本文已被：浏览 3482次 下载 3162次
Received:September 23, 2009 Revised:November 09, 2009
Received:September 23, 2009 Revised:November 09, 2009
中文摘要: 利用小波神经网络自适应学习分类的优点，提出将多个小波神经网络并联使用，改进小波网络结构，在每个小波特征空间中确定小波神经元个数和初始化合适的小波基，用多级小波神经网络对毒品爆炸物的X光能量色谱的进行了识别分类。实验表明，用多级小波神经网络可以实现对不同种类毒品爆炸物的识别和鉴定，为X光能量色散技术用于毒品爆炸物的检测和识别提供了一种有效的方法。
Abstract:Taking advantage of adaptive learning classification of wavelet neural networks, this paper proposes multiple wavelet neural networks used in parallel to improve the wavelet network structure. It also determines the number of wavelet neuron and the appropriate initialization wavelet in each wavelet feature space. The X-ray energy spectrum of drugs and explosives are identified by multiple wavelet neural network. Experiments show that the identification of different types of drugs and explosives can be achieved by multiple wavelet neural network, which provides an effective method for the technology of X-ray energy dispersive used in detection and identification of drugs and explosives.
keywords: multiple wavelet neural network drugs and explosives energy scattering spectrum identification
文章编号： 中图分类号： 文献标志码：
基金项目:国家自然科学基金(10635070)
引用文本：
杨 波,康南生,王 辉.基于多级小波神经网络的毒品爆炸物能量 色散识别①.计算机系统应用,2010,19(6):166-168
YANG Bo,KANG Nan-Sheng,WANG Hui.Identification of Drugs and Explosives in Energy Spectrum Based on Multiple Wavelet Neural Networks.COMPUTER SYSTEMS APPLICATIONS,2010,19(6):166-168
杨 波,康南生,王 辉.基于多级小波神经网络的毒品爆炸物能量 色散识别①.计算机系统应用,2010,19(6):166-168
YANG Bo,KANG Nan-Sheng,WANG Hui.Identification of Drugs and Explosives in Energy Spectrum Based on Multiple Wavelet Neural Networks.COMPUTER SYSTEMS APPLICATIONS,2010,19(6):166-168
