Spectroscopy and hybrid neural network analysis

被引:12
作者
Lu, TW
Lerner, J
机构
[1] Physical Optics Corporation, Torrance
关键词
D O I
10.1109/5.503145
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper reviews the current use of spectroscopy and related instrumentation in chemical analysis. Advancements in digital signal processing technology are making it possible to improve the sensitivity and accuracy of analytical instruments without expensive upgrading of instrument hardware. A hybrid neural network (HNN) is described that can perform nonlinear signal analysis. The HNN approach combines the simple data reduction capability of conventional linear signal processing algorithms with the adaptive learning and recognition ability of a multilayer nonlinear neural network architecture. A number of examples show the use of the HNN for environmental monitoring and real-time process control.
引用
收藏
页码:895 / 905
页数:11
相关论文
共 21 条
[1]  
[Anonymous], 1969, DESIGN OPTICAL SPECT
[2]   A MASSIVELY PARALLEL ARCHITECTURE FOR A SELF-ORGANIZING NEURAL PATTERN-RECOGNITION MACHINE [J].
CARPENTER, GA ;
GROSSBERG, S .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1987, 37 (01) :54-115
[3]  
CHRISP MP, 1987, APPL OPTICS OPTICAL, V10
[4]  
FUKUSHIMA K, 1988, COMPUTER, V4, P65
[5]  
GELADI P, 1986, ANAL CHEM ACTA, V185
[6]  
HORNIK K, 1989, NEURAL NETWORKS, V2
[7]  
Hutley M. C., 1982, Diffraction Gratings
[8]  
Karayiannis N.B., 1993, ARTIFICIAL NEURAL NE
[9]  
KOHONEN K, 1984, SELF ORG ASS MEMORY
[10]  
Lerner J., 1988, JOBIN YVON OPTICAL S