The nature of statistical learning theory
The nature of statistical learning theory
Machine Learning
Solving multiclass learning problems via error-correcting output codes
Journal of Artificial Intelligence Research
Feature extraction from Doppler ultrasound signals for automated diagnostic systems
Computers in Biology and Medicine
Engineering Applications of Artificial Intelligence
A modified mixture of experts network structure for ECG beats classification with diverse features
Engineering Applications of Artificial Intelligence
A novel large-memory neural network as an aid in medical diagnosis applications
IEEE Transactions on Information Technology in Biomedicine
Input feature selection for classification problems
IEEE Transactions on Neural Networks
Automated diagnostic systems: arterial disorders detection
ACS'08 Proceedings of the 8th conference on Applied computer scince
Advances in automated diagnostic systems
NN'09 Proceedings of the 10th WSEAS international conference on Neural networks
Adaptive Neuro-Fuzzy Inference Systems for Automatic Detection of Breast Cancer
Journal of Medical Systems
Hi-index | 0.00 |
In this paper, the multiclass support vector machines (SVMs) with the error correcting output codes (ECOC) were presented for the multiclass time-varying biomedical signals (ophthalmic arterial Doppler signals, internal carotid arterial Doppler signals and electrocardiogram signals) classification problems. Decision making was performed in two stages: feature extraction by computing the Lyapunov exponents and classification using the classifier trained on the extracted features. The purpose was to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. The research demonstrated that the Lyapunov exponents are the features which well represent the studied time-varying biomedical signals and the multiclass SVMs trained on these features achieved high classification accuracies.