DSpace Community: 2009
http://hdl.handle.net/10525/982
The Community's search engineSearch the Channelsearch
http://sci-gems.math.bas.bg/jspui/simple-search
Generating More Boundary Elements of Subset Projections
http://hdl.handle.net/10525/1222
Title: Generating More Boundary Elements of Subset Projections<br/><br/>Authors: Sahakyan, Hasmik; Aslanyan, Levon<br/><br/>Abstract: Composition problem is considered for partition constrained vertex subsets of n dimensional unit cube E^n . Generating numerical characteristics of E^n subsets partitions is considered by means of the same characteristics in 1 − n dimensional unit cube, and construction of corresponding subsets is given for a special particular case. Using pairs of lower layer characteristic vectors for E^(1-n) more characteristic vectors for E^n are composed which are boundary from one side, and which take part in practical recognition of validness of a given candidate vector of partitions.Self Evolving Character Recognition Using Genetic Operators
http://hdl.handle.net/10525/1221
Title: Self Evolving Character Recognition Using Genetic Operators<br/><br/>Authors: Mathur, Shashank<br/><br/>Abstract: In this paper, a novel approach for character recognition has been presented with the help of genetic operators which have evolved from biological genetics and help us to achieve highly accurate results. A genetic algorithm approach has been described in which the biological haploid chromosomes have been implemented using a single row bit pattern of 315 values which have been operated upon by various genetic operators. A set of characters are taken as an initial population from which various new generations of characters are generated with the help of selection, crossover and mutation. Variations of population of characters are evolved from which the fittest solution is found by subjecting the various populations to a new fitness function developed. The methodology works and reduces the dissimilarity coefficient found by the fitness function between the character to be recognized and members of the populations and on reaching threshold limit of the error found from dissimilarity, it recognizes the character. As the new population is being generated from the older population, traits are passed on from one generation to another. We present a methodology with the help of which we are able to achieve highly efficient character recognition.Implementation of Genetic Algorithms for Transit Points Arrangement
http://hdl.handle.net/10525/1220
Title: Implementation of Genetic Algorithms for Transit Points Arrangement<br/><br/>Authors: Panchenko, Dmitry; Shcherbakov, Maxim<br/><br/>Abstract: The problem of transit points arrangement is presented in the paper. This issue is connected with accuracy of tariff distance calculation and it is the urgent problem at present. Was showed that standard method of tariff distance discovering is not optimal. The Genetic Algorithms are used in optimization problem resolution. The UML application class diagram and class content are showed. In the end the example of transit points arrangement is represented.Analysis of P-Systems under a Multiagent Systems Perspective
http://hdl.handle.net/10525/1219
Title: Analysis of P-Systems under a Multiagent Systems Perspective<br/><br/>Authors: Arteta, Alberto; Goñi, Angel; Castellanos, Juan<br/><br/>Abstract: Membrane computing is a recent area that belongs to natural computing. This field works on computational models based on nature's behavior to process the information. Recently, numerous models have been developed and implemented with this purpose. P-systems are the structures which have been defined, developed and implemented to simulate the behavior and the evolution of membrane systems which we find in nature. What we show in this paper is an application capable to simulate the P-systems based on a multiagent systems (MAS) technology. The main goal we want to achieve is to take advantage of the inner qualities of the multiagent systems. This way we can analyse the proper functioning of any given p-system. When we observe a P-system from a different perspective, we can be assured that it is a particular case of the multiagent systems. This opens a new possibility, in the future, to always evaluate the P-systems in terms of the multiagent systems technology.The Cascade Neo-Fuzzy Architecture and its Online Learning Algorithm
http://hdl.handle.net/10525/1218
Title: The Cascade Neo-Fuzzy Architecture and its Online Learning Algorithm<br/><br/>Authors: Bodyanskiy, Yevgeniy; Viktorov, Yevgen<br/><br/>Abstract: In the paper learning algorithm for adjusting weight coefficients of the Cascade Neo-Fuzzy Neural Network (CNFNN) in sequential mode is introduced. Concerned architecture has the similar structure with the Cascade-Correlation Learning Architecture proposed by S.E. Fahlman and C. Lebiere, but differs from it in type of artificial neurons. CNFNN consists of neo-fuzzy neurons, which can be adjusted using high-speed linear learning procedures. Proposed CNFNN is characterized by high learning rate, low size of learning sample and its operations can be described by fuzzy linguistic “if-then” rules providing “transparency” of received results, as compared with conventional neural networks. Using of online learning algorithm allows to process input data sequentially in real time mode.The Production Scheduling in Assembly System with Evolutionary Algorithm
http://hdl.handle.net/10525/1217
Title: The Production Scheduling in Assembly System with Evolutionary Algorithm<br/><br/>Authors: Setlak, Galina<br/><br/>Abstract: In this paper an evolutionary algorithm is proposed for solving the problem of production scheduling in assembly system. The aim of the paper is to investigate a possibility of the application of evolutionary algorithms in the assembly system of a normally functioning enterprise producing household appliances to make the production graphic schedule.Отображение и Вывод по Аналогии на Основе Нейросетевых Распределенных Представлений
http://hdl.handle.net/10525/1216
Title: Отображение и Вывод по Аналогии на Основе Нейросетевых Распределенных Представлений<br/><br/>Authors: Слипченко, Сергей; Рачковский, Дмитрий<br/><br/>Abstract: Развит подход к рассуждениям по аналогии для иерархически структурированных описаний эпизодов, ситуаций и их компонентов на базе представлений аналогов в виде особой формы векторных представлений - распределенных кодвекторных представлений. Предложены распределенные представления компонентов аналогов, позволяющие непосредственно определять соответствующие друг другу представления компонентов для реализации стадии отображения двух аналогов, а также метод вывода по аналогии на их основе. Предложенные методы исследованы на базах аналогий, которые ранее применялись для исследования ведущих моделей аналогии - SME и ACME. Полученные результаты находятся на уровне результатах SME и ACME, однако за счет использования сходства векторных представления обладают низкой вычислительной сложностью и создают основу для более адекватного учета семантики аналогов и их компонентов. Это делает предложенные методы перспективными для отображения фрагментов баз знаний с большим числом компонентов.Применение Нейронной Сети Хемминга и Нечеткой Логики к Обнаружению Краев Объектов на Изображениях в Оттенках Серого
http://hdl.handle.net/10525/1215
Title: Применение Нейронной Сети Хемминга и Нечеткой Логики к Обнаружению Краев Объектов на Изображениях в Оттенках Серого<br/><br/>Authors: Мурга, Николай<br/><br/>Abstract: В данной работе исследуется применение нейронной сети Хемминга для обнаружения краёв объектов на изображении. Изображение в оттенках серого, поступающее на вход предлагаемой системы, подвергается преобразованию с применением нечёткой логики в двуцветное. После этого из изображения последовательно выделяются блоки пикселей заданной размерности и подаются на входы предварительно инициализированной сети Хемминга. Нейронная сеть выполняет идентификацию краёв в блоке, и в новом изображении вставляет на место блока шаблон, который отвечает коду, полученному на выходе сети. Работу завершает практическое применение метода.Инструментальная Среда для Исследования Эволюционных Стратегий с Использованием Нейросетевых Метамоделей
http://hdl.handle.net/10525/1214
Title: Инструментальная Среда для Исследования Эволюционных Стратегий с Использованием Нейросетевых Метамоделей<br/><br/>Authors: Афонин, Павел<br/><br/>Abstract: В статье представлена инструментальная среда для исследования эволюционных стратегий, которые используют механизм аппроксимации целевой функции с помощью аппарата нейронных сетей. Приводится описание алгоритма эволюционной стратегии и подходы к построению метамоделей. Рассмотрены существующие на сегодняшний день алгоритмы оптимизации на основе эволюционных стратегий и метамоделей. Отмечается актуальность применения механизмов адаптации в таких алгоритмах. Описаны основные функции и возможности инструментальной среды. Средством реализации является программный пакет MatLab v.7.1.The Usage of Neural Networks for the Medical Diagnosis
http://hdl.handle.net/10525/1213
Title: The Usage of Neural Networks for the Medical Diagnosis<br/><br/>Authors: Malyshevska, Kateryna<br/><br/>Abstract: The problem of cancer diagnosis from multi-channel images using the neural networks is investigated. The goal of this work is to classify the different tissue types which are used to determine the cancer risk. The radial basis function networks and backpropagation neural networks are used for classification. The results of experiments are presented.Performance Comparison of MATLAB and Neuro Solution Software on Estimation of Fuel Economy by Using Artificial Neural Network
http://hdl.handle.net/10525/1212
Title: Performance Comparison of MATLAB and Neuro Solution Software on Estimation of Fuel Economy by Using Artificial Neural Network<br/><br/>Authors: Serhad Soyhan, Hakan; Emre Kilic, Mehmet; Gokalp, Burak; Taymaz, Imdat<br/><br/>Abstract: In the world, scientific studies increase day by day and computer programs facilitate the human’s life. Scientists examine the human’s brain’s neural structure and they try to be model in the computer and they give the name of artificial neural network. For this reason, they think to develop more complex problem’s solution. The purpose of this study is to estimate fuel economy of an automobile engine by using artificial neural network (ANN) algorithm. Engine characteristics were simulated by using “Neuro Solution” software. The same data is used in MATLAB to compare the performance of MATLAB is such a problem and show its validity. The cylinder, displacement, power, weight, acceleration and vehicle production year are used as input data and miles per gallon (MPG) are used as target data. An Artificial Neural Network model was developed and 70% of data were used as training data, 15% of data were used as testing data and 15% of data is used as validation data. In creating our model, proper neuron number is carefully selected to increase the speed of the network. Since the problem has a nonlinear structure, multi layer are used in our model.Self-Learning Fuzzy Spiking Neural Network as a Nonlinear Pulse-Position Threshold Detection Dynamic System Based on Second-Order Critically Damped Response Units
http://hdl.handle.net/10525/1211
Title: Self-Learning Fuzzy Spiking Neural Network as a Nonlinear Pulse-Position Threshold Detection Dynamic System Based on Second-Order Critically Damped Response Units<br/><br/>Authors: Bodyanskiy, Yevgeniy; Dolotov, Artem; Pliss, Iryna<br/><br/>Abstract: Architecture and learning algorithm of self-learning spiking neural network in fuzzy clustering task are outlined. Fuzzy receptive neurons for pulse-position transformation of input data are considered. It is proposed to treat a spiking neural network in terms of classical automatic control theory apparatus based on the Laplace transform. It is shown that synapse functioning can be easily modeled by a second order damped response unit. Spiking neuron soma is presented as a threshold detection unit. Thus, the proposed fuzzy spiking neural network is an analog-digital nonlinear pulse-position dynamic system. It is demonstrated how fuzzy probabilistic and possibilistic clustering approaches can be implemented on the base of the presented spiking neural network.Определение Понятия «Смысл» Через Онтологию. Семантический Анализ Текстов Естественного Языка
http://hdl.handle.net/10525/1210
Title: Определение Понятия «Смысл» Через Онтологию. Семантический Анализ Текстов Естественного Языка<br/><br/>Authors: Святогор, Леонид; Гладун, Виктор<br/><br/>Abstract: Предложен новый подход к понятию «смысл» и дано его формально-графическое определение через онтологию. Рассмотрена задача семантического (смыслового) анализа текстов ЕЯ, которая основана на процедуре поиске подграфа концептуального графа, отображающего знания о мире.Обработка Предложений Естественного Языка с Использованием Словарей и Частоты Появления Слов
http://hdl.handle.net/10525/1209
Title: Обработка Предложений Естественного Языка с Использованием Словарей и Частоты Появления Слов<br/><br/>Authors: Палагин, Александр; Крывый, Сергей; Бибиков, Дмитрий<br/><br/>Abstract: Описывается один из подходов к анализу естественно-языкового текста, который использует толковый словарь естественного языка, локальный словарь анализируемого текста и частотные характеристики слов в этом тексте.К Анализу Естественно-Языковых Объектов
http://hdl.handle.net/10525/1208
Title: К Анализу Естественно-Языковых Объектов<br/><br/>Authors: Палагин, Александр; Крывый, Сергей; Величко, Виталий; Петренко, Николай<br/><br/>Abstract: Рассматриваются проблемы анализа естественно-языковых объектов (ЕЯО) с точки зрения их представления и обработки в памяти компьютера. Предложена формализация задачи анализа ЕЯО и приведен пример формализованного представления ЕЯО предметной области.Computer Support of Semantic Text Analysis of a Technical Specification on Designing Software
http://hdl.handle.net/10525/1207
Title: Computer Support of Semantic Text Analysis of a Technical Specification on Designing Software<br/><br/>Authors: Zaboleeva-Zotova, Alla; Orlova, Yulia<br/><br/>Abstract: The given work is devoted to development of the computer-aided system of semantic text analysis of a technical specification. The purpose of this work is to increase efficiency of software engineering based on automation of semantic text analysis of a technical specification. In work it is offered and investigated a technique of the text analysis of a technical specification is submitted, the expanded fuzzy attribute grammar of a technical specification, intended for formalization of limited Russian language is constructed with the purpose of analysis of offers of text of a technical specification, style features of the technical specification as class of documents are considered, recommendations on preparation of text of a technical specification for the automated processing are formulated. The computer-aided system of semantic text analysis of a technical specification is considered. This system consist of the following subsystems: preliminary text processing, the syntactic and semantic analysis and construction of software models, storage of documents and interface.