A Novel Chaotic Sequence Optimization Neural Network for Concentration Estimation of Formaldehyde by an Electronic Nose

Electronic nose (E-nose), as an artificial olfactory system, can be used for quantification of odor concentration combined with a pattern recognition module. Back propagation neural network (BPNN) has been recognized as the common pattern recognition in E-nose development. Considering the flaw of easily trap into a local optimal of BPNN, this paper presents a novel chaotic sequence optimization BPNN method for improving the accuracy in E-nose quantification prediction. Three chaos dynamic equations including logistic map, tent map and Gaussian map for chaotic queue with ergodic characteristic were applied in chaos based optimization. Through comparisons with standard particle swarm optimization, the experimental results demonstrate the superiority and efficiency of the chaos based optimization algorithm from the point of view of the search ability and robustness.