{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:17:45Z","timestamp":1762341465815,"version":"build-2065373602"},"reference-count":29,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2020,5,22]],"date-time":"2020-05-22T00:00:00Z","timestamp":1590105600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.61901479"],"award-info":[{"award-number":["No.61901479"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>The symmetric positive definite (SPD) matrix has attracted much attention in classification problems because of its remarkable performance, which is due to the underlying structure of the Riemannian manifold with non-negative curvature as well as the use of non-linear geometric metrics, which have a stronger ability to distinguish SPD matrices and reduce information loss compared to the Euclidean metric. In this paper, we propose a spectral-based SPD matrix signal detection method with deep learning that uses time-frequency spectra to construct SPD matrices and then exploits a deep SPD matrix learning network to detect the target signal. Using this approach, the signal detection problem is transformed into a binary classification problem on a manifold to judge whether the input sample has target signal or not. Two matrix models are applied, namely, an SPD matrix based on spectral covariance and an SPD matrix based on spectral transformation. A simulated-signal dataset and a semi-physical simulated-signal dataset are used to demonstrate that the spectral-based SPD matrix signal detection method with deep learning has a gain of 1.7\u20133.3 dB under appropriate conditions. The results show that our proposed method achieves better detection performances than its state-of-the-art spectral counterparts that use convolutional neural networks.<\/jats:p>","DOI":"10.3390\/e22050585","type":"journal-article","created":{"date-parts":[[2020,5,22]],"date-time":"2020-05-22T10:18:18Z","timestamp":1590142698000},"page":"585","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Spectral-Based SPD Matrix Representation for Signal Detection Using a Deep Neutral Network"],"prefix":"10.3390","volume":"22","author":[{"given":"Jiangyi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Meteorology and Oceanography, National University of Defence Technology, Changsha 410073, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7687-7720","authenticated-orcid":false,"given":"Xiaoqiang","family":"Hua","sequence":"additional","affiliation":[{"name":"School of Meteorology and Oceanography, National University of Defence Technology, Changsha 410073, China"}]},{"given":"Xinwu","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Meteorology and Oceanography, National University of Defence Technology, Changsha 410073, China"}]}],"member":"1968","published-online":{"date-parts":[[2020,5,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1109\/26.664294","article-title":"Algorithms for automatic modulation recognition of communication signals","volume":"46","author":"Nandi","year":"1998","journal-title":"IEEE Trans. Commun."},{"key":"ref_2","first-page":"459","article-title":"Automatic modulation classification using zero crossing","volume":"137","author":"Hsue","year":"1990","journal-title":"IEEE Proc."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5884","DOI":"10.1109\/TWC.2009.12.080883","article-title":"On the likelihood-based approach to modulation classification","volume":"8","author":"Hameed","year":"2009","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Reichert, J. (1992, January 23\u201326). Automatic classification of communication signals using higher order statistics. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Philadelphia, PA, USA.","DOI":"10.1109\/ICASSP.1992.226530"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s11263-005-3222-z","article-title":"A Riemannian Framework for Tensor Computing","volume":"66","author":"Pennec","year":"2006","journal-title":"Int. J. Comput. Vis."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2513","DOI":"10.1109\/TCSVT.2017.2729660","article-title":"Geometry-Aware Similarity Learning on SPD Manifolds for Visual Recognition","volume":"28","author":"Huang","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/TPAMI.2017.2655048","article-title":"Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods","volume":"40","author":"Harandi","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Vantzos, O., and Sminchisescu, C. (2015, January 13\u201316). Matrix backpropagation for deep networks with structured layers. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.339"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Herath, S., Harandi, M., and Porikli, F. (2017, January 21\u201326). Learning an invariant hilbert space for domain adaptation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.421"},{"key":"ref_10","unstructured":"Zhang, J., Wang, L., Zhou, L., and Li, W. (2016). Exploiting structure sparsity for covariance-based visual representation. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhou, L., Wang, L., Zhang, J., Shi, Y., and Gao, Y. (2017, January 21\u201326). Revisiting metric learning for SPD matrix based visual representation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.752"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Brooks, D.A., Schwander, O., Barbaresco, F., Schneider, J.Y., and Cord, M. (2019, January 12\u201317). Exploring complex time-series representations for Riemannian machine learning of radar data. Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing, Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8683056"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hua, X., Cheng, Y., Wang, H., and Qin, Y. (2018). Robust Covariance Estimators Based on Information Divergences and Riemannian Manifold. Entropy, 20.","DOI":"10.3390\/e20040219"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hua, X., Fan, H., Cheng, Y., Wang, H., and Qin, Y. (2018). Information Geometry for Radar Target Detection with Total Jensen\u2013Bregman Divergence. Entropy, 20.","DOI":"10.3390\/e20040256"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wong, K., Zhang, J., and Jiang, H. (2016, January 10\u201313). Multi-sensor signal processing on a PSD matrix manifold. Proceedings of the 2016 IEEE Sensor Array and Multichannel Signal Processing Workshop, Rio de Janeiro, Brazil.","DOI":"10.1109\/SAM.2016.7569757"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1016\/j.measurement.2018.08.076","article-title":"A divergence mean-based geometric detector with a pre-processing procedure","volume":"131","author":"Hua","year":"2019","journal-title":"Measurement"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1049\/iet-spr.2016.0547","article-title":"Geometric means and medians with applications to target detection","volume":"11","author":"Hua","year":"2017","journal-title":"IET Signal Process."},{"key":"ref_18","unstructured":"Fathy, M.E., Alavi, A., and Chellappa, R. (2016, January 9\u201315). Discriminative Log-Euclidean Feature Learning for Sparse Representation-Based Recognition of Faces from Videos. Proceedings of the International Joint Conferences on Artificial Intelligence, IJCAI, New York, NY, USA."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, S., Kasiviswanathan, S., Yuen, P.C., and Harandi, M. (2015, January 25\u201330). Online dictionary learning on symmetric positive definite manifolds with vision applications. Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI, Austin, TX, USA.","DOI":"10.1609\/aaai.v29i1.9595"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Huang, Z., and Van Gool, L. (2017, January 4\u20139). A Riemannian Network for SPD Matrix Learning. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.10866"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Dong, Z., Jia, S., Zhang, C., Pei, M., and Wu, Y. (2017, January 4\u20139). Deep manifold learning of symmetric positive definite matrices with application to face recognition. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.11232"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zheng, W., Cui, Z., Zong, Y., Li, C., Zhou, X., and Yang, J. (2020). Deep Manifold-to-Manifold Transforming Network for Skeleton-based Action Recognition. IEEE Trans. Multimed., 1.","DOI":"10.1109\/TMM.2020.2966878"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.patcog.2019.03.007","article-title":"Learning a robust representation via a deep network on symmetric positive definite manifolds","volume":"92","author":"Gao","year":"2019","journal-title":"Pattern Recognit."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/MSP.2017.2693418","article-title":"Geometric Deep Learning: Going beyond Euclidean data","volume":"34","author":"Bronstein","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Pdf ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 8\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_27","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_28","unstructured":"Wang, R., Guo, H., Davis, L.S., and Dai, Q. (2012, January 18\u201320). Covariance discriminative learning: A natural and efficient approach to image set classification. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA."},{"key":"ref_29","unstructured":"(2020, April 20). The McMaster IPIX Radar Sea Clutter Database. Available online: http:\/\/soma.ece.mcmaster.ca\/ipix\/."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/22\/5\/585\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:31:25Z","timestamp":1760175085000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/22\/5\/585"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,22]]},"references-count":29,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2020,5]]}},"alternative-id":["e22050585"],"URL":"https:\/\/doi.org\/10.3390\/e22050585","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2020,5,22]]}}}