Close
  Indian J Med Microbiol
 

Figure 1: (a) The proposed hybrid dynamic wavelet neural network modeling structure and (b) the proposed hybrid dynamic fuzzy wavelet neural network modeling structure, in which I(k−DI), M(k−DM), and G(k−Dg) are the exogenous insulin rate, carbohydrate, and blood glucose concentration delayed regressors, respectively; u1, u>2,…, umare the useful selected inputs; ϕ(a1, b1), ϕ(a2, b2), …, ϕ(ap, bq) are all wavelet lattice neurons; ϕ1, ϕ2, …, ϕnare the selected dominant wavelet neurons; W1, W2, …, Wn are the weights attributed to the dynamic wavelet neural network output layer; WNN1, WNN2, …, WNNna are the nasubwavelets made from the n dominant selected wavelets, v1, v2, …, vnaare naweights attributed to the dynamic wavelet neural network output layer; [INSIDE:8] are membership functions of each rule in the dynamic fuzzy wavelet neural network modeling; and PH is the prediction horizon

Figure 1: (a) The proposed hybrid dynamic wavelet neural network modeling structure and (b) the proposed hybrid dynamic fuzzy wavelet neural network modeling structure, in which <i>I(k−D</i><sub>I</sub>), <i>M(k−D</i><sub>M</sub>), and <i>G(k−D</i><sub>g</sub>) are the exogenous insulin rate, carbohydrate, and blood glucose concentration delayed regressors, respectively; <i>u</i><sub>1</sub>, <i>u</i>><sub>2</sub>,…, <i>u</i><sub>m</sub>are the useful selected inputs; ϕ(a<sub>1</sub>, b<sub>1</sub>), ϕ(a<sub>2</sub>, b<sub>2</sub>), …, ϕ(a<sub>p</sub>, b<sub>q</sub>) are all wavelet lattice neurons; ϕ<sub>1</sub>, ϕ<sub>2</sub>, …, ϕ<sub>n</sub>are the selected dominant wavelet neurons; W<sub>1</sub>, W<sub>2</sub>, …, Wn are the weights attributed to the dynamic wavelet neural network output layer; WNN<sub>1</sub>, WNN<sub>2</sub>, …, WNN<sub>na</sub> are the n<sub>a</sub>subwavelets made from the n dominant selected wavelets, v<sub>1</sub>, v<sub>2</sub>, …, v<sub>na</sub>are n<sub>a</sub>weights attributed to the dynamic wavelet neural network output layer; [INSIDE:8] are membership functions of each rule in the dynamic fuzzy wavelet neural network modeling; and PH is the prediction horizon