Part of #A New Classification Approach Based on Cooperative Game# :
Publishing year : 2009
Conference : Fourteenth Annual International Conference of Computer Society of Iran
Number of pages : 6
Abstract: Classification is a well known task in data mining and machine learning which aims to predict the class of items as accurately as possible. A well-planned data classification system makes it easy to find essential data. An object is classified into one of the categories called classes according to the features that are well separated classes. Actually, the classification maps an object to its classification label. Many researches used different learning algorithms to classify data; neural networks, decision trees, etc. In this paper, a new classification approach based on a cooperative game is proposed. A cooperative game consists of a set of players and a characteristic function that specifies the value created by different players in the game. In order to find the classes in the classification process, objects can be imagine as players in a game and according to the values obtained by these players, classes will be separated. This approach can be used to classify a population according to their contributions. In other words, it applies equally to different types of data. Through this paper, a special case in medical diagnosis was studied. 304 samples taken from human leukemia tissue consists of 17 attributes that determine different CD markers related to leukemia were analyzed. These samples were collected from different types of leukemia at the Iran Blood Transfusion Organization (IBTO). Obtained results show that the cooperative game is very promising to use directly for classification.