ARTIFICIAL NEURAL NETWORKS APPLIED TO ODOR CLASSIFICATION FOR CHEMICAL-COMPOUNDS

被引：11

作者：

SONG, XH ^{[1
]}

CHEN, Z ^{[1
]}

YU, RQ ^{[1
]}

机构：

[1] HUNAN UNIV,DEPT CHEM & CHEM ENGN,CHANGSHA 410082,PEOPLES R CHINA

来源：

COMPUTERS & CHEMISTRY | 1993年 / 17卷 / 03期

关键词：

D O I：

10.1016/0097-8485(93)80012-3

中图分类号：

O6 [化学];

学科分类号：

0703 ;

摘要：

Three-layer artificial neural networks (ANN) with back-propagation of error were used to classify the odors of chemical compounds. The network's architecture and parameters were optimized, and an empirical rule for dynamically adjusting the learning rate of network was put forward. It was found that the network gave the maximum recognition rate of 100% and converged quickly by using the plural semiconductor gas sensors' response data in combination with the molecular structure codes of odorants. The network's predictive ability for untrained samples was also satisfactory.

引用

页码：303 / 308

页数：6

共 13 条

[1] EXTENDED STUDIES OF THE AUTOMATED ODOR-SENSING SYSTEM BASED ON PLURAL SEMICONDUCTOR GAS SENSORS WITH COMPUTERIZED PATTERN-RECOGNITION TECHNIQUES [J].

ABE, H ;

KANAYA, S ;

TAKAHASHI, Y ;

SASAKI, SI .

ANALYTICA CHIMICA ACTA, 1988, 215 (1-2) :155-168

[2]

[Anonymous], 1987, LEARNING INTERNAL RE

[3]

[Anonymous], 1976, MOL CONNECTIVITY CHE

[4] DETECTION OF ODORANTS USING AN ARRAY OF PIEZOELECTRIC-CRYSTALS AND NEURAL-NETWORK PATTERN-RECOGNITION [J].

CHANG, SM ;

IWASAKI, Y ;

SUZUKI, M ;

TAMIYA, E ;

KARUBE, I ;

MURAMATSU, H .

ANALYTICA CHIMICA ACTA, 1991, 249 (02) :323-329

[5] NEURAL NETWORKS - AN OVERVIEW [J].

JANSSON, PA .

ANALYTICAL CHEMISTRY, 1991, 63 (06) :A357-A362

[6] IMPROVEMENT OF IDENTIFICATION CAPABILITY IN AN ODOR-SENSING SYSTEM [J].

NAKAMOTO, T ;

FUKUDA, A ;

MORIIZUMI, T ;

ASAKURA, Y .

SENSORS AND ACTUATORS B-CHEMICAL, 1991, 3 (03) :221-226

[7]

PAO YH, 1989, ADAPTIVE PATTERN REC, P127

[8] PATTERN-CLASSIFICATION WITH ARTIFICIAL NEURAL NETWORKS - CLASSIFICATION OF ALGAE, BASED UPON FLOW CYTOMETER DATA [J].

SMITS, JRM ;

BREEDVELD, LW ;

DERKSEN, MWJ ;

KATEMAN, G ;

BALFOORT, HW ;

SNOEK, J ;

HOFSTRAAT, JW .

ANALYTICA CHIMICA ACTA, 1992, 258 (01) :11-25

[9] ARTIFICIAL NEURAL NETWORKS APPLIED TO THE CLASSIFICATION OF COMPLEX FLUORIDES BASED ON THE TRANSITION EMISSION OF THE EUROPIUM(II) ION [J].

SONG, XH ;

CHEN, Z ;

YU, RQ .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1992, 16 (03) :213-219

[10]

SONG XH, 1993, IN PRESS CHEMOMETRIC

← 1 2 →