Signal preprocessing of deep-sea laser-induced plasma spectra for identification of pelletized hydrothermal deposits using Artificial Neural Networks
Signal preprocessing of deep-sea laser-induced plasma spectra for identification of pelletized hydrothermal deposits using Artificial Neural Networks
This study investigates methods to analyze Laser-induced breakdown spectroscopy (LIBS) signals generated from water immersed deep-sea hydrothermal deposits irradiated by a long pulse (>100 ns) that are analyzed using Artificial Neural Networks (ANNs). ANNs require large amounts of training data to be effective. For this reason, we propose methods to preprocess full-field spectral signals into an appropriate form for ANNs artificially increase the amount of training data. The ANN was trained using a dataset of signals from immersed pelletized hydrothermal deposit samples that were preprocessed using the proposed method. The proposed method improved the accuracy of identification from 82.5% to 90.1% and significantly increased the speed of learning. The result shows that the ANN can be used to construct a generic method to identify hydrothermal deposits by long pulse underwater LIBS signals without the need for explicit peak detection.
Artificial Neural Networks (ANNs), Chemical analysis, Laser-induced breakdown spectroscopy (LIBS), Signal processing
1-7
Yoshino, Soichi
4da2ce3b-a3f1-498f-b940-90b39580e99c
Thornton, Blair
8293beb5-c083-47e3-b5f0-d9c3cee14be9
Takahashi, Tomoko
3f3f98c5-993c-4e11-b5ec-0fa4dbdbced9
Takaya, Yutaro
5d136173-0577-4dfe-9d9e-6e20a64606c0
Nozaki, Tatsuo
72088ad3-6a8e-44b5-8192-968b3530a545
1 July 2018
Yoshino, Soichi
4da2ce3b-a3f1-498f-b940-90b39580e99c
Thornton, Blair
8293beb5-c083-47e3-b5f0-d9c3cee14be9
Takahashi, Tomoko
3f3f98c5-993c-4e11-b5ec-0fa4dbdbced9
Takaya, Yutaro
5d136173-0577-4dfe-9d9e-6e20a64606c0
Nozaki, Tatsuo
72088ad3-6a8e-44b5-8192-968b3530a545
Yoshino, Soichi, Thornton, Blair, Takahashi, Tomoko, Takaya, Yutaro and Nozaki, Tatsuo
(2018)
Signal preprocessing of deep-sea laser-induced plasma spectra for identification of pelletized hydrothermal deposits using Artificial Neural Networks.
Spectrochimica Acta Part B: Atomic Spectroscopy, 145, .
(doi:10.1016/j.sab.2018.03.015).
Abstract
This study investigates methods to analyze Laser-induced breakdown spectroscopy (LIBS) signals generated from water immersed deep-sea hydrothermal deposits irradiated by a long pulse (>100 ns) that are analyzed using Artificial Neural Networks (ANNs). ANNs require large amounts of training data to be effective. For this reason, we propose methods to preprocess full-field spectral signals into an appropriate form for ANNs artificially increase the amount of training data. The ANN was trained using a dataset of signals from immersed pelletized hydrothermal deposit samples that were preprocessed using the proposed method. The proposed method improved the accuracy of identification from 82.5% to 90.1% and significantly increased the speed of learning. The result shows that the ANN can be used to construct a generic method to identify hydrothermal deposits by long pulse underwater LIBS signals without the need for explicit peak detection.
Text
Yoshino_2018_Spectrochemica
- Accepted Manuscript
Text
signal processsing
- Version of Record
More information
Accepted/In Press date: 28 March 2018
e-pub ahead of print date: 4 April 2018
Published date: 1 July 2018
Keywords:
Artificial Neural Networks (ANNs), Chemical analysis, Laser-induced breakdown spectroscopy (LIBS), Signal processing
Identifiers
Local EPrints ID: 419456
URI: http://eprints.soton.ac.uk/id/eprint/419456
ISSN: 0584-8547
PURE UUID: fce3b571-f88c-4d70-87bb-a2cec628de7b
Catalogue record
Date deposited: 12 Apr 2018 16:30
Last modified: 16 Mar 2024 06:26
Export record
Altmetrics
Contributors
Author:
Soichi Yoshino
Author:
Tomoko Takahashi
Author:
Yutaro Takaya
Author:
Tatsuo Nozaki
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics