Authors: B. Samanta, C. Nataraj
Addresses: Department of Mechanical Engineering, Villanova University, Villanova, PA 19085, USA. ' Department of Mechanical Engineering, Villanova University, Villanova, PA 19085, USA
Abstract: A study is presented for the diagnosis of a patient|s heart conditions using recorded heart sounds and Computational Intelligence (CI) techniques. The digitally recorded heart sound signals are processed through Continuous Wavelet Transform (CWT) to extract time–frequency features for normal and abnormal heart conditions. The wavelet energy distributions are used as inputs to classifiers based on soft computing techniques such as Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Genetic Algorithms (GAs) for diagnosis of heart conditions. The number and the parameters of Membership Functions (MFs) used in ANFIS along with the features from wavelet energy distribution are selected using GAs, maximising the diagnosis success. ANFIS with GAs (GA-ANFIS) are trained with a subset of data with known heart conditions. The trained GA-ANFIS are tested using the other set of data (testing data), not used in training. The results are compared with Artificial Neural Network (ANN) and GA (GA-ANN). The results show the effectiveness of the proposed approach in automated diagnosis of cardiac state in healthcare systems.
Keywords: bioinformatics; cardiovascular disease; CVD; diagnosis; computational intelligence; fuzzy logic; genetic algorithms; GAs; healthcare systems; neural networks; heart conditions; continuous wavelet transform.
International Journal of Services Operations and Informatics, 2008 Vol.3 No.2, pp.162- 177
Available online: 07 Jul 2008 *Full-text access for editors Access for subscribers Purchase this article Comment on this article