ASSIGNMENT -1

ARTIFICIAL INTELLIGENCE

SUBMITTED BY,
SHANMATHI K(12BC089)
CSE B

APPLICATIONS OF ARTIFICIAL INTELLIGENCE:

Intelligent Optimization Methods in Civil Engineering:
Artificial intelligence is a science on the research and application of the
law of the activities of human intelligence. It has been a far-reaching crossfrontier subject, after the 50 years advancement. Nowadays, this technology is
applied in many fields such as expert system, knowledge base system,
intelligent database system, and intelligent robot system. Expert system is the
earliest and most extensive, the most active and most fruitful area, which was
named as the knowledge management and decision-making technology of the
21 century. In the field of civil engineering, many problems, especially in
engineering design, construction management, and program decision-making,
were influenced by many uncertainties which could be solved not only in need
of mathematics, physics, and mechanics calculations but also depend on the
experience of practitioners. This knowledge and experience are illogically
incomplete and imprecise, and they cannot be handled by traditional procedures.
However, artificial intelligence has its own superiority. It can solve complex
problems to the levels of experts by means of imitate experts. All in all, artificial
intelligence has a broad application prospects in the practice of civil
engineering.
Due to a lot of uncertain factors, complicated influence factors in civil
engineering, each project has its individual character and generality; function of
expert system in the special links and cases is a notable effect. Over the past 20
years, in the civil engineering field, development and application of the expert
system have made a lot of achievements, mainly used in project evaluation,
diagnosis, decision-making and prediction, building design and optimization,
the project management construction technology, road and bridge health
detection and some special field.

Artificial Immune Systems:

Provoked by the theoretical immunology, observed immune functions,
principles, and models, artificial immune system (AIS) stimulates the adaptive
immune system of a living creature to unravel the various complexities in realworld engineering optimization problems . In this technique, a combination of
the genetic algorithm and the least-squares method was used to find feasible
structures and the appropriate constants for those structures. The new approach
overcomes the shortcomings of the traditional and artificial neural networkbased methods presented in the literature for the analysis of civil engineering
systems.
Dessalegne and Nicklow employed an artificial life algorithm, derived
from the artificial life paradigm . The resulting multi-reservoir management
model was successfully applied to a portion of the Illinois River Waterway.
According to characteristics of diversity of the immune system, a variety
of immune algorithms have proposed by realization form. But since the immune
system characteristics of the application exploration is still in its initial stage,
the algorithm design has many aspects for improvement, such as the realization
of the algorithm, parameter selection, the theory discussion, and the immune
system in civil engineering application, still needing further development.

APPLICATION OF ARTIFICIAL INTELLIGENCE IN AEROSPACE:

Particular applications:
Search strategies using multi-agent systems
Autonomous multi-agent systems control and modelling
Hardware-in-the-Loop testing of autonomous spacecraft
Sensors-actuators-processors-communications (SAPC) testing
Formation-flying spacecraft control systems design, simulation and testing
Attitude determination and control techniques
Control systems for separated spacecraft
Biologically inspired devices and solutions
Working closely with the Autonomous Vehicle Control Systems lab, recent
research has been looking at developing autonomous spacecraft which have, in
effect, a 'brain' and the ability to follow commands given in system English
rather than computer code. By being able to think for themselves, the satellites
can then react to the environment around them, e.g. avoiding asteroids; and the
technology may also, in time, reduce the need for humans to go into space for
mere routine tasks. A lot of this work is also being applied to land and seabased autonomous vehicles.

Extensive work is also being done in the field of developing novel solutions
for complex, multi-agent system operation and control strategies. Research in
this area covers theoretical modelling, simulation and experimental testing using
model spacecraft.
Innovative work is being done in the area of biologically inspired devices and
solutions, for example, development of search algorithms based on bee swarms,
and research into the neural signalling in invertebrates' leg movements.

THE SIX TASK ENVIRONMENTAL PROPERTIES:

In spite of the difficulty of knowing exactly where the environment ends and the
agent begins in some cases, it is useful to be able to classify AI environments
because it can predict how difficult the task of the AI will be. They are:

Deterministicness (deterministic or stochastic): An environment is

deterministic if the next state is perfectly predictable given knowledge of the
previous state and the agent's action.

Staticness (static or dynamic): Static environments do not change while the

agent deliberates.

Observability (full or partial): A fully observable environments is one in

which the agent has access to all information in the environment relevant to its
task.

Agency (single or multiple): If there is at least one other agent in the

environment, it is a multi-agent environment. Other agents might be apathetic,
cooperative, or competitive.

Knowledge (known or unknown): An environment is considered to be

"known" if the agent understands the laws that govern the environment's
behavior. For example, in chess, the agent would know that when a piece is
"taken" it is removed from the game. On a street, the agent might know that
when it rains, the streets get slippery.

Episodicness (episodic or sequential): Sequential environments require

memory of past actions to determine the next best action. Episodic
environments are a series of one-shot actions. An AI that looks at radiology
images to determine if there is a sickness is an example of an episodic
environment. One image has nothing to do with the next.

Discreteness (discrete or continuous): A discrete environment has fixed

locations or time intervals. A continuous environment could be measured
quantitatively to any level of precision.

In each case, the job of the AI (and for the programmer making the AI) is easier if
the first of the two options is the best descriptor for each category. That is, an AI
that has a much more difficult job if it works in an environment that is stochastic,
dynamic, partially observable, multi-agent, unknown, sequential, and continuous.