Separation of merged mass spectral patterns by feed-forward neural network filtering
| Autor: | Thomas G. Thomas, Dennis G. Smith |
|---|---|
| Rok vydání: | 2002 |
| Předmět: |
Signal processing
Engineering Artificial neural network Pixel Noise (signal processing) business.industry Hyperspectral imaging Pattern recognition Filter (signal processing) Machine learning computer.software_genre Adaptive filter Feedforward neural network Artificial intelligence business computer |
| Zdroj: | Photonic Devices and Algorithms for Computing IV. |
| ISSN: | 0277-786X |
| DOI: | 10.1117/12.460277 |
| Popis: | This paper describes the separation of merged signals from a mass-selective chromatographic detector by means of an adaptive filtering technique. The technique is based on parallel feed-forward neural networks, which are trained to resolve the mass spectra of two merged chemical compounds. Specifically, the chemical mass spectra of the compounds ethyl benzene and xylene were used to evaluate a filter based on probabilistic neural networks (PNN). The results are that the PNN filter shows good noise rejection and is fast enough computationally to be utilized in real time. The filter technique has applications in on-line processing of environmental monitoring instrumentation data and direct processing of pixel spectral data, such as hyperspectral image cubes. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|