Rock mass rating system （RMR） is based on the six parameters which was defined by Bieniawski （1989） [1]. Experts frequently relate joint and discontinuities and ground water conditions in linguistic terms with rou...Rock mass rating system （RMR） is based on the six parameters which was defined by Bieniawski （1989） [1]. Experts frequently relate joint and discontinuities and ground water conditions in linguistic terms with rough calculation. As a result, there is a sharp transition between two modules which create doubts. So, in this paper the proposed weights technique was applied for linguistic criteria. Then by using the fuzzy inference system and the multi-variable regression analysis, the accurate RMR is predicted. Before the performing of regression analysis, sensitivity analysis was applied for each of Bieniawski parameters. In this process, the best function was selected among linear, logarithmic, exponential and inverse func- tions and finally it was applied in the regression analysis for construction of a predictive equation. From the constructed regression equation the relative importance of the input parameters can also be observed. It should be noted that joint condition was identified as the most important effective parameter upon RMR. Finally, fuzzy and regression models were validated with the test datasets and it was found that the fuzzy model predicts more accurately RMR than reression models.展开更多
The paper present the fuzzy logic expert system called MADSYS for an investor＇s portfolio allocation by financial asset classes. MADSYS system will be used in the interface agent （agents） of multi-agent investment ...The paper present the fuzzy logic expert system called MADSYS for an investor＇s portfolio allocation by financial asset classes. MADSYS system will be used in the interface agent （agents） of multi-agent investment management information system. One of the principal tasks of the multi-agent system is to help an investor to make investment decisions and to provide appropriate investment proposals according to the investor＇s profile. From MADSYS depends a lot of things, namely the multi-agent investment management information system accuracy, proposed investment decisions, the right portfolio allocation of financial assets, reliability and investor satisfaction. The usage of MADSYS system in the multi-agent system makes it more intellectual, i.e. the system will be able to adjust automatically to the changing of investor profile. The MADSYS system may be tried online at the following address：www.sprendimutechnologij os.lt/webapp.展开更多
文摘Rock mass rating system （RMR） is based on the six parameters which was defined by Bieniawski （1989） [1]. Experts frequently relate joint and discontinuities and ground water conditions in linguistic terms with rough calculation. As a result, there is a sharp transition between two modules which create doubts. So, in this paper the proposed weights technique was applied for linguistic criteria. Then by using the fuzzy inference system and the multi-variable regression analysis, the accurate RMR is predicted. Before the performing of regression analysis, sensitivity analysis was applied for each of Bieniawski parameters. In this process, the best function was selected among linear, logarithmic, exponential and inverse func- tions and finally it was applied in the regression analysis for construction of a predictive equation. From the constructed regression equation the relative importance of the input parameters can also be observed. It should be noted that joint condition was identified as the most important effective parameter upon RMR. Finally, fuzzy and regression models were validated with the test datasets and it was found that the fuzzy model predicts more accurately RMR than reression models.
文摘The paper present the fuzzy logic expert system called MADSYS for an investor＇s portfolio allocation by financial asset classes. MADSYS system will be used in the interface agent （agents） of multi-agent investment management information system. One of the principal tasks of the multi-agent system is to help an investor to make investment decisions and to provide appropriate investment proposals according to the investor＇s profile. From MADSYS depends a lot of things, namely the multi-agent investment management information system accuracy, proposed investment decisions, the right portfolio allocation of financial assets, reliability and investor satisfaction. The usage of MADSYS system in the multi-agent system makes it more intellectual, i.e. the system will be able to adjust automatically to the changing of investor profile. The MADSYS system may be tried online at the following address：www.sprendimutechnologij os.lt/webapp.
