Wednesday, March 21, 2012

Artificial Intelligence Applications.


Artificial Intelligence Applications.
Applications of Artificial Intelligence:-

1.Problem Solving

2.Game Playing

3.Theorem Proving

4.Natural Language Processing & Understanding

5.Perception General

      · Speech Reorganization

      · Pattern Reorganization

6.Image Processing

7.Expert System

8.Computer Vision

9.Robotics

10.Intelligent Computer Assisted Instruction

11.Automatic programming

12.Planning & Decision Support systems

13.Engineering Design & Comical Analysis

14. Neural Architecture.

15. Heuristic Classification.

1 Problem Solving:-

This is the first application area of AI research., the objective of this particular area of research is how to implement the procedures on AI systems to solve the problems like Human Beings.

2 :- Game Playing:-
Much of early research in state space search was done using common board games such as checkers, chess and 8 puzzle. Most games are played using a well defined set of rules. This makes it easy to generate the search space and frees the researcher from many of the ambiguities and complexities inherent in less structured problems. The board Configurations used in playing these games are easily represented in computer, requiring none of complex formalisms. For solving large and complex AI problems it requires lots of techniques like Heuristics. We commonly used the term intelligence seems to reside in the heuristics used by Human beings to solve the problems.

3 :- Theorem Proving:-

Theorem proving is another application area of AI research., ie. To prove Boolean Algebra theorems as a humans we first try to prove Lemma., i.e it tell us whether the Theorem is having feasible solution or not. If the theorem having feasible solution we will try to prove it otherwise discard it., In the same way whether the AI system will react to prove Lemma before trying to attempting to prove a theorem., is the focus of this application area of research.

4 Natural Langauge understading:-

The main goal of this problem is we can ask the question to the computer in our mother tongue the computer can receive that particular language and the system gave the response with in the same language. The effective use of a Computer has involved the use off a Programming Language of a set of Commands that we must use to Communicate with the Computer. The goal of natural language processing is to enable people and language such as English, rather than in a computer language.

It can be divided in to Two sub fields.

Natural Language Understanding : Which investigates methods of allowing the Computer to improve instructions given in ordinary English so that Computers can understand people more easily.

Natural Language Generation : This aims to have Computers produce ordinary English language so that people an understand Computers more easily.

5. Perception:-

The process of perception is usually involves that the set of operations i.e. Touching , Smelling Listening , Tasting , and Eating. These Perceptual activities incorporation into Intelligent Computer System is concerned with the areas of Natural language Understanding & Processing and Computer Vision mainly. The are two major Challenges in the application area of Perception.

1. Speech Reorganization

2. Pattern Reorganization

¨Speech Reorganization:-

The main goal of this problem is how the Computer System can recognize our Speeches. (Next process is to understand those Speeches and process them i.e. Encoding & Decoding i.e producing the result in the same language.) Its one is very difficult; Speech Reorganization can be described in two ways.

1. Discrete Speech Reorganization

Means People can interact with the Computer in their mother tongue. In such interaction whether they can insert time gap in between the two words or two sentences (In this type of Speech Reorganization the computer takes some time for searching the database).

2. Continues Speech Reorganization

Means when we interact with the computer in our mother tongue we can not insert the time gap in between the two words or sentences , i.e. we can talk continuously with the Computer (For this purpose we can increase speed of the computer).
¨Pattern Reorganization: -

 this the computer can identify the real world objects with the help of “Camera”. Its one is also very difficult , because

- To identify the regular shape objects, we can see that object from any angle; we can imagine the actual shape of the object (means to picturise which part is light fallen) through this we can identify the total structure of that particular object.

-To identify the irregular shape things, we can see that particular thing from any angle; through this we cannot imagine the actual structure. With help of that we can attach the Camera to the computer and picturise certain part of the light fallen image with the help of that whether the AI system can recognize the actual structure of the image or not? It is some what difficult compare to the regular shape things, till now the research is going on. This is related the application area of Computer Vision.

A Pattern is a quantitative or structured description of an object or some other entity of interest of an Image. Pattern is found an arrangement of descriptors. Pattern recognition is the research area that studies the operation and design of systems that recognize patterns in data. It encloses the discriminate analysis, feature extraction, error estimation, cluster analysis, and parsing (sometimes called syntactical pattern recognition). Important application areas are image analysis, character recognition, speech recognition and analysis, man and machine diagnostics, person identification and industrial inspection.

Closely Related Areas Pattern Recognition

Artificial Intelligence

Expert systems and machine learning

Neural Networks

Computer Vision

Cognition

Perception

Image Processing


6.Image Processing:-
Where as in pattern reorganization we can catch the image of real world things with the help of Camera. The goal of Image Processing is to identify the relations between the parts of image.

It is a simple task to attach a Camera to a computer so that the computer can receive visual images. People generally use Vision as their primary means of sensing their environment. We generally see more than we here. i.e. how can we provide such perceptual facilities touch, smell, taste, listen, and eat to the AI System. The goal of Computer Vision research is to give computers this powerful facility for understanding their surroundings. Currently, one of the primary uses of Computer Vision is in the area of Robotics.

Ex: - We can take a Satellite image to identify the roots and forests; we can make digitize all the image and place on the disk. With the help of particular scale to convert the image in to dots form, later we can identify that particular image at any time. Its one is time consuming process. With the help of “ image processing” how to reduce the time to process an image till now the AI research will be continuously going on.

In Image Processing the process of image recognition can be broken into the following main stages.

· Image capture

· Edge detection

· Segmentation

· Recognition and Analysis.

Image capturing can be performed by a simple Camera, which converts light signals from a scale of electrical signals., i.e., done by human visual system. We obtained these light signals in a set of 0’s and 1’s. Each pixel takes on one of a number of possible values often from 0 to 255. Color images are broken down in the same way, but with varying colors instead of gray scales. When a computer receives an image from sensor in form of set of pixels. These pixels are integrated to give the computer an understanding of what it is perceiving.

An image has been obtained, is to determine where the edges are in the image, the very first stage of analysis is called edge detection. Objects in the real world are almost all have solid edges of one kind or another, detecting those images is first step in the process of determining which objects are present in a scene.

Once the edges have been detected, in an image, this information can be used to Segment the image, into homogeneous areas. There are other methods available for segmenting an image, apart from using edge detection, like threshold method. This method involves finding the color of each pixel in an image and considering adjacent pixels to be in the same area as long as their color is similar enough.

A similar method for segmenting images is splitting and merging. Splitting involves taking an area that is not homogeneous and splitting it into two or more smaller areas, each of which is homogeneous. Merging involves taking two areas that are the same as each other, and adjacent to each other and combining them together into a large area. This provides a sophisticated interactive approach to segmenting an image.

Intermediate Level of processing

Low Level Processing High Level Processing

7.§Expert system:- Expert means the person who had complete knowledge in particular field, ie is called as an expert. The main aim of this problem is with the help of experts, to load their tricks on to the compute and make available those tricks to the other users. The expert can solve the problems with in the time.

The goal of this problem is how to load the tricks and ideas of an expert on to the computer, till now the research will be going on.

8. § Computer Vision:- It is a simple task to attach a camera to a computer so that the computer can receive visual images. People generally use vision as their primary means of sensing their environment. We generally see more than we here, feel, smell, or taste.

The goal of computer vision research is to give computers this powerful facility for understanding their surroundings. Currently, one of the primary uses of computer vision is in the area of Robotics.

9. § Robotics:-

A robot is an electro – mechanical device that can be programmed to perfume manual tasks. The robotics industries association formally defines to move a Robot as a “ Programmable multi-functional manipulator designed to move material, parts, tools, or specialized devices through variable programmed motions for the performance of variety of tasks”.

Not all robotics is considered to be part of AI. A Robot that perform sonly the actions that it is has been pre-programmed to perform is considered to be a “dumb” robot, includes some kind of sensory apparatus, such as a camera , that allows it to respond to changes in its environment , rather than just to follow instructions “mindlessly”.

10. § Intelligent Computer – Assisted Instruction:-
Computer - Assisted Instruction (CAI) has been used in bringing the power of the computer to bear on the educational process. Now AI methods are being applied to the development of intelligent computerized “ Tutors” that shape their teaching techniques to fit the leaning patterns of individual students.

11. § Automatic Programming:- Programming is the process of telling the computer exactly what we want to do . the goal of automatic programming is to create special programs that act as intelligent “Tools” to assist programmers and expedite each phase of the programming process. The ultimate aim of automatic programming is a computer system that could develop programs by itself, in response to an in according with the specifications of the program developer.

12. § Planning and Decision Support system:- When we have a goal, either we rely on luck and providence to achieve that goal or we design and implement a plan. The realization of a complex goal may require to construction of a formal and detailed plan. Intelligent planning programs are designed to provide active assistance in the planning process and are expected to the particularly helpful to managers with decision making responsibilities.

13. §Engineering Design & Camical Analysis:-

Artificial Intelligence applications are playing major role in Engineering Drawings & Camical analysis to design expert drawings and Camical synthesis.

14. § Neural Architecture:-

People or more intelligent than Computers,. But AI researchers are trying how make Computers Intelligent. Humans are better at interpreting noisy input, such as recognizing a face in a darkened room from an odd angle. Even where human may not be able to solve some problem, we generally can make a reasonable guess as to its solution. Neural architectures, because they capture knowledge in a large no. of units. Neural architectures are robust because knowledge is distributed somewhat uniformly around the network.

Neural architectures also provide a natural model for parallelism, because each neuron is an independent unit. This showdown searching the data base a massively parallel architecture like the human brain would not suffer from this problem.

15. § Heuristic Classification:-

The term Heuristic means to Find & Discover., find the problem and discover the solution. For solving complex AI problems it’s requires lots of knowledge and some represented mechanisms in form of Heuristic Search Techniques., i.e refered to known as Heuristic Classification.

Planning with Constraints. Planning Sub System.

Planning with Constraints
Hierarchical planners distinguish between important considerations and details. A hierarchical planner creates descriptions of abstract states and divides its planning task into subproblems for refining the abstract states. The abstract states enable it to focus on important considerations, thereby avoiding the burden of trying to deal with everything at once. In most practical planning problems, however, the subproblems interact. Without the ability to handle these interactions, hierarchical planners can deal effectively only with idealized cases where subproblems are independent and can be solved separately.
This paper presents an approach to hierarchical planning, termed constraint posting, that uses constraints to represent the interactions between subproblems. Constraints are dynamically formulated
and propagated during hierarchical planning, and used to coordinate the solutions of nearly independent subproblems. This is illustrated with a computer program, calledMOLGEN, that plans gene-cloning experiments in molecular genetics.

1. Introduction
Divide each problem that you examine into as many parts as you can and as you need to solve them more easily.
This rule of Descartes is of little use as long as the art of dividing. . . remains unexplained. . . . By dividing his problem into unsuit..
able parts, the inexperienced problem -solver may increase his difficulty. Subproblems interact. This observation is central to problem solving, particularly planning and design. When interactions can be anticipated, they can  guide the division of labor. When they are discovered late, the required changes can be difficult and expensive to incorporate. The difficulty of managing interactions is compounded by problem size and complexity. In large design projects, unforeseen interactions often consume a substantial share of the work of project managers [2]. This paper is concerned with ways to cope with and exploit interactions in design. Section 2 presents the constraint posting approach for managing interactions in design. Constraint posting has been implemented in a computer program (named MOLGEN) that has planned a few experiments in molecular genetics. In Section 3, the design of an experiment is used to illustrate the constraint posting ideas. In Section 4, the effectiveness of constraint posting on the sample problem is examined. The remaining sections trace the intellectual connections to other work on problem solving and propose suggestions for further research. This is the first of two papers about my thesis research on MOLGEN. Both papers are concerned with the use and organization of knowledge to make planning effective. This paper discusses the use of constraints to organize knowledge about subproblems in hierarchical planning. A companion paper [21] discusses the use of levels to organize control knowledge. It also develops a rationale for deciding when a planner should use heuristic reasoning. The research was carried out as part of the MOLGEN project at Stanford. A long term goal of this project is to build a knowledge-based program to assist geneticists in planning laboratory experiments. Towards that goal, two prototype planning systems have been constructed and used as vehicles for testing ideas about planning.

2. The Constraint Posting Approach to Design
The constraint posting approach depends on the view of systems as aggregates of loosely coupled subsystems. It models the design of such systems in terms of operations on constraints.
2.1. Nearly independent subproblems
In Sciences of the Artificial, Simon discussed the study and design of complex systems. He observed that when we study a complex system, whether it is natural or man-made, we often divide it into subsystems that can be studied separately without constant attention to their interactions. For example, in studying an automobile, we delineate subsystems such as the electrical system, fuel system, engine, and the brake system; in an animal, we delineate the nervous system, circulatory system, and the digestive system. Similarly, when we design complex systems, we tend to first map out the
design in terms of subsystems. Designers have advocated this top-down ap-PLANNING WITH CONSTRAINTS.