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 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.
实验结果表明,该信号测量和抽取算法在有效保留信号精度的同时,显蓍地减少了信号特征向量的维数。
Experimental results show that the feature extraction approach remarkably reduces the dimensionality of the input vector while the characteristics of the signals have been reserved.
本文探讨了用神经网络从模式中自动抽取特征向量并确定特征向量是否已具有足够特征信息的方法,给出了计算机模拟的结果。
In this paper, we have studied the method of drawing automatically from pattern and assessing whether feature vectors contain enough feature information. The result of computer simulation is given.
应用推荐