IJCA Special Issue on “Artificial Intelligence Techniques - Novel Approaches & Practical Applications” AIT, 2011 11 Fuzzy Logic based Cricket Player Performance Evaluator Gursharan Singh IET Bhaddal, Ropar Punjab, INDIA Nitin Bhatia DAV College, Jalandhar Punjab, INDIA Sawtantar Singh Bhai Maha Singh College of Engg. Mukatsar, Punjab, INDIA ABSTRACT Cricket is amongst the most popular sports. Performance of players directly affects their ranking internationally. We propose a fuzzy logic based technique to evaluate the performance of cricket players. Various input parameters are being considered which are scaled using linguistic variables and a very simple yet effective software tool is developed to compute the effect of input parameters on the ranking of the players. Keywords Fuzzy Logic, Mamdani, Cricket, Player, Performance Evaluator. 1. INTRODUCTION Cricket is a bat and ball game played between two teams having eleven players each. Cricket is one of the most entertaining and favorite game for many people. Because of its popularity, and the fun and glamour involved in it, more and more people from all around the world are becoming interested in this game. This game is played in big oval shaped grass field, having a rectangular strip of 22 yards, called pitch, at the center of the ground. At the both ends of the pitch, three wooden sticks, called wickets, are placed. A white line is marked near these wickets. This white line is called crease. The match is divided into innings during which one team bats and the other team fields. The batting team has only two players, called batsmen, on the ground, whereas, the fielding team has all the eleven players on the ground per innings. Different forms of cricket played at the international level are Test Match, One-Day International (ODI), and Twenty20 (T20). International Cricket Council (ICC) governs all these formats of international cricket and formulates the various rules and regulations. ICC is also responsible for the calculation of ranking of players, which depends on their performance. The ranking is calculated separately for test matches, ODIs and T20s, and also for batsman, bowler and all-rounder. But the rules for calculating the ranking are very vague and crisp, and therefore, the actual performance of player is not visible. Hence, in this research work, we will propose fuzzy based cricket player performance evaluator, that will evaluate the performance of a player using fuzzy logic. Fuzzy logic was first introduced by Zadeh in his first paper on Fuzzy Sets in 1965. Fuzzy logic solves the problems with vague, imprecise and incomplete data and provides better and accurate results. Fuzzy logic is a rule based approach used for solving problems. J. M. Mendel defines fuzzy logic system as a non- linear mapping of an input data vector into a scalar output [1]. Fuzzy logic has many applications including aircraft control, weather forecasting, marketing, economics, politics, biology etc. Numbers of fuzzy logic based commercial products are available which helps to evaluate and control complex systems. It can be applied to number of fields for developing knowledge-based systems. Fuzzy logic is a decision support system and is becoming very popular day-by-day. It is a rule based technique and fuzzy rules are very easy to learn and use. In this paper, the objective is to use the fuzzy logic tool to evaluate the performance of a cricket player. With the fuzzy logic, first of all we have to understand the system behavior by our knowledge. In second step, by using fuzzy rules, we have to design the control algorithm and at last debug the design. 2. RELATED WORK Huge amount of literature is available on fuzzy logic and its applications. Fuzzy logic can handle problems with imprecise data and give more accurate results. Professor L. A. Zadeh introduced the concept of Fuzzy logic [2]. After that, researchers used this theory for developing new algorithms and decision analysis. The use of genetic algorithms for designing and implementation of fuzzy logic controllers was discussed [3]. There are many different formulations and interpretations of the theory of rough sets [4]. The relationship and differences between theories of fuzzy sets and rough sets with respect to two formulations of fuzzy sets and two views of rough sets are examined [5]. Different aspects of fuzzy logic and fuzzy sets are discussed by [6], which are necessary to synthesize a fuzzy logic system. Concepts and techniques used in fuzzy logic from modern perspective are examined that helps to learn fuzzy rule- based models for high dimensional problems [7]. Fuzzy Inference Systems (FIS) are models based on fuzzy logic. FIS does mapping from given input to an output using fuzzy logic. FIS have number of rules based on “if-then” conditions. These rules are easy to learn and use and can be modified according to the situation. FIS helps to make decisions. A. Abraham presented the different ways to learn fuzzy inference systems using neural network learning techniques [8]. M. Z. Shafiq et al. reported a comparative study of Fuzzy Inference Systems, Neural Networks and Adaptive Neuro Fuzzy Inference Systems for Portscan Detection [9]. A synthetic multi-criterion evaluation method based on the Mamdani type FIS is developed to assess compost maturity and stability [10]. A fuzzy logic based loan risk predictor was developed to aid financial organizations in making decisions [11]. Risks associated with software development projects and their impact on software quality is discussed [12]. Fuzzy inference systems can be used in several fields like decision analysis, expert systems, computer vision, robotics and pattern recognition. FIS can also be effectively used in sports like cricket and soccer etc. Using fuzzy logic, the design and implementation of real-time game design of Pac-Man is presented [13]. A batting training system is suggested using fuzzy set theory to aid West Indies Cricket [14]. A decision algorithm using the concept of fuzzy logic is proposed in determining strategic shots in a game of pool [15].