A combinative function approximation model and its applications to electronic noses
作者： Gao Daqi , Tong Zhen , Li Yongli
DOI: 10.1109/IJCNN.2005.1556223
关键词: Artificial intelligence 、 Multilayer perceptron 、 Regression analysis 、 Pattern recognition 、 Multivariate statistics 、 Machine learning 、 Function approximation 、 Computer science 、 Support vector machine 、 Class (biology) 、 Nonlinear regression
摘要: This paper focuses on combinative and modular approximation models to simultaneously estimate odor classes strengths. We first decompose a many-to-many task into multiple many-to-one tasks, then realize them using models. A single model is regarded as an expert, panel or ensemble made up of such experts. Each expert either multivariate logarithmic regression model, multilayer perceptron (MLP), support vector machine (SVM). behalf kind odor. The most similar gives the class label strength experiment for estimating 4 kinds fragrant materials shows that proposed effective.
sci-hub.se 参考文章(18)
Gasser Auda, Mohamed Kamel, Modular Neural Network Classifiers: A Comparative Study Journal of Intelligent and Robotic Systems. ,vol. 21, pp. 117- 129 ,(1998) , 10.1023/A:1007925203918
S Capone, M Epifani, F Quaranta, P Siciliano, A Taurino, L Vasanelli, Monitoring of rancidity of milk by means of an electronic nose and a dynamic PCA analysis Sensors and Actuators B-chemical. ,vol. 78, pp. 174- 179 ,(2001) , 10.1016/S0925-4005(01)00809-7
Gao Daqi, Yang Genxing, Influences of variable scales and activation functions on the performances of multilayer feedforward neural networks Pattern Recognition. ,vol. 36, pp. 869- 878 ,(2003) , 10.1016/S0031-3203(02)00120-6
A.K. Srivastava, Detection of volatile organic compounds (VOCs) using SnO2 gas-sensor array and artificial neural network Sensors and Actuators B-chemical. ,vol. 96, pp. 24- 37 ,(2003) , 10.1016/S0925-4005(03)00477-5
Julian W. Gardner, Detection of vapours and odours from a multisensor array using pattern recognition Part 1. Principal component and cluster analysis Sensors and Actuators B-chemical. ,vol. 4, pp. 109- 115 ,(1991) , 10.1016/0925-4005(91)80185-M
G. Huyberechts, P. Szecówka, J. Roggen, B.W. Licznerski, Simultaneous quantification of carbon monoxide and methane in humid air using a sensor array and an artificial neural network Sensors and Actuators B: Chemical. ,vol. 45, pp. 123- 130 ,(1997) , 10.1016/S0925-4005(97)00283-9
Georg Thimm, Perry Moerland, Emile Fiesler, The interchangeability of learning rate and gain in backpropagation neural networks Neural Computation. ,vol. 8, pp. 451- 460 ,(1996) , 10.1162/NECO.1996.8.2.451
Gao Daqi, Wang Shuyan, Ji Yan, An electronic nose and modular radial basis function network classifiers for recognizing multiple fragrant materials Sensors and Actuators B-chemical. ,vol. 97, pp. 391- 401 ,(2004) , 10.1016/J.SNB.2003.09.018
Haoxian Zhang, Murat Ö. Balaban, José C. Principe, Improving pattern recognition of electronic nose data with time-delay neural networks Sensors and Actuators B-chemical. ,vol. 96, pp. 385- 389 ,(2003) , 10.1016/S0925-4005(03)00574-4
M.S. Nayak, R. Dwivedi, S.K. Srivastava, Application of iteration technique in association with multiple regression method for identification of mixtures of gases using an integrated gas-sensor array Sensors and Actuators B-chemical. ,vol. 21, pp. 11- 16 ,(1994) , 10.1016/0925-4005(93)01203-G