The main point of this project is to research the theories and applications of artificial neural network ( ann ) which is suitable for large scale science data mining . especially , our research focus include : dimension reduction techniques based on independent component analysis ( ica ) and wavelet - based denoising or compressing techniques for feature extraction in scientific datasets which have complex features ; classify and clustering techniques of ann combination with data grid , back - propagation neural network , self - growing multilevel self - organizing map for large scale knowledge founding in sdm 特别深入研究以独立分量分析( ica )为主的降维技术、以小波神经网络为主的压缩降噪技术解决科学数据特征复杂不便识别的问题;以同网格结合的神经网络、误差反向传播的bp神经网络、自适应多级自组织特征映像网络为主的分类、聚类技术解决科学数据挖掘中的大规模知识发现问题。
This dissertation is different from traditional speech enhancement methods which are based on noise characteristic such as adaptive noise cancellation or spectral subtraction processing . in this dissertation the speech signal conducted by bone was taken as the object to be studied and the exploitive study on the acoustical characteristic of speech signal conducted by bone was performed by the method of theory combined with experiment . then a proposition about speech reconstruction based on speech signal conducted by bone was presented , and the design of software and hardware was completed 本文与传统的基于噪声特性的自适应噪声抵消法、频谱减法等语音增强降噪技术不同，是以骨导语言为研究对象，采用理论与实验相结合的方法对骨导信号的声学特性进行了探索性研究，进而提出了基于骨导信号的语音重构技术，并完成了相应的软硬件开发。
