Sunteți pe pagina 1din 6

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN INTERNATIONAL JOURNAL OF ADVANCED RESEARCH IN 0976 6480(Print),

, ISSN 0976 6499(Online) Volume 4, Issue 3, April (2013), IAEME ENGINEERING AND TECHNOLOGY (IJARET) ISSN 0976 - 6480 (Print) ISSN 0976 - 6499 (Online) Volume 4, Issue 3, April 2013, pp. 280-285 IAEME: www.iaeme.com/ijaret.asp Journal Impact Factor (2013): 5.8376 (Calculated by GISI) www.jifactor.com

IJARET
IAEME

FUZZY LOGIC THE FASCINATING LOGIC BEHIND ARTIFICIAL COMPUTATIONAL INTELLIGENCE


Mohammed Sirajuddin1, Dr D. Rajya Lakshmi2, Dr Syed Abdul Sattar3 and Nafisur Rahman4
1

Royal Institute of Technology and Science, Chevella, Hyderabad, India. 2 Gitam Institute of Technology, Gitam University, Vizag, India. 3 Royal Institute of Technology and Science, Chevella, Hyderabad, India. 4 Royal Institute of Technology and Science, Chevella, Hyderabad, India.

ABSTRACT In order to impart artificial intelligence to various systems, fuzzy logic is a very convenient way to express expert and common sense knowledge. Fuzzy logic can be understood as a system of formal (symbolic) deductive systems with a comparative notion of truth, formalizing deduction under vagueness. The basic systems use the real unit interval [0, 1] as the standard set of truth degrees. Apart from its technical aspect, the subject is also of immense historical and philosophical significance. Today, it is widely applied in a variety of fields ranging from embedded control to industrial automation. Key words: Artificial intelligence, fuzzy logic, crisp logic, fuzzy set, member function, fuzzification, defuzzification, etc. INTRODUCTION Artificial intelligence, frequently written as AI, is one of the most fascinating technologies of the present era and is bound to dominate the technological advancements of future. It is the branch of computer science concerned with making computers behave like humans. The term was coined in 1956 by John McCarthy at the Massachusetts Institute of Technology. Fuzzy logic is a huge step forward towards making artificial computational intelligence closer to practical realities and real-life phenomena. It is a specialty research area in computer science that allows shades of grey and does not require everything to be black/white, yes/no, or true/false.
280

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 3, April (2013), IAEME

WHAT IS FUZZY LOGIC? Simply put the term fuzzy means not clear, precise or distinct; blurred. Fuzzy logic is a form of multi-valued logic derived from fuzzy set theory to deal with reasoning that is approximate rather than precise. In contrast with "crisp logic", where binary sets have binary logic, fuzzy logic variables may have a truth value that ranges between 0 and 1 and is not constrained to the two truth values of classic propositional logic. Fuzzy logic enables a computer to make decisions which care more in line with the sort of decisions which a human would make. Classical computer logic is rigorous and deterministic and relates to finite states and numbering systems. Computer logic marks distinct boundaries between any states. For instance, given various weather conditions to process such as, stormy, rainy, cloudy, sunny, ordinary logic would assign one of these values to any weather condition being observed. People however would recognize all sorts of shades in between these states such as dull or drizzle etc. This is exactly what fuzzy logic can do. What is more impressive is that fuzzy logic offers a way of processing these decisions so that a final result is still correct. In fact, it is a form of knowledge representation suitable for notions that cannot be defined precisely, but which depend upon their contexts. Fuzzy logic addresses key problem in expert systems viz. how to represent domain knowledge, how to account for imprecisely calibrated terms used by humans, and how to build decision trees on imprecise thresholds. Despite it being controversial among some statisticians and control engineers, fuzzy logic has been applied to many fields, from control theory to artificial intelligence with great fervor and has registered huge success. HISTORY/TIMELINE The history of Fuzzy Logic can be traced back to Buddha around 500 BC. His philosophy was based on the thought that the world is filled with contradictions, that almost everything contains some of its opposite, or in other words, that things can be A and not-A at the same time. Here we can see a clear connection between Buddha's philosophy and modern fuzzy logic. About 200 years later, the Greek scholar Aristotle developed binary logic. In contrary to Buddha, Aristotle thought that the world was made up of opposites, for example male versus female, hot versus cold, dry versus wet, active versus passive. Everything has to be A or not-A, it can't be both. Over the centuries, these two philosophies developed and spread independently and the debate continued as to which one was better. In 1964, professor Lotfi Asker Zadeh, faculty in Electrical Engineering, U.C. Berkeley, started wondering, if there wasn't a better logic to use in machinery. He had the idea that if you could tell an air-conditioner to work a little faster when it gets hotter, or similar problems, it would be much more efficient than having to give a rule for each temperature. His seminal paper Fuzzy Logic sets the Foundation of the Fuzzy Set Theory in 1965 and that was the day fuzzy logic, the way we know it today, was born. It took a long time until fuzzy logic got accepted even though it fascinated some people right from the beginning. Besides engineers, philosophers, psychologists, and sociologists soon became interested in applying fuzzy logic into their sciences.
281

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 3, April (2013), IAEME

In the year 1987, the first subway system was built which worked with a fuzzy logicbased automatic train operation control system in Japan. It was a big success and resulted in a fuzzy boom. Universities as well as industries got interested in developing the new ideas. Today, almost every intelligent machine has fuzzy logic technology inside it. But fuzzy logic doesn't only help boast machine IQs. If we could give up the idea of everything having to be good or bad, we could also see the good things in other people. We wouldn't have to reduce all our fellow people to gods or devils. NEED Consider the way humans use to speak in normal day to day life. The Statement Today is sunny can be 100% true if there are no clouds 80% true if there are a few clouds 50% true if it's hazy and 0% true if it rains all day

Some other examples are: We Will Probably Have a Successful Business Year. Both of them have more or less same level of understanding. ... a person suffering from hepatitis shows in 60% of all cases a strong fever, in 45% of all cases yellowish colored skin, and in 30% of all cases suffers from nausea ... "If it is sunny and warm today, I will drive fast" Thus we see that most words and evaluations we use in our daily reasoning are not clearly defined in a mathematical manner. This allows humans to reason on an abstract level. So, to make the machines behave like humans, a similar reasoning mechanism is required. In fact, stochastics and fuzzy logic complement each other and hence prove to be of immense importance in AI. FUNDAMENTALS OF FUZZY LOGIC Fuzzy Sets: Fuzzy sets do not have distinct boundaries in the same way as normal sets. Membership of a normal set is either TRUE or FALSE. Each element of a fuzzy set has a value associated with it indicating the degree of membership. Degree of membership for any element of a fuzzy set is considered as a value which lies between '0' for not a number, to '1' which represents complete or full membership. Every element of a fuzzy set will therefore have a number between 0...1 associated with it. The following fuzzy set provides an example. A = {M1/ e1, M2/ e2, M3/ e3, M4/ e4 } Where e1, e2, e3, e4 are fuzzy elements of the set A. M1, M2, M3, M4 are membership values associated with each element.

282

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 3, April (2013), IAEME

For instance, consider the two sets called 'BLACK' and 'WHITE'. Each set contains many elements which may be either by pure black or perfect white and many of the shades of grey in between. So the elements of the set, labeled 'g' for grey in this case, may be: g1, g2, g3, g4, g5, g6, g7 Membership of the set White (W) may look like this: W = {1/g1, 0.96/g2, 0.8/g3, 0.5/g4, 0.2/g5, 0.04/g6, 0/g7} Membership of the set Black (B) may look like this: B = {0/g1, 0.04/g2, 0.2/g3, 0.5/g4, 0.8/g5, 0.04/g5, 0.96/g6, 1/g7} From this description, it can be seen that 'g1' is pure white and 'g7' is pure black. Membership function: Membership function is a curve of the degree of truth of a given input value. Fuzzification: During the fuzzification step the crisp value is input and translated into fuzzy truth values. For example, 78 F a crisp temperature value can be fuzzified into warm with truth value 0.6 (or 60%) and hot with truth value 0.2 (or 20%). Fuzzy inference/Rule evaluation: The if-then-else rules of the Fuzzy Logic Systems are the laws it executes. Aggregation computes how appropriate each rule is for the current situation. Composition computes how each rule influences the output variables. Defuzzification: Defuzzification is, in effect, balancing out the results. During the Defuzzification step, the fuzzy labels are combined using a calculation method in order to produce the crisp output value. FUZZY LOGIC VERSUS PROBABILITY Probability theory measures how likely the proposition is to be correct. While Fuzzy logic measures the degree of correctness to which the proposition is correct. In order to distinguish fuzzy logic from probability, let us consider the example of a glass partially filled with water i.e. neither completely empty nor completely filled. The important distinction between probabilistic information and fuzzy logic is that there is no uncertainty about the fullness of the glass but rather about the degree to which it matches the category full'. If 0.70 represented a probability value, we would read it as there is a 70% chance that the glass is full, and we have a 70% chance of knowing which group it belongs to. If the glass's degree of membership in the set of full glasses is 0.70, we mean that if we take the fuzzy set of full glasses and line them up, this glass is positioned 70% of the way to the fullest.

283

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 3, April (2013), IAEME

APPLICATIONS OF FUZZY LOGIC General applications: Automotive: Cruise control, automatic transmissions, temperature controller, anti lock brake systems, etc. Home: Rice cooker, washing machines, etc. Building: Elevators, air conditioners, etc.

According to the applications study of IEEE, about 1100 successful fuzzy logic applications have been published (an estimated 5% of those in existence). Applications Range from Embedded Control (28%), Industrial Automation (62%) to Process Control (10%) ADVANTAGES Real systems have measurement uncertainty. So, near the border lines, many misclassifications are bound to creep in if we opt for classical binary logic. Consider the classical set of tall people, say, taller than or equal to 1.8 meter. 1.8m, 2m, 3m etc are the members of this set. But 1.0 m, 1.5m or even 1.79999m is not a member of the set. This is what we call misclassification. No such problem arises if we opt for fuzzy logic and employ the concept of fuzzy sets and membership functions. This is indeed a huge advantage over the classical logic. It easily and, of course, efficiently handles the concept of partial truth. It is tolerant of imprecise data. It is intuitive. It deals with the real world vagueness. It is based on linguistic terms. It reduces the complexity of the design process. It is a very convenient way to express expert and common sense knowledge Another significant advantage of fuzzy logic is that it has slashed design time by more than half. LIMITATIONS Fuzzy logic is highly abstract and heuristic It cannot be used for unsolvable problems. This seems fairly reasonable, but its perception of being a guessing game may lead people to believe that it can be used for anything. How to determine the membership functions? Usually requires fine-tuning of parameters Defuzzification can produce undesired results Fuzzy logic can be easily confused with probability theory, and the terms used interchangeably. But, if we analyze, we can easily conclude that most of the limitations of fuzzy logic are perceived rather than real.
284

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 3, April (2013), IAEME

CONCLUSION One can circumvent the need for rigorous mathematical modeling with the use of fuzzy logic. Unlike the reasoning based on classical logic, fuzzy reasoning aims at the modeling of reasoning schemes based on uncertain or imprecise information. The past several years have witnessed a rapid growth in the number and variety of applications of fuzzy logic. The most visible applications are in the realms of consumer products, intelligent control and industrial systems. Less visible, but of growing importance, are applications relating to data processing, fault diagnosis, man-machine interfaces, quality control and decision support systems. Although fuzzy logic has been and still is controversial to some extent, its successes are now too obvious to be denied. REFERENCES [1] L.A. Zadeh, Fuzzy Sets, Information and Control, 1965 [2] H.Zimmermann, Fuzzy set theory and its applications, 2001 [3] Timothy J. Ross, Fuzzy Logic with Engineering Applications, Third Edition [4] Thornber, K.K, A new look at fuzzy-logic inference, Fuzzy Systems, 1992 [5]http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/sbaa/report.html [6]http://domino.research.ibm.com/comm/research_people.nsf/pages/zhanglj8.pubs.html [7]http://www.ortech-engr.com/fuzzy/reservoir.html [8]http://www.wolfram.com/products/applications/fuzzylogic/ [9]http://www.cs.cmu.edu/Groups/AI/html/faqs/ai/fuzzy/part1/faq.html [10] Rajiv Ranjan and Dr. Pankaj Rai, Fuzzy Logic Based MRAC for a Second Order System, International Journal of Electrical Engineering & Technology (IJEET), Volume 4, Issue 2, 2013, pp. 13 - 24, ISSN Print : 0976-6545, ISSN Online: 0976-6553. [11] Shyamsundar D. Hivarale, Prof. Dr. Dilip R. Pangavhane and Nitin H. Ambhore, Application of Knowledge Engineering and Computational Intelligence for Structural Topology Optimization of Forging Connecting Rod Die, International Journal of Mechanical Engineering & Technology (IJMET), Volume 4, Issue 2, 2013, pp. 10 - 20, ISSN Print: 0976 6340, ISSN Online: 0976 6359.

285

S-ar putea să vă placă și