Respiratory sounds carry significant information about the condition of respiratory system. Respiratory sounds are often affected by sounds emanating from heart and other organs thus making the analysis task more comp...
详细信息
ISBN:
(纸本)9781728149561
Respiratory sounds carry significant information about the condition of respiratory system. Respiratory sounds are often affected by sounds emanating from heart and other organs thus making the analysis task more complex. Pneumonia is a very common lungs disease and requires efficient diagnosis at initial stage for proper treatment. In this research, an automated system for diagnosis of Pneumonia based on auscultations is proposed. Auscultation signals are first preprocessed through empiricalmode decomposition (EMD), which decomposes original signal into its constituent components known as intrinsic modefunctions (IMFs). Preprocessed signal is reconstructed by addition of only those IMFs which carry high discriminative information among healthy and Pneumonia subjects. IMFs which carry redundant and noisy data are rejected thus making preprocessing more effective. Next, characteristic features are extracted by fusion of Mel frequency cepstral coefficients (MFCC) and time domain features. Finally, Support Vector Machines (SVM) classifier is trained and tested through 5-fold cross validation. Experimental evaluation of proposed approach is performed on range of various classifiers on self-collected dataset which contains 480 auscultation signals of normal and Pneumonia subjects. SVM with Quadratic kernel achieved best classification results in terms of accuracy of 99.7%.
This paper presents a novel method of the speech recognition in combining the empiricalmode decomposition with radical basis function neural network. Speech signals which pretreated are decomposed by empiricalmode d...
详细信息
ISBN:
(纸本)9783037859155
This paper presents a novel method of the speech recognition in combining the empiricalmode decomposition with radical basis function neural network. Speech signals which pretreated are decomposed by empiricalmode decomposition to get a set of intrinsic modefunctions. It extracts mel frequency cepstrum coefficient from intrinsic modefunction. Features parameters are made up of the coefficients. For BP Neural Network, RBF Neural Network has advantages on approximating ability and learning speed. So using RBF Neural Network as a recognition model is a good method. Experiments show that this new method has good robustness and adaptability. The speech recognition rate of this method reach ninety-one percents accurately under no noise environment. Speech signal recognition is feasible and effective in noisy environment.
暂无评论