Selection of spectral features for land cover type classification

Abstract Sophisticated sensors of satellites help researchers collect detailed maps of land surface in various image wavebands. These wavebands are processed to form spectral features identifying distinct land structures. However, depending on the structures subject to the research topic, only a portion of collected features might be sufficient for identification. Aim of this study is to present a scheme to pick most valuable spectral features derived from ASTER imagery in order to distinguish four types of tree ensembles: ‘Sugi’ (Japanese Cedar), ‘Hinoki’ (Japanese Cypress), ‘Mixed deciduous’, and ‘Others’. Forward selection, a type of wrapper techniques, was employed with four types of classifiers in several train/test splits. Final rank of each feature was determined by Condorcet ranking after application of each classifier. Results showed that among four classifiers, artificial neural networks helped the selection process choose the most valuable features and a high accuracy value of 90.42% (with a true skill statistics score of 91.26%) was obtained using only top-ten features. For feature sets in smaller sizes, support vector machines classifier also performed well and provided an accuracy of 80.33% (with a true skill statistics score of 81.84%) using only top-three features. With help of these findings, landscape data can be represented in smaller forms with spectral features having most discriminative power. This will help reduce processing time and storage needs of expert systems.

[1]  Verónica Bolón-Canedo,et al.  Ensemble Feature Selection for Rankings of Features , 2015, IWANN.

[2]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[3]  Mohammad Ali Zare Chahooki,et al.  A Survey on semi-supervised feature selection methods , 2017, Pattern Recognit..

[4]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[5]  Hugues Bersini,et al.  A Survey on Filter Techniques for Feature Selection in Gene Expression Microarray Analysis , 2012, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[6]  Taskin Kavzoglu,et al.  A kernel functions analysis for support vector machines for land cover classification , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[7]  Albert Y. Zomaya,et al.  Ensemble-Based Wrapper Methods for Feature Selection and Class Imbalance Learning , 2013, PAKDD.

[8]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[9]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[10]  Jianyu Miao,et al.  A Survey on Feature Selection , 2016 .

[11]  Mohammad Kazem Ebrahimpour,et al.  Ensemble of feature selection methods: A hesitant fuzzy sets approach , 2017, Appl. Soft Comput..

[12]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[13]  Andrew Zisserman,et al.  Image Classification using Random Forests and Ferns , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[14]  P. Atkinson.  Spatially weighted supervised classification for remote sensing , 2004 .

[15]  R. G. Davies,et al.  Methods to account for spatial autocorrelation in the analysis of species distributional data : a review , 2007 .

[16]  Tomislav Hengl,et al.  Improving performance of spatio-temporal machine learning models using forward feature selection and target-oriented validation , 2018, Environ. Model. Softw..

[17]  Ryutaro Tateishi,et al.  Using geographically weighted variables for image classification , 2012 .

[18]  Nicoletta Dessì,et al.  Similarity of feature selection methods: An empirical study across data intensive classification tasks , 2015, Expert Syst. Appl..

[19]  Lei Liu,et al.  Sequential data feature selection for human motion recognition via Markov blanket , 2017, Pattern Recognit. Lett..

[20]  Arcot Sowmya,et al.  Modelling and representation issues in automated feature extraction from aerial and satellite images , 2000 .

[21]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[22]  Frédéric Jurie,et al.  Randomized Clustering Forests for Image Classification , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Thibault Helleputte,et al.  Robust biomarker identification for cancer diagnosis with ensemble feature selection methods , 2010, Bioinform..

[24]  Jacques Rivoirard,et al.  Unsupervised classification of multivariate geostatistical data: Two algorithms , 2015, Comput. Geosci..

[25]  J.C. Rajapakse,et al.  SVM-RFE With MRMR Filter for Gene Selection , 2010, IEEE Transactions on NanoBioscience.

[26]  P. Atkinson,et al.  A Geostatistically Weighted k -NN Classifier for Remotely Sensed Imagery , 2010 .

[27]  Yi Yang,et al.  Semisupervised Feature Selection via Spline Regression for Video Semantic Recognition , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[28]  Razieh Sheikhpour,et al.  Particle swarm optimization for bandwidth determination and feature selection of kernel density estimation based classifiers in diagnosis of breast cancer , 2016, Appl. Soft Comput..

[29]  Helmi Zulhaidi Mohd Shafri,et al.  Road condition assessment by OBIA and feature selection techniques using very high-resolution WorldView-2 imagery , 2017 .

[30]  Gavin Brown,et al.  Simple strategies for semi-supervised feature selection , 2017, Machine Learning.

[31]  Adriaan Van Niekerk,et al.  Value of dimensionality reduction for crop differentiation with multi-temporal imagery and machine learning , 2017, Comput. Electron. Agric..

[32]  Senem Kumova Metin,et al.  Feature selection in multiword expression recognition , 2018, Expert Syst. Appl..

[33]  Vinod Chandran,et al.  Evolutionary computation algorithms for feature selection of EEG-based emotion recognition using mobile sensors , 2018, Expert Syst. Appl..

[34]  Sunanda Das,et al.  Ensemble feature selection using bi-objective genetic algorithm , 2017, Knowl. Based Syst..

[35]  Mohamed Limam,et al.  Robust ensemble feature selection for high dimensional data sets , 2013, 2013 International Conference on High Performance Computing & Simulation (HPCS).

[36]  Xing Zhang,et al.  Embedded feature-selection support vector machine for driving pattern recognition , 2015, J. Frankl. Inst..

[37]  Philip S. Yu,et al.  Forward Semi-supervised Feature Selection , 2008, PAKDD.

[38]  Fernando Jiménez,et al.  Multi-objective evolutionary feature selection for online sales forecasting , 2017, Neurocomputing.

[39]  Yunming Ye,et al.  Stratified sampling for feature subspace selection in random forests for high dimensional data , 2013, Pattern Recognit..

[40]  Deron Liang,et al.  Novel feature selection methods to financial distress prediction , 2014, Expert Syst. Appl..