Professional Documents
Culture Documents
The first expert systems were created in the 1970s and then proliferated in the
1980s. Expert systems were among the first truly successful forms of artificial
intelligence (AI) software.
An expert system is divided into two subsystems: the inference engine and the
knowledge base. The knowledge base represents facts and rules. The inference
engine applies the rules to the known facts to deduce new facts. Inference
engines can also include explanation and debugging abilities.
Soon after the dawn of modern computers in the late 1940s – early 1950s,
researchers started realizing the immense potential these machines had for
modern society. One of the first challenges was to make such machine capable of
“thinking” like humans. In particular, making these machines capable of making
important decisions the way humans do. The medical / healthcare field presented
the tantalizing challenge to enable these machines to make medical diagnostic
decisions.
Thus, in the late 1950s, right after the information age had fully arrived,
researchers started experimenting with the prospect of using computer
technology to emulate human decision-making. For example, biomedical
researchers started creating computer-aided systems for
diagnostic applications in medicine and biology. These early diagnostic systems
used patients’ symptoms and laboratory test results as inputs to generate a
diagnostic outcome.
These systems were often described as the early forms of expert systems.
However, researchers had realized that there were significant limitations when
using traditional methods such as flow-charts statistical pattern-matching, or
probability theory.
The limitations of the previous type of expert systems have urged researchers to
develop new types of approaches. They have developed more efficient, flexible,
and powerful approaches in order to simulate the human decision-making
process. Some of the approaches that researchers have developed are based on
new methods of artificial intelligence (AI), and in particular in machine learning
and data mining approaches with a feedback mechanism. Recurrent neural
networks often take advantage of such mechanisms. Related is the discussion on
the disadvantages section.
Modern systems can incorporate new knowledge more easily and thus update
themselves easily. Such systems can generalize from existing knowledge better
and deal with vast amounts of complex data. Related is the subject of big data
here. Sometimes these types of expert systems are called "intelligent systems."
MYCIN operated using a fairly simple inference engine and a knowledge base of
~600 rules. It would query the physician running the program via a long series of
simple yes/no or textual questions. At the end, it provided a list of possible culprit
bacteria ranked from high to low based on the probability of each diagnosis, its
confidence in each diagnosis' probability, the reasoning behind each diagnosis
(that is, MYCIN would also list the questions and rules which led it to rank a
diagnosis a particular way), and its recommended course of drug treatment.
MYCIN sparked debate about the use of its ad hoc, but principled, uncertainty
framework known as "certainty factors". The developers performed studies
showing that MYCIN's performance was minimally affected by perturbations in
the uncertainty metrics associated with individual rules, suggesting that the
power in the system was related more to its knowledge representation and
reasoning scheme than to the details of its numerical uncertainty model. Some
observers felt that it should have been possible to use classical Bayesian statistics.
MYCIN's developers argued that this would require either unrealistic assumptions
of probabilistic independence, or require the experts to provide estimates for an
unfeasibly large number of conditional probabilities.
Subsequent studies later showed that the certainty factor model could indeed be
interpreted in a probabilistic sense, and highlighted problems with the implied
assumptions of such a model. However the modular structure of the system
would prove very successful, leading to the development of graphical models
such as Bayesian networks.
In MYCIN it was possible that two or more rules might draw conclusions about a
parameter with different weights of evidence. For example, one rule may
conclude that the organism in question is E. Coli with a certainty of 0.8 whilst
another concludes that it is E. Coli with a certainty of 0.5 or even -0.8. In the event
the certainty is less than zero the evidence is actually against the hypothesis. In
order to calculate the certainty factor MYCIN combined these weights using the
formula below to yield a single certainty factor:
Where X and Y are the certainty factors. This formula can be applied more than
once if more than two rules draw conclusions about the same parameter. It is
commutative, so it does not matter in which order the weights were combined.
Monitoring systems currently available allow to carry out three kinds of checks on
the value
Therefore, these checks neither deal with more than one instrument at a time,
nor with more than one reading at a time for each instrument. Besides, each
behaviour (either of the structure, or of the instruments, or accidental) that is not
consistent with the reference values generates a warning message. Because of
the poor interpretation skills of the people at the warden houses, false alarms
also require experts' analysis. Within the framework of the DAMSAFE project
(Comerford, Salvaneschi et al., 1992), which aims to investigate the application of
Artificial Intelligence techniques in the field of dam safety, a decision support
system was developed (MISTRAL), in order to provide a software tool for better
using automatic monitoring systems, filtering their alarms and supporting the
tasks of the safety managers. The tool filters and classifies the anomalies by using
models of the structural behaviour based on sets of readings of the monitoring
system. This allows to perform on-line a part of the expert interpretation, and
therefore to reduce the requests of experts' intervention and to increase the
reliance on the safety of the dam. MISTRAL was developed on a personal
computer; the core of the system was written in Prolog, while the interface,
communication mechanisms and data base management functions were
implemented with VisualBasic.
From the civil engineering point of view, MISTRAL deals with features of the
measurements such as homogeneity, priority and congruency, taking into account
structural reference models. Checks carried out by MISTRAL use knowledge about
significance and reliability of the instruments. On the ground of geometric
reasoning, physical models and empirical knowledge, congruency relationships
among sets of measures have been identified. These relations are both qualitative
and quantitative and lead the process of identifying the current state of each
single group of measures; starting from the local state of the groups of
measurements it is possible to define the global state of the structure.
1. checks on sections: instruments within the same section of the dam are taken
into account (e.g. vertical blocks);
2. evaluation of physical phenomena: instruments which measure the same
quantity are taken into account (e.g. displacements, underpressures);
3. evaluation of physical processes: instruments which allow the identification of
ongoing
processes are taken into account (e.g. rotation of the dam body, filtering of water
through dam body); in this case, the instruments can belong to different sections
and measure different quantities.
DESCRIPTION OF THE SYSTEM
MISTRAL is a decision support system comprised of the following modules (figure
1):-
The communication module calls the monitoring system and receives the data
gathered during the last acquisition (normal real-time procedure) or collected
while MISTRAL was, for some reason, not active.
The data are analysed by the evaluation module, that identifies the current state
of the structure. The evaluator acts on a hierarchical model of the dam and uses
information chaining techniques in order to establish the global state starting
from local knowledge of the state of the instruments. Qualitative and quantitative
information, model based reasoning and empirical relations are used by the
evaluator. The dam model is comprised of Prolog predicates which describe the
parts of the physical system and their properties and relations. Pattern matching
techniques are used by the
evaluator to identify the objects to deal with. The system uses several kinds of
representation for codifying the relationships:
We have explained that how they work and for what purpose they have built , as
day goes by , we will see more and more of expert systems in this area.
Reference