Learn More
Use the data mining techniques to discover the regularity knowledge from the gas sensor monitoring history database is very important approach for the supervisors to identify the reason causing the exceptional fluctuation automatically and make the correct decisions promptly. The clustering method based on the DTW distance for the gas time series above the(More)
To satisfy the special needs of confidential networks, a protection method of combining ingress and egress access control for network boundary security is proposed. In preventing network attacks, a combined mechanism of packets filtering firewall and intrusion detection system based on artificial neural network and rule matching is implemented to increase(More)
according to the stability of the membership degree and low identification rate in fuzzy inference system, this dissertation proposes the application of adaptive neural network-based fuzzy inference system to engine error diagnosis. To reduce the impact of excessive parameters on classification accuracy and cost, it also raises an asynchronous parallel(More)
A living expert system needs a mechanism to update and increase knowledge to adapt this changeable world and the knowledge acquired by different approaches need storage in order for reasoning and updating conveniently. The method presented in this paper bears this mission. Simulating the learning procedure of human beings is the core idea of this method(More)
  • 1