Applications of Artificial Intelligence | Computer Science

The vast field of artificial intelligence has a wide spectrum of applications a few of them are given here: 1. General Problem Solving 2. Expert Systems 3. Natural Language Processing 4. Computer Vision 5. Robotics 6. Computer-Aided Instructions (CAI) 7. Planning.

Application # 1. General Problem Solving:

Several specific problems such as water jug problem, travelling sales man problem or other general problems such as Tower of Hanoi, Monkey and Bananas problem, cryparithemic or the Missionaries and Cannibals problem etc., can be taken up with the AI machines which would be described in detail at relevant places.

However, the solution may be approximate or exact depending upon the structure of the problem domain and the knowledge available.

Application # 2. Expert Systems:

These information systems draw upon several areas of artificial intelligence to perform their operations. Developing an expert system requires an understanding of knowledge representation. Human knowledge can be represented as production rules, i.e., simple or complex if then combinations, if antecedent-consequent constructions, first order logical constructions such as- likes (Mary, wine), or extended representations called fames. Frames represent human knowledge as objects which have attributes and which further have values.

These O-V-A combinations can be assembled into recursive structures which map very closely to their real world counterparts. Knowledge about the world and the functioning of these objects can then be applied to real world situations. Knowledge is not always exact, therefore a robust knowledge representation scheme need to have some form of representing ambiguity. Fuzzy logic is a way of capturing ambiguity about a real world phenomena.

For instance one might make the observation that a man is “tall” because he stands 6 feet, 2 inches in height. Would a man who is 6 feet, 1 inch or man who is 6 feet and V4 inches still tall? Fuzzy logic enables ranges of confidence to be expressed about a particular object or rule. Once some form of representation scheme is identified an inferencing strategy is required. Humans use both forward-chaining and backward-chaining strategies.

They often use combination of the two to solve complex problems. Problems which require identification from a few facts is a typical use of forward-chaining. A forward-chainer can be provided with a small set of facts about a situation or object and reason back, about the problem. For instance an ophthalmologist can quickly assess the type of problem which a patient presents just based upon a few facts and observations.

The problem can quickly be identified and classified as to whether it is caused by trauma, infection, toxicity, congenital or systemic (e.g., detached retina as a result of high blood pressure). A backward-chaining system can create theories. A famous backward-chainer was Sherlock Holmes.

Holmes was presented with a finished result. A person might have been murdered under mysterious circumstances. Holmes was able to reason backward from the presented corpse to how the person ended up in a terminal state.

He created theories based upon observations and knowledge about the real world. In order to rapidly achieve a goal or formulate a correct theory means that the chainer utilize operators and meta-operators. Solving rubies cube world requires the use of both.

This is because the act of putting a cube back in order involves interacting-sub-goals i.e., partial goals which conflict with solving the larger puzzle. Operators and meta-operators are used to navigate the search space and constrain the combinatorial explosion which results when one attempts to solve a problem. Knowledge can be characterized in terms of the “strength” of the knowledge. The more effective the knowledge, the less time is required to traverse the space.

Application # 3. Natural Language Processing:

Natural language means the native language i.e., the language one speaks. Computer’s language (machine language) is quite complex. For the computer to understand natural language is equally complex at present.

In order to understand natural language it must know how to:

i. Generate

ii. Understand

iii. Translate.

So a natural language computer is the computer which interacts through natural language, must have a parser, a knowledge representation system and an output translator.

Application # 4. Computer Vision:

It is a technique for a computer system to search beyond the data it is given and to find out almost the real world by analyzing and evaluating visual information. By search and pattern matching techniques a computer can pick up key features, then identify features a human eye can miss.

Vision program consists of three stages program:

(i) Low Level Vision:

Preprocessing the image of filtering from noise.

(ii) Medium Level Vision:

The medium level deals with enhancement of details and segmentation (portioning image into objects of interest).

(iii) The High Level Vision:

a. Recognition of object from segmented image.

b. Labelling the image.

c. Interpretation of scene.

Recognition of objects from its image can be done by process of pattern recognization (done by supervised learning algs). Interpretation is done through knowledge based computation.

Things which computer vision is currently good at (as of 2007) include:

i. Detecting human Faces in a Scene.

ii. Recognizing people from non-frontal views.

iii. Determining the gaze direction of someone with high accuracy.

iv. Recognizing people as they age, wear a hat, shave, or grow a beard.

v. Recognizing whether a face is that of a male or female, or a person who is young or old?, or just about any other kind of discrimination?

vi. Compensating for camera motion in tracking objects.

vii. Forming geometric models of objects.

viii. Determining the rough three-dimensional structure of a scene over a distance of six meters.

Things which computer vision is still not good at (as of 2007) include:

i. Recognizing what people are wearing.

ii. Determining the material properties of something which is viewed.

iii. Discriminating general objects from the background.

iv. Recognizing general objects.

v. Lip readings.

vi. Recognizing emotion.

vii. Gesture recognition.

Application # 5. Robotics:

This is field of engineering devoted to duplicating the physical capabilities of human being; attempts to mimic human mental abilities. They differ from AI programs, which usually operate in computer-simulated world whereas robots operate in physical world. As an example, consider making a move in chess. An AI program can search millions of nodes in a game tree.

The Sony Crop, of Japan has recently designed 23 inch tall, humanoid robot, called “SDR-4X”, which has a photographic memory, an extensive vocabulary and a juke-box phonograph like knowledge of music. It is a robot designed to live with people in homes and costs as much as a luxury car.

It can carry on simple conversations with its 60,000 word vocabulary, recognize colour, dodge obstacles in its path and even sing once programmed with music and lyrics. This robot can even be programmed to recognize 10 people through their faces, stores as digital images shot with its camera and their voices, picked up through seven microphones.

It also remembers their names. It has sensors on the bottom of its feet to help it walk on uneven surfaces such as carpeting and has been programmed to tumble without falling apart and then get up on its own. Walking robot called Asimo, greets visitors at showrooms. Entertainment robots talk with children, play simple games and draw pictures. Robots can help re-habitation patients who need to strengthen their legs.

Researchers in Michigan USA have developed a robot to carry out life saving breast examination combing ultrasound with an artificial sense of touch. This will enable a medical specialist to examine women from a remote location, perhaps even from the other side of the world. The field has expanded into a complete study in itself.

Navigational Planning for Mobile Robots:

In mobile robots sometimes called Automated Guided Vehicles (AGV), AI finds extensive applications.

A mobile robot generally has one or more camera or ultrasonic sensors, which help in identifying the obstacles on its trajectory. The navigational planning problem persists both in static and dynamic environments. In static environ­ment, the position of obstacles is fixed.

In dynamic environment the obstacles may move at arbitrary directions with varying speeds, lower than the maximum speed of the robot. Many researchers using spatio-temporal logic have attempted the navigational planning problems to mobile robots in a static environment. On the other hand for both planning in a dynamic environment the Genetic Algs and the neural networks have made some success.

In the recent future the mobile robots will find extensive application in fire-fighting, mine clearing and factory automation. In accident prone industrial environment mobile robots may be exploited for automated diagnosis, replacement of defective parts of instrument.

Researchers at NEC system technologies and Mie University (both of Japan) have designed a robot which can taste an electromechanical sommelier able to identify dozen of different wines, cheeses and horsd’o euvores. Even they have unveiled the fruits. This robot has a head which swivels and a mouth which lights up whenever the robots talks.

When the robot has identified a wine the robot speaks up in a child like voice, names the brand and adds a comment on the taste.

Application # 6. Computer-Aided Instructions (CAI):

This aspect brings the power of computer to the educational process. CAI methods are being applied to the development of Intelligent Computer-Assisted Instruction (ICAI) systems which can tutor humans by shaping their teaching techniques to fit the learning patterns of individual students. To a certain extent such a machine can be viewed as an expert systems. However, the major objective of an e.s. is to render advice, whereas the purpose of ICAI is to teach.

ICAI applications are not limited to schools, but as a matter of fact have found a sizable niche in the military and corporate sectors. ICAI systems are being used these days for tasks as problem solving, simulation, discovery, learning, drill and practice, games and testing. Such systems are also used to support people with physical or learning impairments. A good number of ICAI programs are now offered on Internet/Internet, creating virtual schools and universities.

Another application of ICAI is interpretive testing using the approach GMAT/TOFFEL and other infamously long tests have been shortened in time. By being better able to interpret the answers, the test can more accurately pinpoint the strength/weakness of the test takers by asking fewer but more relevant questions.

Application # 7. Planning:

Humans excel at creating real world plans on a daily basis seemingly effortlessly. But machines have started to create real world ad hoc plans however they require an extensive knowledge base to account for the combinatorial explosion which typically arises when trying to move forward.

A computing system which is capable of recognizing the plan which an actor or agent is formulating is in the position of either assisting in implementing the plan or may be able to thwart the plan (Henry Kautz-Plan Recognition). Using Kautz’ system, one can create a knowledge base about a specific domain.

The expert system which uses this knowledge base is then able to recognize the activity in question and make inferences about the state of completion of the plan. Sufficiently robust plan recognizers can identify the actions of both individual agents but also teams of agents all of whom may be actively attempting to coordinate their efforts to accomplish a goal.