Abstract: The paper deals with a problem of intelligent system’s design for complex environments. There is discussed a possibility to integrate several technologies into one basic structure that could form a kernel of an autonomous intelligent robotic system. One alternative structure is proposed in order to form a basis of an intelligent system that would be able to operate in complex environments. The proposed structure is very flexible because of features that allow adapting via learning and adjustment of the used knowledge. Therefore, the proposed structure may be used in environments with stochastic features such as hardly predictable events or elements. The basic elements of the proposed structure have found their implementation in software system and experimental robotic system. The software system as well as the robotic system has been used for experimentation in order to validate the proposed structure - its functionality, flexibility and reliability. Both of them are presented in the paper. The basic features of each system are presented as well. The most important results of experiments are outlined and discussed at the end of the paper. Some possible directions of further research are also sketched at the end of the paper.

Keywords: Artificial intelligence, Inductive reasoning, Deductive reasoning, Case based reasoning, Machine learning, Learning algorithms.

ACM Classification Keywords: I.2.9 Robotics; I.2.3 Deduction and Theorem Proving: Deduction, Induction, Uncertainty, Fuzzy, and Probabilistic Reasoning; I.2.6 Learning

Link:

ROBOT CONTROL USING INDUCTIVE, DEDUCTIVE AND CASE BASED REASONING

Agris Nikitenko

http://www.foibg.com/ijita/vol12/ijita12-4-p13.pdf

Abstract: In the present paper the problems of the optimal control of systems when constraints are imposed on the control is considered. The optimality conditions are given in the form of Pontryagin’s maximum principle. The obtained piecewise linear function is approximated by using feedforward neural network. A numerical example is given.

Keywords: optimal control, constraints, neural networks

ACM Classification Keywords: I.2.8 Problem Solving, Control Methods, and Search

Link:

NEURAL NETWORK BASED OPTIMAL CONTROL WITH CONSTRAINTS

Daniela Toshkova, Georgi Toshkov, Todorka Kovacheva

http://www.foibg.com/ijita/vol14/ijita14-3-p11.pdf

Abstract: The questions of designing multicriteria control systems on the basis of logic models of composite dynamic objects are considered.

Keywords: control, logical model, composite dynamic object, balancing network.

ACM Classification Keywords: I.2.8 Problem Solving, Control Methods, and Search: Control theory; F.1.1 Models of Computation: Neural networks

Link:

LOGICAL MODELS OF COMPOSITE DYNAMIC OBJECTS CONTROL

Vitaly Velichko, Victor Gladun, Gleb Gladun, Anastasiya Godunova, Yurii Ivaskiv, Elina Postol, Grigorii Jakemenko

http://www.foibg.com/ijita/vol12/ijita12-4-p01.pdf

Abstract: The paper suggests a classification of dynamic rule-based systems. For each class of systems, limit behavior is studied. Systems with stabilizing limit states or stabilizing limit trajectories are identified, and such states and trajectories are found. The structure of the set of limit states and trajectories is investigated.

Keywords: Dynamic rule-based systems, set of attainable states, limit trajectories.

ACM Classification Keywords: I.2.8 Problem Solving, Control Methods, and Search

Link:

LIMIT BEHAVIOUR OF DYNAMIC RULE-BASED SYSTEMS

Gennady Osipov

http://www.foibg.com/ijita/vol15/ijita15-2-p03.pdf

Abstract: The paper is devoted to the matter of information presented in a natural language search. The method using the statements agreement process is added to the known existing system. It allows the formation of an ordered list of answers to the inquiry in the form of quotations from the documents.

Keywords: Search engine, natural language, coordination of statements, semantic graph

ACM Classification Keywords: I.2.7 Computing Methodologies – Text analysis

Link:

ANALYSIS AND COORDINATION OF EXPERT STATEMENTS IN THE PROBLEMS OF INTELLECTUAL INFORMATION SEARCH1

Gennadiy Lbov, Nikolai Dolozov, Pavel Maslov

http://www.foibg.com/ijita/vol14/ijita14-1-p16.pdf

Abstract: the approaches to the analysis of various information resources pertinent to user requirements at a semantic level are determined by the thesauruses of the appropriate subject domains. The algorithms of formation and normalization of the multilinguistic thesaurus, and also methods of their comparison are given.

Key words: an information resource, ontology, thesaurus, informational retrieval.

ACM Classification Keywords: I.2.7 Natural Language Processing, I.2.4 Knowledge Representation Formalisms and Methods (F.4.1).

Link:

SEMANTIC SEARCH OF INTERNET INFORMATION RESOURCES ON BASE OF ONTOLOGIES AND MULTILINGUISTIC THESAURUSES

Anatoly Gladun, Julia Rogushina

http://www.foibg.com/ijita/vol14/ijita14-1-p07.pdf

Abstract: This paper presents an approach to development of intelligent search system and automatic document classification and cataloging tools for CASE-system based on metadata. The described method uses advantages of ontology approach and traditional approach based on keywords. The method has powerful intelligent means and it can be integrated with existing document search systems.

Keywords: electronic document, automatic document classification and cataloging, ontology approach, information system development.

ACM Classification Keywords: I.2.7 Artificial Intelligence: Natural Language Processing – Text analysis; D.2.2 Software Engineering: Design Tools and Techniques – Computer-aided software engineering (CASE).

Link:

INTELLIGENT SEARCH AND AUTOMATIC DOCUMENT CLASSIFICATION AND CATALOGING BASED ON ONTOLOGY APPROACH

Vyacheslav Lanin, Lyudmila Lyadova

http://www.foibg.com/ijita/vol14/ijita14-1-p03.pdf

Abstract: Modern technology has moved on and completely changed the way that people can use the telephone or mobile to dialogue with information held on computers. Well developed “written speech analysis” does not work with “verbal speech”. The main purpose of our article is, firstly, to highlights the problems and, secondly, to shows the possible ways to solve these problems.

Keywords: data mining, speech recognition, natural language processing

ACM Classification Keywords: I.2.7 Natural Language Processing: Text analysis, speech recognition.

Link:

VERBAL DIALOGUE VERSUS WRITTEN DIALOGUE

David Burns, Richard Fallon, Phil Lewis, Vladimir Lovitskii, Stuart Owen

http://www.foibg.com/ijita/vol12/ijita12-4-p11.pdf

Abstract: A model of the cognitive process of natural language processing has been developed using the formalism of generalized nets. Following this stage-simulating model, the treatment of information inevitably includes phases, which require joint operations in two knowledge spaces – language and semantics. In order to examine and formalize the relations between the language and the semantic levels of treatment, the language is presented as an information system, conceived on the bases of human cognitive resources, semantic primitives, semantic operators and language rules and data. This approach is applied for modeling a specific grammatical rule – the secondary predication in Russian. Grammatical rules of the language space are expressed as operators in the semantic space. Examples from the linguistics domain are treated and several conclusions for the semantics of the modeled rule are made. The results of applying the information system approach to the language turn up to be consistent with the stages of treatment modeled with the generalized net.

Keywords: Cognitive model, Natural Language Processing, Generalized Net, Language Information System

ACM Classification Keywords: I.2.7 Natural Language Processing;

Link:

INFORMATION PROCESSING IN A COGNITIVE MODEL OF NLP

Velina Slavova, Alona Soschen, Luke Immes

http://www.foibg.com/ijita/vol12/ijita12-2-p08.pdf

Abstract: Malapropism is a semantic error that is hardly detectable because it usually retains syntactical links between words in the sentence but replaces one content word by a similar word with quite different meaning. A method of automatic detection of malapropisms is described, based on Web statistics and a specially defined Semantic Compatibility Index (SCI). For correction of the detected errors, special dictionaries and heuristic rules are proposed, which retains only a few highly SCI-ranked correction candidates for the user’s selection. Experiments on Web-assisted detection and correction of Russian malapropisms are reported, demonstrating efficacy of the described method.

Keywords: semantic error, malapropism, error correction, Web-assisted error detection, paronymy dictionaries, correction candidates, Semantic Compatibility Index.

ACM Classification Keywords: I.2.7 Artificial Intelligence: Natural language processing – Text analysis

Link:

EXPERIMENTS IN DETECTION AND CORRECTION OF RUSSIAN MALAPROPISMS BY MEANS OF THE WEB

Elena Bolshakova, Igor Bolshakov, Alexey Kotlyarov

http://www.foibg.com/ijita/vol12/ijita12-2-p06.pdf

Abstract: The paper reports on preliminary results of an ongoing research aiming at development of an automatic procedure for recognition of discourse-compositional structure of scientific and technical texts, which is required in many NLP applications. The procedure exploits as discourse markers various domain-independent words and expressions that are specific for scientific and technical texts and organize scientific discourse. The paper discusses features of scientific discourse and common scientific lexicon comprising such words and expressions. Methodological issues of development of a computer dictionary for common scientific lexicon are concerned; basic principles of its organization are described as well. Main steps of the discourse-analyzing procedure based on the dictionary and surface syntactical analysis are pointed out.

• The work is supported by the grant № 06-01-00571 of Russian Fond of Fundamental Researches (RFFI).

International Journal "Information Theories & Applications" Vol.15 / 2008 190

Keywords: scientific and technical prose, common scientific words and expressions, discourse markers, scientific discourse operations, discourse-compositional analysis.

ACM Classification Keywords: I.2.7 Artificial Intelligence: Natural language processing – Text analysis

Link:

COMMON SCIENTIFIC LEXICON FOR AUTOMATIC DISCOURSE ANALYSIS OF SCIENTIFIC AND TECHNICAL TEXTS *

Elena Bolshakova

http://www.foibg.com/ijita/vol15/ijita15-2-p15.pdf

Abstract: We analyze an approach to a similarity preserving coding of symbol sequences based on neural distributed representations and show that it can be viewed as a metric embedding process.

Keywords sequence similarity, edit distance, metric embeddings, distributed representations, neural networks

ACM Classification Keywords: I.2.6 Connectionism and neural nets, E.m Miscellaneous

Link:

SEARCHING FOR NEAREST STRINGS WITH NEURAL-LIKE STRING EMBEDDING

Artem Sokolov

http://www.foibg.com/ijita/vol14/ijita14-3-p16.pdf

Abstract. The paper discusses a logical expert statements represented as the formulas with probabilities of the first order language consistent with some theory T. Theoretical-models methods for setting metrics on such statements are offered. Properties of metrics are investigated. The research allows solve problems of the best reconciliation of expert statements, constructions of decision functions in pattern recognition, creations the bases of knowledge and development of expert systems.

Keywords: pattern recognition, distance between experts’ statements.

ACM Classification Keywords: I.2.6. Artificial Intelligence - Knowledge Acquisition.

Link:

MEASURE REFUTATIONS AND METRICS ON STATEMENTS OF EXPERTS (LOGICAL FORMULAS) IN THE MODELS FOR SOME THEORY1

Alexander Vikent’ev

http://www.foibg.com/ijita/vol14/ijita14-1-p15.pdf

Abstract: In the paper, an ontogenic artificial neural network (ANNs) is proposed. The network uses orthogonal activation functions that allow significant reducing of computational complexity. Another advantage is numerical stability, because the system of activation functions is linearly independent by definition. A learning procedure for proposed ANN with guaranteed convergence to the global minimum of error function in the parameter space is developed. An algorithm for structure network structure adaptation is proposed. The algorithm allows adding or deleting a node in real-time without retraining of the network. Simulation results confirm the efficiency of the proposed approach.

Keywords: ontogenic artificial neural network, orthogonal activation functions, time-series forecasting.

ACM Classification Keywords: I.2.6 Learning – Connectionism and neural nets

Link:

GROWING NEURAL NETWORKS USING NONCONVENTIONAL ACTIVATION FUNCTIONS

Yevgeniy Bodyanskiy, Iryna Pliss, Oleksandr Slipchenko

http://www.foibg.com/ijita/vol14/ijita14-3-p13.pdf

Abstract: Let Γ be a population of elements or objects concerned by the problem of recognition. By assumption, some experts give probabilistic predictions of unknown belonging classes γ of objects a∈Γ , being already aware of their description X (a) . In this paper, we present a method of aggregating sets of individual statements into a collective one using distances / similarities between multidimensional sets in heterogeneous feature space.

Keywords: pattern recognition, distance between experts statements, consensus.

ACM Classification Keywords: I.2.6. Artificial Intelligence - knowledge acquisition.

Link:

CONSTRUCTING OF A CONSENSUS OF SEVERAL EXPERTS STATEMENTS∗

Gennadiy Lbov, Maxim Gerasimov

http://www.foibg.com/ijita/vol14/ijita14-1-p12.pdf

Abstract: Transition P Systems are a parallel and distributed computational model based on the notion of the cellular membrane structure. Each membrane determines a region that encloses a multiset of objects and evolution rules. Transition P Systems evolve through transitions between two consecutive configurations that are determined by the membrane structure and multisets present inside membranes. Moreover, transitions between two consecutive configurations are provided by an exhaustive non-deterministic and parallel application of active evolution rules subset inside each membrane of the P system. But, to establish the active evolution rules subset, it is required the previous calculation of useful and applicable rules. Hence, computation of applicable evolution rules subset is critical for the whole evolution process efficiency, because it is performed in parallel inside each membrane in every evolution step. The work presented here shows advantages of incorporating decision trees in the evolution rules applicability algorithm. In order to it, necessary formalizations will be presented to consider this as a classification problem, the method to obtain the necessary decision tree automatically generated and the new algorithm for applicability based on it.

Keywords: Decision Tree, ID3, Evolution Rules, Applicability, Transition P System.

ACM Classification Keywords: I.2.6 Learning – Decision Tree; D.1.m Miscellaneous – Natural Computing

Link:

DECISION TREES FOR APPLICABILITY OF EVOLUTION RULES IN TRANSITION P SYSTEMS

Luis Fernandez, Fernando Arroyo, Ivan Garcia, Gines Bravo

http://www.foibg.com/ijita/vol14/ijita14-3-p05.pdf

Abstract: We discuss several approaches to similarity preserving coding of symbol sequences and possible connections of their distributed versions to metric embeddings. Interpreting sequence representation methods with embeddings can help develop an approach to their analysis and may lead to discovering useful properties.

Keywords: sequence similarity, metric embeddings, distributed representations, neural networks

ACM Classification Keywords: I.2.6 Connectionism and neural nets, E.m Miscellaneous, G.2.3 Applications

Link:

APPROACHES TO SEQUENCE SIMILARITY REPRESENTATION

Artem Sokolov, Dmitri Rachkovskij

http://www.foibg.com/ijita/vol13/ijita13-3-p11.pdf

Abstract: Modern enterprises work in highly dynamic environment. Thus, the developing of company strategy is of crucial importance. It determines the surviving of the enterprise and its evolution. Adapting the desired management goal in accordance with the environment changes is a complex problem. In the present paper, an approach for solving this problem is suggested. It is based on predictive control philosophy. The enterprise is modelled as a cybernetic system and the future plant response is predicted by a neural network model. The predictions are passed to an optimization routine, which attempts to minimize the quadratic performance criterion.

Keywords: enterprise strategy, model predictive control, neural network, black-box modeling, business trends.

ACM Classification Keywords: I.2.6 Artificial Intelligence: Neural nets; I.6.3 Simulation and Modeling: Applications

Link:

NEURAL NETWORK BASED APPROACH FOR DEVELOPING THE ENTERPRISE STRATEGY

Todorka Kovacheva, Daniela Toshkova

http://www.foibg.com/ijita/vol13/ijita13-2-p06.pdf

Abstract: Methods of analogous reasoning and case-based reasoning for intelligent decision support systems are considered. Special attention is drawn to methods based on a structural analogy that take the context into account. This work was supported by RFBR (projects 02-07-90042, 05-07-90232).

ACM Classification Keywords: I.2.6 Artificial intelligence: Learning – analogies; I.2.4 Artificial intelligence: Knowledge Representation Formalisms and Methods – semantic networks.

Link:

ANALOGOUS REASONING AND CASE-BASED REASONING FOR INTELLIGENT DECISION SUPPORT SYSTEMS

Alexander Eremeev, Pavel Varshavsky

http://www.foibg.com/ijita/vol13/ijita13-4-p03.pdf

Abstract: Usually, data mining projects that are based on decision trees for classifying test cases will use the probabilities provided by these decision trees for ranking classified test cases. We have a need for a better method for ranking test cases that have already been classified by a binary decision tree because these probabilities are not always accurate and reliable enough. A reason for this is that the probability estimates computed by existing decision tree algorithms are always the same for all the different cases in a particular leaf of the decision tree. This is only one reason why the probability estimates given by decision tree algorithms can not be used as an accurate means of deciding if a test case has been correctly classified. Isabelle Alvarez has proposed a new method that could be used to rank the test cases that were classified by a binary decision tree Alvarez, 2004. In this paper we will give the results of a comparison of different ranking methods that are based on the probability estimate, the sensitivity of a particular case or both.

ACM Classification Keywords: I.2.6 Learning – induction, concept learning; I.5.2 Classifier design and Evaluation

Link:

USING SENSITIVITY AS A METHOD FOR RANKING THE TEST CASES CLASSIFIED BY BINARY DECISION TREES

Sabrina Noblesse, Koen Vanhoof

http://www.foibg.com/ijita/vol13/ijita13-1-p01.pdf

Abstract: An approach is proposed for inferring implicative logical rules from examples. The concept of a good diagnostic test for a given set of positive examples lies in the basis of this approach. The process of inferring good diagnostic tests is considered as a process of inductive common sense reasoning. The incremental approach to learning algorithms is implemented in an algorithm DIAGaRa for inferring implicative rules from examples.

Keywords: Incremental and non-incremental learning, learning from examples, machine learning, common sense reasoning, inductive inference, good diagnostic test, lattice theory.

ACM Classification Keywords: I.2.6 Artificial Intelligence: Learning; K.2.3. Concept Learning

Link:

DIAGARA: AN INCREMENTAL ALGORITHM FOR INFERRING IMPLICATIVE RULES FROM EXAMPLES

Xenia Naidenova

http://www.foibg.com/ijita/vol12/ijita12-2-p10.pdf

Abstract: As is well known, the Convergence Theorem for the Recurrent Neural Networks, is based in Lyapunov´s second method, which states that associated to any one given net state, there always exist a real number, in other words an element of the one dimensional Euclidean Space R, in such a way that when the state of the net changes then its associated real number decreases. In this paper we will introduce the two dimensional Euclidean space R2, as the space associated to the net, and we will define a pair of real numbers ( x, y) , associated to any one given state of the net. We will prove that when the net change its state, then the product x ⋅ y will decrease. All the states whose projection over the energy field are placed on the same hyperbolic surface, will be considered as points with the same energy level. On the other hand we will prove that if the states are classified attended to their distances to the zero vector, only one pattern in each one of the different classes may be at the same energy level. The retrieving procedure is analyzed trough the projection of the states on that plane. The geometrical properties of the synaptic matrix W may be used for classifying the n-dimensional statevector space in n classes. A pattern to be recognized is seen as a point belonging to one of these classes, and depending on the class the pattern to be retrieved belongs, different weight parameters are used. The capacity of the net is improved and the spurious states are reduced. In order to clarify and corroborate the theoretical results, together with the formal theory, an application is presented

Keywords: Learning Systems, Pattern Recognition, Graph Theory, Image Processing, Recurrent Neural Networks.

ACM Classification Keywords: I.2.6 Learning: Connectionism and neural nets; G.2.2. Graph Theory; I.4.0 Image processing software

Link:

A NEW APPROACH FOR ELIMINATING THE SPURIOUS STATES IN RECURRENT NEURAL NETWORKS

Víctor Giménez-Martínez?, Carmen Torres, José Joaquín Erviti Anaut, Mercedes Perez-Castellanos?

http://www.foibg.com/ijita/vol12/ijita12-2-p03.pdf

Abstract: The architecture of adaptive wavelet-neuro-fuzzy-network and its learning algorithm for the solving of nonstationary processes forecasting and emulation tasks are proposed. The learning algorithm is optimal on rateof convergence and allows tuning both the synaptic weights and dilations and translations parameters of waveletactivation functions. The simulation of developed wavelet-neuro-fuzzy network architecture and its learningalgorithm justifies the effectiveness of proposed approach.

Keywords: wavelet, adaptive wavelet-neuro-fuzzy network, recurrent learning algorithm, forecasting, emulation.

ACM Classification Keywords: I.2.6 Learning – Connectionism and neural nets

Link:

ADAPTIVE WAVELET-NEURO-FUZZY NETWORK IN THE FORECASTING AND EMULATION TASKS

Yevgeniy Bodyanskiy, Iryna Pliss, Olena Vynokurova

http://www.foibg.com/ijita/vol15/ijita15-1-p08.pdf

Abstract: The paper presents basic notions and scientific achievements in the field of program transformations, describes usage of these achievements both in the professional activity (when developing optimizing and unparallelizing compilers) and in the higher education. It also analyzes main problems in this area. The concept of control of program transformation information is introduced in the form of specialized knowledge bank on computer program transformations to support the scientific research, education and professional activity in the field. The tasks that are solved by the knowledge bank are formulated. The paper is intended for experts in the artificial intelligence, optimizing compilation, postgraduates and senior students of corresponding specialties; it may be also interesting for university lecturers and instructors.

Keywords: Knowledge bank; Ontology; Knowledge base; Ontology editor; Database editor; Knowledge processing; Program transformations; Optimizing compilation

ACM Classification Keywords: I.2.5 Artificial intelligence: programming languages and software

Link:

A WEB-SYSTEM FOR COMPUTER EXPERIMENTS IN THE FIELD OF PROGRAM TRANSFORMATIONS

Margarita Knyazeva, Alexander Kleshchev

http://www.foibg.com/ijita/vol13/ijita13-4-p05.pdf

Abstract: An approach for knowledge extraction from the information arriving to the knowledge base input and also new knowledge distribution over knowledge subsets already present in the knowledge base is developed. It is also necessary to realize the knowledge transform into parameters (data) of the model for the following decision-making on the given subset. It is assumed to realize the decision-making with the fuzzy sets’ apparatus.

ACM Classification Keywords: I.2.5 - Expert Systems; I.2.6 - Knowledge acquisition

Link:

METHODS OF ADAPTIVE EXTRACTION AND ANALYSIS OF KNOWLEDGEFOR KNOWLEDGE-BASE CONSTRUCTION AND FAST DECISION MAKING

Alexander Kuzemin, Darya Fastova, Igor Yanchevsky

http://www.foibg.com/ijita/vol12/ijita12-1-p13.pdf