摘要
目的建立识别中耳内边界的方法。方法利用CT获取耳部结构并建立数值模型;利用Matlab建立神经网络识别程序。结果利用数值模型在鼓膜外侧施加105dB声压,进行谐响应分析获取训练样本;利用训练成熟的网络识别了中耳内边界参数。结论数值识别结果表明,所建的中耳内边界参数识别方法具有良好的识别精度和较快的收敛速度。
Objective To study the method of internal boundary parameters identification of middle ear. Method The numerical model is created using CT technology. Based on Matlab tools, the neural network for identifying internal boundaryis proposed. Result The uniform pressure of 105 dB is applied at the outside of the tympanic membrane, and the harmonic analysis is calculated on the model to take the training samples. The internal condition parameters are identified using the good neural network. Conclusions The investigation shows that the inverse method reveals a fast convergence and a high degree of accuracy.
出处
《医用生物力学》
EI
CAS
CSCD
2009年第6期414-417,共4页
Journal of Medical Biomechanics
基金
国家自然科学基金(10672036
10872043)
关键词
神经网络
中耳
数值模型
内边界条件
参数识别
Neural network
middle ear
Numerical modeling
Internal boundary condition
Parameter identification
