Class Of Knowledge-based Systems Research Articles

Decision support system for street-road network objects repair

The article analyzes factors influencing managerial decisions adoption on repair of road network facilities (RN). Road repair is a challenge that must take into account a number of conflicting criteria. It is shown that decision-making process is a complex mental activity that consists in choosing the most effective strategy and, at present, repair work planning should be carried out using decision support systems (DSS), that is, a class of knowledge-based systems. DSS developing necessity for repair planning of RN has been substantiated. DSS architecture is described and it is shown that DSS allows increasing knowledge base by adding new knowledge without changing the structure, as well as encapsulating new knowledge into the system, increasing intellectual resource used in decision-making process. The parameters are determined, on the basis of which rules in DSS are formulated, which are necessary for making decisions on determining scope, timing, cost and sequence of repair and restoration work. Production rules examples are given. The general scheme of algorithm for planning repair and restoration works at RNF, as well as algorithm scheme for complex indicator calculating of transport and operational state-ensuring movement design speed dare described. Planning process formalized description and control actions development has been completed. It is shown that intelligent decision-making is an iterative, multi-level procedure, within which decisions table is analyzed to assess technical condition of RN facilities based on regulatory and technical documentation analysis. Situation description is consistently expanded by taking into account the quality of RN road marking, traffic intensity, road construction materials volumes, repair and restoration work cost, traffic management, seasonality and weather conditions, etc. (the number of taken into account parameters and levels of their description is not limited). The advantages of proposed approach to DSS implementation are described. It is shown that proposed DSS version provides situational adaptive intelligent control with ability to issue justified recommendations for carrying out repairs. The prospects for work development in this direction were considered and conclusion was made that management digitalization of repair activities, the digital transformation of management model and business processes in the field of RN repair will increase profits, increase operational efficiency, reduce repair costs and improve its quality.

Two-level pattern recognition in a class of knowledge-based systems

In the paper, the problem of pattern recognition in a two-level expert system with the logical knowledge representation is investigated. In the first part, formulation and solution algorithm of this problem are presented. To solve the pattern recognition problem, a logic-algebraic method is used. In the second part, it is shown how the method of learning may be applied to the pattern recognition system with unknown parameters in knowledge representation. The concepts considered here are illustrated by a simple numerical example.

Learning algorithms in a class of knowledge-based systems

A control system with a static plant described by knowledge representation in the forms of relations and of logical formulas is considered. The learning process consists in using successive knowledge validation and updating it to make current control decisions. Two approaches and algorithms are described: one for the validation and updating of knowledge about the plant, and one on the form of control. In both cases two versions are presented: the learning process in either an open-loop or a closed-loop control system. For a plant with logical knowledge representation, the logic-algebraic method is applied.

A framework for constructing visual knowledge specifications in acquiring organizational knowledge

Most work in knowledge acquisition assumes that there is a single problem-solving task for which the knowledge base being constructed through acquisition will be applied. However, there is growing interest in a class of knowledge-based systems, referred to as organizational knowledge systems , where it cannot be assumed that there is a single task model or problem-solving method for which the knowledge is to be acquired. This paper discusses this type of knowledge-based system, the factors in organizational problem-solving which mitigate its existence, and presents a framework for knowledge acquisition in this environment. The acquisition framework, known as Conceptual Abstraction , has its basis in semantic data modeling, model-based KA, and visual programming. It has been effectively applied in the specification of knowledge schemata for organizational knowledge bases. The paper discusses the underlying model for abstraction and the associated abstraction mechanisms of the Conceptual Abstraction approach, and illustrates their use through example.

NECTAR: a knowledge-based environment to enhance SPICE

An environment for SPICE called NECTAR has been developed which aids in convergence and user-interface problems with SPICE by simulating the actions taken by expert users. NECTAR recognizes patterns which cause nonconvergence and provides ways around the problems. NECTAR identifies errors in the SPICE input file and may automatically correct them. It can be used as a circuit design aid and improves the user interface for SPICE simulations. NECTAR belongs to the class of knowledge-based systems and is based on knowledge acquired from expert SPICE users and circuit designers. >