wavelet packet basis

Results showed that by using bior 2.4 wavelet packet to treat the original determined data and log energe entropy standard for wavelet basis and by selecting appropriate threshold value to compress the variable number from 46 to 25, best prediction result would be obtained.

研究表明，用bior2.4小波包处理原始测定数据，最佳小波基用log energe熵标准，选择适当阈值将变量数由46个压缩成25个（压缩比为0.54），整体预测效果最好。

Firstly, wavelet packet transform is applied to texture-rich image for a full decomposition, and a cost function related with the sequential coding scheme is utilized for best basis selection.

该算法首先用小波包变换对纹理丰富的图像进行完全分解，并用一种与后续编码器相关联的成本函数（Cost function）进行最佳小波包基搜索；