Next Article in Journal
Quantifying Information without Entropy: Identifying Intermittent Disturbances in Dynamical Systems
Next Article in Special Issue
Statistical Approach for Biologically Relevant Gene Selection from High-Throughput Gene Expression Data
Previous Article in Journal
On the Quantumness of Multiparameter Estimation Problems for Qubit Systems
Previous Article in Special Issue
Approximate Learning of High Dimensional Bayesian Network Structures via Pruning of Candidate Parent Sets
Open AccessArticle

FASTENER Feature Selection for Inference from Earth Observation Data

by 1,2,3,†, 1,4,*,† and 1
1
Jožef Stefan Institute, 1000 Ljubljana, Slovenia
2
Faculty of Mathemathics and Physics, University of Ljubljana, 1000 Ljubljana, Slovenia
3
Institute of Mathematics, Physics, and Mechanics, 1000 Ljubljana, Slovenia
4
Jozef Stefan International Postgraduate School, 1000 Ljubljana, Slovenia
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Entropy 2020, 22(11), 1198; https://doi.org/10.3390/e22111198
Received: 19 May 2020 / Revised: 14 October 2020 / Accepted: 21 October 2020 / Published: 23 October 2020
(This article belongs to the Special Issue Statistical Inference from High Dimensional Data)
In this paper, a novel feature selection algorithm for inference from high-dimensional data (FASTENER) is presented. With its multi-objective approach, the algorithm tries to maximize the accuracy of a machine learning algorithm with as few features as possible. The algorithm exploits entropy-based measures, such as mutual information in the crossover phase of the iterative genetic approach. FASTENER converges to a (near) optimal subset of features faster than other multi-objective wrapper methods, such as POSS, DT-forward and FS-SDS, and achieves better classification accuracy than similarity and information theory-based methods currently utilized in earth observation scenarios. The approach was primarily evaluated using the earth observation data set for land-cover classification from ESA’s Sentinel-2 mission, the digital elevation model and the ground truth data of the Land Parcel Identification System from Slovenia. For land cover classification, the algorithm gives state-of-the-art results. Additionally, FASTENER was tested on open feature selection data sets and compared to the state-of-the-art methods. With fewer model evaluations, the algorithm yields comparable results to DT-forward and is superior to FS-SDS. FASTENER can be used in any supervised machine learning scenario. View Full-Text
Keywords: feature selection; machine learning; earth observation; genetic algorithm; information theory feature selection; machine learning; earth observation; genetic algorithm; information theory
Show Figures

Figure 1

  • Externally hosted supplementary file 1
    Doi: 10.1594/PANGAEA.914271
    Link: https://doi.pangaea.de/10.1594/PANGAEA.914271
    Description: Location: Slovenia Year: 2017 The EO data were collected for the whole year on a interval of about 5 days. For each point (pixel) which has dimensions 10x10 meters 10 metrices were calculated: 4 raw band measurements (red, green, blue - RGB and near infrared - NIR) and 6 relevant vegetation-related derived indices (normalized differential vegetation index - NDVI, normalized differential water index - NDWI, enhanced vegetation index - EVI, soil-adjusted vegetation index - SAVI, structureintensive pigment index - SIPI and atmospherically resistant vegetation index - ARVI). On this basic metrices, the 18 indices were calculated. The derived indices are based on extensive domain knowledge and are used for assessing vegetation properties and are defined in [Valero et al. 2016]. Aside from 180 total features from before mentioned indices also the height and land inclination are included which were obtained from Digital Elevation Model (DEM) of Slovenia.
MDPI and ACS Style

Koprivec, F.; Kenda, K.; Šircelj, B. FASTENER Feature Selection for Inference from Earth Observation Data. Entropy 2020, 22, 1198.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop