Use of machine learning for classification of magneto...

Details Use of machine learning for classification of magneto... Use of machine learning for classification of magneto...

2004-07-01

2010-06-22

Manuel, George (Department: 3762)

Surgery

Diagnostic testing

Cardiovascular

Reexamination Certificate

active

07742806

ABSTRACT:
The use of machine learning for pattern recognition in magnetocardiography (MCG) that measures magnetic fields emitted by the electrophysiological activity of the heart is disclosed herein. Direct kernel methods are used to separate abnormal MCG heart patterns from normal ones. For unsupervised learning, Direct Kernel based Self-Organizing Maps are introduced. For supervised learning Direct Kernel Partial Least Squares and (Direct) Kernel Ridge Regression are used. These results are then compared with classical Support Vector Machines and Kernel Partial Least Squares. The hyper-parameters for these methods are tuned on a validation subset of the training data before testing. Also investigated is the most effective pre-processing, using local, vertical, horizontal and two-dimensional (global) Mahanalobis scaling, wavelet transforms, and variable selection by filtering. The results, similar for all three methods, were encouraging, exceeding the quality of classification achieved by the trained experts. Thus, a device and associated method for classifying cardiography data is disclosed, comprising applying a kernel transform to sensed data acquired from sensors sensing electromagnetic heart activity, resulting in transformed data, prior to classifying the transformed data using machine learning.

REFERENCES:
patent: 4958638 (1990-09-01), Sharpe et al.
patent: 5092343 (1992-03-01), Spitzer et al.
patent: 5280792 (1994-01-01), Leong et al.
patent: 5417211 (1995-05-01), Abraham-Fuchs et al.
patent: 5465308 (1995-11-01), Hutcheson et al.
patent: 5680866 (1997-10-01), Kangas et al.
patent: 5819007 (1998-10-01), Elghazzawi
patent: 5827195 (1998-10-01), Lander
patent: 6128608 (2000-10-01), Barnhill
patent: 6210344 (2001-04-01), Perin et al.
patent: 6248063 (2001-06-01), Barnhill et al.
patent: 6342699 (2002-01-01), Jeanguillaume
patent: 6443889 (2002-09-01), Groth et al.
patent: 6572560 (2003-06-01), Watrous et al.
patent: 6714925 (2004-03-01), Barnhill et al.
patent: 6728691 (2004-04-01), Neuneier et al.
patent: 2002/0165837 (2002-11-01), Zhang et al.
A. Bezerianos, L. Vladutu, S. Papadimitriou, Hierarchical state space partitioning with a network self-organising map for the recognition of ST-T segment changes, Med. Biol. Eng. Comput., 2000, 406-415.
M. E. Tagluk, M. J. English, The Analysis of ECG Signals Using Time-Frequency Techniques, Proceedings, 19th International Conference, IEEE/EMBS Oct. 30-Nov. 2, 1997, Chicago, IL, USA.
S. Jankowski, J. Tijink, G. Vumbaca, M. Balsi, G. Karpinski, Support Vector Machine for the Recognition of Atrial and Ventricular Depolarization in Holter ECG Recording, International Journal of Bioelectromagnetism, 2002, vol. 4, No. 2, pp. 343-344.
J. Millet-Roig, R. Ventura-Galiano, F. J. Chorro-Gasco, A. Cebrian, Support Vector Machine for Arrhythmia Discrimination with Wavelet-Transform-Based Feature Selection, Computers in Cardiology 2000:27:407-410.
Bennett, K.P. And Embrechts M.J., An Optimization Perspective on Kernel Partial Least Squares Regression, in Suykens, J.A.K., Horvath, G., Basu, S., Micchelli, C., Vandewalle J. (Eds.), Advances in Learning Theory: Methods, Models and Applications, NATO Science Series III: Computer & Systems Sciences, vol. 190, IOS Press Amsterdam, Jan. 2003, 436pp. (ISBN: 1 58603 341 7).

Affiliated with

Also associated with

Rating

Use of machine learning for classification of magneto... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Use of machine learning for classification of magneto..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Use of machine learning for classification of magneto... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4245355