Abstract
In this paper, we propose a novel feature extraction method for pattern classification problem. We propose to map the original data to subspaces for feature extraction and hope the mapped data can reconstruct the original data. The motive is to avoid of losing of information of the original data in the process of subspace mapping. We assume that if the original data can be reconstructed from the subspace, the critical information can be preserved. Moreover, we also observed that the reconstruction error is a low-rank matrix if the reconstruction is performed well. We propose to measure the reconstruction error matrix rank by the nuclear norm and minimize it to learn the optimal subspace transformation matrix. Meanwhile, the classification is also used to regularize the learning to improve the discriminate ability of the subspace representations. Experiments over several benchmark data sets show the advantage of the proposed method over the existing subspace learning methods.
Similar content being viewed by others
References
Aizenberg I (2017) Multiple-valued logic and complex-valued neural networks. Stud Fuzziness Soft Comput 349:153–171
Altun K, Barshan B, Tunçel O (2010) Comparative study on classifying human activities with miniature inertial and magnetic sensors. Pattern Recognit 43(10):3605–3620
Belachew M, Del Buono N (2017) A dynamical system approach for continuous nonnegative matrix factorization. Mediterr J Math 14(1):14
Cai JF, Candès EJ, Shen Z (2010) A singular value thresholding algorithm for matrix completion. SIAM J Optim 20(4):1956–1982
Candès EJ, Li X, Ma Y, Wright J (2011) Robust principal component analysis? J ACM (JACM) 58(3):11
Cao P, Liu X, Zhang J, Li W, Zhao D, Huang M, Zaiane O (2017) A ℓ2, 1 norm regularized multi-kernel learning for false positive reduction in lung nodule cad. Comput Methods Programs Biomed 140:211–231
de Carvalho Pagliosa L, de Mello R (2017) Applying a kernel function on time-dependent data to provide supervised-learning guarantees. Expert Syst Appl 71:216–229
De La Torre F, Black MJ (2003) A framework for robust subspace learning. Int J Comput Vis 54(1–3):117–142
Ding W, Gu J, Shang Z, Tang S, Wu Q, Duodu E, Yang Z (2017) Semantic recognition of workpiece using computer vision for shape feature extraction and classification based on learning databases. Optik 130:1426–1437
Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Eugen 7(2):179–188
Gamba IM, Zhang C, Fan J (2014) A conservative discontinuous Galerkin scheme with o (n 2) operations in computing Boltzmann collision weight matrix. In: AIP Conference Proceedings, vol 1628, AIP, pp 75–83
Geng Y, Liang RZ, Li W, Wang J, Liang G, Xu C, Wang JY (2016) Learning convolutional neural network to maximize pos@top performance measure. In: ESANN
Geng Y, Zhang G, Li W, Gu Y, Liang G, Wang J, Wu Y, Patil N, Wang JY (2017) A novel image tag completion method based on convolutional neural network. In: International conference on artificial neural networks. Springer
He X, Cai D, Yan S, Zhang HJ (2005) Neighborhood preserving embedding. In: Tenth IEEE international conference on computer vision (ICCV’05) volume 1, vol 2. IEEE, pp 1208–1213
He X, Niyogi P (2004) Locality preserving projections. In: Advances in neural information processing systems
Hnin H, Pa W, Thu Y (2017) Back-propagation neural network approach to Myanmar part-of-speech tagging. Adv Intell Syst Comput 536:212–220
Jia X, Sun F, Li H, Cao Y, Zhang X (2017) Image multi-label annotation based on supervised nonnegative matrix factorization with new matching measurement. Neurocomputing 219:518–525
Jieyi Z, Min T, Ruofeng T, Jinxiang D (2008) The platform of quick development of mobile 3d game. In: International Symposium on computer science and computational technology, 2008. ISCSCT’08, vol 2. IEEE, pp 226–229
Jin Y, Qian GP, Zhao JY, Chang J, Tong RF, Zhang J (2015) Stretch-minimizing volumetric parameterization. J Comput Sci Technol 30(3):553–564
Li LS, Gan SJ, Yin XD (2017) Feedback recurrent neural network-based embedded vector and its application in topic model. Eurasip J Embed Syst 2017(1):5
Li Q, Zhou X, Gu A, Li Z, Liang RZ (2016) Nuclear norm regularized convolutional Max Pos@Top machine. Neural Comput Appl. doi:10.1007/s00521-016-2680-2
Li Y, Liang X, Xu M, Huang W (2017) Early fault feature extraction of rolling bearing based on icd and tunable q-factor wavelet transform. Mech Syst Signal Process 86:204–223
Liu J, Byna S, Chen Y (2013) Segmented analysis for reducing data movement. In: Big Data’13, 2013 IEEE international conference on Big Data. IEEE, pp 344–349
Liu J, Chen Y (2012) Improving data analysis performance for high-performance computing with integrating statistical metadata in scientific datasets. In: High performance computing, networking, storage and analysis (SCC), 2012 SC companion. IEEE, pp 1292–1295
Liu J, Chen Y, Zhuang Y (2013) Hierarchical i/o scheduling for collective i/o. In: 2013 13th IEEE/ACM international symposium on cluster, cloud and grid computing (CCGrid). IEEE, pp 211–218
Liu J, Crysler B, Lu Y, Chen Y (2013) Locality-driven high-level i/o aggregation for processing scientific datasets. In: Big Data’13, 2013 IEEE international conference on Big Data. IEEE, pp 103–111
Liu S, Liu Z, Sun J, Liu L (2011) Application of synergetic neural network in online writeprint identification. Int J Digital Content Technol Appl 5(3):126–135
Ma G, Wang Y, Wu L (2017) Subspace ensemble learning via totally-corrective boosting for gait recognition. Neurocomputing 224:119–127
Miao M, Zeng H, Wang A, Zhao C, Liu F (2017) Discriminative spatial-frequency-temporal feature extraction and classification of motor imagery EEG: an sparse regression and weighted naive Bayesian classifier-based approach. J Neurosci Methods 278:13–24
Mirian NS, Sedehi M, Kheiri S, Ahmadi A (2017) Joint prediction of occurrence of heart block and death in patient with myocardial infarction with artificial neural network model. Koomesh 19(1):241–247
Shahnawazuddin S, Sinha R (2017) Sparse coding over redundant dictionaries for fast adaptation of speech recognition system. Comput Speech Lang 43:1–17
Shang R, Wang W, Stolkin R, Jiao L (2016) Subspace learning-based graph regularized feature selection. Knowl Based Syst 112:152–165
Shi Y, Wan Y, Wu K, Chen X (2017) Non-negativity and locality constrained Laplacian sparse coding for image classification. Expert Syst Appl 72:121–129
Tan M, Hu Z, Wang B, Zhao J, Wang Y (2016) Robust object recognition via weakly supervised metric and template learning. Neurocomputing 181:96–107
Tang M, Zhao JY, Tong RF, Manocha D (2012) GPU accelerated convex hull computation. Comput Graph 36(5):498–506
Teng Y, Xie X, Liu Y, Lu B, Guo C, Zhang Y, Kang Y (2017) Smoothing nonnegative matrix factorizations and its application to extraction of time activity curve in dynamic brain pet. J Med Imaging Health Inform 7(1):224–228
Wang Q, Chen F, Gao Q, Gao X, Nie F (2016) On the Schatten norm for matrix based subspace learning and classification. Neurocomputing 216:192–199
Wang T, Zheng W, Wuyun Q, Wu Z, Ruan J, Hu G, Gao J (2017) Pras: prediction of amidation sites using multiple feature extraction. Comput Biol Chem 66:57–62
Wen H, Liu Y, Rekik I, Wang S, Chen Z, Zhang J, Zhang Y, Peng Y, He H (2017) Multi-modal multiple kernel learning for accurate identification of tourette syndrome children. Pattern Recognit 63:601–611
Wen Z, Yin W (2013) A feasible method for optimization with orthogonality constraints. Math Program 142(1–2):397–434
Wold S, Esbensen K, Geladi P (1987) Principal component analysis. Chemom Intell Lab Syst 2(1–3):37–52
Yang Z, Ce L, Lian L (2017) Electricity price forecasting by a hybrid model, combining wavelet transform, arma and kernel-based extreme learning machine methods. Appl Energy 190:291–305
Yu Z, Wang D, You J, Wong HS, Wu S, Zhang J, Han G (2016) Progressive subspace ensemble learning. Pattern Recognit 60:692–705
Zhang C, Gamba IM (2016) A conservative scheme for vlasov poisson landau modeling collisional plasmas. arXiv preprint arXiv:1605.05787
Zhang C, Gamba IM, Ketsdever A, Struchtrup H (2016) Deterministic conservative solver for the inhomogeneous Fokker–Planck–Landau equation coupled with poisson equation. In: AIP conference proceedings, vol. 1786. AIP Publishing, p 180008
Zhang S, Wang J, Tao X, Gong Y, Zheng N (2017) Constructing deep sparse coding network for image classification. Pattern Recognit 64:130–140
Zhang X, Liu Z, Liu S, Li D, Jia Y, Huang P (2017) Sparse coding of 2D-slice zernike moments for SAR ATR. Int J Remote Sens 38(2):412–431
Zhao JY, Tang M, Tong RF (2012) Connectivity-based segmentation for GPU-accelerated mesh decompression. J Comput Sci Technol 27(6):1110–1118
Zhu F, Honeine P (2017) Online kernel nonnegative matrix factorization. Signal Process 131:143–153
Acknowledgements
This work is supported by the Sichuan Provincial Department of Education research project “Under the big data based on the research of heterogeneous data conversion and transmission platform (Grant No. 16ZB0360).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
The authors of this submission are stating no conflict of interests with the work presented in this paper.
Rights and permissions
About this article
Cite this article
Wang, H., Liu, D. & Pu, G. Nuclear reconstructive feature extraction. Neural Comput & Applic 31, 2649–2659 (2019). https://doi.org/10.1007/s00521-017-3220-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-017-3220-4