The thesis describes a model of electromagnetic pulses from sources between 100MHz and 100GHz for use in the development of Knowledge-Based systems. Each pulse, including its modulations, is described as would be seen by a definable receiving system. The model has been validated against a range of Knowledge-Based systems including a neural network, a Learning systems and an Expert system.

<p dir="ltr">Axial spondyloarthritis (axSpA), a disease that due to its complexity and rarity, presents challenges in diagnosis. With a focus on integrating expert knowledge into an intelligent diagnostic system, the research explores the intricate nature of axSpA, emphasizing the challenges associated with its diverse clinical presentation. By leveraging a comprehensive knowledge base curated by domain experts, encompassing insights into pathophysiology, genetic factors, and evolving diagnostic criteria of axSpA, the expert system strives to provide a nuanced understanding of the disease. The methodology employs a hybrid reasoning approach, combining both forward and backward chaining techniques. Forward chaining iteratively processes clinical data and available evidence, applying logical rules to infer potential diagnoses and refine hypotheses, while backward chaining starts with the desired diagnostic goal and works backward through the knowledge base to validate or refute hypotheses. Additionally, certainty theory is incorporated to manage uncertainty in the diagnostic process, assigning confidence levels to conclusions based on the strength of evidence and expert knowledge. By integrating knowledge base, forward and backward chaining, and certainty theory, the research aims to enhance diagnostic precision for this less common yet impactful inflammatory rheumatic condition, emphasizing the importance of early and accurate identification for effective management and improved patient outcomes. The results indicate a significant improvement in diagnostic accuracy, sensitivity, and specificity compared to traditional methods. The system's potential to enhance early diagnosis and treatment outcomes is discussed, along with suggestions for future research to further refine and expand the system.</p>

O sistema especialista SISTEMAT tem por objetivo auxiliar pesquisadores da área de produtos naturais no processo de determinação estrutural de substâncias. Para tanto, utilizando dados provenientes de várias técnicas espectrométricas e espectroscópicas, principalmente RMN 13C, inúmeros programas foram desenvolvidos com a finalidade de propor o provável esqueleto de uma substância. Essa informação, juntamente com as substruturas apresentadas a partir de um conjunto de dados, é utilizada por geradores estruturais como grandes restrições, a fim de impedir a explosão combinatória e a geração de propostas estruturais incompatíveis com produtos naturais, além de reduzir o elevado tempo computacional gasto durante uma análise. Esse trabalho descreve o desenvolvimento e utilização dos módulos de reconhecimento de esqueletos, determinação e geração estrutural e simulação de dados de RMN 13C de esteróides. Assim, foi elaborada uma base de dados com 1436 substâncias distribuídas entre 119 tipos de esqueletos provenientes das mais diversas fontes naturais. Vários testes foram realizados e bons percentuais de acerto foram obtidos para o reconhecimento de esqueletos e geração de propostas estruturais através da sobreposição dos tipos de anéis encontrados em esqueletos de esteróides. Para validar as propostas estruturais apresentadas pelo gerador, bem como para prever os dados de deslocamentos químicos de novos esteróides, o simulador de dados de RMN 13C foi usado e, quando comparado a um programa comercial de mesma finalidade, apresentou maior exatidão na previsão dos dados. / The aim of the expert system SISTEMAT is to aid natural product researchers in the process of structural determination of organic substances. For that, using data from various spectrometric and spectroscopic techniques, mainly 13C NMR, countless programs were developed to propose the most probable skeleton of a substance. This information together with the substructures shown from the data set are utilized by structural generators as important constraints in order to avoid the combinatorial explosion problem and the generation of incompatible structural proposals for natural products, besides reducing the computational time spent during the analysis. This work describes the development and use of the modules of skeleton identification, structural determination and generation, and the 13C NMR data prediction of steroids. Thus, was built a database containing 1436 steroids distributed in 119 different skeletons originated from the most varied natural sources. Several tests were performed, wherein good hit percentuals were obtained for the skeleton identification and structural generation through the overlapping of the types of rings found in the steroid skeletons. For validation of the structural proposals shown by the generator as well as for prediction of the chemical shift data of new substances, the simulator of 13C NMR data was used and next compared with a commercial program of the same purpose, and exhibited higher accuracy in the data prediction.

<div>This thesis combines human and machine intelligence for consensus decision-making, and it contains four interrelated research areas. Before presenting the four research areas, this thesis presents a literature review on decision-making using two criteria: trust and risk. The analysis involves studying the individual and the multi-stakeholder decision-making. Also, it explores the relationship between trust and risk to provide insight on how to apply them when making any decision. This thesis presents a grouping procedure of the existing trust-based multi-stakeholder decision-making schemes by considering the group decision-making process and models. In the first research area, this thesis presents the foundation of building multi-stakeholder consensus decision-making (MSCDM). This thesis describes trust-based multi-stakeholder decision-making for water allocation to help the participants select a solution that comes from the best model. Several criteria are involved when deciding on a solution such as trust, damage, and benefit. This thesis considers Jain's fairness index as an indicator of reaching balance or equality for the stakeholder's needs. The preferred scenario is when having a high trust, low damages and high benefits. The worst scenario involves having low trust, high damage, and low benefit. The model is dynamic by adapting to the changes over time. The decision to select is the solution that is fair for almost everyone. In the second research area, this thesis presents a MSCDM, which is a generic framework that coordinates the decision-making rounds among stakeholders based on their influence toward each other, as represented by the trust relationship among them. This thesis describes the MSCDM framework that helps to find a decision the stakeholders can agree upon. Reaching a consensus decision might require several rounds where stakeholders negotiate by rating each other. This thesis presents the results of implementing MSCDM and evaluates the effect of trust on the consensus achievement and the reduction in the number of rounds needed to reach the final decision. This thesis presents Rating Convergence in the implemented MSCDM framework, and such convergence is a result of changes in the stakeholders' rating behavior in each round. This thesis evaluates the effect of trust on the rating changes by measuring the distance of the choices made by the stakeholders. Trust is useful in decreasing the distances. In the third research area, this thesis presents Rating Convergence in the implemented MSCDM framework, and such convergence is a result of changes in stakeholders' rating behavior in each round. This thesis evaluates the effect of trust on the rating changes by measuring the perturbation in the rating matrix. Trust is useful in increasing the rating matrix perturbation. Such perturbation helps to decrease the number of rounds. Therefore, trust helps to increase the speed of agreeing upon the same decision through the influence. In the fourth research area, this thesis presents Rating Aggregation operators in the implemented MSCDM framework. This thesis addresses the need for aggregating the stakeholders' ratings while they negotiate on the round of decisions to compute the consensus achievement. This thesis presents four aggregation operators: weighted sum (WS), weighted product (WP), weighted product similarity measure (WPSM), and weighted exponent similarity measure (WESM). This thesis studies the performance of those aggregation operators in terms of consensus achievement and the number of rounds needed. The consensus threshold controls the performance of these operators. The contribution of this thesis lays the foundation for developing a framework for MSCDM that facilitates reaching the consensus decision by accounting for the stakeholders' influences toward one another. Trust represents the influence.</div>

Nos últimos anos a Web obteve um crescimento exponencial, se tornando o maior repositório de informações já criado pelo homem e representando uma fonte nova e relevante de informações potencialmente úteis para diversas áreas, inclusive a área nuclear. Entretanto, devido as suas características e, principalmente, devido ao seu grande volume de dados, emerge um problema desafiador relacionado à utilização das suas informações: a busca e recuperação informações relevantes e úteis. Este problema é tratado por algoritmos de busca e recuperação de informação que trabalham na Web, denominados rastreadores web. Neste trabalho é apresentada a pesquisa e desenvolvimento de um algoritmo rastreador que efetua buscas e recupera páginas na Web com conteúdo textual relacionado ao domínio nuclear e seus temas, de forma autônoma e massiva. Este algoritmo foi projetado sob o modelo de um sistema especialista, possuindo, desta forma, uma base de conhecimento que contem tópicos nucleares e palavras-chave que os definem e um mecanismo de inferência constituído por uma rede neural artificial perceptron multicamadas que efetua a estimação da relevância das páginas na Web para um determinado tópico nuclear, no decorrer do processo de busca, utilizando a base de conhecimento. Deste modo, o algoritmo é capaz de, autonomamente, buscar páginas na Web seguindo os hiperlinks que as interconectam e recuperar aquelas que são mais relevantes para o tópico nuclear selecionado, emulando a habilidade que um especialista nuclear tem de navegar na Web e verificar informações nucleares. Resultados experimentais preliminares apresentam uma precisão de recuperação de 80% para o tópico área nuclear em geral e 72% para o tópico de energia nuclear, indicando que o algoritmo proposto é efetivo e eficiente na busca e recuperação de informações relevantes para o domínio nuclear. / Over the last years the Web has obtained an exponential growth, becoming the largest information repository ever created and representing a new and valuable source of potentially useful information for several topics and also for nuclear-related themes. However, due to the Web characteristics and, mainly, because of its huge data volume, finding and retrieving relevant and useful information are non-trivial tasks. This challenge is addressed by web search and retrieval algorithms called web crawlers. This work presents the research and development of a crawler algorithm able to search and retrieve webpages with nuclear-related textual content, in autonomous and massive fashion. This algorithm was designed under the expert systems model, having, this way, a knowledge base that contains a list of nuclear topics and keywords that define them and an inference engine composed of a multi-layer perceptron artificial neural network that performs webpages relevance estimates to some knowledge base nuclear topic while searching the Web. Thus, the algorithm is able to autonomously search the Web by following the hyperlinks that interconnect the webpages and retrieving those that are more relevant to some predefined nuclear topic, emulating the ability a nuclear expert has to browse the Web and evaluate nuclear information. Preliminary experimental results show a retrieval precision of 80% for the nuclear general domain topic and 72% for the nuclear power topic, indicating that the proposed algorithm is effective and efficient to search the Web and to retrieve nuclear-related information.

Este trabalho apresenta o desenvolvimento de um modelo para quantificar e apoiar o processo diagnóstico de demências (Demência de Alzheimer, Demência Vascular, Demência Frontotemporal e Demência de Corpos de Lewy), composto por três sub modelos. O primeiro modelo matemático proposto e baseado na teoria dos conjuntos fuzzy e tem como objetivo fornecer um escore de comprometimento cognitivo. Como resultado de sua aplicação em uma base com dados reais com 60 casos, obtivemos 52 acertos e 8 erros (13%) e uma área sob a curva ROC de 0,80. O segundo modelo permite identificar o tipo de demência, e optouse por utilizar um diagrama de decisão para representar o conhecimento do especialista. O diagrama foi modelado com base nas características de cada patologia e quando submetido aos testes dos especialistas obtivemos índices de erro que variam de 2% a 18%. Sendo a demência de Alzheimer a mais prevalente entre as demências e considerando a importância das neuroimagens para o diagnóstico diferencial, realizamos a avaliação de três técnicas de análise de neuroimagem, sendo duas multivariadas e uma univariada. Como resultado obtivemos que os modelos multivariados se mostram mais eficientes para avaliação de alterações morfológicas no cerébro em relação aos modelos univariados. Porém a complexidade de realização das análises não permitem nesse momento a integração de técnicas de avaliação de neuroimagens com modelos diagnósticos a serem usados em ambulatório. Durante a anamnese, o médico avalia, além do comprometimento cognitivo, sinais e sintomas que permitam identificar o tipo de demência bem como um conjunto de fatores de risco e de proteção que permite mensurar o risco do indivíduo desenvolver algum tipo de demência. Para avaliar esses fatores foi criado um modelo de risco de demência com base nos fatores de risco e proteção que comumente são analisados pelos médicos. Esse modelo foi avaliado por três especialistas e obtivemos índices de erro que variaram entre 13% e 20% e um índice de correlaço de Spearman que variou de 0,63 a 0,69. / This study proposes the development of a model to quantify and support the process of diagnose of dementia (Alzheimer\'s Dementia, Vascular Dementia, Frontotemporal Dementia and Dementia with Lewy Bodies) composed by three sub-models. The first mathematical model is based in the theory of fuzzy sets, and provides a score for cognitive impairment. As a result we obtained 52 correct classifications and eight errors (13%) and the area under the ROC curve was 0.80. In the second model a decision tree was elaborated to represent the expert\'s knowledge of the type of dementia. The decision diagram was modeled based on the characteristics of each pathology and the decision paths was tested by experts, resulting in erros varing between 2% to 18%. Since the Alzheimer\'s Disease is the most prevalent dementia and considering the importance of neuroimage exams to the dfferential diagnosis, we perform a evaluation of three techniques focused on neuroimage analisys, two multivariate techniques and one univariate technique. As a result it was verified that multivariate models are more efective to evaluate the morphological changes in the brain, compared to univariate models. However, the complexity to perform a analysis does not allows, at this moment, to integrate the neuroimage evaluation techniques whith diagnostic models designed to support the clinician in the ambulatory rotine. During the anamnesis the doctor evaluates (in addition to cognitive impairment and symptoms focused on identify the type of dementia), a number of risk and protection factors that allows measure the risk of the individual developing dementia. To perform the evaluation of these factors, a model of dementia risk was created based on the risk and protective factors that are commonly evaluated during the anmnese process. This model was evaluated by three experts and we achieve erros varing between 13% and 20% and Spearman\'s correlation value between the scores of 0.63 to 0.69.

O presente trabalho apresenta dois novas modelos conexionistas, baseados na teoria da adaptação ressonante (ART): Simplified Fuzzy ARTMAP e Semantic ART (SMART). Descreve-se a modelagem, adaptação, implementação e validação destes, enquanto incorporados ao sistema hibrido HYCONES, para resolução de problemas de diagnostico medico em cardiopatias congênitas e nefrologia. HYCONES é uma ferramenta para a construção de sistemas especialistas híbridos que integra redes neurais com frames, assimilando as qualidades inerentes aos dois paradigmas. 0 mecanismo de frames fornece tipos construtores flexíveis para a modelagem do conhecimento do domínio, enquanto as redes neurais, representadas na versão original de HYCONES pelo modelo neural combinatório (MNC), possibilitam tanto a automação da aquisição de conhecimento, a partir de uma base de casos, quanta a implementação de aprendizado indutivo e dedutivo. A teoria da adaptação ressonante 6 caracterizada, principalmente, pela manutenção do equilíbrio entre as propriedades de plasticidade e estabilidade durante o processo de aprendizagem. ART inclui vários modelos conexionistas, tais como: Fuzzy ARTMAP, Fuzzy ART, ART 1, ART 2 e ART 3. Dentre estes, a rede neural Fuzzy ARTMAP destaca-se por possibilitar o tratamento de padr6es analógicos a partir de dois módulos ART básicos. O modelo Simplified Fuzzy ARTMAP, como o pr6prio nome o diz, a uma simplificação da rede neural Fuzzy ARTMAP. Ao contrario desta, o novo modelo possibilita o tratamento de padrões analógicos, a partir de apenas um modulo ART, responsável pelo tratamento dos padrões de entrada, adicionado de uma camada, responsável pelos padrões alvo. Mesmo com apenas um modulo ART, o modelo Simplified Fuzzy ARTMAP 6 capaz de reter o mesmo nível de desempenho obtido com a rede neural Fuzzy ARTMAP pois, continua a garantir, conjuntamente, a maximização da generalização e a minimização do erro preditivo, através da execução da estratégia match-tracking. Para a construção da base de casos de cardiopatias congênitas, 66 prontuários médicos, das três cardiopatias congênitas mais freqüentes, foram extraídos do banco de dados de pacientes submetidos a cirurgia cardíaca no Instituto de Cardiologia RS (ICFUC-RS). Tais prontuários abrangem o período de janeiro de 1986 a dezembro de 1990 e reportam 22 casos de Comunicação Interatrial (CIA), 29 de Comunicação Interventricular (CIV) e 15 de Defeito Septal Atrioventricular (DSAV). Para a análise de desempenho do sistema, 33 casos adicionais, do referido período, foram extraídos aleatoriamente do banco de dados do ICFUC-RS. Destes 33 casos, 13 apresentam CIA, 10 CIV e 10 DSAV. Para a construção da base de casos de síndromes renais, 381 prontuários do banco de dados de síndromes renais da Escola Paulista de Medicina foram analisados e 58 evidencias, correspondentes a dados de hist6ria clinica e exame físico dos pacientes, foram extraídas semi-automaticamente. Do total de casos selecionados, 136 apresentam Uremia, 85 Nefrite, 100 Hipertensão e 60 Litiase. Dos 381 casos analisados, 254 foram escolhidos aleatoriamente para a composicao do conjunto de treinamento, enquanto que os demais foram utilizados para a elaboração do conjunto de testes. Para que HYCONES II fosse validado, foram construídas 46 versões da base de conhecimento hibrida (BCH) para o domínio de cardiopatias congênitas e 46 versões da BCH para o de nefrologia. Em ambos os domínios médicos as respectivas bases de conhecimento foram construídas, automaticamente, a partir das respectivas bases de casos de treinamento. Das 46 versões geradas para cada grupo, uma representa o modelo MNC e 45 os modelos ART. As versões ART dividem-se em grupos de 3: 15 versões foram formadas a partir do modelo Simplified Fuzzy ARTMAP; 15 a partir deste mesmo modelo, sem que os padrões de entrada fossem normalizados; e, finalmente, 15 para o modelo Semantic ART. Na base de testes CHD, o desempenho da versa° HYCONES II - Simplified Fuzzy ARTMAP foi semelhante ao da versa° MNC. A primeira acertou 29 dos 33 diagnósticos (87,9%), enquanto a segunda apontou corretamente 31 dos 33 diagnósticos apresentados (93,9%). Na base de testes de síndromes renais, o desempenho de HYCONES II Fuzzy ARTMAP foi superior ao da versão MNC (p < 0,05). Ambas -Simplified acertaram, respectivamente, 108 (85%) e 95 (74,8%) diagnósticos, em 127 casos submetidos. Ainda que o desempenho da versão HYCONES II - Simplified Fuzzy ARTMAP se revelasse promissor, ao se examinar o conteúdo das redes geradas por este modelo, pode-se observar que estas divergiam completamente daquelas obtidas pelo MNC. As redes que levaram a conclusão diagnostica, na versão HYCONES - MNC, possuíam conteúdo praticamente igual aos grafos de conhecimento, elicitados de especialistas em cardiopatias congênitas. JA, as redes ativadas na versa° HYCONES II - Simplified Fuzzy ARTMAP, além de representarem numero bem major de evidencias que as redes MNC, a grande maioria destas ultimas representam a negação do padrão de entrada. Este fato deve-se a um processo de normalização, inerente ao modelo Simplified Fuzzy ARTMAP, no qual cada padrão de entrada e duplicado. Nesta duplicação, são representadas as evidências presentes em cada caso e, ao mesmo tempo, complementarmente, as evidencias ausentes, em relação ao total geral das mesmas na base de casos. Esta codificação inviabiliza o mecanismo de explanação do sistema HYCONES, pois, na área módica, os diagnósticos costumam ser feitos a partir de um conjunto de evidencias presentes e, não, pela ausência delas. Tentou-se, então, melhorar o conteúdo semântico das redes Simplified Fuzzy ARTMAP. Para tal, o processo de normalização ou codificação complementar da implementação do modelo foi retirado, validando-o novamente, contra o mesma base de testes. Na base de testes CHD, o desempenho de HYCONES II - Simplified Fuzzy ARTMAP, sem a codificação complementar, foi inferior ao da versão MNC (p < 0,05). A primeira acertou 25 dos 33 diagnósticos (75,8%), enquanto a segunda apontou corretamente 31 dos mesmos (93,9%). Na base de testes renais, o desempenho da versa° HYCONES II - Simplified Fuzzy ARTMAP, sem a codificação complementar, foi semelhante ao da versa° MNC. Dos 127 casos apresentados, a primeira acertou 98 diagn6sticos (77,2%), contra 95 da segunda (74,8%). Constatou-se, ainda, que as categorias de reconhecimento formadas pelo modelo Simplified Fuzzy ARTMAP continuavam a apresentar diferenças marcantes quanto ao seu conteúdo, quando comparadas as redes MNC ou aos grafos de conhecimento elicitados de especialistas. O modelo Semantic ART foi, então, proposto, na tentativa de se melhorar o conteúdo semantic° das redes ART. Modificou-se, então, o algoritmo de aprendizado do modelo Simplified Fuzzy ARTMAP, introduzindo-se o mecanismo de aprendizado indutivo do modelo MNC, i.e., o algoritmo de punições e recompensas, associado ao de poda e normalização. Nova validação com a mesma base de testes foi realizada. Para a base de testes de CHD, o desempenho de HYCONES II - SMART foi semelhante ao da versão Simplified Fuzzy ARTMAP e da versão MNC. A primeira e a segunda acertaram 29 dos 33 diagnósticos (87,9%), enquanto a versão MNC apontou corretamente 31 dos 33 diagnósticos apresentados (93,9%). Na base de testes de síndromes renais, o desempenho de HYCONES II - SMART foi superior ao da versão MNC (p < 0,05) e igual ao da versão Simplified Fuzzy ARTMAP. A primeira e a Ultima acertaram 108 dos 127 diagnósticos (85%), enquanto a segunda apontou corretamente 95 dos mesmos (74,8%). Desta feita, observou-se que as redes neurais geradas por HYCONES II - SMART eram semelhantes em conteúdo as redes MNC e aos grafos de conhecimento elicitados de múltiplos especialistas. As principais contribuições desta dissertação são: o projeto, implementação e validação dos modelos Simplified Fuzzy ARTMAP e SMART. Destaca-se, porem, o modelo SMART, que apresentou major valor semântico nas categorias de reconhecimento do que o observado nos modelos ART convencionais, graças a incorporação dos conceitos de especificidade e relevância. Esta dissertação, entretanto, representa não só a modelagem e validação de dois novos modelos neurais, mas sim, o enriquecimento do sistema HYCONES, a partir da continuação de dissertação de mestrado previamente defendida. A partir do presente trabalho, portanto, é dada a possibilidade de escolha, ao engenheiro de conhecimento, de um entre três modelos neurais: o MNC, o Semantic ART e o Simplified Fuzzy ARTMAP que, sem exceção, apresentam Born desempenho. Os dois primeiros destacam-se, contudo, por suportarem semanticamente o contexto. / This dissertation presents two new connectionist models based on the adaptive resonance theory (ART): Simplified Fuzzy ARTMAP and Semantic ART (SMART). The modeling, adaptation, implementation and validation of these models are described, in their association to HYCONES, a hybrid connectionist expert system to solve classification problems. HYCONES integrates the knowledge representation mechanism of frames with neural networks, incorporating the inherent qualities of the two paradigms. While the frames mechanism provides flexible constructs for modeling the domain knowledge, neural networks, implemented in HYCONES' first version by the combinatorial neuron model (CNM), provide the means for automatic knowledge acquisition from a case database, enabling, as well, the implementation of deductive and inductive learning. The Adaptive Resonance Theory (ART) deals with a system involving selfstabilizing input patterns into recognition categories, while maintaining a balance between the properties of plasticity and stability. ART includes a series of different connectionist models: Fuzzy ARTMAP, Fuzzy ART, ART 1, ART 2, and ART 3. Among them, the Fuzzy ARTMAP one stands out for being capable of learning analogical patterns, using two basic ART modules. The Simplified Fuzzy ARTMAP model is a simplification of the Fuzzy ARTMAP neural network. Constrating the first model, the new one is capable of learning analogical patterns using only one ART module. This module is responsible for the categorization of the input patterns. However, it has one more layer, which is responsible for receiving and propagating the target patterns through the network. The presence of a single ART module does not hamper the Simplified Fuzzy ARTMAP model. The same performance levels are attained when the latter one runs without the second ART module. This is certified by the match-tracking strategy, that conjointly maximizes generalization and minimizes predictive error. Two medical domains were chosen to validate HYCONES performance: congenital heart diseases (CHD) and renal syndromes. To build up the CHD case base, 66 medical records were extracted from the cardiac surgery database of the Institute of Cardiology RS (ICFUC-RS). These records cover the period from January 1986 to December 1990 and describe 22 cases of Atrial Septal Defect (ASD), 29 of Ventriculal Septal Defect (VSD), and 15 of Atrial- Ventricular Septa! Defect (AVSD), the three most frequent congenital heart diseases. For validation purposes, 33 additional cases, from the same database and period mentioned above, were also extracted. From these cases, 13 report ASD, 10 VSD and 10 AVSD. To build the renal syndromes case base, 381 medical records from the database of the Escola Paulista de Medicina were analyzed and 58 evidences, covering the patients' clinical history and physical examination data, were semiautomatically extracted. From the total number of selected cases, 136 exhibit Uremia, 85 Nephritis, 100 Hypertension, and 60 Calculosis. From the 381 cases analyzed, 245 were randomically chosen to build the training set, while the remaining ones were used to build the testing set. To validate HYCONES II, 46 versions of the hybrid knowledge base (HKB) with congenital heart diseases were built; for the renal domain, another set of 46 HKB versions were constructed. For both medical domains, the HKBs were automatically generated from the training databases. From these 46 versions, one operates with the CNM model and the other 45 deals with two ART models. These ART versions are divided in three groups: 15 versions were built using the Simplified Fuzzy ARTMAP model; 15 used the Simplified Fuzzy ARTMAP model without the normalization of the input patterns, and 15 used the Semantic ART model. HYCONES II - Simplified Fuzzy ARTMAP and HYCONES - CNM performed similarly for the CH D domain. The first one pointed out correctly to 29 of the 33 testing cases (87,9%), while the second one indicated correctly 31 of the same cases (93,9%). In the renal syndromes domain, however, the performance of HYCONES II - Simplified Fuzzy ARTMAP was superior to the one exhibited by CNM (p < 0,05). Both versions pointed out correctly, respectively, 108 (85%) and 95 (74.8%) diagnoses of the 127 testing cases presented to the system. HYCONES II - Simplified Fuzzy ARTMAP, therefore, displayed a satisfactory performance. However, the semantic contents of the neural nets it generated were completely different from the ones stemming from the CNM version. The networks that pointed out the final diagnosis in HYCONES - CNM were very similar to the knowledge graphs elicited from experts in congenital heart diseases. On the other hand, the networks activated in HYCONES II - Simplified Fuzzy ARTMAP operated with far more evidences than the CNM version. Besides this quantitative difference, there was a striking qualitative discrepancy among these two models. The Simplified Fuzzy ARTMAP version, even though pointing out to the correct diagnoses, used evidences that represented the complementary coding of the input pattern. This coding, inherent to the Simplified Fuzzy ARTMAP model, duplicates the input pattern, generating a new one depicting the evidence observed (on-cell) and, at the same time, the absent evidence, in relation to the total evidence employed to represent the input cases (off-cell). This coding shuts out the HYCONES explanation mechanism, since medical doctors usually reach a diagnostic conclusion rather from a set of observed evidences than from their absence. The next step taken was to improve the semantic contents of the Simplified Fuzzy ARTMAP model. To achieve this, the complement coding process was removed and the modified model was, then, revalidated, through the same testing sets as above described. In the CHD domain, the performance of HYCONES II - Simplified Fuzzy ARTMAP, without complementary coding, proved to be inferior to the one presented by CNM (p < 0,05). The first model singled out correctly 25 out of the 33 testing cases (75,8%), while the second one singled out correctly 31 out of the same 33 cases (93,9%). In the renal syndromes domain, the performances of HYCONES II - Simplified Fuzzy ARTMAP, without complementary coding, and HYCONES - CNM were similar. The first pointed out correctly to 98 of the 127 testing cases (77,2%), while the second one pointed out correctly to 95 of the same cases (74.8%). However, the recognition categories formed by this modified Simplified Fuzzy ARTMAP still presented quantitative and qualitative differences in their contents, when compared to the networks activated by CNM and to the knowledge graphs elicited from experts. This discrepancy, although smaller than the one observed in the original Fuzzy ARTMAP model, still restrained HYCONES explanation mechanism. The Semantic ART model (SMART) was, then, proposed. Its goal was to improve the semantic contents of ART recognition categories. To build this new model, the Simplified Fuzzy ARTMAP archictecture was preserved, while its learning algorithm was replaced by the CNM inductive learning mechanism (the punishments and rewards algorithm, associated with the pruning and normalization mechanisms). A new validation phase was, then, performed over the same testing sets. For the CHD domain, the perfomance comparison among SMART, Simplified Fuzzy ARTMAP, and CNM versions showed similar results. The first and the second versions pointed out correctly to 29 of the 33 testing cases (87,9%), while the third one singled out correctly 31 of the same testing cases (93,9%). For the renal syndromes domain, the performance of HYCONES II - SMART was superior to the one presented by the CNM version (p < 0,05), and equal to the performance presented by the Simplified Fuzzy ARTMAP version. SMART and Simplified Fuzzy ARTMAP singled out correctly 108 of the 127 testing cases (85%), while the CNM version pointed out correctly 95 of the same 127 testing cases (74.8%). Finally, it was observed that the neural networks generated by HYCONES II - SMART had a similar content to the networks generated by CNM and to the knowledge graphs elicited from multiple experts. The main contributions of this dissertation are: the design, implementation and validation of the Simplified Fuzzy ARTMAP and SMART models. The latter one, however, stands out for its learning mechanism, which provides a higher semantic value to the recognition categories, when compared to the categories formed by conventional ART models. This important enhancement is obtained by incorporating specificity and relevance concepts to ART's dynamics. This dissertation, however, represents not only the design and validation of two new connectionist models, but also, the enrichment of HYCONES. This is obtained through the continuation of a previous MSc dissertation, under the same supervision supervision. From the present work, therefore, it is given to the knowledge engineering, the choice among three different neural networks: CNM, Semantic ART and Simplified Fuzzy ARTMAP, all of which, display good performance. Indeed, the first and second models, in contrast to the third, support the context in a semantic way.

Submitted by Maicon Juliano Schmidt (maicons) on 2015-04-24T13:06:47Z No. of bitstreams: 1 Jonathan Simon Prates.pdf: 2514736 bytes, checksum: 58b7bca77d32ecba8467a3e3a533d2a0 (MD5) / Made available in DSpace on 2015-04-24T13:06:48Z (GMT). No. of bitstreams: 1 Jonathan Simon Prates.pdf: 2514736 bytes, checksum: 58b7bca77d32ecba8467a3e3a533d2a0 (MD5) Previous issue date: 2015-01-31 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Os Sistemas de Interação Multimodal possibilitam uma utilização mais amigável dos sistemas de computação. Eles permitem que os usuários recebam informações e indiquem suas necessidades com maior facilidade, amparados por recursos de interação cada vez mais diversos. Neste contexto, um elemento central é o diálogo que se estabelece entre os usuários e estes sistemas. Alguns dos desafios observados na área de Interação Multimodal estão ligados à integração dos diversos estímulos a serem tratados, enquanto outros estão ligados à geração de respostas adequadas a estes estímulos. O gerenciamento do diálogo nestes sistemas envolve atividades diversas associadas tanto com a representação dos assuntos tratados, como com a escolha de alternativas de resposta e com o tratamento de modelos que representam tarefas e usuários. A partir das diversas abordagens conhecidas para estas implementações, são observadas demandas de modelos de diálogo que aproximem os resultados das interações que são geradas pelos sistemas daquelas interações que seriam esperados em situações de interação em linguagem natural. Uma linha de atuação possível para a obtenção de melhorias neste aspecto pode estar ligada à utilização de estudos da psicologia cognitiva sobre a memória de trabalho e a integração de informações. Este trabalho apresenta os resultados obtidos com um modelo de tratamento de diálogo para sistemas de Interação Multimodal baseado em um modelo cognitivo, que visa proporcionar a geração de diálogos que se aproximem de situações de diálogo em linguagem natural. São apresentados os estudos que embasaram esta proposta e a sua justificativa para uso no modelo descrito. Também são demonstrados resultados preliminares obtidos com o uso de protótipos para a validação do modelo. As avaliações realizadas demonstram um bom potencial para o modelo proposto. / Multimodal interaction systems allow a friendly use of computing systems. They allow users to receive information and indicate their needs with ease, supported by new interaction resources. In this context, the central element is the dialogue, established between users and these systems. The dialogue management of these systems involves various activities associated with the representation of subjects treated, possible answers, tasks model and users model treatment. In implementations for these approaches, some demands can be observed to approximate the results of the interactions by these systems of interaction in natural language. One possible line of action to obtain improvements in this aspect can be associated to the use of cognitive psychology studies on working memory and information integration. This work presents results obtained with a model of memory handling for multimodal dialogue interaction based on a cognitive model, which aims to provide conditions for dialogue generation closer to situations in natural language dialogs. This research presents studies that supported this proposal and the justification for the described model’s description. At the end, results using two prototypes for the model’s validation are also shown.

「個案小教授」是一篇探討專家系統方法的研究與應用的探索性論文，主要的應用領域是企管個案教學的輔助教學工具，我們嘗試擴大專家系統的應用的領域，也嘗試去突破一些困難，我們發展出了一個「個案小教授」的雛型。由於專家系統在個案教學上的應用算是首創，如何利用有限的工具來完成千變萬化的個案教學是一大挑戰。本論文將依照知識工程的方法，逐步將個案教學的的精髓融入專家系統的方法中，並以此發現專家系統研究上的一些限制，提供給後續人工智慧與專家系統研究學者參考，使得專家系統能夠跨入更多的領域，幫助人類解決日常決策的問題。本論文採取的研究方法為 　　1.文獻探討：在於整理出發展專家系統的步驟與技術，包括知識擷取方法，知識表現與推理方式，以歸納出知識工程在個案分析教學上應用。 　　2.深入訪談法：知識擷取的工作以知識工程師為界面，透過知識工程師為主導，以交談與口語資料分析(Protocol analysis)等方式將專家知識擷取出來。 　　3.觀察法：利用專家工作的現場與情境實際觀察(使用錄影或是錄音)專家工作方式與推理過程，藉以了解專家知識表現的方式。本研究則是到個案研討的教室實地觀察並記錄司徒達賢教授上課之情形。 　　4.發展系統雛型：專家系統又稱為知識基礎系統(knowledge-based systems)，或知識系統。 　　其系統架構可分為五部份： 　　(1)知識庫(knowledge base)用以儲存專家用以解決問題之知識部份。 　　(2)推理機(inference engine)用以控制推理過程之機制。 　　(3)使用者界面(user interface)用以供使用者友善的解釋及諮詢功能介紹之界面。 　　(4)知識擷取界面(knowledgeacquisition interface)用以提供編輯，增修知識庫之界面。 　　(5)工作記憶區(working memory)用以儲存在推理過程中當時之事實之部份。本研究是以NEURON DATA公司所出品的NEXPERT OBJECT作為系統發展工具，將個案教學專家的知識與推理過程以專家系統加以表現。

It has been suggested 'expert systems' might have a significant role in the future through enabling many more people to access human experts. It is, therefore, important to understand how potential users interact with these computer systems. This study investigates the effect of extension agents' attitudes towards the features and use of an example expert system for rice disease diagnosis and management(POSOP). It also considers the effect of extension agents' personality traits and intelligence on their attitudes towards its use, and the agents' perception of control over using it. Answers to these questions lead to developing better systems and to increasing their adoption. Using structural equation modelling, two models - the extension agents' perceived usefulness of POSOP, and their attitude towards the use of POSOP, were developed (Models ATU and ATP). Two of POSOP's features (its value as a decision support tool, and its user interface), two personality traits (Openness (0) and Extraversion (E)), and the agents' intelligence, proved to be significant, and were evaluated. The agents' attitude towards POSOP's value had a substantial impact on their perceived usefulness and their attitude towards using it, and thus their intention to use POSOP. Their attitude towards POSOP's user interface also had an impact on their attitude towards its perceived usefulness, but had no impact on their attitude towards using it. However, the user interface did contribute to its value. In Model ATU, neither Openness (0) nor Extraversion (E) had an impact on the agents' perceived usefulness indicating POSOP was considered useful regardless of the agents' personality background. However, Extraversion (E) had a negative impact on their intention to use POSOP in Model ATP indicating that 'introverted' agents had a clear intention to use POSOP relative to the 'extroverted' agents. Extension agents' intelligence, in terms of their GPA, had neither an impact on their attitude, nor their subjective norm (expectation of 'others' beliefs), to the use of POSOP. It also had no association with any of the variables in both models. Both models explain and predict that it is likely that the agents will use POSOP. However, the availability of computers, particularly their capacity, are likely to impede its use. Although the agents believed using POSOP would not be difficult, they still believed training would be beneficial. To be a useful decision support tool, the expert system's value and user interface as well as its usefulness and ease of use, are all crucially important to the preliminary acceptance of a system. Most importantly, the users' problems and needs should be assessed and taken into account as a first priority in developing an expert system. Furthermore, the users should be involved in the system development. The results emphasise that the use of an expert system is not only determined by the system's value and its user interface, but also the agents' perceived usefulness, and their attitude towards using it. In addition, the agents' perception of control over using it is also a significant factor. The results suggested improvements to the system's value and its user interface would increase its potential use, and also providing suitable computers, coupled with training, would encourage its use.