Search

In this study, mechanomyography (MMG) was used to evaluate the effectiveness and sensibility of the degree of muscle fatigue. The preprocessed MMG signal was decomposed by 6-scale discrete wavelet transform (DWT) to acquire the coefficients of each scale. The coefficients of low frequency of scale 3, 4, 5 (A3, A4, A5) were used to reconstruct signals respectively. Frequency-domain features were extracted, and linear regression equations were established to make comparisons, which indicated that 15–62Hz frequency bands play a major role in that frequency spectrum shifting to lower frequencies. To learn more information, the MMG signal was processed by 6-layer wavelet packet decomposition (WPD), and the coefficients of each node were acquired. The coefficients of 6 nodes (ADAAAA6, DDAAAA6, AADAAA6, DADAAA6, ADDAAA6, DDDAAA6) were selected to reconstruct signals. The change of power of reconstructed signals during muscle fatigue were calculated and compared. The results suggested that power of MMG was decreasing and 31–54 Hz frequency band showed more sensitivity to muscle fatigue induced by static exertion.

Auscultation signals are nonstationary in nature. Wavelet packet transform (WPT) has currently become a very useful tool in analyzing nonstationary signals. Sample entropy (SampEn) has recently been proposed to act as a measurement for quantifying regularity and complexity of time series data. WPT and SampEn were combined in this paper to analyze auscultation signals in traditional Chinese medicine (TCM). SampEns for WPT coefficients were computed to quantify the signals from qi- and yin-deficient, as well as healthy, subjects. The complexity of the signal can be evaluated with this scheme in different time-frequency resolutions. First, the voice signals were decomposed into approximated and detailed WPT coefficients. Then, SampEn values for approximated and detailed coefficients were calculated. Finally, SampEn values with significant differences in the three kinds of samples were chosen as the feature parameters for the support vector machine to identify the three types of auscultation signals. The recognition accuracy rates were higher than 90%.

Pulse diagnosis with finger pulse-taking is popular in Chinese culture. Wrist pulse waveform analysis has becoming common in Traditional Chinese Medicine (TCM) engineering and diagnosis modernization. An improved two-step classification method is proposed in this paper to differentiate seven common TCM pulse conditions, include four mono and three concurrent pulses. For both time-domain and frequency-domain feature-based patterns, a total of ten effective discrimination functions (five for each domain) are trained and tested for majority-rule based voting analysis. Case studies based on both basic one-step and improved two-step methods are given. Results show that the overall classification performance has been improved from 52% to 57% by introducing two-step method, and four out of seven individual classification accuracies are also improved.

In this paper, the wavelet packet transform is introduced to analyze the signal of TCM auscultation. To accomplish this, the energy feature of the signal is extracted after the signal is decomposed by the wavelet packet transform. Then the energy feature is analyzed by the nonparametric test. The five vowels /a:/, /e:/, /i:/, /o:/, /u:/ are analyzed in respectively. In each vowel, the samples are divided into two groups. One is analyzed by Mann-Whitey U algorithm in each two illness and the other is analyzed by K-S algorithm in six illness. The result of the analysis shows that the energy features of sound signal for different vowels have obviously difference in different frequency. So, combining with different vowels in all frequency, there is an obviously difference for each five organs illness in different frequency.

As the traditional diagnosis in traditional Chinese medicine, wrist pulses reflect the condition of the cardiovascular system which contains much nonlinearity. The linear analysis might not provide the enough useful information for the wrist pulse signals any more, so it is proposed the combination of wavelet packet and recurrence quantification plot analysis to analyze the wrist pulses in this paper. In this paper, 5 kinds of wrist pulse signals, which are the slippery pulses, the normal pulses, the thread pulses, the taut pulses and the slippery and taut pulses, are analyzed by using the recurrence quantification analysis which based on wavelet packets transform, and some results are obtained finally. From recurrence plot and recurrence quantification plot analysis based on wavelet packets transform, the differences can be observed among those 5 kinds of wrist pulses, which mean that the recurrence quantification plot analysis measures are the useful features to distinguish different kinds of traditional Chinese medicine (TCM) wrist pulses for the further classification.

In this paper, wavelet packet is used to extract the feature of the energy, and nonparametric test is used to analyze the significant difference of the sound of energy feature. Auscultation diagnosis of TCM means to use the correspondence of five kinds of sounds to find out the lesion in five internal organs. The sound signal is a typical non-stationary signal. Wavelet analysis is more flexible, and it can obtain any resolutions of time domain or frequency domain. The feature parameter: energy is extracted by the wavelet packet and the values of the energy of healthy and unhealthy people are tested by the Mann-Whitey U test. The results of the test show that the vocal energy of unhealthy people is higher than that of healthy people.

The auscultation diagnosis of TCM means to use the correspondence of five kinds of sounds to find out the lesion in the five internal organs. The signal of the auscultation is always accompanied by noise. Unfortunately, the common filters can only denoise in the linear signals. In this paper, the noise is reduced by the locally projective algorithm in the nonlinear signals. Using Grassberger-Procaccia algorithm to calculate correlation dimension, the correlation dimension of the signal after the denoise is lower than that of original signal. The results show that the method well reproduces the nonlinear characteristics of the corrupted signal. The accuracy and reliability of the signal could be improved in TCM signal analysis by nonlinear denoise.

In this paper, wavelet packet energy entropy (WPEE) and support vector machine (SVM) were utilized to detect and classify auscultation signals in Traditional Chinese Medicine (TCM). The auscultation signals of health and qi-vacuity and yin-vacuity subjects were collected from the outpatient by Shanghai University of TCM. And the wavelet packet decomposition (WPD) at level 6 was employed to split more elaborate frequency bands of the auscultation signals, then to obtain energy entropies features of frequency bands. SVM are designed and trained for making a decision regarding the type of the auscultation signals. The experimental results showed the algorithm using WPEE and SVM classifier feasibility and effectiveness, and this paper is valuable for auscultation research in TCM.

The purpose of this paper is to study the objective auscultation of Traditional Chinese Medicine utilizing the wavelet analysis theory and two novel parameters. Digital auscultation information, which are the voice samples in this paper were analyzed using wavelet analysis. Two parameters including the energy ratio and max power ratio were proposed as the feature parameters. The used voice samples including: qi-deficiency, yin-deficiency, and health subjects are decomposed into ten layers of wavelet decomposition coefficients. Based on these coefficients, the parameters corresponding to the ranges of the frequency were obtained for every sample. Then the parameters with significant differences among different kinds of signals were studied in order to find the feature information contained in the three kinds of auscultation signals.

the purpose of this paper is to analyze the auscultation signals in Traditional Chinese Medicine utilizing discrete wavelet (DWT) and approximate entropy (ApEn). In this paper ApEn is used to quantify pathological voicing in qi-deficiency, yin-deficiency and health using the voice samples in the time and frequency domain. Since ApEn is a viable single figure of merit, it has the potential to make assessment of aberrant voicing both more concise and objective than the subjective analysis adopted by speech and language therapists (SALTs). In this paper, in the first stage, voice signal were decomposed into approximation and detail coefficients using DWT. In the second stage, ApEn values of approximation and detail coefficients were computed. Finally, ApEn values among three kinds of samples were analyzed.

A Mechanomyography (MMG) based hand-motion patterns recognition approach was proposed in this paper. With the MMG signal acquired in the upper arm via a single sensor, eleven original features were extracted, and they were further processed by principal components analysis (PCA) in order to reduce the dimension of the feature space. Quadratic discriminant analysis (QDA) was used for four hand-motion patterns recognition. The cross-validated experimental results show that PCA method is practical in dimension reduction and QDA is functional in classifying the four types of hand-motion modes. The average classification accuracy of eight subjects is 79.66%±7.32%. It also reveals that MMG signal is effective in classifying more than two hand-motion patterns even with only one channel signal, and can provide a new choice of control signal for upper-limb prosthetic hand design.

Auscultation is one of the Four Diagnosis Methods in traditional Chinese medicine (TCM). Objective auscultation based on applications of computer and digital signal processing techniques became a new trend in modern days. However, speech is inevitably corrupted by ambient noise which leads to rapid deterioration on the accuracy of diagnosis on the part of objective auscultation system. This paper attempts to apply ICA method in a noise reduction process. The basic principles of ICA and noise reduction are illuminated briefly. Experiments are conducted to evaluate the effect of different kinds of ICA algorithm. Finally, the paper concludes with a discussion on the feasibility and practicality of this method.

The cardiovascular system is complex system containing many nonlinearities. Pulse signals are nonlinear reflecting the status of the heart and the vascular system. Sample entropy analysis can quantify signal regularity or the system complexity generating the signal. In this paper the wrist pulse signals of healthy group and coronary heart disease group are analyzed and studied with sample entropy analysis, and the selection of parameters is discussed. The pulse signals of two groups are classified using support vector machine (SVM), the classification results are analyzed. The results indicate there was difference between the sample entropy of two groups of wrist pulse signals; SVM classifiers have good performance for classification of the two groups. Sample entropy analysis of wrist pulse was helpful for non-destructive inspection of coronary heart disease.

Time-domain feature analysis on wrist pulse waveform is common in Traditional Chinese Medical (TCM) engineering and diagnosis modernization. A derivative-based method on the automated time-domain feature extraction of wrist pulse waveform is proposed in this paper with the consideration of some practical issues. Variability analysis is performed on the features extracted from the pulse waveform trends. The dimension of pattern, i.e. vector of features, is then reduced by the cross-correlation analysis on the variability of features. A real classification case, with dataset including pulse waveform from 20 healthy person and 50 persons with cardiovascular disease, is performed based on pattern containing both reduced features and other combinations. Comparison results show that features are properly selected and the classification performance is acceptable.

TCM acoustic diagnosis is an important part of the diagnostics of traditional Chinese medicine. Voice can be used to reflect the functions of the viscera and the variations of the pathological conditions. In this paper vowel /a/ signals of healthy persons and patients with deficiency syndrome are analyzed and studied with Delay Vector Variance method. The results indicated that there exists distinct difference between two groups of vowel /a/ signals; the obtained statistic is helpful in recognizing the person with deficiency syndrome.

This study aims at utilising Wavelet Packet Transform (WPT) and Support Vector Machine (SVM) algorithm to make objective analysis and quantitative research for the auscultation in Traditional Chinese Medicine (TCM) diagnosis. First, Wavelet Packet Decomposition (WPD) at level 6 was employed to split more elaborate frequency bands of the auscultation signals. Then statistic analysis was made based on the extracted Wavelet Packet Energy (WPE) features from WPD coefficients. Furthermore, the pattern recognition was used to distinguish mixed subjects' statistical feature values of sample groups through SVM. Finally, the experimental results showed that the classification accuracies were at a high level.