Copyright ACM, 2000

Industrial Applications of Fuzzy Systems

(invited paper)

 

L.C.Jain

Knowledge-Based Intelligent Engineering Systems (KES) Centre

University of South Australia

Adelaide

Mawson Lakes, S.A. 5095

Australia

Tel: 618 8302 3315

L.Jain@unisa.edu.au

 

Key words: Fuzzy systems, Applications

 


ABSTRACT

I am honoured for this opportunity to speak at this ACM Symposium on Applied Computing (SAC 2000). I will present some of our research projects incorporating fuzzy systems, undertaken by my postgraduate candidates in the Knowledge-Based Intelligent Engineering Systems. Centre. Some of these projects include fuzzy fusion based landmine detection, Fuzzy Systems to Evaluate Weather and Terrain Effects on Military Operations, Minimising Tremor in a Joystick Controller using Fuzzy Logic, Knowledge-Based Real-Time Video Link, Computer Aided Tutorials with Randomised Parameters

 

1. INTRODUCTION

The Knowledge-based Intelligent Engineering Systems (KES) Centre was founded in 1991. The KES offers a postgraduate program by research in knowledge-based engineering paradigms and their applications. The KES activities are mainly focused on modelling, analysis and design in the areas of Intelligent Information Systems, Physiological Sciences Systems, Electronic commerce and Service Engineering [4-23]. The Centre aims to provide applied research support to the Information, Defence and Health Industries. The overall goal will be to Synergise contributions from researchers in the diverse disciplines such as Engineering, Information Technology, Science, Commerce and Security Engineering [26-31].

 

1.1 Key Research Area

Modelling design and implementation of Knowledge-Based Intelligent Systems.

 

Artificial Neural Networks in efficient signal processing and real time medical diagnosis.


Fuzzy systems in automation, Monte Carlo methods in medical and health physics and

hybrid systems.

Genetic algorithms and chaos theory in system design.

Secure System Engineering.

Service Engineering, E-commerce, Information appliances and servers.

 

1.2 Objectives

Develop and offer knowledge-based cost-effective electronic system design and diagnostic techniques to industry.

Develop excellence in teaching, attract postgraduate students and provide research support to local industries.

Enhance electronic system design methodology by applying novel techniques such as knowledge- based techniques in system design, intelligent signal processing and real time pattern recognition.

Develop new techniques for E-commerce and Secure systems.

Section 2 provides a brief summary of some of the research projects undertaken by our postgraduate students. The final section of this paper presents a summary.

 

2 RESEARCH PROJECTS

We are involved in researching techniques for the design and implementation of knowledge-based intelligent information systems. Following is a brief summary of some of the research projects on the industrial applications of fuzzy systems, undertaken by our postgraduate research students.

 

2.1 Fuzzy Fusion in Landmine Detection [3]

A fuzzy rule based fusion is used to develop a system for the detection of surface land-mines from a distant platform. Two classifier inputs to the fusion process are the real time output from ART2 and multi-layer perceptron and the third input is the infrared polarisation image. We have demonstrated that the fusion of the outputs derived from three sensors has been able to drastically reduce the false alarm rate obtained in both the multispectral and polarisation resolved images.

 

2.2 Fuzzy Systems to Evaluate Weather and Terrain Effects on Military Operations

 

Weather affects military operations capabilities for both friend or foe in the areas of mobility, observations, helicopter landing zones, etc. The military aspects of weather are visibility, wind, precipitation, cloud cover, temperature and humidity. The weather on varying geography may for example, effect military operations for determining mobility corridors in a course of action by different transportations being used. For example, low lying terrain may become exceptionally boggy and unsuitable for wheeled vehicles, or rivers may widen and become impassable. Currently weather facility overlays are produced to determine the weather effects on military operations.

 

The research work will model the differing weather effects at different types of terrain to create mobility corridors for different modes of military transportations. The mobility corridors will be calculated from the present observation position towards a likely destination indicated as a likelihood. A fuzzy rule based model will combine for example two GIS maps such as weather and geography to create a third GIS map indicating mobility corridors effects of foot or vehicles to a possible destination.

 

Another example is part of the terrain data base for the area of operation could have attributes defining characteristics such as what type of surface it is and its trafficability characteristic for vehicles at varying degrees of rainfall. By fusing the expected rainfall (or fog, wind, temperature, & humidity) with soil data type in the area of interest the computer using a rule based expert system could produce a display (or GIS map) of the going rate of a foot soldier or 4W drive. Similarly the effects on the ranges that weapons and other military equipment can be used will be effected by the weather conditions.

 

Currently Map Basic is used to manipulate each value on a GIS map. The initial demonstration will be using Map Basic running on a PC to demonstrate the rule based expert system. Weather data will be simulated and used together with existing raster maps. The geography GIS database on elevation, rivers, roads, soil types can either be real or simulated. The output of the expert system will automatically combine several GIS geographical data (i.e., elevation, vegetation, soil types etc.) with weather data (i.e., wind, rainfall, fog etc.) to produce value added GIS maps in the area of interest indicating movement, speed corridors for foot or vehicles or even weapon and equipment suitability for the terrain & weather conditions.

 

2.3 Minimising Tremor in a Joystick Controller using Fuzzy Logic [32]

 

We have designed and built a fuzzy logic controller, which minimises the effect of Multiple Sclerosis (MS) hand tremors. The main aim of this research has been to give people with MS better control of an electric wheelchair by removing tremors


from the joystick signal. We have demonstrated that our fuzzy logic controller is particularly useful for people with severe MS tremors.

 

2.4 Knowledge-Based Real-Time Video Link [1-2]

 

The real-time multi-user wireless video link is being developed with the aim of enhancing the capabilities of soldiers by improving their ability to detect, acquire, locate and engage targets by day or night and in all visibility conditions [a][b]. The primary objective of this work, undertaken as part of the 125 Soldier Combat System Project, is to improve a soldier's capability by removing the needs for cables between a thermal weapon sight mounted on a weapon and a visual display mounted on a soldier's helmet. We are in the process of developing a prototype system for multiple mobile users. It is envisaged that knowledge-based techniques including neural networks and fuzzy logic may be applicable in video compression in interference suppression. The parallelism of the neural networks can be exploited to provide real-time compressed video with varying data rates dependent on the quality of the communication channel available.

 

2.5 Computer Aided Tutorials with Randomised Parameters [25][26]

 

We are in the process of developing a teaching and learning tool for a typical first year subject, Electricity and Electronics, common for all undergraduate students in our school [c]. This tool incorporates a library of questions grouped according to the relevant topics with the objective to intensively train students in fundamentals of electricity and electronic engineering including circuit analysis. The advantage of this package over the other packages is the randomisation of numerical and string values that appear both in the question statements and the answers offered to students as a part of multiple-choice or like questions. We wish to extend our efforts for other subjects including knowledge-based engineering which includes expert systems, fuzzy systems, neural networks and evolutionary computing techniques.

 

3 SUMMARY

A number of systems are developed using fuzzy logic. It is useful to fuse various knowledge-based intelligent paradigms to offset the demerits of one paradigm by the demerits of another. . Some of these techniques are: neural networks for designing fuzzy systems, fuzzy systems for designing neural networks, evolutionary computing for the design of fuzzy systems and evolutionary computing in automatically training and generating neural network architecture.

 

4 ACKNOWLEDGEMENTS

 

Contribution by my postgraduate candidates and colleagues is acknowledged.


5 REFERENCES

 

[1] Daniels, W.M., Jain, L.C., Mahajan, A., Forbes, S. and Puri, V., Multi-User Wireless Link for Real-time Video Transfer, Proceedings of the Third International Conference on Knowledge-Based Intelligent Information Engineering Systems, IEEE Press, USA, (1999), pp. 1-4.

 

[2] Daniels, W.M., Forbes, S., Jain, L.C., Mahajan, A.,. and Puri, V., The Defence Application of a Real-time Multi-User Wireless Video, Proceedings of the Land Weapons Systems Conference, Defence Science and Technology Organisation, South Australia, November (1999).

 

[3] Filippidis, A., Jain, L.C., and Martin, N.M., Using Genetic Algorithms and Neural Networks for Surface Land Mine Detection, IEEE Transactions on Signal Processing, Vol. 47, No. 1, (1999), pp. 176-186.

 

[4] Jain, L.C. (Editor), Proceedings of the Third International Conference on Knowledge-Based Intelligent Information Engineering Systems, IEEE Press, USA (1999).

 

[5] Jain, L.C. and Jain, R.K. (Editors), Proceedings of the Second International Conference on Knowledge-Based Intelligent Engineering Systems, Volume 2, IEEE Press, USA (1998).

 

[6] Jain, L.C. and Jain, R.K. (Editors), Proceedings of the Second International Conference on Knowledge-Based Intelligent Engineering Systems, Volume 1, IEEE Press, USA (1998).

 

[7] Jain, L.C. (Editor), Proceedings of the First International Conference on Knowledge-Based Intelligent Engineering Systems, Volume 2, IEEE Press, USA (1997).

 

[7] Jain, L.C. (Editor), Proceedings of the First International Conference on Knowledge-Based Intelligent Engineering Systems, Volume 1, IEEE Press, USA (1997).

 

[8] Jain, L.C. (Editor), Electronic Technology Directions Towards 2000, ETD2000, IEEE Computer Society Press, USA (1995).

 

[9] Jain, L.C. and de Silva, C.W. (Editors), Intelligent Adaptive Control: Industrial Applications, CRC Press, USA (1998).

 

[10] Jain, L.C., Johnson, R. P., Takefuji, Y. and Zadeh, L.A. (Editors), Computational Intelligence Techniques in Industry, CRC Press, USA (1998).

 

[11] Jain, L.C. and Vemuri, R. (Editors), Industrial Applications of Neural Networks, CRC Press, USA (1998).

 

[12] Jain, L.C. (Editor), Innovative Teaching and Learning: Knowledge-Based Paradigms, Springer-Verlag, Germany(2000).

 

[13] Jain, L.C (Editor), Evolution of Engineering and Information Systems and their Applications, CRC Press, USA (2000).


[14] Jain, L.C. and Lazzerini, B. (Editors), Knowledge-Based Intelligent Techniques in Character Recognition, CRC Press, USA (1999).

 

[15] Jain, L.C. and Martin, N.M. (Editors), Fusion of Neural Networks, Fuzzy Systems and Evolutionary Computing Techniques: Industrial Applications, CRC Press , USA (1999).

 

[16] Jain, L. C., Halici, U.,Hayashi, I.,Lee, S.B. and Tsutsui, S.. (Editor), Intelligent Biometric techniques in Fingerprint and Face Recognition, CRC Press, USA (1999).

 

[17] Jain, L.C. (Editor), Soft Computing Techniques in Knowledge-Based Intelligent Engineering Systems, Springer-Verlag, Germany (1997).

 

[18] Jain, L.C. and Jain, R.K. (Editors), Hybrid Intelligent Engineering Systems, World Scientific Publishing Company, Singapore (1997).

 

[19] Karr, C.L. and Freeman, L.M. (Editors), Industrial Applications of Genetic Algorithms, CRC Press, USA (1998).

 

[20] Karr, C.L. (Editor), Practical Applications of Computational Intelligence for Adaptive Control, CRC Press, USA (1999).

 

[21] Medsker, L. and Jain, L. C. (Editors), Recurrent Neural Networks: Design and Applications, CRC Press, USA (2000).

 

[22] Narasimhan, V.L., and Jain, L.C. (Editors), The Proceedings of the Australian and New Zealand Conference on Intelligent Information Systems, IEEE Press, USA (1996).

 

[23] Nedic, Z., Raza, S.R., Jain, L.C., and Machotka, J, Computer Aided Tutorials with Randomised Parameters, Third UICEE Conference on Engineering Education, Tasmania (2000).

 

[24] Nedic, Z., Machotka, J, and Jain, L.C., Multimedia Package for Interactive Design of Laboratory Experiments, Proceedings of the Third International Conference on Knowledge-Based Intelligent Information Engineering Systems, IEEE Press, USA, 1999, pp. 17-20.

 

[25] Sato, M., Sato, Y. and Jain, L.C., Fuzzy Clustering Models and Applications, Springer-Verlag, Germany (1997).

 

[26] Teodorescu, H.N., Kandel, A. and Jain, L.C. (Editors), Fuzzy and Neuro-Fuzzy Systems in Medicine, CRC Press , USA (1999).

 

[27] Teodorescu, H.N., Kandel, A. and Jain, L.C. (Editors), Soft Computing in Human-related Sciences, CRC Press , USA (1999).

 

[28] Teodorescu, H.N and Jain, L.C. (Editors), Intelligent systems and Techniques in Rehabilitation Engineering , CRC Press , USA (2000).


[29] Vonk, E., Jain, L.C., and Johnson, R.P., Automatic Generation of Neural Networks Architecture Using Evolutionary Computing, World Scientific Publishing Company, Singapore (1997).

 

[30] Van Rooij, A., Jain, L.C., and Johnson, R.P., Neural Network Training Using Genetic Algorithms, World Scientific, Singapore (1996).

 

[31] Van Der Zwaag, B.J., Corbett, D., and Jain, L.C., Minimizing Tremor in a Joystick Using Fuzzy Logic, Proceedings of the Third International Conference on Knowledge-Based Intelligent Information Engineering Systems, IEEE Press, USA, (1999), pp. 5-8.

 

 

 

Biography

 

L.C. Jain is a Director/Founder of the Knowledge-Based Intelligent Engineering Systems (KES) Centre, located in the University of South Australia. He is a fellow of the Institution

of Engineers Australia. He has initiated a postgraduate stream


by research in the Knowledge-based Intelligent Engineering Systems area. He has presented a number of Keynote addresses in International Conferences on Knowledge-Based Systems, Neural Networks, Fuzzy Systems and Hybrid Systems.

 

He is the Founding Editor-in-Chief of the International Journal of Knowledge-Based Intelligent Engineering Systems and served as an Associate Editor of the IEEE Transactions on Industrial Electronics. Dr. Jain was the Technical chair of the ETD2000 International Conference in 1995, Publications Chair of the Australian and New Zealand Conference on Intelligent Information Systems in 1996 and the Conference Chair of the International Conference on Knowledge-based Intelligent Electronic Systems in 1997, 1998 and 1999. He served as the Vice President of the Electronics Association of South Australia in 1997. He is the Editor-in-Chief of the International Book Series on Computational Intelligence, CRC Press USA. His interests focus on the applications of novel techniques such as knowledge-based systems, artificial neural networks, fuzzy systems and genetic algorithms and the application of these techniques

 

Copyright 2000 ACM

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and or fee.
SAC 2000 March 19-21 Como, Italy
(c) 2000 ACM 1-58113-239-5/00/003>...>$5.00