A Mechanical Method for Evaluating Trainee Answers in a Risk Prediction Training System Based on the 4R Method
Abstract
The 4R training method is used to train workers in many industrial workplaces, to reduce accidents caused by human factors. The 4R training method enables trainees to develop their hazard prediction abilities and response capabilities to avoid hazardous situations. In general, this training involves identifying hazards shown in hazard prediction training sheets. However, there is a significant problem with the 4R method: a single trainee cannot train themselves using the 4R method, because this training requires the assistance of an expert instructor. To solve this problem, this study aims to develop a hazard prediction training system. This system enables trainees to use the 4R method to train themselves anytime and anywhere. This paper provides a summary of the proposed training system, which uses a machine learning method to generate a subsystem for evaluating the trainee answers. Experimental results show the accuracy rates (precision) for two sheets were 64±14 [%] and 70±12 [%].
References
M. J. Burke, S. A. Sarpy, K. Smith-Crowe, S. Chan-Serafin, R. O. Salvador, and G. Islam, “Relative effectiveness of worker safety and health training methods,” Am. J. Public Health, vol. 96, no. 2, Feb. 2006, pp. 315–324.
E. S. Wallen and K. B. Mulloy, “Computer-based training for safety: Comparing methods with older and younger workers,” Journal of Safety Research, vol. 37, no. 5, 2006, pp. 461–467.
Japan industrial Safety & Health Association, Zero Accident movement Q & A for the hazard prediction activities trainer [Japanese]. Japan industrial Safety & Health Association, 2003.
Japan industrial Safety & Health Association, Ed., Hazard prediction training [Japanese]. Japan industrial Safety & Health Association, 2011.
H. Araki, H. Minowa, and Y. Munesawa, “Research of questions and answers judgment technique to develop 4R risk prediction training system,” in Proceedings of the 3rd Asian Conference on Technology in the Classroom (ACTC). Infoar, Mar. 2013, pp. 279–287.
H. Minowa, H. Fujimoto, and K. Takeuchi, “Automatic evaluation methods of trainee’s answers to develop a 4R risk prediction training system,” in Proceedings of the 4th IIAI International Congress on Advanced Applied Informatics, Okayama Convention Center, Okayama, Japan, Jul. 2015, pp. 283–286.
K. Watanabe, “A study on needs for e-learning-through the analysis of national survey and case studies,” Prog. Inform., no. 2, 2005, p. 77.
S. Graf and Kinshuk, “Adaptivity and personalization in ubiquitous learning systems,” in Springer Berlin Heidelberg, ser. Lecture Notes in Computer Science (LNCS), vol. 5298. USAB 2008, Graz, Austria: Springer Berlin Heidelberg, Nov. 2008, pp. 331–338.
M. Cha, S. Han, J. Lee, and B. Choi, “A virtual reality based fire training simulator integrated with fire dynamics data,” Fire Saf. J., vol. 50, May 2012, pp. 12–24.
N. Kishida, H. Minowa, Y. Munesawa, and K. Suzuki, “Proposal for branch criteria for training depending on educational purpose in chemical plant,” in Proceedings of Asia Pacific Symposium on Safety (APSS), ser. English, Oct. 2011, pp. 373–376.
B. Schwald and B. d. Laval, “An augmented reality system for training and assistance to maintenance in the industrial context,” J. WSCG, vol. 11, no. 1-3, Feb. 2003, pp. 3–7.
H. Minowa, M. Nakao, and K. Minato, “A method for sharing hapic information in manipulating virtual elastic objects [japanese],” Jpn. Soc. Med. Virtual Real. JSMVR, vol. 5, no. 1, 2007, pp. 17–23.
H. Minowa, “Image recognition method which measures angular velocity from a back of hand for developing a valve UI,” in Proceedings of the second international conference on Human-agent interaction, Tsukuba, Japan, Oct. 2014, pp. 125–128.
Japan industrial Safety & Health Association, Illustration sheets for hazard prediction training –traffic edition- [Japanese]. Japan industrial Safety & Health Association, Jan. 2013.
Japan industrial Safety & Health Association, Ed., KYT illustrations sheet collection of ready-to-use. Japan industrial Safety & Health Association, Apr. 2014.
T. Kudo, K. Yamamoto, and Y. Matsumoto, “Applying conditional random fields to japanese morphological analysis,” in Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP-2004), 2004, pp. 230–237.
R. Kohavi, “A study of cross-validation and bootstrap for accuracy estimation and model selection,” in International Joint Conference on Artificial Intelligence, vol. 14, 1995, pp. 1137–1143.
C.-C. Chang and C.-J. Lin, “LIBSVM: A library for support vector machines,” ACM Trans. Intell. Syst. Technol., vol. 2, no. 3, Apr. 2011, pp. 1–27.
