首页 | 本学科首页   官方微博 | 高级检索  
检索        

基于神经网络的人中耳内边界参数识别
引用本文:刘迎曦,李生,孙秀珍.基于神经网络的人中耳内边界参数识别[J].医用生物力学,2009,24(6):414-417.
作者姓名:刘迎曦  李生  孙秀珍
作者单位:大连理工大学 工业装备结构分析国家重点实验室;大连理工大学 工业装备结构分析国家重点实验室;大连理工大学 工业装备结构分析国家重点实验室;大连医科大学第二临床附属医院 耳鼻咽喉科
基金项目:国家自然科学基金(10672036,10872043)
摘    要:目的 研究识别中耳内边界的方法。方法 利用CT获取耳部结构临床资料建立数值模型;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。

关 键 词:神经网络  中耳数值模型  内边界条件  参数识别
收稿时间:2009/3/30 0:00:00
修稿时间:5/5/2009 12:00:00 AM

Internal boundary parameters identification of human Middle Ear with neural network
LIU Ying-xi,LI Sheng and SUN Xiu-zhen.Internal boundary parameters identification of human Middle Ear with neural network[J].Journal of Medical Biomechanics,2009,24(6):414-417.
Authors:LIU Ying-xi  LI Sheng and SUN Xiu-zhen
Institution:State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology;State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology;State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology;ENT Department, The Second Affiliated Hospital of Dalian Medical University
Abstract:Objective To study the method of internal boundary parameters identification of middle ear. Methods The numerical model is created using CT technology. Based on Matlab tools, the neural network for identifying internal boundary is proposed. Results 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. Conclusion The investigation shows that the inverse method reveals a fast convergence and a high degree of accuracy.
Keywords:Neural network  Numerical modeling of the middle ear  Internal  boundary condition  Parameter identification
点击此处可从《医用生物力学》浏览原始摘要信息
点击此处可从《医用生物力学》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号