Página 1 dos resultados de 201 itens digitais encontrados em 0.279 segundos

Explicação em sistemas que utilizam diagramas de influências como formalismo de representação do conhecimento; Explanation in systems that use influence diagrams for Knowledge representation.

Castiñeira, Maria Inés
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Tese de Doutorado Formato: application/pdf
Publicado em 18/10/1996 Português
Relevância na Pesquisa
75.94%
O presente trabalho discute a necessidade da representação e manipulação de incertezas na resolução de problemas por sistemas baseados em conhecimento, e como isto pode ser realizado utilizando redes de crenças. Este tipo de representação do conhecimento combina a teoria das probabilidades e teoria da decisão, para representar incertezas, com a teoria dos grafos, esta última apropriada para representar as relações de dependência entre as variáveis do modelo. Os diagramas de inferência - redes de crenças que permitem representar incertezas, decisões e preferências do usuário - são discutidos e adotados neste trabalho para desenvolver um sistema normativo de apoio à decisão. A problemática da explicação em sistemas bayesianos, relativamente nova quando comparada com a dos sistemas baseados em regras, é abordada. Neste contexto dois mecanismos de explicação para diagramas de influência são propostos: análise de sensibilidade e as redes probabilísticas qualitativas. Estes mecanismos são usados para gerar conclusões genéricas bem como para entender qualitativamente as relações entre as ações e eventos que fazem parte do modelo. Uma ferramenta gráfica de apoio à decisão baseada em diagramas de influências foi implementada na linguagem Smalltalk. Este aplicativo não só permite representar e avaliar o problema do usuário como também incorpora as facilidades de explicação acima descritas. A possibilidade de observar graficamente o que acontece com o modelo quando os valores das variáveis são modificados - análise de sensibilidade - permite compreender melhor o problema descobrindo quais as variáveis que influenciam as decisões e auxilia a refinar os valores das variáveis envolvidas. Por outro lado às redes probabilísticas qualitativas permitem realizar abstrações e simplificações apropriadas do modelo...

Construtos ontológicos para representação simbólica de conhecimento visual; Ontological constructs for visual knowledge representation

Santin, Carlos Eduardo
Tipo: dissertação Formato: application/pdf
Português
Relevância na Pesquisa
66%
Em domínios com forte conteúdo visual, a interpretação de imagens por raciocínio visual pode ser mais eficaz na solução de problemas do que a interpretação de dados puramente textuais ou numéricos. No entanto, a representação do conhecimento visual é difícil de ser realizada por tratar-se de um conhecimento implícito para o observador. As ontologias de representação possibilitam a criação de estruturas para auxiliar na captura desse tipo de conhecimento, de forma a atribuir uma representação simbólica e significado semântico ao que está sendo visualizado. A formalização do conhecimento visual permite a sua utilização em processos de inferência, resultando na interpretação automática da imagem. O objetivo deste trabalho é a definição de construtos ontológicos que permitam descrever aspectos visuais presentes em uma imagem, com ênfase na atenção visual mais do que nos aspectos físicos dos objetos. Esses aspectos visuais são associados aos objetos físicos da imagem bem como aos objetos descritos no nível do conhecimento de domínio. Para cada um dos níveis foi definida uma ontologia de representação, sendo assim possível atribuir semântica específica a esses objetos através da descrição de seus atributos e manter a independência do conhecimento relativo a cada nível. O nível da imagem descreve os objetos passíveis de serem extraídos por algoritmos de processamento de imagem (embora esses algoritmos não tenham sido foco de estudo neste trabalho). O nível visual descreve objetos que são foco da atenção visual...

Evaluation of concrete deterioration through artificial neural networks based systems

Gomes, Guida; Vicente, Henrique; Neves, José
Fonte: Europment Publicador: Europment
Tipo: info:eu-repo/semantics/bookpart
Publicado em //2014 Português
Relevância na Pesquisa
85.93%
The deterioration of concrete structures is one of the major concerns of our society. Indeed, concrete is a relatively sensitive material, which degrades throughout time. Factors like age, use, periodic maintenance, type of environmental exposure and aggression by biological, chemical, mechanical and physical agents are important to determine the level of degradation of the concrete structures. Logic Programming was used for knowledge representation and reasoning, letting the modeling of the universe of discourse in terms of defective data, information and knowledge. Artificial Neural Networks were used in order to evaluate the deterioration of concrete structures and the degree of confidence that one has on such a happening.

School dropout screening through artificial neural networks based systems

Figueiredo, Margarida; Vicente, Lídia; Vicente, Henrique; Neves, José
Fonte: Europment Publicador: Europment
Tipo: info:eu-repo/semantics/bookpart
Publicado em //2014 Português
Relevância na Pesquisa
85.93%
School dropout is one of the major concerns of our society. Indeed, it is a complex phenomenon, resulting in economic and social losses, either to the individual, family or the community to which the person belongs. Academic difficulty and failure, poor attendance, retention, disengagement from school together with family and socio-economic reasons can lead to such occurrence. In this work Logic Programming was used for knowledge representation and reasoning, letting the modeling of the universe of discourse in terms of defective data, information and knowledge. Artificial Neural Networks were used in order to evaluate potential situations of school dropout and the degree of confidence that one has on such a happening.

Evaluation of Concrete Deterioration through Artificial Neural Networks based Systems

Gomes, Guida; Vicente, Henrique; Neves, José
Fonte: Europment Publicador: Europment
Tipo: bookpart
Português
Relevância na Pesquisa
85.93%
The deterioration of concrete structures is one of the major concerns of our society. Indeed, concrete is a relatively sensitive material, which degrades throughout time. Factors like age, use, periodic maintenance, type of environmental exposure and aggression by biological, chemical, mechanical and physical agents are important to determine the level of degradation of the concrete structures. Logic Programming was used for knowledge representation and reasoning, letting the modeling of the universe of discourse in terms of defective data, information and knowledge. Artificial Neural Networks were used in order to evaluate the deterioration of concrete structures and the degree of confidence that one has on such a happening.

School Dropout Screening through Artificial Neural Networks based Systems

Figueiredo, Margarida; Vicente, Lídia; Vicente, Henrique; Neves, José
Fonte: INASE Publicador: INASE
Tipo: bookpart
Português
Relevância na Pesquisa
85.93%
School dropout is one of the major concerns of our society. Indeed, it is a complex phenomenon, resulting in economic and social losses, either to the individual, family or the community to which the person belongs. Academic difficulty and failure, poor attendance, retention, disengagement from school together with family and socio-economic reasons can lead to such occurrence. In this work Logic Programming was used for knowledge representation and reasoning, letting the modeling of the universe of discourse in terms of defective data, information and knowledge. Artificial Neural Networks were used in order to evaluate potential situations of school dropout and the degree of confidence that one has on such a happening.

An Artificial Neuronal Network Approach to Diagnosis of Attention Deficit Hyperactivity Disorder

Pereira, Sónia; Gomes, Sabino; Vicente, Henrique; Ribeiro, Jorge; Abelha, António; Novais, Paulo; Machado, José; Neves, José
Fonte: Institute of Electrical and Electronics Engineers, Inc. Publicador: Institute of Electrical and Electronics Engineers, Inc.
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
95.9%
On the one hand about 3% to 12% of school-aged children present Attention Deficit Hyperactivity Disorder (ADHD), a situation that is characterized by attention deficit, impulsiveness and restlessness, coming from a change in the neurotransmitters of the central nervous system, caused by psychological messes, environment effects or genetic characteristics. One the other hand, when one´s aim is the prediction of ADHD in children and teenagers, we need to be able to handle incomplete or default data, like the one in ActiGraph´s images that may exhibit potential disordered sleep patterns. Indeed, using a new approach to knowledge representation and reasoning based on Logic Programming, complemented with a computational framework based on Artificial Neural Networks, ActiGraph’s pioneering actigraphy monitoring systems may deliver, on the fly, real world information about sleep/wake behavior, circadian rhythms, daytime physical activity, and environmental light intensity for the study and clinical assessment of sleep disorders and the relationship between sleep and chronic disease.

An Assessment on the Length of Hospital Stay through Artificial Neural Networks

Abelha, Vasco; Vicente, Henrique; Machado, José; Neves, José
Fonte: Cyprus Library Publicador: Cyprus Library
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
85.93%
The attitude of stashing costs and preventing people of any kind of intervention on the valuation of the problem referred to above, may undermine their belief on present society values and on their way of living. Cutting funds from Education to Health is at best delaying the inevitable crash that is foreshadowed. Indeed, regarding people, a major concern may be described as jeopardizing their health condition, i.e., providing healthcare is a very sensitive issue and prunes to drastic changes in short spaces of time. Factors like age, sex, and context – house conditions, daily lives – should also be central when deciding how long a specific patient should remain in a hospital. In no way, ought this be decided by economic circumstances alone. To fulfill this goal, a Logic Programming based approach is used for knowledge representation and reasoning, letting the modeling of the universe of discourse in terms of defective data, information and knowledge. Artificial Neural Networks are enforced as the computational framework, allowing one to predict how long a patient should remain in a hospital.

Systematic Coronary Risk Evaluation through Artificial Neural Networks based Systems

Rodrigues, Bruno; Gomes, Sabino; Vicente, Henrique; Abelha, António; Novais, Paulo; Machado, José; Neves, José
Fonte: International Society of Computers and their Applications - ISCA Publicador: International Society of Computers and their Applications - ISCA
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
95.9%
On the one hand, cardiovascular diseases have severe consequences on an individual and for the society in general, once they are the main cause to death. These facts reveal that it is vital to get preventive, by knowing how probable is to have that kind of illness. On the other hand, and until now, this risk has been assessed by a Systematic Coronary Risk Evaluation procedure that takes data from charts based on gender, age, total cholesterol, systolic blood pressure and smoking status, but with no conceivable potential to deal with the incomplete or default data that is presented on those tools. Therefore, the focus in this work will be on the development of a risk evaluation support system based on a low-risk record, grounded on a new approach to knowledge representation and reasoning, that based on an extension to the Logic Programming language, will be able to overcome the drawbacks of the present ones. This will be complemented with a computational framework based on Artificial Neural Networks.

Thrombophilia Screening – An Artificial Neural Network Approach

Vilhena, João; Martins, M. Rosário; Vicente, Henrique; Nelas, Luís; Machado, José; Neves, José
Fonte: Scitepress – Science and Technology Publications Publicador: Scitepress – Science and Technology Publications
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
95.9%
Thrombotic disorders have severe consequences for the patients and for the society in general, being one of the main causes of death. These facts reveal that it is extremely important to be preventive; being aware of how probable is to have that kind of syndrome. Indeed, this work will focus on the development of a decision support system that will cater for an individual risk evaluation with respect to the surge of thrombotic complaints. The Knowledge Representation and Reasoning procedures used will be based on an extension to the Logic Programming language, allowing the handling of incomplete and/or default data. The computational framework in place will be centered on Artificial Neural Networks.

Artificial Neural Networks in Stroke Predisposition Screening

Neves, José; Vicente, Henrique; Gonçalves, Nuno; Oliveira, Ruben; Neves, João; Abelha, António; Machado, José
Fonte: IADIS Press Publicador: IADIS Press
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
85.9%
On the one hand there are stroke events that cannot be avoid, which stem from unchangeable processes like aging, sex, family or medical history. In particular, elderly people have a higher risk of stroke, with almost 80% of strokes occurring in individuals over 60 years of age, and at an earlier age than in women, although women are catching up fast (in fact more women than men die from heart incidents). Stroke diseases have severe consequences for the patients and for the society in general, being one of the main causes of death. On the other hand these facts reveal that it is extremely important to be hands-on, being aware of how critical is the early diagnosis of this kind of diseases. Indeed, this work will focus on the development of a diagnosis support system, in terms of its knowledge representation and reasoning procedures, under a formal framework based on Logic Programming, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate stroke predisposing and the respective Degree-of-Confidence that one has on such a happening.

Artificial Neural Networks in Acute Coronary Syndrome Screening

Martins, M. Rosário; Mendes, Teresa; Grañeda, José; Gusmão, Rodrigo; Vicente, Henrique; Neves, José
Fonte: Springer International Publishing Publicador: Springer International Publishing
Tipo: bookpart
Português
Relevância na Pesquisa
85.9%
In Acute Coronary Syndrome (ACS), early use of correct therapy plays a key role in altering the thrombotic process resulting from plaque rupture, thereby minimizing patient sequels. Indeed, current quality improvement efforts in acute cardiovascular care are focused on closing treatment gaps, so more patients receive evidence-based therapies. Beyond ensuring that effective therapies are administered, attention should also be directed at ensuring that these therapies are given both correctly and safely. Indeed, this work will focus on the development of a diagnosis support system, in terms of its knowledge representation and reasoning procedures, under a formal framework based on Logic Programming, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate ACS predisposing and the respective Degree-of-Confidence that one has on such a happening.

Prediction of Organ Donation after Irreversible Brain Damage

Torres, Luís; Vicente, Henrique; Novais, Paulo; Abelha, António; Neves, José
Fonte: CRC Press Publicador: CRC Press
Tipo: bookpart
Português
Relevância na Pesquisa
85.9%
An assessment of a patient, who may die within one hour following the removal of life-sustaining care, is the key to a successful donation of organs after cardiac death. Indeed, the accurate prediction of potential organ donation is paramount, due to the narrow time window in which different tasks must be done in parallel, and in a quick and effective way. In this work, it is stated that through a novel approach to knowledge representation and reasoning, based on an extension to the language of Logic Programming, and complemented with a view to computing based on Artificial Neural Networks, it is possible to determine if a patient who suffers from irreversible brain damage may stand as a future candidate for organ donation.

Logic Programming and Artificial Neural Networks in Breast Cancer Detection

Neves, José; Guimarães, Tiago; Gomes, Sabino; Vicente, Henrique; Santos, Mariana; Neves, João; Machado, José; Novais, Paulo
Fonte: Springer International Publishing Publicador: Springer International Publishing
Tipo: bookpart
Português
Relevância na Pesquisa
95.9%
About 90% of breast cancers do not cause or are capable of producing death if detected at an early stage and treated properly. Indeed, it is still not known a specific cause for the illness. It may be not only a beginning, but also a set of associations that will determine the onset of the disease. Undeniably, there are some factors that seem to be associated with the boosted risk of the malady. Pondering the present study, different breast cancer risk assessment models where considered. It is our intention to develop a hybrid decision support system under a formal framework based on Logic Programming for knowledge representation and reasoning, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the risk of developing breast cancer and the respective Degree-of-Confidence that one has on such a happening.

An Evaluation of Parchments’ Degradation - A Hybrid Approach

Neves, José; Machado, José; Gomes, Guida; Sousa, Sérgio; Tereso, Daniela; Coelho, Ana; Caldeira, A. Teresa; Pereira, António; Candeias, António; Vicente, Henrique
Fonte: European Council for Modelling and Simulation Publicador: European Council for Modelling and Simulation
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
95.9%
Parchment stands for a multifaceted material made from animal skin, which has been used for centuries as a writing support or as bookbinding. Due to the historic value of objects made of parchment, understanding their degradation and their condition is of utmost importance to archives, libraries and museums, i.e., the assessment of parchment degradation is mandatory, although it is hard to do with traditional methodologies and tools for problem solving. Hence, in this work we will focus on the development of a hybrid decision support system, in terms of its knowledge representation and reasoning procedures, under a formal framework based on Logic Programming, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate Parchment Degradation and the respective Degree-of-Confidence that one has on such a happening.

Quality of Learning under an All-inclusive Approach

Neves, José; Figueiredo, Margarida; Vicente, Lídia; Gomes, Guida; Macedo, Joaquim; Vicente, Henrique
Fonte: Springer International Publishing Publicador: Springer International Publishing
Tipo: bookpart
Português
Relevância na Pesquisa
85.95%
Learning, knowledge, educations are syntax forms that stand for a multifaceted matter, and its assets set the advances on culture, organization, and social matters of any society. However, it is not enough just to instruct, it is necessary to do it with quality, in a holistic way, in order to develop academic and social skills. From this point of view, the weight of the formal, non-formal and informal learning contexts should be underlined, and the use of defective information must be emphasizing. Under this setting the assessment to quality of learning is mandatory, although it is hard to do with traditional methodologies for problem solving. Indeed, in this work we will focus on the development of a decision support system, in terms of its knowledge representation and reasoning procedures, under a formal framework based on Logic Programming, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the Quality of Learning and the respective Degree-of-Confidence that one has on such a happening.

The interaction of representation and reasoning

Bundy, Alan
Fonte: The Royal Society Publishing Publicador: The Royal Society Publishing
Tipo: text
Publicado em 08/09/2013 Português
Relevância na Pesquisa
66.18%
Automated reasoning is an enabling technology for many applications of informatics. These applications include verifying that a computer program meets its specification; enabling a robot to form a plan to achieve a task and answering questions by combining information from diverse sources, e.g. on the Internet, etc. How is automated reasoning possible? Firstly, knowledge of a domain must be stored in a computer, usually in the form of logical formulae. This knowledge might, for instance, have been entered manually, retrieved from the Internet or perceived in the environment via sensors, such as cameras. Secondly, rules of inference are applied to old knowledge to derive new knowledge. Automated reasoning techniques have been adapted from logic, a branch of mathematics that was originally designed to formalize the reasoning of humans, especially mathematicians. My special interest is in the way that representation and reasoning interact. Successful reasoning is dependent on appropriate representation of both knowledge and successful methods of reasoning. Failures of reasoning can suggest changes of representation. This process of representational change can also be automated. We will illustrate the automation of representational change by drawing on recent work in my research group.

Theoretical foundations for information representation and constraint specification

Mayer, Richard J.; Menzel, Christopher P.
Tipo: nasa-cr-190286; nas 1.26:190286 Formato: application/pdf
Português
Relevância na Pesquisa
75.84%
Research accomplished at the Knowledge Based Systems Laboratory of the Department of Industrial Engineering at Texas A&M University is described. Outlined here are the theoretical foundations necessary to construct a Neutral Information Representation Scheme (NIRS), which will allow for automated data transfer and translation between model languages, procedural programming languages, database languages, transaction and process languages, and knowledge representation and reasoning control languages for information system specification.

Principles of Knowledge Representation and Reasoning in the FRAPPE System

Feldman, Yishai A.; Rich, Charles
Fonte: MIT Artificial Intelligence Laboratory Publicador: MIT Artificial Intelligence Laboratory
Tipo: working paper
Português
Relevância na Pesquisa
85.95%
The purpose of this paper is to elucidate the following four important architectural principles of knowledge representation and reasoning with the example of an implemented system: limited reasoning, truth maintenance, hybrid architecture, and many sorted logic.; MIT Artificial Intelligence Laboratory