Monika
Monika
Monika
I. Introduction
Real-time expert systems [1] are on-line knowledge-based
systems that combine analytical process models with
conventional process control while reasoning about the past,
present, and future to assess on-going developments and plan
appropriate actions.
Indicators that a real-time expert system might be appropriate,
especially when conventional techniques have failed or are
impractical, include problem-solving situations where humans
suffer from cognitive overload, fail to effectively monitor
all available information, are unable to resolve conflicting
constraints, are expensive.
Many "real-time" expert systems are 'soft' real-time systems, in
that they claim to be fast. A 'hard' real-time system would have
features that guarantee a response within a fixed amount of
real-time (e.g., bounded computation, not just a fast match-
recognize-act cycle). Fig. 2: Life cycle of real time expert system
Systems like G2 use event-driven processing as a method of
limiting forward chaining. A. Task analysis and specification
As expert system development is very large project and so work
II. Real time expert system architecture [2] begins by establishing the requirements for all system elements
Here we have passive elements like data files and knowledge and then allocating some subset of these requirements to
base which are denoted by square boxes and active elements software. This system view is essential when the system must
are data, knowledge manager, processes which are denoted interface with other elements such as hardware, people and
by dashed ovals. Data exchange between active and passive other resources. System is the basic and very critical requirement
elements is shown by arrows and communication between for the existence of software in any entity. So if the system is
active elements is shown by dashed arrows. We have divided not in place, the system should be engineered and put in place.
this architecture into two subsystems: intelligent subsystem Once the ideal system is engineered, the development team
and real time subsystem. The interface divides and connects studies the software requirement for the system.
the two subsystems. This process is also known as feasibility study. In this phase, the
development team visits the customer and studies their system.
They investigate the need for possible software automation
in the given system. By the end of the feasibility study, the
team furnishes a document that holds the different specific
recommendations for the candidate system. It also includes
the personnel assignments, costs, project schedule, target
dates etc. The requirement gathering process is intensified
and focused specially on system. To understand the nature of
the program to be built, the system engineer or "Analyst" must
understand the information domain for the software, as well
as required function, behavior, performance and interfacing.
The essential purpose of this phase is to find the need and to
Fig.1: Real time expert system architecture define the problem that needs to be solved.
B. Software Design
In this phase, the expert system development process, the
150 International Journal of Computer Science and Technology w w w. i j c s t. c o m
ISSN : 2229-4333(Print) | ISSN : 0976-8491(Online) IJCST Vol. 1, Issue 2, December 2010
system's overall structure and its nuances are defined. In terms should be handled with care:
of the client/server technology, the number of tiers needed 1. Normal operation with various extreme loads
for the package architecture, the database design, the data 2. Abnormal and faulty operation modes like missing data,
structure design etc. are all defined in this phase. An expert missing elements, faulty elements, resources not available
system development model is thus created. Analysis and etc.
Design are very crucial. Any problem in the design phase could 3. Conflict in data and knowledge elements.
be very expensive to solve in the later stage of the software
development. Much care is taken during this phase. The logical IV. Real-Time Expert System- Applications
system of the product is developed in this phase. Real time expert systems [4] are being used in almost all fields
like medical, aerospace, communications, process control,
C. Code Generation robotics etc. Following are few expert systems used in medical
The design must be translated into a machine-readable form. field:
The code generation step performs this task. If the design
is performed in a detailed manner, code generation can be 1. CAPS: CAPS is a system that combines a pattern-
accomplished without much complication. Programming recognition module with a system module to perform respiratory
tools like compilers, interpreters, debuggers etc. are used to and anesthesia monitoring. The pattern-recognition module
generate the code. Different high level programming languages characterizes and analyzes each segment of a capnogram.
like C, C++, Pascal, and Java are used for coding. With respect (A capnogram is a carbon dioxide wave form produced by
to the type of application, the right programming language is monitoring patient respired gases during surgery.) The analysis
chosen. of the capnogram is then used by the expert system module
to generate a probable diagnosis and recommend therapy or
D.Testing equipment adjustments. The system was implemented using
Once the code is generated, the system testing begins. Different the EXSYS tool on an IBM PC/AT.
testing methodologies are available to unravel the bugs that
were committed during the previous phases. Different testing 2. FORTES: Forth Oriented Real-Time Polysomnographer
tools and methodologies are already available. Some companies Expert System. FORTES was developed at the Stanford University
build their own testing tools that are tailor made for their own of Medicine to perform real-time sleep staging. Sleep staging
development operations. is a means of classifying a person's state while asleep. It is
usually performed by a trained human scorer who evaluates
E. Documentation and Implementation a linear time varying graph of the electroencephalograms,
The development and maintenance is a staged roll out of the electrocardiogram, and eletromyographic activity while a
new application, this involves installation and initial training and person is sleeping. FORTES is implemented on an IBM PC and
may involve hardware and network upgrades. Expert System will is interfaced to a polygraph with a standard digital to analog
definitely undergo change once it is delivered to the customer. converter. The Ventilator Manager VM was one of the first and
Change could be happen because of some unexpected input most significant applications of knowledge-based systems to a
values into the system. In addition, the changes in the system real-time domain. VM interprets online physiological data in an
could be directly affecting the software operations. The intensive care unit. An automatic monitoring system provides
software should be developed to accommodate changes that VM with the values of 30 physiological measurements at 2 or
could happen during the post implementation period. 10 minute intervals. The data are used to manage postsurgical
Some special steps which help in the development of real time patients receiving mechanical ventilatory assistance. VM
expert system are: maintains a set of patient-specific expectations and goals
for future evaluation. It is expectation driven and uses the
1. Design prototype current and past patient history to establish guidelines for
2. Special test tools patient measurements. The guidelines are used to dynamically
3. Test plan establish upper and lower limits for comparison with each new
measurement from the monitoring system. VM responds with
1. Design prototype suggestions to clinicians and periodic summaries. VM uses
Its function is to test and demonstrate the operation of a partial forward chaining, checks that information previously acquired
solution, knowledge representation and reasoning technique. is still valid for making conclusions, and cycles through the rule
Only a part of the knowledge base and only a few functions set each time new information is available.
are implemented so this is a downsized partial version of the
final system. 3. STOCHASM : STOCHASM is a computer program for
performing real time fault detection and diagnosis for the
2. Special testing tools lubrication oil subsystem in a gas turbine propulsion unit on a
Expert system shells offer special testing tools to test the United States Navy surface ship. The system utilizes knowledge
stand alone functions of intelligent subsystem. These tools of the order in which alarms are triggered to diagnose the
test the interface and operation of a real time expert system cause of malfunctions. Malkoff (1986) reports the system
under different time varying real time conditions. These tools had learning capabilities that allowed it to automatically adapt
are needed as it is very difficult to test ant real time system to changes in the system and the environment. STOCHASM
properly. was interfaced to a simulator and works in real time. Several
different approaches for performing temporal reasoning.
3. Testing plan
Since it is very difficult to test the real time system properly so 4. G2 Real Time Expert System is used to monitor complex
to prepare a test plan in advance is must. Following situations industrial processes and to assist in problem identification.
w w w. i j c s t. c o m International Journal of Computer Science and Technology 151
IJCST Vol. 1, Issue 2, December 2010 ISSN : 2229-4333(Print) | ISSN : 0976-8491(Online)
from Zorica Nedic, Vladimir Nedic and Jan Machotka (2002) in Information Technology from Guru Nanak Dev University
Campus, Amritsar. He has also done Masters in Business
10. The Environmental Control Expert System in Space Administration as dual specialization in Marketing & Human
(ECESIS). ECESIS was designed for use on a manned Resource Management. Now he is pursuing Ph.D. in Computer
space station to shift modes for various subsystems of an Sciences. His area of interest is Computer Networks, Parallel
environmental control-life support subsystem (EC-LSS) as the Computation & Distributed Computing. He is the life member
station passes from shadow to sun. ECESIS monitors the EC- of Indian Society For Technical Education (I.S.T.E.) and has
LSS and performs various actions in response to detected published & presented papers 05 in International Journals,
events. The system is implemented in Yet Another Production 07 in International Conferences as well as 18 in National
System (YAPS) and incorporates both rule based and semantic conferences. He is also serving on the Editorial Board of
net architectures (Dickey and Toussaint 1984). International Journal of Computer Science & Technology (IJCST)
and International Journal on Electronics and Communication
11. COOKER is a real-time process monitoring and Technology (IJECT). He has also written & published 07 highly
operator advisory system for batch manufacturing processes. acclaimed books. He has attended 10 weeks Short Term/FDP/
It runs on a Symbolics 3640 Lisp machine connected by an IBM Workshop programs at various Institutes. He has Teaching &
AT microcomputer to a Honeywell TDC 2000 process control Industry Experience of more than 8.
system and a programmable logic controller. COOKER has four
main subsystems:
data frames, data gatherer, operator interface, and inference
engine. The latter three subsystems run as concurrent Er. Monika Verma is currently working as an
processes. The data gatherer sends data requests to, and Assistant Professor in Computer Science
buffers data from, the IBM AT. The operator interface manages and Engineering Department at Swami
all windows, displaying advice and questions to the operator, Vivekanand Institute of Engineering &
and receives replies. The inference engine handles un buffering Technology, Banur. She holds the degree
data from the data gatherer into data frames, receives of M.Tech in Computer Scienece-Hons. and
replies from the operator, runs the monitoring and problem- B.Tech in Computer Science & Engineering.
recognition mechanism on the goals, and runs any problem She was the Topper during M.Tech in her
solving required by the goals. The system uses a knowledge University. She has around 6 years of
representation scheme called Goal/Subgoal (GSG). Allard and teaching experience. Her research interests include Digital
Kaemmerer (1987) report that COOKER has been installed in Image Processing. She has authored and co-authored many
a manufacturing plant. papers in International Journals, International Conferences
and National Conferences and has attended many short term
V. Conclusion courses. She is Life Time Member of ISTE. She is also serving
This paper focuses on architecture of real time expert system. on the Editorial Board of International Journal of Managing
And its life cycle is almost similar to that of a software Information Technology (IJMIT) , Signal and Image Processing:
development life cycle (SDLC) which includes various phases An International Journal (SIPIJ), The International Journal on
like analysis, designing, coding, testing, implementation and Computer Science and Technology (IJCST) and International
maintenance. Then various applications in real world have been Journal on Electronics and Communication Technology
discussed and we came to know various fields where real time (IJECT).
expert systems are being used.
References
[1] Ali, M., and Scharnhorst, D. A. 1985. Sensor-Based Fault
Diagnosis in a Flight Expert System.
[2] In Proceedings of the Second Conference on Artificial
Intelligence Applications, 49-52. Washington D.C. IEEE
Computer Society.
[3] Park, J. 1986. Toward the Development of a Real-
Time Expert System. Journal of Forth Applications and
Research.
[4] Schwartz, T. J. 1987. Real Time Processing on the PC.
Spang Robinson Report.
[5] Shaw, R. 1987. RESCU—On-Line Real-Time Artificial
Intelligence. Computer-Aided Engineering Journal