Advertisement

Development Age Groups Estimation Method Using Pressure Sensors Array

  • Junjirou Hasegawa
  • Takuya Tajima
  • Takehiko Abe
  • Haruhiko Kimura
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 253)

Abstract

This paper aims to estimate age groups by walking data using pressure sensors array. Techniques of the age groups estimation in many retail businesses (for example, convenience stores, supermarkets, shopping malls, etc.) are marketable. There are many researches of the age estimation using face images, walking silhouette data, etc. However, there are some problems too. One of problem is that the estimation classes are a few. Moreover, many age estimation systems use some video cameras. Therefore, these systems may invade surveyed person’s privacy by taking one’s face images. In this study, this fact is one of merit in using the pressure sensors. The pressure sensors array gets feature quantity including center of gravity, pressure value, etc. In this study, our system classifies surveyed persons to 7 age groups as each decade. Here, surveyed persons are 20–80 s. Average estimation accuracy of all age groups is 72.86 %. The highest estimation accuracy is 86.67 % at 70 s.

Keywords

Marketing Age estimation Walking data Pressure sensors 

References

  1. 1.
    Cabinet Office in Japan (2012) White paper on aging society (in Japanese)Google Scholar
  2. 2.
    Guadagni PM, Littlem JDC (1983) A logit model of brand choice calibrated on scanner data. Mark Sci 2:203–238CrossRefGoogle Scholar
  3. 3.
    Gupta S (1988) Impact sales promotions on when, what, and how much to buy. J Mark Res 25:342–355CrossRefGoogle Scholar
  4. 4.
    Hamuro et al (1998) Mining pharmacy data helps to make profits. Data Min Knowl Discov 2:391–398Google Scholar
  5. 5.
    Lantis A, Draganova C, Christodoulou C (2004) Comparing different classifiers for automatic age estimation. IEEE Trans Syst Man Cybern B 34(1):621–628Google Scholar
  6. 6.
    Lu J, Tan Y-P (2010) Ordinary preserving manifold analysis for human age estimation. In: IEEE computer society and IEEE biometrics council workshop on biometrics 2010, San Francisco, CA, USA, pp 1–6Google Scholar
  7. 7.
    Davis J (2001) Visual categorization of children and adult walking style. In: Proceedings of the international conference on audio- and video- based biometric Pearson authentication, pp 295–300Google Scholar
  8. 8.
    Begg R (2005) Support vector machine for automated gait classification. IEEE Trans Biomed Eng 52(5):828–839Google Scholar
  9. 9.
    Mannami H, Makihara Y, Yagi Y (2010) Gait analysis of gender and age using a large-scale multi-view gait database. In: Proceedings of the 10th Asian conference on computer vision, Queenstown, New Zealand, Nov 2010, pp 975–986Google Scholar
  10. 10.
  11. 11.
  12. 12.
    Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machine and other kernel based learning methods. Cambridge University Press, New YorkGoogle Scholar
  13. 13.
    Tsuda K (2000) What is support vector machine. IEICE Trans 83(6):460–466Google Scholar
  14. 14.
    Pontil M (1998) Support vector machines for 3D object recognition. IEEE Trans PAMI 20(6):637–646Google Scholar
  15. 15.
    Vapnik V (1995) The nature of statistical learning theory, statistics for engineering and information science. Springer, New York Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  • Junjirou Hasegawa
    • 1
  • Takuya Tajima
    • 1
  • Takehiko Abe
    • 2
  • Haruhiko Kimura
    • 3
  1. 1.FukuokaJapan
  2. 2.AichiJapan
  3. 3.IshikawaJapan

Personalised recommendations