User Behavior Prediction with SVM for Garment Ordering System
In this paper, a iPAD based garment ordering system is first developed via support vector machine (SVM) learning algorithm. The garment ordering system is introduced with its development history and current situation. SVM algorithm has the advantages of pattern recognition which is used to deal with the binary issues for the user selection. From the perspective of requirement of the ordering meeting, the ordering system is designed and accomplished with module decomposition. The data are collected from the central unit of actual ordering meetings and uploaded in the system based on the potential selection so as to reduce the loading pressure and waiting time of the end users. Experiments are performed to testify the efficacy of the proposed algorithm for users behaviour prediction with higher system performance and user satisfaction.
KeywordsSupport vector machine User behaviour prediction Garment ordering system iPAD
This work is supported under the Shenzhen Science and Technology Innovation Commission Project Grant Ref. JCYJ20160510154736343 and JCYJ201703071654 42023, and Guangdong Provincial Engineering Technology Research Center of Intelligent Unmanned System and Autonomous Environmental Perception.
- 1.Z. Dong, The user behaviour preference of mobile internet based support vector machine. Beijing University of Posts and Telecommunications. Ph.D. Thesis, in Chinese, 2014Google Scholar
- 2.V. Geetha, K.A. Rangarajan, A conceptual Framework for Perceived Rish in Consumer Online Shopping. Glob. Manag. Rev. (2015)Google Scholar
- 4.B. Schölkopf, C. Burges, V. Vapnik, Incorporating invariances in support vector learning machines, in International Conference on Artificial Neural Networks (1996), pp. 47–52Google Scholar
- 6.J. Hauschild, A. Kazeminia, A. Braasch, Reliability prediction for automotive components using Real-Parameter Genetic Algorithm, in Proceedings of the Joint ESREL and SRA-Europe Conference, vol. 3 (2009), pp. 2245–2249Google Scholar
- 7.M. Nguyen, J. Perez, F. De La Torre, Facial feature detection with optimal pixel reduction SVM, in The 8th IEEE International Conference on Automatic Face and Gesture Recognition, Article number: 4813372 (2008)Google Scholar
- 8.C. Chen, H. Lee, M. Kao, Multi-class SVM with negative data selection for web page classification, in IEEE International Conference on Neural Networks vol. 3 (2004), pp. 2047–2052Google Scholar
- 9.A. Braun, U. Weidner, S. Hinz, Classifying roof materials using data fusion through kernel composition—Comparing v-SVM and one-class SVM, inProceedings of the Joint Urban Remote Sensing Event (2011), pp. 377–380Google Scholar
- 10.S. Watanabe, Y. Kimura, A methodology using EMO for parameter estimation of SVM kernel function, in Proceedings of the IEEE Conference on Soft Computing on Industrial Applications (2008), pp. 211–216Google Scholar
- 13.N. Zhang, C. Williams, P. Behera, Water quantity prediction using least squares support vector machines (LS-SVM) method, in Proceedings of the 18th World Multi-Conference on Systemics, Cybernetics and Informatics, (2014), pp. 251–256Google Scholar