Variable neural adaptive robust control: a switched system approach.

Variable neural adaptive robust control strategies are proposed for the output tracking control of a class of multiinput multioutput uncertain systems. The controllers incorporate a novel variable-structure radial basis function (RBF) network as the self-organizing approximator for unknown system dynamics. It can determine the network structure online dynamically by adding or removing RBFs according to the tracking performance. The structure variation is systematically considered in the stability analysis of the closed-loop system using a switched system approach with the piecewise quadratic Lyapunov function. The performance of the proposed variable neural adaptive robust controllers is illustrated with simulations.

Sport skill level and gender with relation to age, physical development and special fitness of the participants of Olympic volleyball tournament Beijing 2008.

The aim of this study was to provide an answer to the question whether and how age, body height, body mass, body mass index and results from fitness tests are related to sport skill level and gender of the participants of the Olympic volleyball tournament. Two-Way ANOVA was used to find the dependency of the variables on the factor of sport skill level (A--teams which took places 1 to 4, B--places from 5 to 8; C--places from 9 to 12) and gender (F--female; M--male). Statistical significance was set at p < 0.05. The Bonferroni's adjustment was carried out for three p = 0.017 and fifteen p = 0.003 pairs of comparisons). The M and F athletes included in A-C groups (N = 48 in each group) were than compared to the classification in the neural network of Probabilistic Neural Network (PNN). A combined effect of the factors of sports level and gender on the height of attack jump (F = 4.13; p = 0.02) and block jump (F = 9.22; p < 0.001) was identified. The level of achievement was modified by the differences between the men and women. A significant advantage over the groups B and C was found for attack height and block height. In the group A, the differences between the results obtained for women and men in the ranges of attack and block with respect to the net height were not significant. Mean range of block jump did not match up to attack jump, particularly in women. The application of PNN network showed that age, BMI, relative attack jump and block jump are good predictors of sport results. The percentage of properly classified players in the group of men was lower than in women (42.4 vs. 56.3%). In this regard, big differences were found at the lower level of sport results: A (77.1 vs. 79.2%), B (25.0 vs. 25.0%) and C (25.0 vs. 64.6%). In conclusion, selection for national teams should take into consideration the players with long competitive experience with adequate weight/height ratios, who exhibit good training adaptations to jumping exercise.

Correcting hypothalamic-pituitary-adrenal axis dysfunction using observer-based explicit nonlinear model predictive control.

The hypothalamic-pituitary-adrenal (HPA) axis is critical in maintaining homeostasis under physical and psychological stress by modulating cortisol levels in the body. Dysregulation of cortisol levels is linked to numerous stress-related disorders. In this paper, an automated treatment methodology is proposed, employing a variant of nonlinear model predictive control (NMPC), called explicit MPC (EMPC). The controller is informed by an unknown input observer (UIO), which estimates various hormonal levels in the HPA axis system in conjunction with the magnitude of the stress applied on the body, based on measured concentrations of adreno-corticotropic hormones (ACTH). The proposed closed-loop control strategy is tested on multiple in silico patients and the effectiveness of the controller performance is demonstrated.

Large-scale pattern storage and retrieval using generalized brain-state-in-a-box neural networks.

In this paper, a generalized Brain-State-in-a-Box (gBSB)-based hybrid neural network is proposed for storing and retrieving pattern sequences. The hybrid network consists of autoassociative and heteroassociative parts. Then, a large-scale image storage and retrieval neural system is constructed using the gBSB-based hybrid neural network and the pattern decomposition concept. The notion of the deadbeat stability is employed to describe the stability property of the vertices of the hypercube to which the trajectories of the gBSB neural system are constrained. Extensive simulations of large scale pattern and image storing and retrieval are presented to illustrate the results obtained.

Self-organizing radial basis function network for real-time approximation of continuous-time dynamical systems.

Real-time approximators for continuous-time dynamical systems with many inputs are presented. These approximators employ a novel self-organizing radial basis function (RBF) network, which varies its structure dynamically to keep the prescribed approximation accuracy. The RBFs can be added or removed online in order to achieve the appropriate network complexity for the real-time approximation of the dynamical systems and to maintain the overall computational efficiency. The performance of this variable structure RBF network approximator with both Gaussian RBF (GRBF) and raised-cosine RBF (RCRBF) is analyzed. The compact support of RCRBF enables faster training and easier output evaluation of the network than that of the network with GRBF. The proposed real-time self-organizing RBF network approximator is then employed to approximate both linear and nonlinear dynamical systems to illustrate the effectiveness of our proposed approximation scheme, especially for higher order dynamical systems. The uniform ultimate boundedness of the approximation error is proved using the second method of Lyapunov.

Neural network prediction of peptide separation in strong anion exchange chromatography.

MOTIVATION: The still emerging combination of technologies that enable description and characterization of all expressed proteins in a biological system is known as proteomics. Although many separation and analysis technologies have been employed in proteomics, it remains a challenge to predict peptide behavior during separation processes. New informatics tools are needed to model the experimental analysis method that will allow scientists to predict peptide separation and assist with required data mining steps, such as protein identification. RESULTS: We developed a software package to predict the separation of peptides in strong anion exchange (SAX) chromatography using artificial neural network based pattern classification techniques. A multi-layer perceptron is used as a pattern classifier and it is designed with feature vectors extracted from the peptides so that the classification error is minimized. A genetic algorithm is employed to train the neural network. The developed system was tested using 14 protein digests, and the sensitivity analysis was carried out to investigate the significance of each feature. AVAILABILITY: The software and testing results can be downloaded from ftp://ftp.bbc.purdue.edu.

Autoassociative memory design using interconnected generalized brain-state-in-a-box neural networks.

A class of interconnected neural networks composed of generalized Brain-State-in-a-Box (gBSB) neural subnetworks is considered. Interconnected gBSB neural network architectures are proposed along with their stability conditions. The design of the interconnected neural networks is reduced to the problem of solving linear matrix inequalities (LMIs) to determine the interconnection parameters. A method for solving LMIs is devised generating the solutions that, in general, are further away from zero than the corresponding solutions obtained using MATLAB's LMI toolbox, thus resulting in stronger interconnections between the subnetworks. The proposed architectures are then used to construct neural associative memories. Simulations are performed to illustrate the results obtained.

Associative memory design using overlapping decomposition and generalized brain-state-in-a-box neural networks.

This paper is concerned with large scale associative memory design. A serious problem with neural associative memories is the quadratic growth of the number of interconnections with the problem size. An overlapping decomposition algorithm is proposed to attack this problem. Specifically, a pattern to be processed is decomposed into overlapping sub-patterns. Then, neural sub-networks are constructed that process the sub-patterns. An error correction algorithm operates on the outputs of each sub-network in order to correct the mismatches between sub-patterns that are obtained from the independent recall processes of individual sub-networks. The performance of the proposed large scale associative memory is illustrated using two-dimensional images. It is shown that the proposed method reduces the computing cost of the design of the associative memories compared with non-interconnected associative memories.

Real-time synthesis of sparsely interconnected neural associative memories.

The problem of implementing associative memories using sparsely interconnected generalized Brain-State-in-a-Box (gBSB) network is addressed in this paper. In particular, a "designer" neural network that synthesizes the associative memories is proposed. An upper bound on the time required for the designer network to reach a solution is determined. A neighborhood criterion with toroidal geometry for the cellular gBSB network is analyzed, in which the number of adjacent cells is independent of the generic cell location. A design method of neural associative memories with prespecified interconnecting weights is presented. The effectiveness of the proposed synthesis method is demonstrated with numerical examples.

On the Brain-State-in-a-Convex-Domain Neural Models.

We propose and investigate new types of neural network models. They can be viewed as discrete linear systems operating on closed and bounded, that is, compact, convex domains. We first analyze the dynamic behavior of a neural network model on an arbitrary convex domain. Then, we analyze two specific cases: when the convex domain is a ball, and the case when the convex domain is a simplex. The equilibrium points of the proposed neural models are located and their stability is investigated. Copyright 1996 Elsevier Science Ltd

Learning and Forgetting in Generalized Brain-state-in-a-box (BSB) Neural Associative Memories.

We propose learning and forgetting techniques for the generalized brain-state-in-a-box (BSB) based associative memories. A generalization of the BSB model allows each neuron to have its own bias and the synaptic weight matrix does not have to be symmetric. A pattern is learned by a memory if its noisy or an incomplete version presented to the memory is mapped back to this pattern. A pattern, previously stored, is forgotten or deleted from the memory if a stimulus that is a perturbed version of the pattern, when presented to the memory, is not mapped back to this pattern. In this paper we propose "on-line" memory storage and deletion methods using an iterative method of computing the pseudo-inverse of a given matrix. The proposed methods allow one to "add" or "delete" a memory pattern by updating, rather than recomputing from scratch, the current synaptic weight matrix in a single step. We first analyze the desired characteristics of neural network associative memories. After that, we review the existing methods for design of neural associative memories. Then we discuss the generalized BSB neural model and its possible function as an associative memory and proffer arguments in support of using such models for neural associative memories. In particular, the generalized BSB type models are easier to analyze, synthesize, and implement than other neural networks. The results obtained are illustrated by numerical examples. Copyright 1996 Elsevier Science Ltd