Research And Application Of Intuitionistic Fuzzy Support Vector Machine

Support vector machine has strong generalization ability and good classification effect.Different from the traditional model of support vector machine,the least square support vector machine only needs to solve a linear equation set to get the closed solution,and the training speed is fast,so it is widely used in classification problems.However,the model of least squares support vector machine is easily affected by outliers and noise,which often makes its classification accuracy decrease.At the same time,these existing classification models deal with problems based on the assumption of class balance,when dealing with the classification problem of imbalanced data,they often have poor classification effect on a minority classes.Therefore,this paper will explore how to reduce the influence of outliers and noise on the model and how to deal with the classification problem of class imbalance.Fuzzy weighting of sample points is an effective method to solve outlier and noise problems.Intuitionistic fuzzy sets contain both membership information and non-membership information of sample points,which can describe the distribution characteristics of sample points in more detail.Therefore,based on the intuitionistic fuzzy set,this paper obtained a more accurate class center by eliminating outliers,and then calculated the distance between the sample point and the class center to obtain the membership degree of the sample point to its class.At the same time,the kernel k-nearest neighbor method is used to find the number of k neighboring sample points of another class,and then the non-membership information of sample points is obtained.Finally,a new fuzzy value is obtained according to the membership degree and non-membership degree of sample points.Then,the proposed fuzzy value are used to improve the model of least square support vector machine.By giving outliers and noise low fuzzy values,their influence on the model is reduced.At the same time,the accuracy of the model is improved.Experimental results show that,the proposed algorithm can effectively reduce the influence of outliers and noise on the model,and improve the robustness of the model.The combination of cost sensitive learning and fuzzy support vector machine can solve the class imbalance problem effectively.According to this idea,based on the intuitionistic fuzzy set,this paper introduces the prior information of the relative density of sample points and uses it to replace the commonly used Euclidean distance to calculate the membership and non-membership information of sample points.The intra-class relative density and inter-class relative density of sample points are used to calculate the membership and non-membership information of sample points,and then the final fuzzy value is obtained according to these two membership degrees.At the same time,different methods are used to calculate fuzzy values for the majority and minority classes respectively.Then,the obtained fuzzy values are used to improve the SVM model,and combined with the idea of cost sensitive learning,the intuitionistic fuzzy support vector machine model based on relative density is obtained,and it is used to deal with the classification problem of data imbalance.The model can not only reduce the influence of outliers and noise,but also reduce the influence of imbalance between classes.Experimental results show that the model can effectively deal with class imbalance problems compared with some class imbalance learning algorithms.