D. W. Yu

Learn More
In this paper, we use night light imagery data at two scales – the city and within the city. Since many of the urban characteristics of cities including traffic and paved area are correlated with each other we derive components for our sample of 286 cities in China. We then correlate these measures for average DN values from night light imagery at the(More)
A new model order and time-delay selection method for neural network modelling of SISO non-linear systems has been recently proposed. The extension of this method to the MIMO case is developed in this paper. The MIMO form of the NARX model is considered and the order and time-delay for each input are selected by identifying linearised models of the system.(More)
An adaptive neural network-based predictive strategy is applied to a pilot multivariable chemical reactor. The first stage of the project, simulation study, has been investigated and is presented in this paper, together with the description of the adaptive network. A pseudo-linear radial basis function (PLRBF) network is developed to model the real process(More)
  • 1