The week's pick
Reseach Article
Comparative Study of different Methodologies to Predict Human Character
| International Journal of Applied Information Systems |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 8 - Number 4 |
| Year of Publication: 2015 |
| Authors: Ankur M. Bobade, N. N. Khalsa |
10.5120/ijais15-451301
|
Ankur M. Bobade, N. N. Khalsa . Comparative Study of different Methodologies to Predict Human Character. International Journal of Applied Information Systems. 8, 4 ( February 2015), 8-13. DOI=10.5120/ijais15-451301
Abstract
Realistic data modeling can be used to predict human performance and explore the relationships between diverse sets of variables. A major challenge of realistic data modeling is how to simplify or anticipate the findings with a limited amount of pragmatic data to a broader perspective. In this paper, the individuality of some of the categorization methods that have been effectively applied to handwritten script recognition and results of SVM and ANNs categorization method, applied on handwritten script. After preprocessing the handwritten image the psychological individuality in the writing namely size, slant and pressure, baseline, number of breaks, margins, speed of writing and spacing between the words is extracted. These attributes are subsequently provided to Neural classifier and into support vector machine for categorization. In neural classifier, it is discovered that three ways of combining decisions of various MLP's, designed for various attributes. To exhibit the method and the value of modeling human performance with SVM, SVM applied to a real world human factors problem of identification of character of a person. The results specify that the SVM based model of person's character detection gives good performance. Various propositions on modeling human character by using SVM have been discussed. From machine learning an approach is introduced, known as support vector machine (SVM), which can help deal with this challenge.
References
- C. Wu, Y. Liu, and C. Walsh, "Queueing network modeling of a realtime psychophysiological index of mental workload—P300 in evoked brain potential (ERP)," IEEE Trans. Syst. , Man, Cybern. A, Syst. , Humans, vol. 38, no. 5, pp. 1068–1084, Sep. 2008.
- Y. Liu, R. Feyen, and O. Tsimhoni, "Queueing network-model human processor (QN-MHP): A computational architecture for multitask performance," ACM Trans. Hum. Comput. Interact, vol. 13, no. 1, pp. 37–70, Mar. 2006.
- L. Allender, "Modeling human performance: Impacting system design, performance, and cost," in Proc. Mil. , Gov. Aerosp. Simul. Symp. , Adv. Simul. Technol. Conf. , Washington, DC, 2000, pp. 139–144.
- Y. Liu, "Queuing network modeling of elementary mental processes," Psychol. Rev. , vol. 103, no. 1, pp. 116–136, Jan. 1996.
- Champa H. N. and K. R. Ananda Kumar. 2010. Automated Human Behavior Prediction through Handwriting Analysis. First International Conference on Integrated Intelligent Computing.
- Ball G. R. , Stittmeyer R. and Srihari S. N. 2010. Writer verification in historical documents. Proceedings Document Recognition and Retrieval XVII San Jose, CA, SPIE.
- Champa H N and K R Ananda Kumar. Handwriting Analysis for Writer's Personality Prediction. Intl. Conference on Biometric Technologies and Applications- the Indian perspective. Biometrics India Expo New Delhi India. pp. 182-191.
- K. A. Gluck and R. Pew, Modeling Human Behavior With Integrated Cognitive Architectures: Comparison, Evaluation, and Validation. Mahwah, NJ: Lawrence Erlbaum, 2005.
- M. Bauerly and Y. L. Liu, "Computational modeling and experimental investigation of effects of compositional elements on interface and design aesthetics," Int. J. Hum. -Comput. Stud. , vol. 64, no. 8, pp. 670–682, Aug. 2006.
- Z. Liu, R. E. Torres, N. Patel, and Q. Wang, "Further development of input-to-state stabilizing control for dynamic neural network systems," IEEE Trans. Syst. , Man, Cybern. A, Syst. , Humans, vol. 38, no. 6, pp. 1410–1433, Nov. 2008.
- E. Asua, V. Etxebarria, and A. Garcia-Arribas, "Neural network-based micropositioning control of smart shape memory alloy actuators," Eng. Appl. Artif. Intell. , vol. 21, no. 5, pp. 796–804, Aug. 2008.
- A. Cevik, M. A. Kutuk, A. Erklig, and I. H. Guzelbey, "Neural network modeling of arc spot welding," J. Mater. Process. Technol. , vol. 202, no. 1–3, pp. 137–144, Jun. 2008.
- S. J. Wu, N. Gebraeel, M. A. Lawley, and Y. Yih, "A neural network integrated decision support system for condition-based optimal predictive maintenance policy," IEEE Trans. Syst. , Man, Cybern. A, Syst. , Humans, vol. 37, no. 2, pp. 226–236, Mar. 2007.
- S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd. Englewood Cliffs, NJ: Prentice-Hall, 1998.
- O. Bousquet, S. Boucheron, and G. Lugosi, "Introduction to statistical learning theory," in Advanced Lectures on Machine Learning. New York: Springer-Verlag, 2004, pp. 169–207.
- M. Cimen, "Estimation of daily suspended sediments using support vector machines," Hydrol. Sci. J. , vol. 53, no. 3, Jun. 2008.
- V. Vapnik, The Nature of Statistical Learning Theory. New York: Springer Verlag, 1995.
- V. Vapnik, Statistical Learning Theory. New York: Wiley, 1998.
- C. J. C. Burges, "A tutorial on support vector machines for pattern recognition," Data Mining Knowl. Discovery, vol. 2, no. 2, Jun. 1998.
- O. Bunke and B. Droge, "Bootstrap and cross-validation estimates of the prediction error for linear regression models," Ann. Statist. , vol. 12, no. 4, pp. 1400–1424, Dec. 1984.
- D. J. Spitzner, "Constructive cross-validation in linear prediction," Commun. Statist. —Theory Methods, vol. 36, no. 5, pp. 939–953, Apr. 2007.
- A. J. Smola and B. Scholkopf, "A tutorial on support vector regression," Statist. Comput, vol. 14, no. 3, Aug. 2004.
- C. L. Liu, K. Marukawa, Handwritten numeral string recognition: character level training vs. string level training, Proc. 7th ICPR, Cambridge, UK, 2004,Vol. 1.
- C. C. Chang and C. J. Lin, LIBSVM, A Library for Support-Vector-Machines. Available: http://www. csie. ntu. edu. tw/~cjlin/libsvm/
- J. Franke, Isolated handprinted digit recognition, Handbook of Character Recognition and Document Image Analysis.
Index Terms
Keywords