In this thesis, research efforts are dedicated towards the development of practical adaptable techniques to be used in Smart Homes and Buildings, with the aim to improve energy management and conservation, while enhancing the learning capabilities of Programmable Communicating Thermostats (PCT) – “transforming” them into smart adaptable devices, i.e., “Smart Thermostats”. An Adaptable Hybrid Intelligent System utilizing Wireless Sensor Network (WSN) and Artificial Intelligence (AI) techniques is presented, based on which, a novel Adaptive Learning System (ALS) model utilizing WSN, a rule-based system and Adaptive Resonance Theory (ART) concepts is proposed. The main goal of the ALS is to adapt to the occupant’s pattern and/or schedule changes by providing comfort, while not ignoring the energy conservation aspect. The proposed ALS analytical model is a technique which enables PCTs to learn and adapt to user input pattern changes and/or other parameters of interest. A new algorithm for finding the global maximum in a predefined interval within a two dimensional space is proposed. The proposed algorithm is a synergy of reward/punish concepts from the reinforcement learning (RL) and agent-based technique, for use in small-scale embedded systems with limited memory and/or processing power, such as the wireless sensor/actuator nodes. An application is implemented to observe the algorithm at work and to demonstrate its main features. It was observed that the “RL and Agent-based Search”, versus the “RL only” technique, yielded better performance results with respect to the number of iterations and function evaluations needed to find the global maximum. Furthermore, a “House Simulator” is developed as a tool to simulate house heating/cooling systems and to assist in the practical implementation of the ALS model under different scenarios. The main building blocks of the simulator are the “House Simulator”, the “Smart Thermostat”, and a placeholder for the “Adaptive Learning Models”. As a result, a novel adaptive learning algorithm, “Observe, Learn and Adapt” (OLA) is proposed and demonstrated, reflecting the main features of the ALS model. Its evaluation is achieved with the aid of the “House Simulator”. OLA, with the use of sensors and the application of the ALS model learning technique, captures the essence of an actual PCT reflecting a smart and adaptable device. The experimental performance results indicate adaptability and potential energy savings of the single in comparison to the zone controlled scenarios with the OLA capabilities being enabled.

This thesis deals with the study of home automation systems. The main goal of this thesis is to prove their effectiveness. The sample project shows how to calculate the efficiency and profitability of investment in the home automation systems. The result of this work is a methodology for determining the efficiency of investment projects into automation systems. The work is divided into two parts. The theoretical part is to provide the reader with the basic understanding of automation systems. their functionality and their advantages and disadvantages. A technical model is provided describing an automation system iNELS. The practical part describes the procedures and the outcomes of the effectiveness of the system.

Recent advances in technology have increased awareness of the necessity for automated systems in people’s everyday lives. Artificial systems are more frequently being introduced into environments previously thought to be too perilous for humans to operate in. Some robots can be used to extract potentially hazardous materials from sites inaccessible to humans, while others are being developed to aid humans with laborious tasks. A crucial aspect of all artificial systems is the manner in which they interact with their immediate surroundings. Developing such a deceivingly simply aspect has proven to be significantly challenging, as it not only entails the methods through which the system perceives its environment, but also its ability to perform critical tasks. These undertakings often involve the coordination of numerous subsystems, each performing its own complex duty. To complicate matters further, it is nowadays becoming increasingly important for these artificial systems to be able to perform their tasks in real-time. The task of object recognition is typically described as the process of retrieving the object in a database that is most similar to an unknown, or query, object. Pose estimation, on the other hand, involves estimating the position and orientation of an object in three-dimensional space, as seen from an observer’s viewpoint. These two tasks are regarded as vital to many computer vision techniques and regularly serve as input to more complex perception algorithms. An approach is presented which regards the object recognition and pose estimation procedures as mutually dependent. The core idea is that dissimilar objects might appear similar when observed from certain viewpoints. A feature-based conceptualisation, which makes use of a database, is implemented and used to perform simultaneous object recognition and pose estimation. The design incorporates data compression techniques, originally suggested by the image-processing community, to facilitate fast processing of large databases. System performance is quantified primarily on object recognition, pose estimation and execution time characteristics. These aspects are investigated under ideal conditions by exploiting three-dimensional models of relevant objects. The performance of the system is also analysed for practical scenarios by acquiring input data from a structured light implementation, which resembles that obtained from many commercial range scanners. Practical experiments indicate that the system was capable of performing simultaneous object recognition and pose estimation in approximately 230 ms once a novel object has been sensed. An average object recognition accuracy of approximately 73% was achieved. The pose estimation results were reasonable but prompted further research. The results are comparable to what has been achieved using other suggested approaches such as Viewpoint Feature Histograms and Spin Images. / Dissertation (MEng)--University of Pretoria, 2013. / gm2014 / Electrical, Electronic and Computer Engineering / unrestricted

No description available.

Master's thesis of Pliner A.A. "Cognitive Science: an integrated approach" is devoted to the study of cognitive science as a set of scientific research in various fields of philosophy, psychology, artificial intelligence, linguistics, united by a common research interest in the issue of knowledge. The emergence of interest in cognitive science could attributed to the middle of the XX century and related to the work of such thinkers as J. Miller, N. Chomsky, W. McCarthy and others. At the present stage of development, it is time to study the cognitive sciences as systems containing components operating in other systems and having different nature, and they connected with the original system in the complex functional dependence. The aim of investigation is the implementation of an integrated approach to the analysis of the phenomenon of cognitive sciences. The object of study - a cognitive science as a set. Subject of research – a specific complex relationship cognitive sciences and their implementation in a variety of applications. The work consists of four chapters. The first chapter is devoted to the history of the formation of the concept of cognitive science, the second chapter describes the basic methods of the cognitive sciences, the third chapter highlights the major features of complexing cognitive sciences, the fourth chapter builds complex cognitive science as an element of other polysystem. / Магистерская диссертация Плинер А.А. "Cognitive Science: комплексный подход" посвящена изучению когнитивных наук как комплекса научных исследований в различных областях философии, психологии, искусственного интеллекта, лингвистики, объединенных единым исследовательским интересом к вопросу познания. Возникновение интереса к когнитивным наукам можно отнести к середине XX в. и связать с работами таких мыслителей, как Дж. Миллер, Н. Хомский, У. Маккарти и других. На современном этапе развития пришло время изучения когнитивных наук как системы, содержащей элементы, функционирующие и в других системах, имеющих иную природу, и находящихся с первоначальной системой в сложной функциональной зависимости. Целью работы является осуществление комплексного подхода к анализу феномена когнитивных наук. Объект исследования – это когнитивные науки как комплекс. Предмет исследования – специфические комплексные взаимосвязи когнитивных наук и их реализация в различных сферах применения. Работа состоит из четырех глав. Первая глава посвящена истории формирования понятия когнитивных наук, вторая глава описывает основные методы когнитивных наук, третья глава выделяет основные комплексообразующие черты когнитивных наук, четвертая глава строит комплекс когнитивных наук как элемент других полисистем.

Магистерская диссертация Макуриной А.Ю. "Воображение как когнитивный процесс" посвящена воображению как когнитивному процессу и к проблеме его развития в процессе когнитивной деятельности. В известных психологических концепциях (Леонтьев В.Г., Майер Г., Маслоу А., Рибо Т. и другие). нет единого подхода к классификации воображения, нет определенного понимания когнитивной деятельности, нет единого взгляда на виды воображения. Целью исследования является изучение воображения как когнитивного процесса и его развития в процессе когнитивной деятельности. Объект исследования - воображение как когнитивный процесс и психическая деятельность. Предмет исследования – факторы развития воображения в процессе когнитивной деятельности. Работа состоит из двух глав. В первой главе рассмотрена дефиниция понятия «воображение», принятая в психологии, исследовано воображение как творческий процесс и форма психической деятельности, проанализирован онтогенез воображения и проведено разграничение понятия «воображение» от понятий «мышление», «представление», «память». Во второй главе дано подробное определение когнитивной деятельности, когнитивной мотивации и рассмотрено их влияние на развитие воображения, изучен феномен понимания и его связь с воображением. / Master's thesis of Makurina A.Y. "The imagination as a cognitive process" devoted to the imagination as a cognitive process and the issue of its development in the process of cognitive activity. In the known psychological concepts (V.G. Leont'ev, G. Meyer, A. Maslow, T. Ribot and others), there is no unit approach to the classification of the imagination, there is no certain understanding of cognitive activity, there is no common view on the types of imagination. The aim of the study is the investigation of imagination as a cognitive process and its development in the process of cognitive activity. The object of study - the imagination as a cognitive process and mental activity. Subject of research - the factors of development of imagination in the process of cognitive activity. The work consists of two chapters. The first chapter examined the definition of the concept "imagination", adopted in psychology, studied the imagination as a creative process and a form of mental activity, to analyze the ontogeny of the imagination and held distinction between "imagination" of the concepts of "thinking", "view", "memory". The second chapter provides a detailed definition of cognitive activity, cognitive motivation, and examines their impact on the development of imagination, also examines the phenomenon of understanding and its relationship with the imagination.

Embodied Conversational Agents (ECA) form part of a range of virtual characters whose intended purpose include engaging in natural conversations with human users. While works in literature are ripe with descriptions of attempts at producing viable ECA architectures, few authors have addressed the role of episodic memory models in conversational agents. This form of memory, which provides a sense of autobiographic record-keeping in humans, has only recently been peripherally integrated into dialog management tools for ECAs. In our work, we propose to take a closer look at the shared characteristics of episodic memory models in recent examples from the field. Additionally, we propose several enhancements to these existing models through a unified episodic memory model for ECA's. As part of our research into episodic memory models, we present a process for determining the prevalent contexts in the conversations obtained from the aforementioned interactions. The process presented demonstrates the use of statistical and machine learning services, as well as Natural Language Processing techniques to extract relevant snippets from conversations. Finally, mechanisms to store, retrieve, and recall episodes from previous conversations are discussed. A primary contribution of this research is in the context of contemporary memory models for conversational agents and cognitive architectures. To the best of our knowledge, this is the first attempt at providing a comparative summary of existing works. As implementations of ECAs become more complex and encompass more realistic conversation engines, we expect that episodic memory models will continue to evolve and further enhance the naturalness of conversations.

Este trabalho apresenta um conjunto de métodos para a proteção e o monitoramento de transformadores de potência baseado em sistemas inteligentes e na aplicação das transformadas de Clarke e Wavelet. A abordagem inteligente utilizada permite analisar a condição operativa dos transformadores de potência e detectar a ocorrência de defeito interno, distinguindo-a de outras situações de operação, como, a energização, a energização solidária, a saturação dos transformadores de corrente e a sobreexcitação. As tomadas de decisão das técnicas desenvolvidas são realizadas pela lógica fuzzy após o pré-processamento dos sinais de entrada por meio de diversos métodos, os quais variam de acordo com o algoritmo que esta sendo executado. Os algoritmos propostos foram testados por meio de simulações realizadas através do software Alternative Transients Program (ATP). É importante salientar que nas simulações do ATP foram modelados diversos equipamentos que constituem o sistema elétrico de potência, incluindo um gerador síncrono com regulação de velocidade, linhas de transmissão com variação em frequência, transformadores de potência com suas respectivas curvas de saturação, transformadores de potencial e de corrente. Estas modelagens tiveram por objetivo gerar dados das distintas situações de operação para a verificação e análise da metodologia proposta. Os resultados da pesquisa mostram a aplicabilidade dos algoritmos propostos na proteção e no monitoramento dos transformadores de potência, mesmo nas condições mais adversas, como na ocorrência da saturação dos transformadores de corrente, uma vez que os sinais de entrada distorcidos pela saturação são corrigidos por uma rede neural artificial. Os resultados apresentados comparam as respostas obtidas pelas técnicas propostas em relação às saídas de um relé comercial, habilitado à proteção diferencial percentual. / This work presents a set of methods for protecting and monitoring power transformers based on intelligent systems and the application of Clarke and Wavelet transforms. The intelligent approach allowed us to analyze the operating condition of power transformers and it discriminates between an internal fault and different operating conditions, as energization, sympathetic inrush, saturation of current transformers and overexcitation. Decision making is performed by fuzzy logic after the preprocessing of the input signals through various methods, varying according to which algorithm is running. It is important to point out that in the simulations using ATP many different power system equipment had been modeled, including a synchronous generator with speed regulation, transmission lines with variation in frequency, power transformers with their saturation curves, potential transformers and current transformers. The objective of these tests was to generate data for distinct situations for the verification and the analysis of the proposed methodologies. The results of the research show the applicability of the algorithms considered in protection and monitoring of power transformers, even in adverse conditions, such as saturation of current transformers, since the input signals are distorted by CT saturation corrected by artificial neural network. The results are compared to the ones presented by a commercial percentage differential relay.

Este trabalho tem por objetivo desenvolver uma abordagem fuzzy focando na estimação de curto prazo da demanda de potência ativa de um alimentador de sistema de distribuição de energia elétrica. A motivação para este trabalho encontra-se na redução do erro de estimação para que o sistema de distribuição como um todo seja corretamente operado. O destaque da abordagem desenvolvida é a metodologia de seleção de entradas para o sistema de estimação, que o treina fornecendo-lhe informações não redundantes e não desnecessárias sobre o comportamento da série temporal. Os resultados, obtidos com treinamento e teste de um sistema de inferência fuzzy multicamadas, mostram que as estimações realizadas selecionando as entradas do sistema de forma criteriosa apresentam menor erro que quando não há critério de seleção. Conclui-se então que a metodologia foi funcional e eficiente para o caso estudado, o que faz com que este trabalho resulte em válidas contribuições nas áreas de sistemas inteligentes, de sistemas dinâmicos e inclusive na forma metodológica de especificação de modelos de estimação de séries temporais. / This work aims to develop a fuzzy approach focusing on the short-term active power demand forecast in a feeder of an electrical energy distribution system. This work motivation lies on the reduction of the forecast error so that the whole distribution system can be correctly operated. The highlight of the developed approach is the methodology to select the inputs for the estimation system, which trains it giving to it non-redundant and non-unnecessary information about the time series behavior. The results, obtained by training and testing a multilayer fuzzy inference system, show that the estimations made by following a criterion to select the inputs have smaller error than when there is no selection criterion at all. It is therefore concluded that the methodology was functional and efficient for the case under study, what makes this work result in valid contributions for the fields of intelligent systems, dynamic systems and in the methodological way to specify models to estimate time series.

Os motores de indução desempenham um importante papel na indústria, fato este que destaca a importância do correto diagnóstico e classificação de falhas ainda em fase inicial de sua evolução, possibilitando aumento na produtividade e, principalmente, eliminando graves danos aos processos e às máquinas. Assim, a proposta desta tese consiste em apresentar um multiclassificador inteligente para o diagnóstico de motor sem defeitos, falhas de curto-circuito nos enrolamentos do estator, falhas de rotor e falhas de rolamentos em motores de indução trifásicos acionados por diferentes modelos de inversores de frequência por meio da análise das amplitudes dos sinais de corrente de estator no domínio do tempo. Para avaliar a precisão de classificação frente aos diversos níveis de severidade das falhas, foram comparados os desempenhos de quatro técnicas distintas de aprendizado de máquina; a saber: (i) Rede Fuzzy Artmap, (ii) Rede Perceptron Multicamadas, (iii) Máquina de Vetores de Suporte e (iv) k-Vizinhos-Próximos. Resultados experimentais obtidos a partir de 13.574 ensaios experimentais são apresentados para validar o estudo considerando uma ampla faixa de frequências de operação, bem como regimes de conjugado de carga em 5 motores diferentes. / Induction motors play an important role in the industry, a fact that highlights the importance of correct diagnosis and classification of faults on these machines still in early stages of their evolution, allowing increase in productivity and mainly, eliminating major damage to the processes and machines. Thus, the purpose of this thesis is to present an intelligent multi-classifier for the diagnoses of healthy motor, short-circuit faults in the stator windings, rotor broken bars and bearing faults in induction motors operating with different models of frequency inverters by analyzing the amplitude of the stator current signal in the time domain. To assess the classification accuracy across the various levels of faults severity, the performances of four different learning machine techniques were compared; namely: (i) Fuzzy ARTMAP network, (ii) Multilayer Perceptron Network, (iii) Support Vector Machine and (iv) k-Nearest-Neighbor. Experimental results obtained from 13.574 experimental tests are presented to validate the study considering a wide range of operating frequencies and also load conditions using 5 different motors.