Study on Pilot Performance Model

Abstract:

In order to evaluate pilot performance objectively, back propagation (BP) neural network model of 621423 form in topology with eye movement data was established. Data source of BP neural networks that came from former experiment and random interpolation was divided into training set and test set and normalized. Based on neural networks toolbox in Matlab, hidden layer nodes of BP networks were determined with empirical formula and experimental comparison ; BP algorithms in the toolbox were optimized; The training set data and test data were input into model for training and simulation; Pilot performance of the three skill levels was predicated and evaluated. The research shows that pilot performance can be accurately evaluated by setting up BP neural networks model with eye movement data and the evaluation method can provide a reference for flight training.

• Periodical: Advanced Materials Research (Volumes 383-390)
• Pages: 2545-2549
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.383-390.2545
• Online since: November 2011
• Authors: Wei Liu, Cheng Kun Liu, Da Min Zhuang, Zhong Qi Liu, Xiu Gan Yuan
• Keywords: Evaluation, Eye Movement, Pilot Performance

References

[1] Johnson N R, Rantanen E M. Objective p ilot performance measurement: a literature review and taxonomy of metrics [C]/ /Proceedings of the 13th International Symposium on Aviation Psychology. Dayton, OH: Wright State University, 2005: 283 – 288.

[2] Kasarskis P, Stehwien J, Hickox J, et al. Comparison of expert and novice scan behaviors during VFR flight [EB/OL]. Columbus, OH: The Ohio State University, (2001).

http: / /www. humanfactors. illinois. edu /Reports&PapersPDFs/isapol/p rocedo1. Pdf.

[3] Han Liqun. Atificial neural networks theory, design and app lication[M]. Beijing: Chemical Industry Press, 2002: 1-2 (in Chinese).

[4] Liu Zhongqi, Yuan Xiugan, Fan Yubo, et al. Comparison of expert and novice eye movement behaviors during simulated landing fligh [J]. Space Medicine & Medical Engineering, 2009, 22 (5): 358 - 361 (in Chinese).

[5] Dong Changhong. Matlab neural networks and app lication [M]. Beijing: National Defense Industry Press, 2007: 64 - 91 (in Chinese).

[6] Yu Tongyang. The study ofmarketing risk on BP neural network [D]. Wuhan: Management Institute, Wuhan University of Technology, 2006: 44 - 45 (in Chinese).