HHT和HMM在血细胞信号识别中的应用

Application of HHT and HMM in blood cell signal recognition

针对血细胞信号具有多形态、非线性、非平稳的特点,提出将希尔伯特黄变换(HHT)和隐马尔可夫模型(HMM)相结合的血细胞信号识别方法。该方法采用HHT对血细胞信号进行分析,选取经过经验模态分解得到的各本质模态函数中相关性较大的分量,以这些分量的能量矩作为信号的特征量,由HMM训练得到正常人和病患者的模型参数并用做分类识别。实验结果表明,该方法可以较好地识别正常人和病患者的血细胞信号,综合准确率达89.13%。

For the multi-form, nonlinear and non-stationary characteristics of the blood cell signal, the blood cell signal re- cognition method based on Hilbert Huang transform （HHT） and hidden Markov model （HMM） is proposed, The HHT is used in the method to analyze the blood cell signal. The strong dependency components in each intrinsic mode function obtained with empiri- cal mode decomposition are selected, and their energy moments are taken as the signal feature value to achieve the model parame- ters of healthy people and patient by HMM training for classification and recognition. The experimental results indicate this method can recognize the blood cells signals of the healthy people and patient, and the synthetical accuracy rate can reach up to 89.13%.