| EPSRC Reference: |
GR/J50514/01 |
| Title: |
LOW SNR ECG COMPRESSION USING ARTIFICIAL NEURAL NETWORKS WITH NOVEL OP TIMISATION STRATEGIES |
| Principal Investigator: |
Hamilton, Dr DJ |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Electronic and Electrical Engineering |
| Organisation: |
University of Strathclyde |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 January 1994 |
Ends: |
31 December 1995 |
Value (£): |
85,263
|
| EPSRC Research Topic Classifications: |
| Digital Signal Processing |
|
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
A new compression system for low SNR AECG recordings is proposed. An ANN operating in the unsupervised learning mode will be employed to pre-classify individual beats into similar groups without attempting to impose a clinical classification. Other ANNs will then be used to compress these groups of beats by using each beat within a group as both input and target data for an ANN with a restricted number of hidden layer neurons. For each such ANN the weight matrices are stored together with the activation levels to allow the original beats to be reconstructed. Since ANNs can reject certain types of noise, the quality of the reconstructed data compared with the original, will be investigated beyond simple RMS measures. The figure of merit obtained in this way will be verified by comparing the classification made by a commercial analyser, for the original and reconstructed signals, with various clinical settings. It is envisaged that this new technique will be efficient and overcome reluctance from cardiologists to accept data compression, since full clinical data is always retained, allowing the cardiologist full control of the final diagnosis.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.strath.ac.uk |