Geodesic
Identification of Earth's surface objects using ensembles of convolutional neural networks
Journal of the Belarusian State University. Mathematics and Informatics, Tome 2 (2021), pp. 114-123.

Voir la notice de l'article provenant de la source Math-Net.Ru

The paper proposes an identification technique of objects on the Earth's surface images based on combination of machine learning methods. Different variants of multi-layer convolutional neural networks and support vector machines are considered as original models. A hybrid convolutional neural network that combines features extracted by the neural network and experts is proposed. Optimal values of hyperparameters of the models are calculated by grid search methods using k-fold cross-validation. The possibility of improving the accuracy of identification based on the ensembles of these models is shown. Effectiveness of the proposed technique is demonstrated by the example of images obtained by synthetic aperture radar.
Keywords: convolutional neural network; support vector machine; neural network ensemble; Earth's surface image; remote sensing; identification; synthetic aperture radar. 
@article{BGUMI_2021_2_a10,
     author = {E. E. Marushko and A. A. Doudkin and X. Zheng},
     title = {Identification of {Earth's} surface objects using ensembles of convolutional neural networks},
     journal = {Journal of the Belarusian State University. Mathematics and Informatics},
     pages = {114--123},
     publisher = {mathdoc},
     volume = {2},
     year = {2021},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/BGUMI_2021_2_a10/}
}
TY  - JOUR
AU  - E. E. Marushko
AU  - A. A. Doudkin
AU  - X. Zheng
TI  - Identification of Earth's surface objects using ensembles of convolutional neural networks
JO  - Journal of the Belarusian State University. Mathematics and Informatics
PY  - 2021
SP  - 114
EP  - 123
VL  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/BGUMI_2021_2_a10/
LA  - en
ID  - BGUMI_2021_2_a10
ER  - 
%0 Journal Article
%A E. E. Marushko
%A A. A. Doudkin
%A X. Zheng
%T Identification of Earth's surface objects using ensembles of convolutional neural networks
%J Journal of the Belarusian State University. Mathematics and Informatics
%D 2021
%P 114-123
%V 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/BGUMI_2021_2_a10/
%G en
%F BGUMI_2021_2_a10
E. E. Marushko; A. A. Doudkin; X. Zheng. Identification of Earth's surface objects using ensembles of convolutional neural networks. Journal of the Belarusian State University. Mathematics and Informatics, Tome 2 (2021), pp. 114-123. http://geodesic.mathdoc.fr/item/BGUMI_2021_2_a10/

[1] M. Kim, W. Choi, Y. Jeon, L. Liu, “A hybrid neural network model for power demand forecasting”, Energies, 12(5) (2019), 931 | DOI

[2] A. Frankel, K. Tachida, R. Jones, “Prediction of the evolution of the stress field of polycrystals undergoing elastic-plastic deformation with a hybrid neural network model”, Machine Learning: Science and Technology, 1(3) (2020), 035005 | DOI

[3] H. Liu, R. Yang, T. Wang, L. Zhang, “A hybrid neural network model for short-term wind speed forecasting based on decomposition, multi-learner ensemble, and adaptive multiple error corrections”, Renewable Energy, 165 (2021), 573–594 | DOI

[4] C. Ma, X. Du, L. Cao, “Analysis of multi-types of flow features based on hybrid neural network for improving network anomaly detection”, IEEE Access, 7 (2019), 148363–148380 | DOI

[5] S. Berkhahn, L. Fuchs, I. Neuweiler, “An ensemble neural network model for real-time prediction of urban floods”, Journal of hydrology, 575 (2019), 743–754 | DOI

[6] B. Cheng, W. Wu, D. Tao, S. Mei, T. Mao, J. Cheng, “Random cropping ensemble neural network for image classification in a robotic arm grasping system”, IEEE Transactions on Instrumentation and Measurement, 69(9) (2020), 6795–6806 | DOI

[7] “Large scale visual recognition challenge”, 2021 | DOI

[8] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, “Backpropagation applied to handwritten zip code recognition”, Neural computation, 1(4) (1989), 541–551 | DOI

[9] I. Goodfellow, Y. Bengio, A. Courville, “Deep Learning”, MIT Press, Cambridge, 2016, 781 | MR

[10] D. Parikh, R. Polikar, “An ensemble-based incremental learning approach to data fusion”, IEEE Transactions on Systems, Man and Cybernetics. Part B: Cybernetics, 37(2) (2007), 437450 | DOI | MR

[11] E. E. Marushko, A. A. Doudkin, “Ensembles of neural networks for forecasting of time series of spacecraft telemetry”, Optical Memory and Neural Networks, 26(1) (2017), 47–54 | DOI

[12] N. Kourentzes, D. Barrow, S. Crone, “Neural network ensemble operators for time series forecasting”, Expert Systems with Applications, 41(9) (2014), 4235–4244 | DOI

[13] V. Vapnik, “The nature of statistical learning theory”, Springer, New York, 1999, 314 | MR

[14] J. Bergstra, Y. Bengio, “Random search for hyper-parameter optimization”, Machine Learning Research, 13 (2012), 281–305 | MR | Zbl

[15] B. Josh, “Statoil/C-CORE iceberg classifier challenge”, 2021 | DOI

[16] D. P. Kingma, JAdam. Ba, A method for stochastic optimization, 2017, arXiv: 1412.6980

[17] K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, 2015, arXiv: href{https://arxiv.org/abs/1409.1556}{1409.1556}

[18] F. Chollet, “Xception. Deep learning with depthwise separable convolutions”, IEEE Computer Society, 2017, 1251–1258 | DOI

[19] K. He, X. Zhang, S. Ren, J. Sun, “Deep residual learning for image recognition”, IEEE Computer Society, 2016, 770–778 | DOI | MR

[20] M. Tan, Q. V. Le, “Efficient net: rethinking model scaling for convolutional neural networks”, 2020, 11, arXiv: href{https://arxiv.org/abs/1905.11946}{1905.11946}

[21] G. Huang, Z. Liu, Der. Van, K. Q. Weinberger, “Densely connected convolutional networks”, IEEE Computer Society, 2017, 2261–2269 | DOI

[22] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L. C. Chen, “MobilenetV2: inverted residuals and linear bottlenecks”, IEEE Computer Society, 2018, 4510–4520 | DOI

[23] L. Prechelt, “Early stopping – but when?”, Springer, Berlin, 1998, 55–69

[24] P. Goyal, P. Dollar, R. Girshick, P. Noordhuis, L. Wesolowski, A. Kyrola, “Accurate, large minibatch SGD: training imagenet in 1 hour”, 2018, 12, arXiv: href{https://arxiv.org/abs/1706.02677}{1706.02677} | Zbl