EXAMPLE OF EXPERT SYSTEM

MEDICAL EXPERT SYSTEM

The basic tasks that are carried out by the medical expert system is diagnosis, prognosis, treatment, monitoring. In terms of treatment, the patient or the physician could access the system through internet. From here the user could choose from a choice of patients database or patience disease database. Each database would perform a particular task, either from diagnosis module or prediction module as shown on the diagram. The feedback is sent to the user through internet so that the treatment can be performed. Expert must also access this system, to update the data stored in the knowledge base. WHO ARE THE USERS The main purpose for the creation of the medical expert system was to support the physicians and doctors. The rapid growth of ever expanding detailed medical knowledge leave physicians without adequate time to study or train and does not let them to keep all the relevant information constantly in their minds. The medical expert system was created to aid the physicians memory and judgments. However, now it is increasing being used for training of the students in medicine as it is a very effective education and training system. ADVANTAGES AND BENEFITS IN EXPERT SYSTEM

Medical expert systems can provide; precise, quick and inexpensive consultation with a restless, multipliable and alert consultant of minimum needs. Medical expert systems lead to less undiagnosed cases, lower iatrogenic disorders and more effective treatment i.e. Improved and cost-effective healthcare. They can also be used for effective education and training. A large database of knowledge can be added to and kept up-to-date - it can store more knowledge than a person. The system cannot 'forget' or get facts wrong. It survives forever. There is no loss of knowledge as there is when a doctor retires. The computer can access specialist knowledge that a doctor may not have.

ETHICAL AND SOCIAL ISSUES Firstly, the issue of reliability must be addressed. For the medical expert system to work, it is important that the knowledge base is kept reliable. This is because if the knowledge base gives a wrong method of treatment to the user, they may suffer from medical error and cause their injury to worsen. Secondly, the issue of security is another concern. The administrator of the system must strictly control who is allowed to have access to the system. This is because if anyone is able to access the system and change the information that is in them, it would cause the system to operate wrongly. This links with the issue of reliability. The system operation must be closely supervised and must be made sure that only the certified expert has the right to change the information on them. Thirdly, however the medical expert system also brought benefit regarding equality of access. As some medical knowledge became available through the internet; people who were not able to reach the doctors are now able to obtain some sense of support. Furthermore, physicians in the rural area are able to acquire the latest knowledge that has been discovered elsewhere single handedly through the expert system.

AIR TRAFFIC CONTROL

Expert system for air traffic control and controller training

A expert system form of artificial intelligence for control of air traffic which may also be utilized for air traffic controller training. The expert system receives input data representing the altitude and heading of all aircraft in the control area. The aircraft data is compared with the data of the other aircraft. Sequencing and local flow control is optimized and if a potential conflict arises between two aircraft, clearances are transmitted to the aircraft to resolve the conflict. The aircraft data is also compared with a knowledge base of air traffic control rules for the particular airport involved. An inference engine written in LISP (or another AI language) allows real time access to the knowledge base. The position and heading of each aircraft is monitored and controlled until turned over to the tower for final approach. The uses and users The expert system may also be used for air traffic controller training and be used as a intelligent tutor. The air traffic controller trainee's clearances are input and compared to those generated by the system. If the trainee's clearances are in error, or can be improved, the expert system prompts the trainee and coaches him in a way so that he learns from his past errors Pilots, staff in the control tower. Make routing/scheduling decisions, Analyze effects of some safety policy decisions, Incorporate safety metric into strategic vision, Objectively communicate safety issues within and between organizations. ADV

 Apply to all risk categories Customizable to different safety environments Adapt to technological and procedural changes in airline environments Use data and expert judgments in a unified model & Good for complex problems where humans dont have expert knowledge Issues Issues Accomodating more input variables Reducing number of model parameters Use of training data and testing data Model development used artificial data Different data sets must be used to train and to test Generating target values Model development used artificial targets Strategies for simplifying target acquisition Validation strategies - Forecasted Weather: Inaccurate forecasts will lead to higher risk as users of the forecast may ignore information or users may make incorrect decisions based on the inaccurate forecast. b Hypothetical example: Heavy rain is forecasted by NWS at ORD. When heavy rain is forecasted by NWS at ORD, heavy rain occurs X percent of the time.

Detecting Problems in Computer/Help Desk

A help desk is a type of expert system which allows customers to obtain service or help when detect problems relating to a certain object, for example, a person is having problems connecting to the internet, there will be a message that appears on the screen that may give a specific error number, and the system will allow the customer to go through a series of questions and tries to solve the problem. There are many forms of a help desk, for example telephone, online services or troubleshooting programs for various programs.

An example of a series of questions that a customer may have to answer that could help them solve their problem Who are the users? The main purpose for having a help desk or an expert system that detects problems in a computer is that it helps privde on the spot assistance to customers who are experiencing problems with a program or their computer. Thus, the main users of this expert system are the customers, as they are the ones that benefit from using this system. Furthermore, it can also be used by any IT professionalist as it can help them save time and assist customers experinecing greater technical difficulties that the expert system can not see to. The advantages and benefits of having the expert system Customers can receive on the spot assistance if they are experiencing any technical difficulties with their

computer or any program Less time consuming; Customers do not have to wait for long for the assistance if the system can provide them with the solution to their problem Customers can receive 24/7 support as they can use the troubleshooter or go online and seek for assistance It enables a business to expand as it helps potential and existing customers to communicate with the business more and smoothens problems faced by the customer The system can store information (whethere in a database or any other program) and can retrieve the information automatically and does not need be controlled by any expert to help find the solution Any social the ethical and social issues arising from this application

The expert system is made by experts and may not contain the true facts, thus the information inputted could be wrong and therefore lead to further problems Also, there is a concern with how reliable is the source that the customers are receiving their assistance from, for example, is the site secured? (Hackers?) Another point that could be raised is that whether everyone has access to benefit from these services, for example, people who may not have internet may not receive online support/assistance Websites http://www.help-desk-world.com/functions.htm http://www.gslis.utexas.edu/~palmquis/courses/project98/help/helpdsk1.htm http://www.pcai.com/web/ai_info/help_desk.html http://ezinearticles.com/?10-Advantages-Of-Installing-Help-Desk-Software&id=852602 http://articles.techrepublic.com.com/5100-10878-6091121.html

Expert System Example

A specific example of a expert system is PXDES which is a pneumoconiosis, a lung disease, X-ray diagnosis. This expert system incorporates the inference engine to examine the shadows on the X-ray. The shadows are used to determine the type and the degree of pneumoconiosis. This system also includes three other modes: the knowledge base, the explanation interface, and the knowledge acquisition modes. The knowledge base mode contains the data of X-ray representations of various stages of the disease. These elements are in the form of fuzzy production rules discussed in the previous paragraphs. The explanation interface details the conclusions, and the knowledge acquisition mode allows medical experts to add or change information in the system. Another example of a diagnosis rule-based expert system is EMERGE designed to be used in an emergency room. This system uses a form of production rules which incorporates weighing factors which are determined by a neural network. The neural network is composed of input and output blocks with a hidden layer block in between which communicates input to the output. The neural network learns from examples then predicts an output based on this knowledge. This system also uses an IF-THEN-UNLESS statement instead of an IF-THEN statement. Because of this, the decision process may be more precise, the results may be more accurate and the explanations may be better understood. A specific example from EMERGE using the IF-THEN and the IFTHEN-UNLESS indicates that the latter case is more compact and less complicated. IF-THEN IF-THEN-UNLESS IF forced volume capacity is high (.625) IF forced volume capacity is high AND Bronchoscopy results are positive (.250) AND Bronchoscopy results are positive AND local symptoms are present (.125) AND local symptoms are present

THEN surgery is probably necessary THEN Surgery is probably appropriate IF Metastasis is present (.500) UNLESS Metastasis is present OR Contraindications to surgery exist (.500) OR Constraindictions to surgery exist THEN surgery is probably not appropriate The IF-THEN-UNLESS rule allows for less rules, therefore, permitting a more rapid search. The logical operators, AND and OR, used in both these methods give their corresponding rules different weighing factors and can be seen in the parenthesis next to each statement in the IF-THEN case. The threshold value for OR is lower than that for AND. Thus, for each additional AND you have a lower weighing factor but for each OR, the weighing factor is divided evenly. It can be seen from the example above that the weighing factors must add up to one.
http://www.myacquire.com/aiinc/whalewatcher/ Fuzzy logic A specialty research area in computer science that allows shades of gray and does not require everything to be simply yes/no, or true/false

Explanation facility A part of the expert system that allows a user or decision maker to understand how the expert system arrived at certain conclusions or results Knowledge acquisition facility Provides a convenient and efficient means of capturing and storing all components of the knowledge base Knowledge acquisition is the transfer and transformation of problem-solving expertise from some knowledge source to a program. Where Are Expert Systems Used? Medical diagnosis (the knowledge base would contain medical information, the symptoms of the patient would be used as the query, and the advice would be a diagnose of the patients illness) Playing strategy games like chess against a computer (the knowledge base would contain strategies and moves, the player's moves would be used as the query, and the output would be the computer's 'expert' moves) Providing financial advice - whether to invest in a business, etc. (the knowledge base would contain data about the performance of financial markets and businesses in the past) Helping to identify items such as plants / animals / rocks / etc. (the knowledge base would contain characteristics of every item, the details of an unknown item would be used as the query, and the advice would be a likely identification) Helping to discover locations to drill for water / oil (the knowledge base would contain characteristics of likely rock formations where oil / water could be found, the details of a particular location would be used as the query, and the advice would be the likelihood of finding oil / water there) Helping to diagnose car engine problems (like medical diagnosis, but for cars!)