Search results for "Expert"

Redes Neuronales (2009/2010)

2009

An Expert System for the Design of Agents

2007

The growing interest for the design and development of multi-agent systems has brought to the creation of a specific research area called Agent-Oriented Software Engineering (AOSE), specifically conceived for the development of complex systems. The development of such systems needs the support of appropriate tools that could help the designer in producing the design artefacts. We developed a tool called Metameth that may be used to define a new (agent-oriented) design process as well as to apply it. In this paper, we describe only a slice of this complex tool, specifically addressing the interaction with human actors (the designers). This subsystem is conceived as a collaborative multi-agen…

A Knowledge Management and Decision Support Model for Enterprises

2011

We propose a novel knowledge management system (KMS) for enterprises. Our system exploits two different approaches for knowledge representation and reasoning: a document-based approach based on data-driven creation of a semantic space and an ontology-based model. Furthermore, we provide an expert system capable of supporting the enterprise decisional processes and a semantic engine which performs intelligent search on the enterprise knowledge bases. The decision support process exploits the Bayesian networks model to improve business planning process when performed under uncertainty. Copyright © 2011 Patrizia Ribino et al.

Optimal Reporting of Predictions

1989

Abstract Consider a problem in which you and a group of other experts must report your individual predictive distributions for an observable random variable X to some decision maker. Suppose that the report of each expert is assigned a prior weight by the decision maker and that these weights are then updated based on the observed value of X. In this situation you will try to maximize your updated, or posterior, weight by appropriately choosing the distribution that you report, rather than necessarily simply reporting your honest predictive distribution. We study optimal reporting strategies under various conditions regarding your knowledge and beliefs about X and the reports of the other e…

The (micro) processes of integration as dialectic of structure and agency : the case of seconded national experts within the European Commission

2008

Masteroppgave i offentlig politikk og ledelse - Universitetet i Agder 2008 Micro-processes of integration – i.e. how agents develop identities, properties and decision-making behaviours preferred by a particular institution – have been a topic of significant scholarly debate. Most previous work builds on one underlying theoretical framework and thereby excludes (potentially important) elements lying outside it. My thesis attempts to contribute to the ongoing debate by developing a more holistic understanding of these processes, based on the dialectics of structure and agency and thereby positions actors’ decision-making behaviour on a continuum between ‘structural idiocy’ and ‘structural en…

A probabilistic expert system for predicting the risk of Legionella in evaporative installations

2011

Research highlights? The bacterium Legionella usually lives in water sources such as cooling towers. ? We discuss a probabilistic expert system for predicting the risk of Legionella. ? The expert system has a master-slave architecture. ? The inference engine is implemented through Bayesian reasoning. ? Bayesian networks model and connect relationships for chemical and physical variables. Early detection in water evaporative installations is one of the keys to fighting against the bacterium Legionella, the main cause of Legionnaire's disease. This paper discusses the general structure, elements and operation of a probabilistic expert system capable of predicting the risk of Legionella in rea…

Having the Final Say: Machine Support of Ethical Decisions of Doctors

2014

Machines that support highly complex decisions of doctors have been a reality for almost half a century. In the 1950s, computer-supported medical diagnostic systems started with “punched cards in a shoe box”. In the 1960s and 1970s medicine was, to a certain extent, transformed into a quantitative science by intensive interdisciplinary research collaborations of experts from medicine, mathematics and electrical engineering; This was followed by a second shift in research on machine support of medical decisions from numerical probabilistic to knowledge based approaches. Solutions of the later form came to be known as (medical) expert systems, knowledge based systems research or Artificial In…

HyperShell: An expert system shell in a hypermedia environment—application in medical audiology

1990

HyperShell is an expert system shell developed in a hypermedia environment. Several artificial intelligence techniques such as frames and semantic networks are used in an original interpretation to enhance the interaction between the user and the program. The typical navigation tools of hypermedia such as clickable buttons and text search are extended to the semantic structure of HyperShell, creating a set of new tools. Examples from a medical expert system (Audex HM) developed in HyperShell are described.

Knowledge Extraction from Healthcare Data Using User-Adaptable Keywords-Based Query Language

2020

Nowadays, the volume of the information gathered by any organization increases more and more rapidly. It is essential to be able to use this information efficiently for it to benefit the operation of the organization. There is no point of gathering the information if it is not converted into knowledge. The knowledge extraction process becomes the backbone of any successful organization. Moreover, the extraction of the knowledge must be quick and efficient, so that the newly-obtained knowledge can be put in use at once. The problem addressed in this paper is how to allow the domain expert to extract the knowledge from their information systems themselves without involving the third party in …

Domain Expert Platform for Goal-Oriented Dialog Collection

2021

Today, most dialogue systems are fully or partly built using neural network architectures. A crucial prerequisite for the creation of a goal-oriented neural network dialogue system is a dataset that represents typical dialogue scenarios and includes various semantic annotations, e.g. intents, slots and dialogue actions, that are necessary for training a particular neural network architecture. In this demonstration paper, we present an easy to use interface and its back-end which is oriented to domain experts for the collection of goal-oriented dialogue samples. The platform not only allows to collect or write sample dialogues in a structured way, but also provides a means for simple annotat…