No abstract

In this paper, a classification method based on Support Vector Machine (SVM) is given in the digital modulation signal classification. The second, fourth and sixth order cumulants of the received signals are used as classification vectors firstly, then the kernel thought is used to map the feature vector to the high dimensional feature space and the optimum separating hyperplane is constructed in space to realize signal recognition. In order to build an effective and robust SVM classifier, the radial basis kernel function is selected, one against one or one against rest of multi-class classifier is designed, and method of parameter selection using crossvalidation grid is adopted. Through the experiments it can be concluded that the classifier based on SVM has high performance and is more robust.

No abstract

No abstract

With the development of rehabilitation medicine and kinematics, the study of Electromyographic (EMG) signal come into people's sight. The information obtained from the surface EMG signals can not only reflect the motion state of muscles and joints, but also judge people's motion type, which is one of the important indexes in the study of human body. Based on the EMG as the research object with the detailed analysis to understand the EMG of time domain, frequency domain and SNR, etc. The study of EMG signal denoising and feature extraction is of great value and significance in the field of medical diagnosis. Such as using sEMG signals to assess muscle status and determine postoperative recovery status. Empirical Mode Decomposition (EMD) based on hilbert-huang is a time frequency analysis method for non-linear and non-stationary signals like EMG signals, which has unique advantages and broad prospects in signal analysis and processing. In this paper, we used EMD to decompose signal which contain multiple frequency component into a series of inherent modal parameters, and then combine the method of EMD decomposition and wavelet transform to carry out denoising processing and feature extraction for EMG signals, which can effectively weaken the noise of surface EMG signals and reflect the essential characteristics of the original signal, and classify the damage of EMG signals by analyzing the characteristic values.