Neural network modeling in optimisation of continuous fermentation processes

The capability of self-recurrent neural networks in dynamic modeling of continuous fermentation is investigated in this simulation study. In the past, feedforward neural networks have been successfully used as one-step-ahead predictors. However, in steady-state optimisation of continuous fermentations the neural network model has to be iterated to predict many time steps ahead into the future in order to get steady-state values of the variables involved in objective cost function, and this iteration may result in increasing errors. Therefore, as an alternative to classical feedforward neural network trained by using backpropagation method, self-recurrent multilayer neural net trained by backpropagation through time method was chosen in order to improve accuracy of long-term predictions. Prediction capabilities of the resulting neural network model is tested by implementing this into the Integrated System Optimisation and Parameter Estimation (ISOPE) optimisation algorithm. Maximisation of cellular productivity of the baker's yeast continuous fermentation was used as the goal of the proposed optimising control problem. The training and prediction results of proposed neural network and performances of resulting optimisation structure are demonstrated.     

A hybrid neural learning algorithm using evolutionary learning and derivative free local search method

In this paper we investigate a hybrid model based on the Discrete Gradient method and an evolutionary strategy for determining the weights in a feed forward artificial neural network. Also we discuss different variants for hybrid models using the Discrete Gradient method and an evolutionary strategy for determining the weights in a feed forward artificial neural network. The Discrete Gradient method has the advantage of being able to jump over many local minima and find very deep local minima. However, earlier research has shown that a good starting point for the discrete gradient method can improve the quality of the solution point. Evolutionary algorithms are best suited for global optimisation problems. Nevertheless they are cursed with longer training times and often unsuitable for real world application. For optimisation problems such as weight optimisation for ANNs in real world applications the dimensions are large and time complexity is critical. Hence the idea of a hybrid model can be a suitable option. In this paper we propose different fusion strategies for hybrid models combining the evolutionary strategy with the discrete gradient method to obtain an optimal solution much quicker. Three different fusion strategies are discussed: a linear hybrid model, an iterative hybrid model and a restricted local search hybrid model. Comparative results on a range of standard datasets are provided for different fusion hybrid models.     

Efficient training of RBF networks for classification

Radial Basis Function networks with linear outputs are often used in regression problems because they can be substantially faster to train than Multi-layer Perceptrons. For classification problems, the use of linear outputs is less appropriate as the outputs are not guaranteed to represent probabilities. We show how RBFs with logistic and softmax outputs can be trained efficiently using the Fisher scoring algorithm. This approach can be used with any model which consists of a generalised linear output function applied to a model which is linear in its parameters. We compare this approach with standard non-linear optimisation algorithms on a number of datasets.     

Set-based particle swarm optimization applied to the multidimensional knapsack problem

Particle swarm optimization algorithms have been successfully applied to discrete/valued optimization problems. However, in many cases the algorithms have been tailored specifically for the problem at hand. This paper proposes a generic set-based particle swarm optimization algorithm for use in discrete-valued optimization problems that can be formulated as set-based problems. A detailed sensitivity analysis of the parameters of the algorithm is conducted. The performance of the proposed algorithm is then compared against three other discrete particle swarm optimization algorithms from literature using the multidimensional knapsack problem and is shown to statistically outperform the existing algorithms.     

Estimation of Spatiotemporal Neural Activity Using Radial Basis Function Networks

We report a method using radial basis function (RBF) networks to estimate the time evolution of population activity in topologically organized neural structures from single-neuron recordings. This is an important problem in neuroscience research, as such estimates may provide insights into systems-level function of these structures. Since single-unit neural data tends to be unevenly sampled and highly variable under similar behavioral conditions, obtaining such estimates is a difficult task. In particular, a class of cells in the superior colliculus called buildup neurons can have very narrow regions of saccade vectors for which they discharge at high rates but very large surround regions over which they discharge at low, but not zero, levels. Estimating the dynamic movement fields for these cells for two spatial dimensions at closely spaced timed intervals is a difficult problem, and no general method has been described that can be applied to all buildup cells. Estimation of individual collicular cells' spatiotemporal movement fields is a prerequisite for obtaining reliable two-dimensional estimates of the population activity on the collicular motor map during saccades. Therefore, we have developed several computational-geometry-based algorithms that regularize the data before computing a surface estimation using RBF networks. The method is then expanded to the problem of estimating simultaneous spatiotemporal activity occurring across the superior colliculus during a single movement (the inverse problem). In principle, this methodology could be applied to any neural structure with a regular, two-dimensional organization, provided a sufficient spatial distribution of sampled neurons is available.     

Hierarchical genetic algorithm for near optimal feedforward neural network design

In this paper, we propose a genetic algorithm based design procedure for a multi layer feed forward neural network. A hierarchical genetic algorithm is used to evolve both the neural networks topology and weighting parameters. Compared with traditional genetic algorithm based designs for neural networks, the hierarchical approach addresses several deficiencies, including a feasibility check highlighted in literature. A multi objective cost function is used herein to optimize the performance and topology of the evolved neural network simultaneously. In the prediction of Mackey Glass chaotic time series, the networks designed by the proposed approach prove to be competitive, or even superior, to traditional learning algorithms for the multi layer Perceptron networks and radial basis function networks. Based upon the chosen cost function, a linear weight combination decision making approach has been applied to derive an approximated Pareto optimal solution set. Therefore, designing a set of neural networks can be considered as solving a two objective optimization problem.     

A biologically inspired neural network for dynamic programming

An artificial neural network with a two-layer feedback topology and generalized recurrent neurons, for solving nonlinear discrete dynamic optimization problems, is developed. A direct method to assign the weights of neural networks is presented. The method is based on Bellmann's Optimality Principle and on the interchange of information which occurs during the synaptic chemical processing among neurons. The neural network based algorithm is an advantageous approach for dynamic programming due to the inherent parallelism of the neural networks; further it reduces the severity of computational problems that can occur in methods like conventional methods. Some illustrative application examples are presented to show how this approach works out including the shortest path and fuzzy decision making problems.     

Characterising the searchability of continuous optimisation problems for PSO

The focus of research in swarm intelligence has been largely on the algorithmic side with relatively little attention being paid to the study of problems and the behaviour of algorithms in relation to problems. When a new algorithm or variation on an existing algorithm is proposed in the literature, there is seldom any discussion or analysis of algorithm weaknesses and on what kinds of problems the algorithm is expected to fail. Fitness landscape analysis is an approach that can be used to analyse optimisation problems. By characterising problems in terms of fitness landscape features, the link between problem types and algorithm performance can be studied. This article investigates a number of measures for analysing the ability of a search process to improve fitness on a particular problem (called evolvability in literature but referred to as searchability in this study to broaden the scope to non-evolutionary-based search techniques). A number of existing fitness landscape analysis techniques originally proposed for discrete problems are adapted to work in continuous search spaces. For a range of benchmark problems, the proposed searchability measures are viewed alongside performance measures for a traditional global best particle swarm optimisation (PSO) algorithm. Empirical results show that no single measure can be used as a predictor of PSO performance, but that multiple measures of different fitness landscape features can be used together to predict PSO failure.     

Prediction of structural and functional features of protein and nucleic acid sequences by artificial neural networks.

The applications of artificial neural networks to the prediction of structural and functional features of protein and nucleic acid sequences are reviewed. A brief introduction to neural networks is given, including a discussion of learning algorithms and sequence encoding. The protein applications mostly involve the prediction of secondary and tertiary structure from sequence. The problems in nucleic acid analysis tackled by neural networks are the prediction of translation initiation sites in Escherichia coli, the recognition of splice junctions in human mRNA, and the prediction of promoter sites in E. coli. The performance of the approach is compared with other current statistical methods.     

Robust algorithm for arrhythmia classification in ECG using extreme learning machine

Background  

Recently, extensive studies have been carried out on arrhythmia classification algorithms using artificial intelligence pattern recognition methods such as neural network. To improve practicality, many studies have focused on learning speed and the accuracy of neural networks. However, algorithms based on neural networks still have some problems concerning practical application, such as slow learning speeds and unstable performance caused by local minima.     

Stochastic stability of particle swarm optimisation

Particle swarm optimisation (PSO) is a metaheuristic algorithm used to find good solutions in a wide range of optimisation problems. The success of metaheuristic approaches is often dependent on the tuning of the control parameters. As the algorithm includes stochastic elements that effect the behaviour of the system, it may be studied using the framework of random dynamical systems (RDS). In PSO, the swarm dynamics are quasi-linear, which enables an analytical treatment of their stability. Our analysis shows that the region of stability extends beyond those predicted by earlier approximate approaches. Simulations provide empirical backing for our analysis and show that the best performance is achieved in the asymptotic case where the parameters are selected near the margin of instability predicted by the RDS approach.     

A competitive clustering particle swarm optimizer for dynamic optimization problems

Optimization in dynamic optimization problems (DOPs) requires the optimization algorithms not only to locate, but also to continuously track the moving optima. Particle swarm optimization (PSO) is a population-based optimization algorithm, originally developed for static problems. Recently, several researchers have proposed variants of PSO for optimization in DOPs. This paper presents a novel multi-swarm PSO algorithm, namely competitive clustering PSO (CCPSO), designed specially for DOPs. Employing a multi-stage clustering procedure, CCPSO splits the particles of the main swarm over a number of sub-swarms based on the particles positions and on their objective function values. The algorithm automatically adjusts the number of sub-swarms and the corresponding region of each sub-swarm. In addition to the sub-swarms, there is also a group of free particles that explore the environment to locate new emerging optima or exploit the current optima which are not followed by any sub-swarm. The adaptive search strategy adopted by the sub-swarms improves both the exploitation and tracking characteristics of CCPSO. A set of experiments is conducted to study the behavior of the proposed algorithm in different DOPs and to provide guidelines for setting the algorithm’s parameters in different problems. The results of CCPSO on a variety of moving peaks benchmark (MPB) functions are compared with those of several state-of-the-art PSO algorithms, indicating the efficiency of the proposed model.     

Evolutionary optimization of RBF networks

One of the main obstacles to the widespread use of artificial neural networks is the difficulty of adequately defining values for their free parameters. This article discusses how Radial Basis Function (RBF) networks can have their parameters defined by genetic algorithms. For such, it presents an overall view of the problems involved and the different approaches used to genetically optimize RBF networks. A new strategy to optimize RBF networks using genetic algorithms is proposed, which includes new representation, crossover operator and the use of a multiobjective optimization criterion. Experiments using a benchmark problem are performed and the results achieved using this model are compared to those achieved by other approaches.     

Artificial astrocytes improve neural network performance

Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function.     

Comparison of physics-based and data-driven modelling techniques for dynamic optimisation of fed-batch bioprocesses

The development of digital bioprocessing technologies is critical to operate modern industrial bioprocesses. This study conducted the first investigation on the efficiency of using physics-based and data-driven models for the dynamic optimisation of long-term bioprocess. More specifically, this study exploits a predictive kinetic model and a cutting-edge data-driven model to compute open-loop optimisation strategies for the production of microalgal lutein during a fed-batch operation. Light intensity and nitrate inflow rate are used as control variables given their key impact on biomass growth and lutein synthesis. By employing different optimisation algorithms, several optimal control sequences were computed. Due to the distinct model construction principles and sophisticated process mechanisms, the physics-based and the data-driven models yielded contradictory optimisation strategies. The experimental verification confirms that the data-driven model predicted a closer result to the experiments than the physics-based model. Both models succeeded in improving lutein intracellular content by over 40% compared to the highest previous record; however, the data-driven model outperformed the kinetic model when optimising total lutein production and achieved an increase of 40–50%. This indicates the possible advantages of using data-driven modelling for optimisation and prediction of complex dynamic bioprocesses, and its potential in industrial bio-manufacturing systems.     

Dynamic output feedback stabilization for nonlinear systems based on standard neural network models

A neural-model-based control design for some nonlinear systems is addressed. The design approach is to approximate the nonlinear systems with neural networks of which the activation functions satisfy the sector conditions. A novel neural network model termed standard neural network model (SNNM) is advanced for describing this class of approximating neural networks. Full-order dynamic output feedback control laws are then designed for the SNNMs with inputs and outputs to stabilize the closed-loop systems. The control design equations are shown to be a set of linear matrix inequalities (LMIs) which can be easily solved by various convex optimization algorithms to determine the control signals. It is shown that most neural-network-based nonlinear systems can be transformed into input-output SNNMs to be stabilization synthesized in a unified way. Finally, some application examples are presented to illustrate the control design procedures.