针对100架民航飞机识别的现实问题，设计了包含数据分析/处理、特征参数标准数据库建立、分类、优化等模块的多特征值联合射频指纹识别模型。数据分析/处理中，分析了小波系数、瞬时相位、希尔伯特黄变换能量谱、相关系数、时域包络、概率密度函数等参数的区分度，并选定特征参数。特征参数数据库建立中，为避免RFF特征丢失，利用直接测量法建立特征参数标准数据库。分类过程中，基于相关度和阈值理念，定义了单特征分类规则及联合分类规则。最后通过人工修订参数的方法实现了模型的优化。结果表明，在硬件资源受限、选择样本数偏低的情况下，该模型平均识别率达到69.75%，为解决飞机数据识别的现实问题提供了一定的理论参考。
Aiming to solve the real problem of civilian aircraft identification, a novel combined radio frequency fingerprint (RFF) identification model is proposed, consisting of data analyzing/processing, standard characteristic parameter database establishment, classification and optimization. In data analyzing/processing step, discrimination was realized for wavelet coefficients, instantaneous phase, Hilbert Huang transform energy spectrum, coefficients, time field envelope, probability density function, on basis of which, characteristic parameters were confirmed. In standard characteristic parameter database establishment step, a standard database was found through direct measurement method to avoid losing the RFF feature. In classification step, single character assortment rule and combined classifying rule were defined, with correlative concept and threshold concept. Finally, optimization for the model was realized by modifying parameters manually. Results show that, though hardware was limited and amount of samples were fewer, average identification rate is near 69.75, providing a theoretical reference for the real problem of identifying different aircrafts.
References
[1]
Hall, J., Barbeau, M. and Kranakis, E. (2003) Detection of Transient in Radio Frequency Fingerprinting Using Signal Phase. Proceedings of 3rd IASTED International Conference on Wireless and Optical Communications, Banff, Alberta, 2003, 13-18.
