仓储物害虫声音的模式识别  

Voice-pattern Recognition of Storedproducted Insects

作　　者：韩萍[1] 

机构地区：[1]郑州工程学院计算机系,郑州450052

出　　处：《计算机工程》2003年第22期151-152,154,共3页Computer Engineering

基　　金：河南省科技攻关项目(0224010011)

摘　　要：提出了基于声音模式识别技术的仓储物害虫计算机自动分类的新方法。借助声音传感器采集仓虫声音信号，针对仓虫声音的特点先后经过Madaline神经网降噪、数值归一化处理以及利用FFT算法作频谱分析,最终提取仓虫声音的特征向量,送入BP神经网络中进行分类识别。A new method-coputer automatic classification of storedproducted insects based on voice-pattern recognation technology is presented in this paper. Insects' voice signals are picked with sensor . Then it does some processing to the signals such as denoise by Madline neural network, making an uproar, number value normalization and utilizing FFT(fast fourier transforn) as frequency spectrum analysis.The feature of the storedproducted insects' voice is vectorial. At last, these features of insects' voice are sent into BP neural network to discern.

关 键 词：仓储物害虫 神经网络 声音降噪 频谱分析 特征提取 模式识别 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]