Abstract
Locally linear embedding algorithm (LLE) is needed to be improved, since there were redundant information in its low dimensional feature space and no category information of the samples embedded into the low dimensional [1,2]. In this paper, we introduce a local linear maximum dispersion matrix algorithm (FSLLE), which integrated the sample category information. On this basis, the algorithm of locally linear embedding was improved and reexamined from the perspective of uncorrelated statistics. A kind of uncorrelated statistical with maximum dispersion matrix algorithm of locally linear embedding (OFSLLE) is proposed, with the application of elimination of redundant information among base vectors. Our algorithm was verified using the face library, showing that the base vector using uncorrelated constraints can effectively improve the performance of the algorithm and improve the recognition rate.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kouropteva, O., Okun, O., et al.: Incremental Locally Linear Embedding Algorithm. J. Pattern Recognition 38(10), 1764–1767 (2005)
Zheng, J.: One Improved LLE Method. J. Journal of Hunan Institute of Science and Technolohy 20, 30–32 (2007)
Roweis, S.T., Saul, L.K.: Nonlinear Dimensionality Reduction by Locally Liner Embedding. Science 290(5500), 2323–2326 (2000)
An introduction to locally linear embedding, http://www.cl.cam.ac.uk/Research/DTG/attar2chive:pub/data/att_faces.zip.
Ridder, K., Okun, O., et al.: Supervised Locally Linear Embedding. J. Artificial Neural Networks and Neural Information Processing 2714, 333–341 (2003)
Ming, Z.: Maximum Scatter Matrix Algorithm Based on Local Linear. J. Computer Engineering 37, 176–180 (2011)
Yang, M.: Research on Feature Extraction with Correlation Projection Analysis and Its Applications. NanJing Uniersity of Science and Technology, Nan Jing (2010)
Weinberger, K.Q., Saul, L.K.: Distance Metric Learning for Large Magin Nearest Nerghbor Class-Sification. J. Journal of Machine Learning Research 10, 207–244 (2009)
Wang, X., Miao, Y., Cheng, M.: Finding Motifs in DNA Sequences Using Low-Dispersion Sequences. Journal of Computational Biology 21(4), 320–329 (2014)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Deng, T., Deng, Y., Shi, Y., Zhou, X. (2014). Research on Improved Locally Linear Embedding Algorithm. In: Pan, L., Păun, G., Pérez-Jiménez, M.J., Song, T. (eds) Bio-Inspired Computing - Theories and Applications. Communications in Computer and Information Science, vol 472. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45049-9_15
Download citation
DOI: https://doi.org/10.1007/978-3-662-45049-9_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-45048-2
Online ISBN: 978-3-662-45049-9
eBook Packages: Computer ScienceComputer Science (R0)