An offset-free neural controller based on a non-extrapolating scheme for approximating the inverse process dynamics

This work presents a novel control scheme based on approximating the inverse process dynamics with a radial basis function (RBF) neural network model, trained with the fuzzy means algorithm. The produced RBF network constitutes an inverse model of the process, which can be applied as an explicit control law. In order to avoid extrapolation in the RBF model predictions, a concept borrowed from chemometrics, namely the applicability domain, is incorporated to the proposed framework. Moreover, an error correction term is added, allowing the inverse neural controller to account for modeling errors and process uncertainty and eliminate offset. The proposed approach is applied to the control of a nonlinear Continuous Stirred Tank Reactor (CSTR) exhibiting multiple equilibrium points, including an unstable one. A comparison with other control schemes on various tests, including set-point tracking, unmeasured disturbance rejection and process uncertainty highlights the advantages of the proposed controller.     

Editorial

This study investigates the potential of applying the radial basis function (RBF) neural network architecture for the classification of multispectral very high spatial resolution satellite images into 13 classes of various scales. For the development of the RBF classifiers, the innovative fuzzy means training algorithm is utilized, which is based on a fuzzy partition of the input space. The method requires only a short amount of time to select both the structure and the parameters of the RBF classifier. The new technique was applied to the area of Lake Kerkini, which is a wetland of great ecological value, located in northern Greece. Eleven experiments were carried out in total in order to investigate the performance of the classifier using different input parameters (spectral and textural) as well as different window sizes and neural network complexities. For comparison purposes the same satellite scene was classified using the maximum likelihood (MLH) classification with the same set of training samples. Overall, the neural network classifiers outperformed the MLH classification by 10–17%, reaching a maximum overall accuracy of 78%. Analysis showed that the selection of input parameters is vital for the success of the classifiers. On the other hand, the incorporation of textural analysis and/or modification of the window size do not affect the performance substantially.     

Substrate Specificity of the Highly Thermostable Esterase EstDZ3

Esterases are among the most studied enzymes, and their applications expand into several branches of industrial biotechnology. Yet, despite the fact that information on their substrate specificity is crucial for selecting or designing the best fitted biocatalyst for the desired application, it cannot be predicted from their amino acid sequence. In this work, we studied the substrate scope of the newly discovered hydrolytic extremozyme, EstDZ3, against a library of esters with variable carbon chain lengths in an effort to understand the crucial amino acids for the substrate selectivity of this enzyme. EstDZ3 appears to be active against a wide range of esters with high selectivity towards medium- to long-carbon chain vinyl esters. In-silico studies of its 3D structure revealed that the selectivity might arise from the mainly hydrophobic nature of the active site's environment.     

Nonlinear model predictive control for distributed parameter systems using data driven artificial neural network models

In this work the radial basis function neural network architecture is used to model the dynamics of Distributed Parameter Systems (DPSs). Two pure data driving schemes which do not require knowledge of the governing equations are described and compared. In the first method, the neural network methodology generates the full model of the system that is able to predict the process outputs at any spatial point. Past values of the process inputs and the coordinates of the specific location provide the input information to the model. The second method uses empirical basis functions produced by the Singular Value Decomposition (SVD) on the snapshot matrix to describe the spatial behavior of the system, while the neural network model is used to estimate only the temporal coefficients. The models produced by both methods are then implemented in Model Predictive Control (MPC) configurations, suitable for constrained DPSs. The accuracies of the modeling methodologies and the efficiencies of the proposed MPC formulations are tested in a tubular reactor and produce encouraging results.     

The politics and science behind GMO acceptance

The question of nutritional quality has arisen in the International Community over the last few years along with other important issues such as population aging, multipopulation societies, and political conflicts. The nutritional issue is questioned both quantitatively and qualitatively. It is well known that the planet faces enormous problems with food that is available. Nowadays 20% of the population consumes approximately 80% of the produced energy and natural resources. During the last 15 years, a series of food scares and crises (BSE, dioxin, foot and mouth disease, bird flu) have seriously undermined public confidence in food producers and operators and their capacity to produce safe food. As a result, food safety has become a top priority of the European legislative authorities. Genetically Modified Organisms (GMOs) is the new food safety concern which despite the intense reactions from Non Governmental Organizations and consumer organizations have entered our lives with inadequate legislative measures to protect consumers from their consumption. The GMO issue will be the issue for discussion in the long run not only for the European Community but also for the international community as far as scientific, economical, political, ideological, ethical, and human issues are concerned. These issues are discussed in this paper along with a case of study of GM fish.     

A metaheuristic approach for the sequencing by hybridization problem with positive and negative errors

This work introduces a metaheuristic method for the reconstruction of the DNA string from its l-mer content in the presence of large amounts of positive and negative errors. The procedure consists of three parts: the formulation of the problem as an asymmetric traveling salesman problem (ATSP), a technique for handling the positive errors and an optimization algorithm that solves the formulated problem. The optimization algorithm is a variation of the threshold accepting method with intense local search and its function is controlled by a size diminishing shell. The optimization algorithm is used consecutively on ATSPs of continuously decreasing sizes till it reaches a final solution. The proposed method provides solutions of better quality compared to algorithms in the recent bibliography.     

A new neural network model for evaluating the performance of various hourly slope irradiation models: Implementation for the region of Athens

The present study is divided into two parts. The first part deals with the comparison of various hourly slope irradiation models, found in the literature, and the selection of the most accurate for the region of Athens. In the second part the prediction of global solar irradiance on inclined surfaces is performed, based on neural network techniques.The models tested are classified as isotropic (Liu and Jordan, Koronakis, Jimenez and Castro, Badescu, Tian) and anisotropic (Bugler, Temps and Coulson, Klucher, Ma and Iqbal, Reindl) based on the treatment of diffuse irradiance. For the aforementioned models, a qualitative comparison, based on diagrams, was carried out, and several statistical indices were calculated (coefficient of determination R², mean bias error MBE, relative mean bias error MBE/A(%), root mean square error RMSE, relative root mean square error RMSE/A(%),statistical index t-stat), in order to select the optimal.The isotropic models of “Tian” and “Badescu” show the best accordance to the recorded values. The anisotropic model of “Ma&Iqbal” and the pseudo-isotropic model of “Jimenez&Castro”, show poor performance compared to other models. Finally, a neural network model is developed, which predicts the global solar irradiance on a tilted surface, using as input data the total solar irradiance on a horizontal surface, the extraterrestrial radiation, the solar zenith angle and the solar incidence angle on a tilted plane. The comparison with the aforementioned models has shown that the neural network model, predicts more realistically the total solar irradiance on a tilted surface, as it performs better in regions where the other models show underestimation or overestimation in their calculations.     

Determination of the optimal tilt angle and orientation for solar photovoltaic arrays

This paper deals with the determination of optimum tilt angle and orientation for solar photovoltaic arrays in order to maximize incident solar irradiance exposed on the array, for a specific period of time. The method is extended, by introducing a second objective, i.e. minimization of variance of the produced power, in terms of hourly power generation throughout the given period of time. The proposed method uses both well-established models and data collected from the particular area where the photovoltaic panels will be installed and is built upon four steps. In the first step, the recorded data are used in order to select the most accurate, among several isotropic and anisotropic models that can be found in the literature, for predicting diffuse solar irradiance on inclined surfaces. In the second step, the recorded data and the selected model are used to construct a database that contains the averages and the variances of the hourly global solar irradiance on tilted surfaces over specific periods of time, for various tilt angles and orientations. In the third step, the database of the previous step is utilized to produce meta-models that correlate tilt angle and orientation with mean global irradiance and its variance on tilted surfaces. Finally, an optimization problem is formulated, aiming to determining the optimum values of tilt angle and orientation, taking into account the constraints and limitations of the system.     

Safety and Security in Multiagent Systems: Report on the 2nd SASEMAS workshop (SASEMAS'05)

As intelligent autonomous agents and multiagent systems' applications become more pervasive, it becomes increasingly more important to understand the risks associated with using these systems. Incorrect or inappropriate agent behaviour can have harmful effects including financial cost, loss of data, and injury to humans or systems. Thus, security and safety are two central issues when developing and deploying such systems.However, the process of developing safe and secure multiagent systems, and verifying and validating them, is much more difficult than for conventional software systems. This is due to many agent-related aspects, such as the complex and rich multiagent environments, the risks involved in such environments, and the characteristics that can be found in agent systems such as learning, dynamic reacting and adapting. Hence, new and different techniques and perspectives are required to assist with the development and deployment of such systems.The Safety and Security in Multiagent Systems (SASEMAS) workshop presents new developments, and lessons learned from real world cases, and it provides a forum for the exchange of ideas and discussion on areas related to security and safety in multiagent systems.