| 基于神经网络和小波分析的血细胞识别算法 |
| |
| 引用本文： | 贾丹丹,李宏.基于神经网络和小波分析的血细胞识别算法[J].计算机应用与软件,2009,26(8):29-31. |
| |
| 作者姓名： | 贾丹丹 李宏 |
| |
| 作者单位： | 宁波大学信息科学与工程学院,浙江,宁波,315211 |
| |
| 基金项目： | 国家自然科学基金项目 |
| |
| 摘 要： | 结合小波变换时频局部化特性和神经网络的优势,提出了一种基于神经网络和小波分析的血细胞识别算法.首先对血细胞信号进行小波分解,然后利用小波分解系数重构信号的能量,结合时域特征参数构造特征向量作为神经网络的输入,最后建立神经网络模型进行训练.通过实验分析了不同条件下的信号识别情况,并与传统的识别算法作了比较,结果表明算法具有较强的血细胞识别能力,与传统的识别算法相比,识别准确度更高.
|
| 关 键 词： | 神经网络 小波变换 血细胞识别 特征提取 |
BLOOD CELL RECOGNITION BASED ON NEURAL NETWORK AND WAVELET ANALYSIS |
| |
| Jia Dandan,Li Hong.BLOOD CELL RECOGNITION BASED ON NEURAL NETWORK AND WAVELET ANALYSIS[J].Computer Applications and Software,2009,26(8):29-31. |
| |
| Authors: | Jia Dandan Li Hong |
| |
| Affiliation: | School of Information Science and Engineering;Ningbo University;Ningbo 315211;Zhejiang;China |
| |
| Abstract: | In combination with the advantages of neural network and the localized characteristic in time-frequency domains of wavelet transform,a blood cell recognition algorithm based on neural network and wavelet analysis is presented.The blood cell signals were decomposed,then the signals' energy was reconstructed using decomposing wavelet coefficients,and energy values combining with seven features in time domain together were constructed the feature vectors used as the inputs of the BP network.Finally the network... |
| |
| Keywords: | Neural network Wavelet transform Blood cell recognition Feature extraction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
