DOI: 10.1109/ICCCA.2012.6179185
关键词: Prediction system 、 Class (biology) 、 Genetic algorithm 、 Disease 、 Backpropagation 、 Machine learning 、 Artificial neural network 、 Set (abstract data type) 、 Computer science 、 Data mining 、 Medical diagnosis 、 Artificial intelligence
摘要: Medical Diagnosis Systems play a vital role in medical practice and are used by practitioners for diagnosis treatment. In this paper, system is presented predicting the risk of cardiovascular disease. This built combining relative advantages genetic algorithm neural network. Multilayered feed forward networks particularly suited to complex classification problems. The weights network determined using because it finds acceptably good set less number iterations. dataset provided University California, Irvine (UCI) machine learning repository training testing. It consists 303 instances heart disease data each having 14 attributes including class label. First, preprocessed order make them suitable training. Genetic based system. final stored weight base accuracy obtained approach 94.17%.