Analysis of Behaviors by Audience in Lectures by Using Time-series Models

Eiji Watanabe, Takashi Ozeki, Takeshi Kohama

Abstract

In this paper, the dominant behaviors defined by the face direction of the speaker and audience in lectures are analyzed by using the time-series models. First, we detect the face region of the speaker and audience by the image processing and we adopt the number of skin-colored pixels in face region as features for behaviors by them. Next, we construct piecewise time series models for behaviors by the speaker and audience. Finally, we analyze the synchronization phenomena in speaker and audience by comparing time series models. Concretely, we show that the parameters in the time series models denote the dominant section in lectures. Moreover, we discuss the relationships among notes, test and behaviors by audience.

References

  1. E. Watanabe, N. N. and Mitani, Y. (1997). A prediction method of non-stationary time series data by using a modular structured neural network. In IEICE Trans. Fundamentals, volume E80-A, pages 971-976.
  2. E. Watanabe, T. O. and Kohama, T. (2011a). Analysis of behaviors by lecturer and students in lectures based on piecewise auto-regressive modeling. In Proc. of 2011 IEEE International Conference on Intelligent Computer Communication and Processing, pages 385- 390.
  3. E. Watanabe, T. O. and Kohama, T. (2011b). Extraction of relations between lecturer and students by using multi-layered neural networks. In Proc. of IMAGAPP 2011. SCITEPRESS.
  4. Hatakeyama, M. and Mori, K. (2001). Interaction between gesture and eye contact in communication - developmental investigation of eye contact and gesture -. In Memoirs of the College of Education, Akita University, volume 56, pages 69-75.
  5. Iso, K. (2011). Effects of nonverbal behaviors on the perception of “skillfulness of speech” - focusing on gestures during speech -. In Japanese Journal of Interpersonal and Social Psychology, volume 4, pages 133-146.
  6. Land, M. F. and Taters, B. W. (2009). Looking and Acting - Vision and Eye Movements in Natural Behaviour -. Oxford University Press.
  7. T. Marutani, Y. Sugimoto, K. K. and Minoh, M. (2007). Lecture context recognition base on statistical feature of lecture action for automatic video recording. In IEICE Trans. Information and Systems, volume 90-D, pages 2775-2786.
  8. Y. Miyanaga, N. Miki, N. N. and Hatori, K. (1991). Adaptive simultaneous estimation of time variable autoregressive and moving-average parameters. In IEICE Trans. Fundamentals, volume J64-A, pages 308-315.
  9. Y. Miyoshi, K. Yamamoto, M. Y. and Kakusho, O. (1987). Analysis of speech signals of short pitch period by a two-stage sample-selective linear prediction. In IEICE Trans. Fundamentals, volume J70-A, pages 1146- 1156.
Download


Paper Citation


in Harvard Style

Watanabe E., Ozeki T. and Kohama T. (2014). Analysis of Behaviors by Audience in Lectures by Using Time-series Models . In Proceedings of the 6th International Conference on Computer Supported Education - Volume 1: CSEDU, ISBN 978-989-758-020-8, pages 191-196. DOI: 10.5220/0004787801910196


in Bibtex Style

@conference{csedu14,
author={Eiji Watanabe and Takashi Ozeki and Takeshi Kohama},
title={Analysis of Behaviors by Audience in Lectures by Using Time-series Models},
booktitle={Proceedings of the 6th International Conference on Computer Supported Education - Volume 1: CSEDU,},
year={2014},
pages={191-196},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004787801910196},
isbn={978-989-758-020-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Computer Supported Education - Volume 1: CSEDU,
TI - Analysis of Behaviors by Audience in Lectures by Using Time-series Models
SN - 978-989-758-020-8
AU - Watanabe E.
AU - Ozeki T.
AU - Kohama T.
PY - 2014
SP - 191
EP - 196
DO - 10.5220/0004787801910196