Xintao Qiu
Department of Automation, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, People Republic of China
Dongmei Fu
Department of Automation, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, People Republic of China
Tao Yang
Department of Automation, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, People Republic of China
ABSTRACT
Current data analysis methods in processing sensor data, does not take into account the different contribution between the new data and the old data for the whole dataset, which fails to reflect the importance of new data. In this paper, a recent-biased dimensionality reduction method is proposed for sensor data analysis, which uses a multilinear dimensionality reduction learning algorithm with forgetting factor introduced. With the proposed dimensionality reduction method, the impact of the new sample data for the future trend of sensor data is highlighted, which can avoid the dilemma of data saturation phenomenon; the sensor data is organized into high order tensor pattern, which keeps the original structure, discriminates information and integrity of the data. Moreover, in order to evaluate the proposed dimensionality reduction method, a new framework of datasets quality assessment is introduced. The experiment results show that, compared with principal component analysis and multilinear principal component analysis, the proposed novel dimensionality reduction method can be more effectively applied to analyzing the sensor data.
PDF References Citation
How to cite this article
Xintao Qiu, Dongmei Fu and Tao Yang, 2013. A Novel Recent-biased Dimensionality Reduction Framework for Sensor Data
Analysis. Journal of Applied Sciences, 13: 2781-2787.
DOI: 10.3923/jas.2013.2781.2787
URL: https://scialert.net/abstract/?doi=jas.2013.2781.2787
DOI: 10.3923/jas.2013.2781.2787
URL: https://scialert.net/abstract/?doi=jas.2013.2781.2787
REFERENCES
- Tao, D., X. Li, X. Wu, W. Hu and S.J. Maybank, 2007. Supervised tensor learning. Knowledge Inform. Syst., 13: 1-42.
CrossRef - Doulamis, A., N. Doulamis, K. Ntalianis and S. Kollias, 2003. An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture. IEEE Trans. Neural Networks, 14: 616-630.
CrossRef - Fawcett, T., 2006. An introduction to ROC analysis. Pattern Recognit. Lett., 27: 861-874.
CrossRefDirect Link - Hand, D.J. and R.J. Till, 2001. A simple generalisation of the area under the roc curve for multiple class classification problems. Mach. Learn., 45: 171-186.
CrossRef - Khedr, M.E. and A.K. Mahmoud, 2012. Achieving scalability in wireless sensor network using hexagonal multi-layer grid data dissemination approach. J. Applied Sci., 12: 1982-1994.
CrossRefDirect Link - Kudo, M., N. Masuyama, J. Toyama and M. Shimbo, 2003. Simple termination conditions for k-nearest neighbor method. Pattern Recognit. Lett., 24: 1203-1213.
CrossRef - Lathauwer, L.D., B. De Moor and J. Vandewalle, 2000. On the best rank-1 and rank-(R1 ,R2 ,..,RN) approximation of higher-order tensors. SIAM J. Matrix Anal. Appl., 21: 1324-1342.
CrossRef - Le Borgne, Y.A., S. Raybaud and G. Bontempi, 2008. Distributed principal component analysis for wireless sensor networks. Sensors, 8: 4821-4850.
CrossRef - Li, X.R., Y. Lu, J.M. Zhou and Y.J. Wang, 2011. Galaxy/quasar classification based on nearest neighbor method. Spectrosc. Spectral Anal., 31: 2582-2585.
PubMed - Lu, H., K.N. Plataniotis and A.N. Venetsanopoulos, 2008. MPCA: Multilinear principal component analysis of tensor objects. IEEE Trans. Neural Networks, 19: 18-39.
CrossRef - Lu, H., K.N. Plataniotis and A.N. Venetsanopoulos, 2011. A survey of multilinear subspace learning for tensor data. Pattern Recognit., 44: 1540-1551.
CrossRef - Nielsen, A.A., 2002. Multiset canonical correlations analysis and multispectral, truly multitemporal remote sensing data. IEEE Trans. Image Process., 11: 293-305.
CrossRef - Paleologu, C., J. Benesty and S. Ciochina, 2008. A robust variable forgetting factor recursive least-squares algorithm for system identification. IEEE Signal Process. Lett., 15: 597-600.
CrossRef - Phithakkitnukoon, S. and C. Ratti, 2010. A recent-pattern biased dimension-reduction framework for time series data. J. Adv. Inform. Technol., 1: 160-180.
CrossRef - Rittner, L., F.C. Flores and R.A. Lotufo, 2010. A tensorial framework for color images. Pattern Recognit. Lett., 31: 277-296.
CrossRef - Sikirzhytski, V., K. Virkler and I.K. Lednev, 2010. Discriminant analysis of raman spectra for body fluid identification for forensic purposes. Sensors, 10: 2869-2884.
CrossRef - Tuah, N., M. Ismail and K. Jumari, 2012. An energy-efficient node-clustering algorithm in heterogeneous wireless sensor networks: A survey. J. Applied Sci., 12: 1332-1344.
CrossRefDirect Link - Younis, M., O. Farrag and B. Althouse, 2012. TAM: A tiered authentication of multicast protocol for ad-hoc networks. IEEE Trans. Network Serv. Manag., 9: 100-113.
CrossRef - Yu, H., Y. Wang and J. Wang, 2009. Identification of tea storage times by linear discrimination analysis and back-propagation neural network techniques based on the eigenvalues of principal components analysis of e-nose sensor signals. Sensors, 9: 8073-8082.
CrossRef - Zalik, K.R., 2008. An efficient k'-means clustering algorithm. Pattern Recognit. Lett., 29: 1385-1391.
CrossRef - Zhao, X. and S. Zhang, 2011. Facial expression recognition based on local binary patterns and kernel discriminant isomap. Sensors, 11: 9573-9588.
CrossRef