Title :
Three dimensional knowledge learning memory with dynamic Bayesian associative matrix for the medical diagnosis
Author_Institution :
Dept. of Comput. Software, YongIn SongDam Coll., South Korea
Abstract :
Three dimensional knowledge learning memory with dynamic Bayesian associative matrix (DBAM) is proposed. Adopting Bayesian´s formalism, the DBAM has been specially designed. Using the DBAM it can perform the efficient memory management. Three dimensional Knowledge learning memory has the hierarchical structure performing the mechanisms of adaptive learning, selective processing, perception, inference and information retrieval. We applied this system to the medical diagnostic area for the group of virus (coxsackievirus, echovirus, cold) and the group of Rhinitis (nonallergic, allergic)
Keywords :
content-addressable storage; inference mechanisms; information retrieval; knowledge based systems; learning (artificial intelligence); medical diagnostic computing; neural nets; 3D knowledge learning memory; adaptive learning; dynamic Bayesian associative matrix; inference; information retrieval; medical diagnosis; memory management; neural networks; perception; Bayesian methods; Data mining; Humans; Information retrieval; Knowledge based systems; Knowledge management; Medical diagnosis; Medical diagnostic imaging; Memory management; Neural networks;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.938740