Reconstruction of Ultra-High Vacuum Mass Spectra Using Genetic Algorithms
In ultra-high vacuum systems, obtaining the composition of a mass spectrum is often a challenging task due to the highly overlapping nature of the individual profiles of the gas species that contribute to that spectrum, as well as the high differences in terms of degree of contribution (several orde...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/24/11754 |
| _version_ | 1797506789394087936 |
|---|---|
| author | Carlos Flores-Garrigós Juan Vicent-Camisón Juan J. Garcés-Iniesta Emilio Soria-Olivas Juan Gómez-Sanchís Fernando Mateo |
| author_facet | Carlos Flores-Garrigós Juan Vicent-Camisón Juan J. Garcés-Iniesta Emilio Soria-Olivas Juan Gómez-Sanchís Fernando Mateo |
| author_sort | Carlos Flores-Garrigós |
| collection | DOAJ |
| description | In ultra-high vacuum systems, obtaining the composition of a mass spectrum is often a challenging task due to the highly overlapping nature of the individual profiles of the gas species that contribute to that spectrum, as well as the high differences in terms of degree of contribution (several orders of magnitude). This problem is even more complex when not only the presence but also a quantitative estimation of the contribution (partial pressure) of each species is required. This paper aims at estimating the relative contribution of each species in a target mass spectrum by combining a state-of-the-art machine learning method (multilabel classifier) to obtain a pool of candidate species based on a threshold applied to the probability scores given by the classifier with a genetic algorithm that aims at finding the partial pressure at which each one of the species contributes to the target mass spectrum. For this purpose, we use a dataset of synthetically generated samples. We explore different acceptance thresholds for the generation of initial populations, and we establish comparative metrics against the most novel method to date for automatically obtaining partial pressure contributions. Our results show a clear advantage in terms of the integral error metric (up to 112 times lower for simpler spectra) and computational times (up to 4 times lower for complex spectra) in favor of the proposed method, which is considered a substantial improvement for this task. |
| first_indexed | 2024-03-10T04:37:30Z |
| format | Article |
| id | doaj.art-3cab55377ec046f59b69dc50b6f47ded |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:37:30Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-3cab55377ec046f59b69dc50b6f47ded2023-11-23T03:37:52ZengMDPI AGApplied Sciences2076-34172021-12-0111241175410.3390/app112411754Reconstruction of Ultra-High Vacuum Mass Spectra Using Genetic AlgorithmsCarlos Flores-Garrigós0Juan Vicent-Camisón1Juan J. Garcés-Iniesta2Emilio Soria-Olivas3Juan Gómez-Sanchís4Fernando Mateo5IDAL, Intelligent Data Analysis Laboratory, Electronic Engineering Department, University of Valencia (UV), 46010 Valencia, SpainIDAL, Intelligent Data Analysis Laboratory, Electronic Engineering Department, University of Valencia (UV), 46010 Valencia, SpainIDAL, Intelligent Data Analysis Laboratory, Electronic Engineering Department, University of Valencia (UV), 46010 Valencia, SpainIDAL, Intelligent Data Analysis Laboratory, Electronic Engineering Department, University of Valencia (UV), 46010 Valencia, SpainIDAL, Intelligent Data Analysis Laboratory, Electronic Engineering Department, University of Valencia (UV), 46010 Valencia, SpainIDAL, Intelligent Data Analysis Laboratory, Electronic Engineering Department, University of Valencia (UV), 46010 Valencia, SpainIn ultra-high vacuum systems, obtaining the composition of a mass spectrum is often a challenging task due to the highly overlapping nature of the individual profiles of the gas species that contribute to that spectrum, as well as the high differences in terms of degree of contribution (several orders of magnitude). This problem is even more complex when not only the presence but also a quantitative estimation of the contribution (partial pressure) of each species is required. This paper aims at estimating the relative contribution of each species in a target mass spectrum by combining a state-of-the-art machine learning method (multilabel classifier) to obtain a pool of candidate species based on a threshold applied to the probability scores given by the classifier with a genetic algorithm that aims at finding the partial pressure at which each one of the species contributes to the target mass spectrum. For this purpose, we use a dataset of synthetically generated samples. We explore different acceptance thresholds for the generation of initial populations, and we establish comparative metrics against the most novel method to date for automatically obtaining partial pressure contributions. Our results show a clear advantage in terms of the integral error metric (up to 112 times lower for simpler spectra) and computational times (up to 4 times lower for complex spectra) in favor of the proposed method, which is considered a substantial improvement for this task.https://www.mdpi.com/2076-3417/11/24/11754residual gas analysismass spectrum reconstructiongenetic algorithmsmachine learning |
| spellingShingle | Carlos Flores-Garrigós Juan Vicent-Camisón Juan J. Garcés-Iniesta Emilio Soria-Olivas Juan Gómez-Sanchís Fernando Mateo Reconstruction of Ultra-High Vacuum Mass Spectra Using Genetic Algorithms Applied Sciences residual gas analysis mass spectrum reconstruction genetic algorithms machine learning |
| title | Reconstruction of Ultra-High Vacuum Mass Spectra Using Genetic Algorithms |
| title_full | Reconstruction of Ultra-High Vacuum Mass Spectra Using Genetic Algorithms |
| title_fullStr | Reconstruction of Ultra-High Vacuum Mass Spectra Using Genetic Algorithms |
| title_full_unstemmed | Reconstruction of Ultra-High Vacuum Mass Spectra Using Genetic Algorithms |
| title_short | Reconstruction of Ultra-High Vacuum Mass Spectra Using Genetic Algorithms |
| title_sort | reconstruction of ultra high vacuum mass spectra using genetic algorithms |
| topic | residual gas analysis mass spectrum reconstruction genetic algorithms machine learning |
| url | https://www.mdpi.com/2076-3417/11/24/11754 |
| work_keys_str_mv | AT carlosfloresgarrigos reconstructionofultrahighvacuummassspectrausinggeneticalgorithms AT juanvicentcamison reconstructionofultrahighvacuummassspectrausinggeneticalgorithms AT juanjgarcesiniesta reconstructionofultrahighvacuummassspectrausinggeneticalgorithms AT emiliosoriaolivas reconstructionofultrahighvacuummassspectrausinggeneticalgorithms AT juangomezsanchis reconstructionofultrahighvacuummassspectrausinggeneticalgorithms AT fernandomateo reconstructionofultrahighvacuummassspectrausinggeneticalgorithms |