Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/114552
Título: Empirical Mode Decomposition Based Hyperspectral Data Analysis for Brain Tumor Classification
Autores/as: Baig, Nauman
Fabelo Gómez, Himar Antonio 
Ortega, Samuel 
Callico, Gustavo Marrero 
Alirezaie, Javad
Umapathy, Karthikeyan
Clasificación UNESCO: 220990 Tratamiento digital. Imágenes
3314 Tecnología médica
Palabras clave: Hyperspectral imaging
Feature selection
Empirical mode decomposition
Pattern classification
Fecha de publicación: 2021
Editor/a: Institute of Electrical and Electronics Engineers (IEEE) 
Conferencia: 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Resumen: The capability of Hyperspectral Imaging (HSI) in rapidly acquiring abundant reflectance data in a non-invasive manner, makes it an ideal tool for obtaining diagnostic information about tissue pathology. Identifying wavelengths that provide the most discriminatory clues for specific pathologies will greatly assist in understanding their underlying biochemical characteristics. In this paper, we propose an efficient and computationally inexpensive method for determining the most relevant spectral bands for brain tumor classification. Empirical mode decomposition was used in combination with extrema analysis to extract the relevant bands based on the morphological characteristics of the spectra. The results of our experiments indicate that the proposed method outperforms the benchmark in reducing computational complexity while performing comparably with a 7-times reduction in the feature-set for classification on the test data.
URI: http://hdl.handle.net/10553/114552
ISSN: 2375-7477
DOI: 10.1109/EMBC46164.2021.9629676
Fuente: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Colección:Actas de congresos
Vista completa

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.