Rough Sets: Theoretical Aspects of Reasoning about Data
Rough Sets: Theoretical Aspects of Reasoning about Data
Rough Set Approach to the Survival Analysis
TSCTC '02 Proceedings of the Third International Conference on Rough Sets and Current Trends in Computing
ELEM2: A Learning System for More Accurate Classifications
AI '98 Proceedings of the 12th Biennial Conference of the Canadian Society for Computational Studies of Intelligence on Advances in Artificial Intelligence
A new rough sets model based on database systems
Fundamenta Informaticae - Special issue on the 9th international conference on rough sets, fuzzy sets, data mining and granular computing (RSFDGrC 2003)
Hybrid Intelligent Systems: Selecting Attributes for Soft-Computing Analysis
COMPSAC '05 Proceedings of the 29th Annual International Computer Software and Applications Conference - Volume 01
RSFDGrC'05 Proceedings of the 10th international conference on Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing - Volume Part I
Transactions on Rough Sets IV
RSFDGrC '07 Proceedings of the 11th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing
| Hi-index | 0.00 |
The integration of mathematical and statistical data analysis research can engender a novel and better approach, especially for survival analysis. This paper is devoted to Professor Pawlak and his ideas about rough sets and its applications. We propose MULTIHYRIS, an alternative hybrid intelligent system with a rough sets and population based approach for survival analysis. MULTIHYRIS is designed to increase the versatility and efficiency of survival analysis techniques. The MULTIHYRIS architecture incorporates mathematics - rough sets (with discernibility relations and individual patient consideration) - with statistics - Kaplan-Meier and Cox methods (with population estimates). The central idea behind MULTIHYRIS is to perform univariate analysis by using rough sets, database management and the Kaplan-Meier method with soft computing. All results from the univariate analysis are subsequently used in further mulitvariate analysis. In this stage, we provide two optional approaches to serve different requirements; rough sets integrated with database management and the Cox method. The former approach is able to produce decision rules while the latter generates a Cox model. Furthermore, set operations are used to unite these two outcomes and generate new reducts - hybrid reducts based on our rough sets-population based system. The informativeness of the rules and models can be verified within this analysis by validation processes and statistical tests. To demonstrate MULTIHYRIS, we have implemented it on a real-world geriatric data set, collected from the Dalhousie Medical School.