The spectrum signal was pretreated and several key characteristic parameters were extracted and then a set of new feature vector was obtained by reducing the dimensions.
首先对光谱信号进行预处理并抽取了多个关键性的特征参数，通过降维分析得到一组新的特征向量。
The result shows that, compared with the time-wavelet power spectrum, the scale-wavelet power spectrum has a higher recognition accuracy and smaller dimension of feature vector.
结果表明，尺度-小波能量谱和时间-小波能量谱相比有较好的分类效果和较低的特征维数。
The result shows that, compared with the time-wavelet power spectrum, the scale-wavelet power spectrum has a higher recognition accuracy and smaller dimension of feature vector.
结果表明，尺度-小波能量谱和时间-小波能量谱相比有较好的分类效果和较低的特征维数。
应用推荐