Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
A new probabilistic neural network for fault detection in MEMS
ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Hi-index | 0.00 |
The increased complexity of recent integrated circuits and Micro Electro Mechanical Systems (MEMS) production requires a significant effort in testing that has to keep pace with this progress in circuit and system design in order to ensure their quality and reliability. Thus a powerful tool or method is needed to detect different faults in MEMS devices. In MEMS, electrical, mechanical, electromagnetical and other nonelectrical parts are used and multi domain energies are usually converted to electrical signals. Because of complexity and microscopic material properties, there are a wide range of analog and digital faults. Nowadays, we have not a comprehensive science of microscopic fault mechanisms and most of them are analog faults which are difficult to be detected. Artificial Intelligence (AI) methods seemed to be a good candidate for fault detection. In this paper a new Genetic Algorithm (GA) is proposed for good classification of patterns and distinguishing fault free and faulty clusters. Different formulas have been used to calculate Closeness and evaluation function of patterns.