menu_book Explore the article's raw data

BENCHMARKING DEEP LEARNING FRAMEWORKS FOR THE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE MULTISPECTRAL DATA

Abstract

In this paper we evaluated deep-learning frameworks based on Convolutional Neural Networks for the accurate classification of multi-spectral remote sensing data. Certain state-of-the-art models have been tested on the publicly available SAT-4 and SAT-6 high resolution satellite multispectral datasets. In particular, the performed benchmark included the AlexNet, AlexNet-small and VGG models which had been trained and applied to both datasets exploiting all the available spectral information. Deep Belief Networks, Autoencoders and other semi-supervised frameworks have been, also, compared. The high level features that were calculated from the tested models managed to classify the different land cover classes with significantly high accuracy rates i.e., above 99.9%. The experimental results demonstrate the great potentials of advanced deep-learning frameworks for the supervised classification of high resolution multispectral remote sensing data.

article Proceedings Paper

date_range 2016

language English

link Link of the paper

format_quote

Papadomanolaki M.

Vakalopoulou M.

Zagoruyko S.

Karantzalos K.

Sorry! There is no raw data available for this article.

Loading references...

Loading citations...

Featured Keywords

Machine Learning

Classification

Land Cover

Land Use

Convolutional

Neural Networks

Data Mining

shopping_basket PURCHASE DATA

Performance evaluation of mortar with ground and thermo-activated recycled concrete cement

Abstract

The main objective of this study was to examine the combined effect of ground recycled concrete cement (GRC) and thermo-activated recycled concrete cement (TARC) on properties of mortar. The physical, chemical and microstructural tests were conducted to characterize GRC and TARC before mortar mixtures were produced. The microscopic morphology of GRC and TARC revealed uneven edges and a rough surface that is slightly porous. The GRC and TARC powders were used to replace cement in the range of 0-50% at increments of 10% by volume. The fresh, mechanical, microstructure, and durability characteristics of mortar were tested for different proportion of GRC and TARC as partial replacement of cement. The usage of GRC and TARC decreases the workability of mortar marginally. However, the mechanical performance of the mortar mixtures showed an increasing trend when GRC and TARC share increases in the mixture. Predominantly, compressive strength, bulk density, and ultrasonic pulse velocity (UPV) have all been increased by as much as 20% cement replacement. Furthermore, the incorporation of GRC and TARC enhances the mortar’s durability properties. The microstructure analysis reveals that 20% replacement (GT20) mix has superior structural compactness. In general, partially substitution of GRC and TARC by ordinary Portland cement improves several characteristics of mortar. This will help solve the most prevalent problems that concrete produces, including the high embedded carbon dioxide creation, the high resource usage, and the high waste generation after demolition.

article Article

date_range 2024

language English

link Link of the paper

Compressive Strength

GT0-GT50 (xlsx)