A taxonomy for wavelet neural networks applied to nonlinear modelling

This article presents a novel classification of wavelet neural networks based on the orthogonality/non-orthogonality of neurons and the type of nonlinearity employed. On the basis of this classification different network types are studied and their characteristics illustrated by means of simple one-dimensional nonlinear examples. For multidimensional problems, which are affected by the curse of dimensionality, the idea of spherical wavelet functions is considered. The behaviour of these networks is also studied for modelling of a low-dimension map.

Deflation based nonlinear canonical correlation analysis

This paper introduces two new techniques for determining nonlinear canonical correlation coefficients between two variable sets. A genetic strategy is incorporated to determine these coefficients. Compared to existing methods for nonlinear canonical correlation analysis (NLCCA), the benefits here are that the nonlinear mapping requires fewer parameters to be determined, consequently a more parsimonious NLCCA model can be established which is therefore simpler to interpret. A further contribution of the paper is the investigation of a variety of nonlinear deflation procedures for determining the subsequent nonlinear canonical coefficients. The benefits of the new approaches presented are demonstrated by application to an example from the literature and to recorded data from an industrial melter process. These studies show the advantages of the new NLCCA techniques presented and suggest that a nonlinear deflation procedure should be considered. (c) 2006 Elsevier B.V. All rights reserved.

On velocity-based local model networks for nonlinear identification

This paper exposes the strengths and weaknesses of the recently proposed velocity-based local model (LM) network. The global dynamics of the velocity-based blended representation are directly related to the dynamics of the underlying local models, an important property in the design of local controller networks. Furthermore, the sub-models are continuous-time and linear providing continuity with established linear theory and methods. This is not true for the conventional LM framework, where the global dynamics are only weakly related to the affine sub-models. In this paper, a velocity-based multiple model network is identified for a highly nonlinear dynamical system. The results show excellent dynamical modelling performances, highlighting the value of the velocity-based approach for the design and analysis of LM based control. Three important practical issues are also addressed. These relate to the blending of the velocity-based local models, the use of normalised Gaussian basis functions and the requirement of an input derivative.

Robust fuzzy Gustafson-Kessel clustering for nonlinear system identification

This paper deals with Takagi-Sugeno (TS) fuzzy model identification of nonlinear systems using fuzzy clustering. In particular, an extended fuzzy Gustafson-Kessel (EGK) clustering algorithm, using robust competitive agglomeration (RCA), is developed for automatically constructing a TS fuzzy model from system input-output data. The EGK algorithm can automatically determine the 'optimal' number of clusters from the training data set. It is shown that the EGK approach is relatively insensitive to initialization and is less susceptible to local minima, a benefit derived from its agglomerate property. This issue is often overlooked in the current literature on nonlinear identification using conventional fuzzy clustering. Furthermore, the robust statistical concepts underlying the EGK algorithm help to alleviate the difficulty of cluster identification in the construction of a TS fuzzy model from noisy training data. A new hybrid identification strategy is then formulated, which combines the EGK algorithm with a locally weighted, least-squares method for the estimation of local sub-model parameters. The efficacy of this new approach is demonstrated through function approximation examples and also by application to the identification of an automatic voltage regulation (AVR) loop for a simulated 3 kVA laboratory micro-machine system.

Deletion of TRPC4 and TRPC6 in Mice Impairs Smooth Muscle Contraction and Intestinal Motility In Vivo.

BACKGROUND & AIMS: Downstream effects of muscarinic receptor stimulation in intestinal smooth muscle include contraction and intestinal transit. We thought to determine whether classic transient receptor potential (TRPC) channels integrate the intracellular signaling cascades evoked by the stimulated receptors and thereby contribute to the control of the membrane potential, Ca-influx, and cell responses. METHODS: We created trpc4-, trpc6-, and trpc4/trpc6-gene-deficient mice and analyzed them for intestinal smooth muscle function in vitro and in vivo. RESULTS: In intestinal smooth muscle cells TRPC4 forms a 55 pS cation channel and underlies more than 80% of the muscarinic receptor-induced cation current (mI(CAT)). The residual mI(CAT) depends on the expression of TRPC6, indicating that TRPC6 and TRPC4 determine mI(CAT) channel activity independent of other channel subunits. In TRPC4-deficient ileal myocytes the carbachol-induced membrane depolarizations are diminished greatly and the atropine-sensitive contraction elicited by acetylcholine release from excitatory motor neurons is reduced greatly. Additional deletion of TRPC6 aggravates these effects. Intestinal transit is slowed down in mice lacking TRPC4 and TRPC6. CONCLUSIONS: In intestinal smooth muscle cells TRPC4 and TRPC6 channels are gated by muscarinic receptors and are responsible for mI(CAT). They couple muscarinic receptors to depolarization of intestinal smooth muscle cells and voltage-activated Ca(2+)-influx and contraction, and thereby accelerate small intestinal motility in vivo.

Amolopkinins W1 and W2 – novel bradykinin-related peptides (BRPs) from the skin of the Chinese torrent frog, Amolops wuyiensis: antagonists of bradykinin-induced smooth muscle contraction of the rat ileum.

Bradykinin-related peptides (BRPs) represent one of the most widespread and closely studied families of amphibian defensive skin secretion peptides. Apart from canonical bradykinin (RPPGFSPFR) that was first reported in skin extracts of the European brown frog, Rana temporaria, many additional site-substituted, N- and/or C-terminally extended peptides have been isolated from skin extracts and secretions from representative species of the families Ranidae, Hylidae, Bombinatoridae and Leiopelmatidae. The most diverse range of BRPs has been found in ranid frog skin secretions and this probably reflects the diversity and number of species studied and their associated life histories within this taxon. Amolops (torrent or cascade frogs) is a genus within the Ranidae that has been poorly studied. Here we report the presence of two novel BRPs in the skin secretions of the Chinese Wuyi Mountain torrent frog (Amolops wuyiensis). Amolopkinins W1 and W2 are dodecapeptides differing in only one amino acid residue at position 2 (Val/Ala) that are essentially (Leu1, Thr6)-bradykinins extended at the N-terminus by either RVAL (W1) or RAAL (W2). Amolopkinins W1 and W2 are structurally similar to amolopkinin L1 from Amolops loloensis and the major BRP (Leu1, Thr6, Trp8)-bradykinin from the skin of the Japanese frog, Rana sakuraii. A. wuyiensis amolopkinins were separately encoded as single copies within discrete precursors of 61 amino acid residues as deduced from cloned skin cDNA. Synthetic replicates of both peptides were found to potently antagonize the contractile effects of canonical bradykinin on isolated rat ileum smooth muscle preparations. Amolopkinins thus appear to represent a novel sub-family of ranid frog skin secretion BRPs.