Non-invasive Detection of Sound Signals for Diagnosis of Ligament Injuries around Knee based on Mel-frequency Cepstrum
Non-invasive Detection of Sound Signals for Diagnosis of Ligament Injuries around Knee based on Mel-frequency Cepstrum
复制标题
基于梅尔频率倒谱的声信号无创检测诊断膝关节周围韧带损伤
DOI：
10.3233/978-1-61499-484-8-1940
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Mei
中科院分区：
文献类型：
--
作者：
Ya;Chi;Chiu;Tsair;Yu;Mei
抽象的。我们进行了一个非侵入性的方法来检测膝关节韧带损伤。检测工具是自制的电子听诊器。通过检测并记录膝关节周围的声音，判断韧带损伤的可能性。记录受试者膝关节被动运动时的膝关节音。在我们的研究中，我们增加了膝关节周围的传感位置。采用均方法可以使损伤韧带的声信号比正常声信号更加清晰。采用MFCC作为声音的特征值，从而对声音信号进行分类，以判断受试者韧带是否损伤及损伤程度。我们进行了实验并评估了因素。结果表明，KSLDM方法对韧带的识别准确率可达89%.在本研究中，KSLDM在46个被试者被检测到膝盖声音信号时表现出良好的识别性能。关键词：膝关节声信号，无创，梅尔频率，均方。
Abstract. We conducted a non-invasive method to detect ligament injuries of knee. The detection tool is an electronic stethoscope made by myself. We detect and record the sound around knee-joint to determine the possibility of ligament injury . The subjects’ knee-joint sound was recorded during the passive motion of knee joint. In our study, we increase the sensing positions around the knee joint. Using the mean square method could make the sound signals of stricken ligament more distinct than normal sound signals. Adopting the MFCC as the characteristic value of sound, thus classify sound signals to judge whether the subject’s ligament get hurt and the extent of damage. We conducted experiments and evaluated factors. The results suggested that the proposed KSLDM had accuracy about 89 % of ligament identification. In this study, the KSLDM showed good recognition performance under 46 subjects being detected with the knee sound signal. Keywords: Knee sound signal, Non-invasive, Mel-frequency, Mean-square.