This paper presents an effective and efficient combination of feature extraction and multi-class classifier for motion classification by analyzing the surface electromyografic(sEMG) signals. In contrast to the existin...This paper presents an effective and efficient combination of feature extraction and multi-class classifier for motion classification by analyzing the surface electromyografic(sEMG) signals. In contrast to the existing methods,considering the non-stationary and nonlinear characteristics of EMG signals,to get the more separable feature set,we introduce the empirical mode decomposition(EMD) to decompose the original EMG signals into several intrinsic mode functions(IMFs) and then compute the coefficients of autoregressive models of each IMF to form the feature set. Based on the least squares support vector machines(LS-SVMs) ,the multi-class classifier is designed and constructed to classify various motions. The results of contrastive experiments showed that the accuracy of motion recognition is improved with the described classification scheme. Furthermore,compared with other classifiers using different features,the excellent performance indicated the potential of the SVM techniques embedding the EMD-AR kernel in motion classification.展开更多
The diffuse attenuation coefficient for downwelling irradiance(Kd(λ)) is an important parameter for ocean studies.Based on the optical profile data measured during three cruises in the northern South China Sea in aut...The diffuse attenuation coefficient for downwelling irradiance(Kd(λ)) is an important parameter for ocean studies.Based on the optical profile data measured during three cruises in the northern South China Sea in autumn from 2003 to 2005,variations in the Kd(λ) spectra were analyzed.The variability of Kd(λ) shows much distinct features in both magnitude and spectra pattern,it is much higher in coastal waters than that of open oceanic waters;and the blue-to-green(443/555) ratio of Kd(λ) tends to increase with chlorophyll a concentration([Chl-a]) from open ocean to coastal waters.These characteristics can be explained most by the increase of aw+p(443)/aw+p(555) with [Chl-a].In short waveband,the relation between Kd(λ)-Kw(λ) and [Chl-a] can be well described by a power law function,indicating the large contribution of phytoplankton to the variations in Kd(λ).As for the spectral model of the diffuse attenuation coefficient,there are good linear relationships between Kd(490) and Kd(λ) in other wavelengths with own slope and intercept of a linear functions in the spectral range 412-555 nm.Kd(490) is well correlated with the spectral ratio of remote sensing reflectance;and should enough measurement data are given,this empirical algorithm would be used in the Kd(λ) retrieval from ocean color satellite data.The variation in Kd(λ) provides much useful information for us to study the bio-optical property in the northern South China Sea.展开更多
基金Project (No. 2005CB724303) supported by the National Basic Re-search Program (973) of China
文摘This paper presents an effective and efficient combination of feature extraction and multi-class classifier for motion classification by analyzing the surface electromyografic(sEMG) signals. In contrast to the existing methods,considering the non-stationary and nonlinear characteristics of EMG signals,to get the more separable feature set,we introduce the empirical mode decomposition(EMD) to decompose the original EMG signals into several intrinsic mode functions(IMFs) and then compute the coefficients of autoregressive models of each IMF to form the feature set. Based on the least squares support vector machines(LS-SVMs) ,the multi-class classifier is designed and constructed to classify various motions. The results of contrastive experiments showed that the accuracy of motion recognition is improved with the described classification scheme. Furthermore,compared with other classifiers using different features,the excellent performance indicated the potential of the SVM techniques embedding the EMD-AR kernel in motion classification.
基金Supported by the Chinese Academy of Sciences (No. KZCX2-YW-215)the National Natural Science Foundation of China (No. 40476019)the Project of Knowledge Innovation of South China Sea Institute of Oceanology (No. LYQY200701)
文摘The diffuse attenuation coefficient for downwelling irradiance(Kd(λ)) is an important parameter for ocean studies.Based on the optical profile data measured during three cruises in the northern South China Sea in autumn from 2003 to 2005,variations in the Kd(λ) spectra were analyzed.The variability of Kd(λ) shows much distinct features in both magnitude and spectra pattern,it is much higher in coastal waters than that of open oceanic waters;and the blue-to-green(443/555) ratio of Kd(λ) tends to increase with chlorophyll a concentration([Chl-a]) from open ocean to coastal waters.These characteristics can be explained most by the increase of aw+p(443)/aw+p(555) with [Chl-a].In short waveband,the relation between Kd(λ)-Kw(λ) and [Chl-a] can be well described by a power law function,indicating the large contribution of phytoplankton to the variations in Kd(λ).As for the spectral model of the diffuse attenuation coefficient,there are good linear relationships between Kd(490) and Kd(λ) in other wavelengths with own slope and intercept of a linear functions in the spectral range 412-555 nm.Kd(490) is well correlated with the spectral ratio of remote sensing reflectance;and should enough measurement data are given,this empirical algorithm would be used in the Kd(λ) retrieval from ocean color satellite data.The variation in Kd(λ) provides much useful information for us to study the bio-optical property in the northern South China Sea.
