A. E. Ruano

Fast Line, Arc/Circle and Leg Detection from Laser Scan Data in a Player Driver

A feature detection system has been developed for real-time identification of lines, circles and people legs from laser range data. A new method suitable for arc/circle detection is proposed: the Inscribed Angle Variance (IAV). Lines are detected using a recursive line fitting method. The people leg detection is based on geometrical relations. The system was implemented as a plugin driver in Player, a mobile robot server. Real results are presented to verify the effectiveness of the proposed algorithms in indoor environment with moving objects.

Neural network models in greenhouse air temperature prediction

Abstract The adequacy of radial basis function neural networks to model the inside air temperature of a hydroponic greenhouse as a function of the outside air temperature and solar radiation, and the inside relative humidity, is addressed. As the model is intended to be incorporated in an environmental control strategy both off-line and on-line methods could be of use to accomplish this task. In this paper known hybrid off-line training methods and on-line learning algorithms are analyzed. An off-line method and its application to on-line learning is proposed. It exploits the linear–non-linear structure found in radial basis function neural networks.

Real-time parameter estimation of dynamic temperature models for greenhouse environmental control

Abstract For a greenhouse located at UTAD-University, the methods used to estimate (in real-time) the parameters of the inside air temperature model will be described. The structure and the parameters of the climate discrete-time dynamic model were previously identified using data acquired during two different periods of the year. Several experiments showed that the second-order models identified achieve a close agreement between simulated and experimental data. Later, it was found that parameters change with varying operational conditions. Thus, for an efficient use of these models in real-time control, a recursive identification technique was implemented for the estimation of the parameters.

Nonlinear identification of aircraft gas-turbine dynamics

Abstract Identification results for the shaft-speed dynamics of an aircraft gas turbine, under normal operation, are presented. As it has been found that the dynamics vary with the operating point, nonlinear models are employed. Two different approaches are considered: NARX models, and neural network models, namely multilayer perceptrons, radial basis function networks and B-spline networks. A special attention is given to genetic programming, in a multiobjective fashion, to determine the structure of NARMAX and B-spline models.

Genetic assisted selection of RBF model structures for greenhouse inside air temperature prediction

This paper presents results on the application of Multi-Objective Genetic Algorithms to the selection of Radial Basis Function Neural Networks structures. The neural networks are to be incorporated in a real-time predictive greenhouse environmental control strategy, as predictors of the inside air temperature. Previous research conducted by the authors modelled the inside air temperature as a function of the inside relative humidity and of the outside temperature and solar radiation. A second-order model structure previously selected in the context of dynamic temperature models identification was used. Several training and learning methods were compared, and the application of the Levenberg-Marquardt optimisation method was found to be the best way to determine the neural network parameters. The application of correlation-based model-validity tests revealed that the validity of such a second-order model structure could be manually improved after inspection of the tests results. Both network performance and validity are certainly affected by the number of neurons, the input variables considered and the time delays used. As the number of alternatives is huge, Multi-Objective Genetic Algorithms are applied here to the selection of network inputs and number of neurons.

Exploiting the separability of linear and nonlinear parameters in radial basis function networks

In intelligent control applications, neural models and controllers are usually designed by performing an off-line training, and then adapting it online when placed in the operating environment. It is therefore of crucial importance to obtain a good off-line model by means of a good off-line training algorithm. In the paper a method is presented that fully exploits the linear-nonlinear structure found in radial basis function networks, being additionally applicable to other feedforward supervised neural networks. The new algorithm is compared with two known hybrid methods.

Supervised training algorithms for B-Spline neural networks and neuro-fuzzy systems

Complete supervised training algorithms for B-Spline neural networks and fuzzy rule-based systems are discussed. By introducing the relationships between B-Spline neural networks and Mamdani (satisfying certain assumptions) and Takagi-Kang-Sugeno fuzzy models, training algorithms developed initially for neural networks can be adapted to fuzzy systems. The standard training criterion is reformulated, by separating its linear and nonlinear parameters. By employing this reformulated criterion with the Levenberg-Marquardt algorithm, a new training method, offering a fast rate of convergence is obtained. It is also shown that the standard Error-Back Propagation algorithm, the most common training method for this class of systems, exhibits a very poor and unreliable performance.

Anytime information processing based on fuzzy and neural network models

In modern measurement and control systems, the available time and resources are often not only limited, but could change during the operation of the system. In these cases, the so called anytime algorithms could be used advantageously. While different soft computing methods are in widespread use in system modeling, their usability in these cases are limited, because the lack of a universal method for the determination of the needed complexity often results in huge and redundant neural networks/fuzzy rule-bases. This paper proposes a possible way to carry out anytime information processing in fuzzy systems or neural networks, with the help of the SVD-based complexity reduction algorithm.

Online Sliding-Window Methods for Process Model Adaptation

Online learning algorithms are needed when the process to be modeled is time varying or when it is impossible to obtain offline data that cover the whole operating region. To minimize the problems of parameter shadowing and interference, sliding-window-based algorithms are used. It is shown that, by using a sliding-window policy that enforces the novelty of the data it stores and by using a procedure to prevent unnecessary parameter updates, the performance achieved is improved over a first-in-first-out (FIFO) policy with fixed interval parameter updates. Important savings in computational effort are also obtained.

A Soft-Computing Methodology for Noninvasive Time-Spatial Temperature Estimation

The safe and effective application of thermal therapies is restricted due to lack of reliable noninvasive temperature estimators. In this paper, the temporal echo-shifts of backscattered ultrasound signals, collected from a gel-based phantom, were tracked and assigned with the past temperature values as radial basis functions neural networks input information. The phantom was heated using a piston-like therapeutic ultrasound transducer. The neural models were assigned to estimate the temperature at different intensities and points arranged across the therapeutic transducer radial line (60 mm apart from the transducer face). Model inputs, as well as the number of neurons were selected using the multiobjective genetic algorithm (MOGA). The best attained models present, in average, a maximum absolute error less than 0.5 C, which is pointed as the borderline between a reliable and an unreliable estimator in hyperthermia/diathermia. In order to test the spatial generalization capacity, the best models were tested using spatial points not yet assessed, and some of them presented a maximum absolute error inferior to 0.5 C, being ldquoelectedrdquo as the best models. It should be also stressed that these best models present implementational low-complexity, as desired for real-time applications.