http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Lahmiri (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
Salim Lahmiri,Debra Ann Dawson,Amir Shmuel 대한의용생체공학회 2018 Biomedical Engineering Letters (BMEL) Vol.8 No.1
Parkinson’s disease (PD) is a widespreaddegenerative syndrome that affects the nervous system. Itsearly appearing symptoms include tremor, rigidity, andvocal impairment (dysphonia). Consequently, speechindicators are important in the identification of PD basedon dysphonic signs. In this regard, computer-aided-diagnosissystems based on machine learning can be useful inassisting clinicians in identifying PD patients. In this work,we evaluate the performance of machine learning basedtechniques for PD diagnosis based on dysphonia symptoms. Several machine learning techniques were consideredand trained with a set of twenty-two voice disordermeasurements to classify healthy and PD patients. Thesemachine learning methods included linear discriminantanalysis (LDA), k nearest-neighbors (k-NN), naı¨ve Bayes(NB), regression trees (RT), radial basis function neuralnetworks (RBFNN), support vector machine (SVM), andMahalanobis distance classifier. We evaluated the performanceof these methods by means of a tenfold cross validationprotocol. Experimental results show that the SVMclassifier achieved higher average performance than allother classifiers in terms of overall accuracy, G-mean, andarea under the curve of the receiver operating characteristicplot. The SVM classifier achieved higher performancemeasures than the majority of the other classifiers also interms of sensitivity, specificity, and F-measure statistics. The LDA, k-NN and RT achieved the highest averageprecision. The RBFNN method yielded the highestF-measure.; however, it performed poorly in terms of otherperformance metrics. Finally, t tests were performed toevaluate statistical significance of the results, confirmingthat the SVM outperformed most of the other classifiers onthe majority of performance measures. SVM is a promisingmethod for identifying PD patients based on classificationof dysphonia measurements.
-
A Weighted Bio-signal Denoising Approach Using Empirical Mode Decomposition
Salim Lahmiri,Mounir Boukadoum 대한의용생체공학회 2015 Biomedical Engineering Letters (BMEL) Vol.5 No.2
Purpose The purpose of this study is to show the effectiveness of a physiological signal denoising approach called EMDDWT- CLS. Methods This paper presents a new approach for signal denoising based on empirical mode decomposition (EMD), discrete wavelet transform (DWT) thresholding, and constrained least squares (CLS). In particular, the noisy signal is decomposed by empirical mode decomposition (EMD) to obtain intrinsic mode functions (IMFs) plus a residue. Then, each IMF is denoised by using the discrete wavelet transform (DWT) thresholding technique. Finally, the denoised signal is recovered by performing a weighted summation of the denoised IMFs except the residue. The weights are determined by estimating a constrained least squares coefficients; where, the sum of the coefficients is constrained to unity. We used human ECG and EEG signals, and also two EEG signals from left and right cortex of two healthy adult rats. Results The 36 experimental results show that the proposed EMD-DWT-CLS provides higher signal-to-noise ratio (SNR) and lower mean of squared errors (MSE) than the classical EMD-DWT model. Conclusions Based on comparison with classical EMDDWT model used in the literature, the proposed approach was found to be effective in human and animal physiological signals denoising.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
