Hyperspectral classification of blood-like substances using machine learning methods combined with genetic algorithms in transductive and inductive scenarios
Authors:
- Filip Pałka,
- Wojciech Książek,
- Paweł Pławiak,
- Michał Romaszewski,
- Kamil Książek
Abstract
This study is focused on applying genetic algorithms (GAs) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspectral images with blood and five visually similar substances to test GA-optimised classifiers in two scenarios: when the training and test data come from the same image and when they come from different images, which is a more challenging task due to significant spectral differences. In our experiments, we compare GA with a classic model optimisation through a grid search. Our results show that GA-based model optimisation can reduce the number of bands and create an accurate classifier that outperforms the GS-based reference models, provided that, during model optimisation, it has access to examples similar to test data. We illustrate this with experiments highlighting the importance of a validation set.
- Record ID
- CUT3f8fc825ad8a4fada364461b5a311ae4
- Publication categories
- ;
- Author
- Journal series
- Sensors, ISSN , e-ISSN 1424-8220, Biweekly
- Issue year
- 2021
- Vol
- 21
- No
- 7
- Pages
- [1-18]
- Article number
- 2293
- Other elements of collation
- rys.; tab.; wykr.; Bibliografia (na s.) - 16-18; Bibliografia (liczba pozycji) - 55; Oznaczenie streszczenia - Abstr.; Numeracja w czasopiśmie - Vol. 21, Iss. 7, Spec. Iss.
- Substantive notes
- Special Issue: Vision Sensors and Systems in Structural Health Monitoring
- Keywords in English
- hyperspectral classification, blood, SVM, genetic algorithm, machine learning
- DOI
- DOI:10.3390/s21072293 Opening in a new tab
- URL
- https://www.mdpi.com/1424-8220/21/7/2293/htm Opening in a new tab
- Language
- eng (en) English
- License
- Score (nominal)
- 100
- Publication indicators
- Citation count
- 3
- Additional fields
- Indeksowana w: Web of Science, Scopus
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUT3f8fc825ad8a4fada364461b5a311ae4/
- URN
urn:pkr-prod:CUT3f8fc825ad8a4fada364461b5a311ae4
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.