基于声学特征的管制员疲劳检测方法研究
Controller Fatigue Detecting Study Method Based on Acoustic Features
DOI: 10.12677/OJTT.2022.113028, PDF,    科研立项经费支持
作者: 姚光明：中国民用航空华东地区空中交通管理局飞行服务中心，上海
关键词: 管制员；疲劳；无线电通话；支持向量机；Controller； Fatigue； Radiotelephony； Support Vector Machine
摘要: 针对管制员工作疲劳问题，提出一种基于陆空通话分析的方法。利用雷达模拟机设计实验环境，采集一组包含PVT值和陆空通话记录数据。基于声学特征，分析了其对疲劳水平的贡献。随着疲劳程度的加重，各个参数均发生变化。通过SVM的基础上，验证了特征组合能够较准确地检测疲劳等级，为进一步形成管制员疲劳监测工具提供支持。
Abstract: In this paper, a novel method based on radiotelephony records was proposed. Designing expe-rimental environment with ATC simulator, a bundle of data containing PVT values, and radi-otelephony records was collected. Based on selective acoustic features, analyzing of each feature in contribution to fatigue level has been done. It can be found that with the fatigue levels getting severe, changes exhibit in each parameter. Upon using SVM, it has also been proved that the combination of features is able to accurately detect fatigue level. The contributions of this paper could be used to construct applied tools for real-time controllers’ fatigue after further studies.
文章引用：姚光明. 基于声学特征的管制员疲劳检测方法研究[J]. 交通技术, 2022, 11(3): 287-297. https://doi.org/10.12677/OJTT.2022.113028

参考文献

[1] Sun, T. and Chen, Y. (2005) Fatigue Management and Prevention of Air Traffic Control. Air Traffic Management, No. 5, 4-8.
[2] Williamson, A., Lombardi, D.A., Folkard, S., Stutts, J., Courtney, T.K. and Connor, J.L. (2011) The Link between Fatigue and Safety. Accident Analysis & Prevention, 43, 498-515. [Google Scholar] [CrossRef] [PubMed]
[3] 许弘佳. 空中交通管制员职业紧张及职业倦怠现状研究[D]: [硕士学位论文]. 唐山: 华北理工大学, 2016.
[4] 王洁宁, 侯小庆, 贾奇. 管制员疲劳状态下认知能力差异分析[J]. 安全与环境学报, 2021, 21(6): 2652-2659.
[5] Smats, E.M., Garssen, B., Bonke, B. and De Haes, J.C. (1995) The Multidimensional Fatigue Inventory (MFI) Psychometric Qualities of an Instrument to Assess Fatigue. Psychosomatic Research, 39, 315-325. [Google Scholar] [CrossRef] 
[6] Charbonnier, S., Roy, R.N., Bonnet, S. and Campagne, A. (2016) EEG Index for Control Operators’ Mental Fatigue Monitoring Using Interactions between Brain Regions. Expert Systems with Applications, 52, 91-98. [Google Scholar] [CrossRef] 
[7] Chen, Z., Xu, X., Zhang, J., Liu, Y., Xu, X., Li, L., et al. (2016) Application of LCMS-Based Global Metabolomic Profiling Methods to Human Mental Fatigue. Analytical Chemistry, 88, 11293-11296. [Google Scholar] [CrossRef] [PubMed]
[8] Jap, B.T., Lal, S., Fischer, P. and Bekiaris, E. (2009) Using EEG Spectral Components to Assess Algorithms for Detecting Fatigue. Expert Systems with Applications, 36, 2352-2359. [Google Scholar] [CrossRef] 
[9] 汪磊, 孙瑞山. 基于面部特征识别的管制员疲劳监测方法研究[J]. 中国安全科学学报, 2012, 22(7): 66-71.
[10] 李响, 李国正, 石俊刚, 彭理群. 基于语音心理声学分析的驾驶疲劳检测[J]. 仪器仪表学报, 2018, 39(10): 166-175.
[11] 吴迪. 管制员疲劳风险预测模型研究[D]: [硕士学位论文]. 天津: 中国民航大学, 2018.
[12] Teixeira, J. (2014) Evaluating the Effectiveness of Schedule Changes for Air Traffic Service (ATS) Providers: Controller Alertness and Fatigue Monitoring Study. Federal Aviation Administration, Washington DC.
[13] Disorders Center Florida (2019) Psychomotor Vigilance Test (PVT). http://www.sleepdisordersflorida.com/pvt1.html
[14] Schmidt, M. and Gish, H. (1996) Speaker Identification via Support Vector Classifiers. 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings, Atlanta, 9 May 1996, 105-108. [Google Scholar] [CrossRef] 
[15] Wolf, J.J. (1972) Efficient Acoustic Parameters for Speaker Recognition. Journal of the Acoustical Society of America, 51, 2044-2056. [Google Scholar] [CrossRef] 
[16] 孙禾, 贾奇, 刘畅. 疲劳状态下陆空通话语音特征变化研究[J]. 中国安全科学学报, 2020, 30(2): 158-164.
[17] 贺海侠. 改进支持向量机的图书馆书籍自动推荐研究[J]. 自动化与仪器仪表, 2022(1): 144-147+152.

为你推荐