Abstract
A description is given of spike-train tomographic scanning (ST-scanning), a feature extraction method useful in the separation of component action potentials from composite spike-trains. Using ST-scanning, spike-train components are differentially represented in histograms according to the scan angle used. These histogram waveforms are then analyzed using a 3-layer perceptron, employing a least mean square (LMS) learning algorithm. The neural network is first trained to relate specific ST-scan histograms to known spike-train patterns. After training, the perceptron is run on feedforward mode to allow the separation of component action potentials from composite waveforms. Results obtained with this technique are discussed.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of the Annual Conference on Engineering in Medicine and Biology |
| Place of Publication | Piscataway, NJ, United States |
| Publisher | Publ by IEEE |
| Pages | 1435-1436 |
| Number of pages | 2 |
| Edition | pt 3 |
| ISBN (Print) | 0879425598 |
| State | Published - 1990 |
| Externally published | Yes |
| Event | Proceedings of the 12th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Philadelphia, PA, USA Duration: Nov 1 1990 → Nov 4 1990 |
Other
| Other | Proceedings of the 12th Annual International Conference of the IEEE Engineering in Medicine and Biology Society |
|---|---|
| City | Philadelphia, PA, USA |
| Period | 11/1/90 → 11/4/90 |
ASJC Scopus subject areas
- Bioengineering