Generalized rough sets, entropy, and image ambiguity measures
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on human computing
ICALT '10 Proceedings of the 2010 10th IEEE International Conference on Advanced Learning Technologies
| Hi-index | 0.00 |
The objective of the paper is to propose a fault detection technique for an embedded system using rough set classifiers. In a tightly coupled information system where the data dependency is high and embedded, the need for a strong mathematical model for fault detection in embedded system is needed. The system faults may be due to the constituent components including the hardware, application software and the operation environment at the target. The indiscernibility relation is generated due to the lack of information about the correct functionality or behavior of the components in the system. The properties or attributes of the components and the dependency between them give a tool for the detection of faulty components in an embedded application. The decision through Boolean reasoning and reduction of attributes excluding the necessary redundant components enhance the detection capability. The rough set approximation theory with the fuzzy membership functions helps not only to remove the vagueness in the detection method but also to locate the faulty components.