Self-adaptive Differential Evolutionary Extreme Learning Machine and Its Application in Facial Age Estimation

Ku, Junhua; Xing, Kongduo

doi:10.21307/ijanmc-2017-031

Abstract

In this paper, Self-adaptive Differential Evolutionary Extreme Learning Machine (SaDE-ELM) was proposed as a new class of learning algorithm for single-hidden layer feed forward neural network (SLFN). In order to achieve good generalization performance, SaDE-ELM calculates the error on a subset of testing data for parameter optimization. Since SaDE-ELM employs extra data for validation to avoid the over fitting problem, more samples are needed for model training. In this paper, the cross-validation strategy is proposed to be embedded into the training phase so as to solve the overtraining problem. Experimental results demonstrate that the proposed algorithms are efficient for Facial Age Estimation.

References

A. Lanitis, C. Draganova, and C. Christodoulou. Comparing different classifiers for automatic age estimation. IEEE Trans. Syst. Man Cybern. B, 34(1):621–628, 2004.
Search in Google Scholar Back to article
A. Lanitis, C. J. Taylor, and T. F. Cootes. Toward automatic simulation of aging effects on face images. TPAMI, 24(4):442–455, 2002.
Search in Google Scholar Back to article
Huang GB, Zhu QY, Siew CK. Extreme learning machine: a new learning scheme of feedforward neural networks. In: Proceedings of international joint conference on neural networks (IJCNN2004), vol 2, no 25–29, pp 985–990.
Search in Google Scholar Back to article
Huang GB, Zhu QY, Siew CK. Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501.
Search in Google Scholar Back to article
Espana-Boquera S, Zamora-Martnez F, Castro-Bleda M J, et al. Efficient BP algorithms for general feedforward neural networks[C]//International Work-Conference on the Interplay Between Natural and Artificial Computation. Springer Berlin Heidelberg, 2007: 327-336.
Search in Google Scholar Back to article
G. Thatte, U. Mitra, and J. Heidemann, “Parametric methods for anomaly detection in aggregate traffic,” IEEE/ACM Transactions on Networking, vol. 19, no. 2, pp. 512–525, April 2011.
Search in Google Scholar Back to article
M. Qin and K. Hwang, “Frequent episode rules for internet anomaly detection,” in Proceedings of the Network Computing and Applications, Third IEEE International Symposium. Washington, DC, USA: IEEE Computer Society, 2004, pp. 161–168.
Search in Google Scholar Back to article
X. He, C. Papadopoulos, J. Heidemann, U. Mitra, and U. Riaz, “Remote detection of bottleneck links using spectral and statistical methods,” Computer Networks, vol. 53, pp. 279–298, February 2009.
Search in Google Scholar Back to article
W. W. Streilein, R. K. Cunningham, and S. E. Webster, “Improved detec- tion of low-profile probe and denial-of-service attacks,” in Proceedings of the 2001 Workshop on Statistical and Machine Learning Techniques in Computer Intrusion Detection, June 2001.
Search in Google Scholar Back to article
C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, pp. 273–297, 1995.
Search in Google Scholar Back to article
G.-B. Huang, D. H. Wang, and Y. Lan, “Extreme learning machines: a survey,” International Journal of Machine Leaning and Cybernetics, vol. 2, no. 2, pp. 107–122, 2011.
Search in Google Scholar Back to article
G. Tandon, “Weighting versus pruning in rule validation for detecting network and host anomalies,” in In Proceedings of the 13th ACM SIGKDD international. ACM Press, 2007.
Search in Google Scholar Back to article
Y. Liao and V. R. Vemuri, “Use of k-nearest neighbor classifier for intrusion detection,” Computers & Security, vol. 25, pp. 439–448, 2002.
Search in Google Scholar Back to article
Storn R, Price K (2004) Differential evolution—a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 11(4):341–359
Search in Google Scholar Back to article
Ilonen J, Kamarainen JI, Lampinen J (2003) Differential evolution training algorithm for feedforward neural networks. Neural Process Lett 17:93–105
Search in Google Scholar Back to article
Subudhi B, Jena D (2008) Differential evolution and levenberg marquardt trained neural network scheme for nonlinear system identification. Neural Process Lett 27:285–296.
Search in Google Scholar Back to article
P. Viola and M. J. Jones. Robust real-time face detection. IJCV, 57(2):137–154, 2004.
Search in Google Scholar Back to article
[18] M. Mathias, R. Benenson, M. Pedersoli, and L. Van Gool. Face detection without bells and whistles. In ECCV, 2014, pages 720–735.
Search in Google Scholar Back to article
S. Escalera, M. Torres, B. Martnez, X. Bar, H. J. Escalante, I. Guyon, G. Tzimiropoulos, C. Corneanu, M. Oliu, M. A. Bagheri, and M. Valstar. Chalearn looking at people and faces of the world: Face analysis workshop and challenge 2016. In ChaLearn Looking at People and Faces of the World, CVPRW, 2016
Search in Google Scholar Back to article

Self-adaptive Differential Evolutionary Extreme Learning Machine and Its Application in Facial Age Estimation

Abstract

Paradigm

My account