MPRI Ship Analytics


Intelligent Systems and Artificial Intelligence

Artificial Intelligence is the branch of computer science concerned with making computers behave like humans. The term was coined in 1956 by John McCarthy at the Massachusetts Institute of Technology.

The term 'Artificial Intelligence' is used as a general description for many techniques that are being tried to create intelligence within a machine. Some of these techniques include, though are not limited too:

  • games playing : programming computers to play games such as chess and checkers
  • expert systems : programming computers to make decisions in real-life situations (for example, some expert systems help doctors diagnose diseases based on symptoms)
  • natural language : programming computers to understand natural human languages
  • neural networks : Systems that simulate intelligence by attempting to reproduce the types of physical connections that occur in animal brains
  • robotics : programming computers to see and hear and react to other sensory stimuli

Currently, no computers exhibit full artificial intelligence (that is, are able to simulate human behavior) and are unlikely to do so for a few years yet primarily due to the limitation on computing power that is currently available, even in the largest supercomputers.

WISE Systems are currently based on the use of Expert Systems.

An expert system can be described as a computer application that performs a task that would otherwise be performed by a human expert. An expert system is a collection of data which clearly defines in computer form the expertise usually found in a human undertaking the same task. It is not a system that learns as time progresses, as is the case with neural networks, and to produce such a system one needs a knowledge engineer who is an individual who studies how human experts make decisions and translates that into terms that a computer can understand.

Examples of the use of expert systems include those that can diagnose human illnesses, make financial forecasts, and schedule routes for delivery vehicles. Some expert systems are designed to take the place of human experts, while others are designed to aid them.

In the early 1980s, expert systems were believed to represent the future of artificial intelligence and of computers in general. However as time progressed a number of problems began to become apparent most notably with the difficulty in defining expertise on a large scale in usable forms and the amount of processing required to achieve the required result and consequently such systems have until recently had fallen out of favor.

By taking a new approach to how expert systems are structured, the WISE Systems address many of the issues involved in the initial development and actual performance enabling the resulting systems to be used very effectively in a real time environment.






© 2008 MPRI