synchronous and asynchronous MAS is carried out

MULTI AGENT INTELLIGENT CONTROL OF CENTRALIZED HVAC SYSTEMS

Abstract The perspective of Multi Agent Systems (MAS) implementation in thermal control of centralized HVAC systems is considered. MAS are implemented in all functional levels of hierarchical HVAC control system: estimation of representative control variables by agent based softsensing, evaluation of Predicted Mean Vote (PMV) index using intelligent agents, local control applying agent-based Ant Colony Optimization (ACO). A non-square control problem of realization comfort is solved via ACO. Software agents are realized into the framework of JADE – plathform in JAVA. Simulation results are presented for single input-two output (SITO) control system.

Adaptation of fuzzy ontology for cascade multi - agent system

An intelligent multicascade control system is proposed using hybrid multi-agent and ontology framework. Fuzzy logic based extension of conventional ontology is implemented to meet uncertainties in the plant, its environment and sensor information. Ant colony optimization is applied to realize trade-off between requirements and control resources as well as for significant reduction of the communication rate among the intelligente agents. To react on unexpected changes in operational conditions certain adaptation functionality of the fuzzy ontology is foreseen. Some simulation results are presented.

Innovative Issues in Intelligent Systems

This book presents a broad variety of different contemporary IT methods and applications in Intelligent Systems is displayed. Every book chapter represents a detailed, specific, far reaching and original re-search in a respective scientific and practical field. However, all of the chapters share the common point of strong similarity in a sense of being innovative, applicable and mutually compatible with each other. In other words, the methods from the different chapters can be viewed as bricks for building the next generation thinking machines as well as for other futuristic logical applications that are rapidly changing our world nowadays.

An essay on complex valued propositional logic

In the decision making logic it is often necessary solving of logical equations for which, due to the features of disjunction and conjunction, no admissible solutions exist. An approach is suggested in which by introducing of Imaginary Logical Variables (ILV) the classical propositional logic is extended to a complex one. This provides a possibility to solve a large class of logical equations. The real and imaginary variables each satisfy the axioms of the Boolean algebra and of the lattice. It is shown that the Complex Logical Variables (CLV) observe the requirements of the Boolean algebra and the lattice axioms. Suitable definitions are found for these variables for the operations disjunction, conjunction, and negation. A series of results are obtained, included also the truth tables of the operations disjunction, conjunction, negation, implication, and equivalence for complex variables. Inference rules are deduced for them analogous to Modus Ponens and Modus Tollens in the classical propositional logic. Values of the complex variables are obtained, corresponding to TRUE (T) and FALSE (F) in the classic propositional logic. A conclusion may be made from the initial assumptions and the results attained, that the imaginary logical variable i introduced hereby is “truer” than the condition “T” of the classic propositional logic and ¬i—“falser” than the condition “F”, respectively. Possibilities for further investigations of this class of complex logical structures are pointed out.

Optimal Control of the Flow of Risk on Networks

Abstract A new network flow method is proposed in this work for optimal distribution of risk between the different sections (arcs) of the network. It is supposed at that that the maximum admissible risks on the arcs are known in advance. This provides a possibility these values to be considered as arc capacities and the risk itself as a network flow. Such an approach lets the maximal admissible risk to be determined on the network on the base of the well-known mincut-maxflow theorem as well as the minimal cut. Three different numerical examples are given through which the possibility of the method being proposed is confirmed in the real practices.

Intelligent Control of Flows with Risks on a Network

Methods for calculating the max network flow with min cut and a flow of min cost, considering the risk on the separate sections of the network, are proposed in this work. The capacity of each arc is so defined, that it does not exceeds ‘the physical’ arc constraints as well as the admissible risk of the arc network flow function. The maximal flow of minimal cost is calculated in two steps – first the max flow is calculated, and then on the base of this value the optimal arc functions of min cost are defined. Three numerical examples are described which illustrate the potentials of the proposed methods for optimization of the network flows with risks. The concepts of ‘minimal cut of the network risk’ and ‘max flow of min cost and min cut of network risk’ are introduced.

Human-centered methods for applications of fuzzy probabilities in intelligent systems

The paper introduces a synthetic metamethod SMM which is aimed at automation of fuzzy perceptions approval. Also the considered methods are applicable in creative processes concerning different types of intelligent systems. The metamethod is based on an analysis of incoming perception-oriented knowledge and a successive check in the domain. The proposed main methods - SMM, INCONSISTENCY, FUNNEL, and CROSSWORD - interact on a competitive principle. Two additional methods, FRONTAL and CALEIDOSCOPE, also can be put in the same group. A research is going on for the possibilities of including methods by other scientists under the general control of SMM. An evolution of the solution is used in cases of applications in environments poor of knowledge or of missing precise orientation to the final solution. The approval of fuzzy probabilities frequently needs an act of creation especially if it is applied in a knowledge-poor environment. It is shown that even in this case the creative processes are based on applications of clear and well-formalized methods included in many different sophisticated combinations.