E-nose combined with a pattern recognition module can be used for estimating gases concentration. This chapter introduces the concentration estimations of indoor contaminants using chaos-based optimization artificial neural network integrated into our E-nose instrument. Back-propagation neural network (BPNN) has been the common pattern recognition algorithm for E-nose; however, it has local optimal flaw. This chapter presents a novel chaotic sequence optimization BPNN method. Experimental results demonstrate the superiority and efficiency of the portable E-nose instrument integrated into chaos-based artificial neural network optimization algorithms in real-time monitoring of air quality in dwellings.
CITATION STYLE
Zhang, L., Tian, F., & Zhang, D. (2018). Chaos-Based Neural Network Optimization Approach. In Electronic Nose: Algorithmic Challenges (pp. 47–60). Springer Singapore. https://doi.org/10.1007/978-981-13-2167-2_4
Mendeley helps you to discover research relevant for your work.