Abstract—Our preceding study proposed the possibility of
producing video previews that enhance viewer motivations
towards assembly work in practical training classes by picking
scenes of work situations with good performance from the
videos of past classes. In the study, two conceptual attributes for
categorizing work situations from the viewpoint of the
performance were introduced with reference to previous studies
for evaluating productivity of human intellectual work with
computers. Based on those two conceptual attributes, our
preceding study employed observable features for estimating
work situations in the videos and showed that those features
seem to reflect the difference of work situations with respect to
the conceptual attributes. However, quantitative precision for
estimating work situations from those features has not yet been
evaluated. Moreover, those observable features are employed
without considering whether humans actually pay attention to
them. It is also not clear whether videos with work situations
sufficient for each of the conceptual attributes actually enhance
viewer motivations towards the work. This article clarifies these
issues based on our recent experimental results with
experimental participants.
Index Terms—Practical training class, assembly task, work
situation estimation, observable feature, physical activity,
mental concentration.
Kai Okamoto, Koh Kakusho, and Michiya Yamamoto are with School of
Science and Technology, Kwansei Gakuin University, Sanda, Japan (e-mail:
{kaisea, kakusho, michiya.yamamoto}@kwansei.ac.jp).
Takatsugu Kojima is with Faculty of Medicine, Shiga University of
Medical Science, Otsu, Japan (e-mail: kojima@kojima-lab.net).
Masayuki Murakami is with Research Center for Multi-Media Education,
Kyoto University of Foreign Studies, Kyoto, Japan (e-mail:
masayuki@murakami-lab.org).
Cite: K. Okamoto, K. Kakusho, M. Yamamoto, T. Kojima, and M. Murakami, "Estimating Work Situations from Videos of Practical Training Classes with Assembly Tasks," International Journal of Information and Education Technology vol. 8, no. 1, pp. 38-45, 2018.