Összesen 1 találat.


001-es BibID:BIBFORM093074
Első szerző:Aldabbas, Ashraf Khaled Abd Elkareem (informatikus)
Cím:Cassini-Huygens mission images classification framework by deep learning advanced approach / Ashraf AlDabbas, Zoltan Gal
ISSN:2088-8708 2722-2578
Megjegyzések:Developing a deep learning (DL) model for image classification commonly demands a crucial architecture organization. Planetary expeditions produce a massive quantity of data and images. However, manually analyzing and classifying flight missions image databases with hundreds of thousands of images is ungainly and yield weak accuracy. In this paper, we speculate an essential topic related to the classification of remotely sensed images, in which the process of feature coding and extraction are decisive procedures. Diverse feature extraction techniques are intended to stimulate a discriminative image classifier. Features extraction is the primary engagement in raw data processing with the purpose of data classification; when it comes across the task of analysis of vast and varied data, these kinds of tasks are considered as time-consuming and hard to be treated with. Most of these classifiers are either, in principle, quite intricate or virtually unattainable to calculate for massive datasets. Stimulated by this perception, we put forward a straightforward, efficient classifier based on feature extraction by analyzing the cell of tensors via layered MapReduce framework beside meta-learning LSTM followed by a SoftMax classifier. Experiment results show that the provided model attains a classification accuracy of 96.7%, which makes the provided model quite valid for diverse image databases with varying sizes.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény külföldi lapban
Deep learning
Machine learning
Remote sensing datasets
Saturn images classification
Megjelenés:International Journal of Electrical and Computer Engineering. - 11 : 3 (2021), p. 2457-2466. -
További szerzők:Gál Zoltán (1966-) (informatikus)
Internet cím:Szerző által megadott URL
Intézményi repozitóriumban (DEA) tárolt változat
Rekordok letöltése1