Unlike the Brock,Dechert,and Scheinkman(BDS)test,the Surrogate Data method is not only able to provide a nonlinearity test for exchange rates,but also distinguish whether the nonlinear features come from the economic ...Unlike the Brock,Dechert,and Scheinkman(BDS)test,the Surrogate Data method is not only able to provide a nonlinearity test for exchange rates,but also distinguish whether the nonlinear features come from the economic system itself.Our analysis gives some evidence on the presence of nonlinear dependency of five emerging markets' exchange rates by using BDS test.Furthermore,we present evidence in existence of intrinsic and deterministic nonlinearity in the five exchange rates using the Surrogate Data method,comparing the original data and surrogate data and rejecting the null hypothesis in confidence coefficient 95%.The results provide the basis for the analyses of the chaotic properties of exchange rate time series and their future nonlinear forecasting.展开更多
In this paper, we propose an improved Directed Acyclic Graph Support Vector Machine （DAGSVM） for multi-class classification. Compared with the traditional DAGSVM, the improved version has advantages that the structu...In this paper, we propose an improved Directed Acyclic Graph Support Vector Machine （DAGSVM） for multi-class classification. Compared with the traditional DAGSVM, the improved version has advantages that the structure of the directed acyclic graph is not chosen random and fixed, and it can be adaptive to be optimal according to the incoming testing samples, thus it has a good generalization performance. From experiments on six datasets, we can see that the proposed improved version of DAGSVM is better than the traditional one with respect to the accuracy rate.展开更多
文摘Unlike the Brock,Dechert,and Scheinkman(BDS)test,the Surrogate Data method is not only able to provide a nonlinearity test for exchange rates,but also distinguish whether the nonlinear features come from the economic system itself.Our analysis gives some evidence on the presence of nonlinear dependency of five emerging markets' exchange rates by using BDS test.Furthermore,we present evidence in existence of intrinsic and deterministic nonlinearity in the five exchange rates using the Surrogate Data method,comparing the original data and surrogate data and rejecting the null hypothesis in confidence coefficient 95%.The results provide the basis for the analyses of the chaotic properties of exchange rate time series and their future nonlinear forecasting.
文摘In this paper, we propose an improved Directed Acyclic Graph Support Vector Machine （DAGSVM） for multi-class classification. Compared with the traditional DAGSVM, the improved version has advantages that the structure of the directed acyclic graph is not chosen random and fixed, and it can be adaptive to be optimal according to the incoming testing samples, thus it has a good generalization performance. From experiments on six datasets, we can see that the proposed improved version of DAGSVM is better than the traditional one with respect to the accuracy rate.
