Neural networks assisted PID autotuning

A scheme of automatically tuning the existing industrial PID controllers using neural networks is proposed. The scheme estimates the process critical data on-line in proportional control mode.

A neural network PID autotuner

Proportional, Integral and Derivative (PID) regulators are standard building blocks for industrial automation. Their popularity comes from their rebust performance and also from their functional simplicity. Whether because the plant is time-varying, or because of components ageing, these controllers need to be regularly retuned.

A neural network controller

Proportional, Integral and Derivative (PID) regulators are standard building blocks for industrial automation. The popularity of these regulators comes from their rebust performance in a wide range of operating conditions, and also from their functional simplicity, which makes them suitable for manual tuning.

A new formulation of the learning problem for a neural network controller

In this paper we consider the learning problem for a class of multilayer perceptrons which is practically relevant in control systems applications. By reformulating this problem, a new criterion is developed, which reduces the number of iterations required for the learning phase.

Supervised training approach using spiking neural networks

One of the basic aspects of some neural networks is their attempt to approximate as much as possible their biological counterparts. The goal is to achieve a simple and robust network, easy to understand and able of simulating the human brain at a computational level. Recently a third generation of neural networks (NN) [1], called Spiking Neural Networks(SNN) was appeared. This new kind of networks use the time of a electrical pulse, or spike, to encode the information. In the first and second generation of NN analog values are used in the communication between neurons.

Prediction of the solar radiation using RBF neural networks and ground-to-sky images

In this study, Artificial Neural Networks are applied to multistep long term solar radiation prediction. The networks are trained as one-step-ahead predictors and iterated over time to obtain multi-step longer term predictions. Auto-regressive and Auto-regressive with exogenous inputs solar radiationmodels are compared, considering cloudiness indices as inputs in the latter case. These indices are obtained through pixel classification of ground-to-sky images. The input-output structure of the neural network models is selected using evolutionary computation methods.

Predicting the greenhouse inside air temperature with RBF neural networks

The application of the Radial Basis Function (RBF) Neural Network (NN) to greenhouse inside air temperature modelling has been previously investigated (Ferreira et al., 2000a). In those studies, the inside air temperature is modelled as a function of the inside relative humidity and of the outside temperature and solar radiation. A second-order model structure previously selected (Cunha et al., 1996) in the context of dynamic temperature models identification, is used.

Development of non-viral vectors for gene therapy for pathologies of the retina

Tese de doutoramento, Ciências Biomédicas, Departamento de Ciências Biomédicas e Medicina, Universidade do Algarve, 2015

Face recogniton based on the optimal combination of neural networks, eigenfaces and least squares matching methods

Report of a research project of the Fachhochschule Hannover, University of Applied Sciences and Arts, Department of Information Technologies. Automatic face recognition increases the security standards at public places and border checkpoints. The picture inside the identification documents could widely differ from the face, that is scanned under random lighting conditions and for unknown poses. The paper describes an optimal combination of three key algorithms of object recognition, that are able to perform in real time. The camera scan is processed by a recurrent neural network, by a Eigenfaces (PCA) method and by a least squares matching algorithm. Several examples demonstrate the achieved robustness and high recognition rate.

Nuclear and mitochondrial control of the apoptosis machinery regulates neural stem cell fate

Tese de doutoramento, Farmácia (Bioquímica), Universidade de Lisboa, Faculdade de Farmácia, 2014

Exploring the modulatory role of A2A receptors in oligodendrogenesis derived from neural stem/progenitor cells of the subventricular zone

Tese de mestrado, Neurociências, Faculdade de Medicina, Universidade de Lisboa, 2015

Identification of meat spoilage by FTIR spectroscopy and neural networks

Freshness and safety of muscle foods are generally considered as the most important parameters for the food industry. To address the rapid determination of meat spoilage, Fourier transform infrared (FTIR) spectroscopy technique, with the help of advanced learning-based methods, was attempted in this work. FTIR spectra were obtained from the surface of beef samples during aerobic storage at various temperatures, while a microbiological analysis had identified the population of Total viable counts. A fuzzy principal component algorithm has been also developed to reduce the dimensionality of the spectral data. The results confirmed the superiority of the adopted scheme compared to the partial least squares technique, currently used in food microbiology.

3D Reconstruction of Medical Images from Slices Automatically Landmarked with Growing Neural Models

In this study, we utilise a novel approach to segment out the ventricular system in a series of high resolution T1-weighted MR images. We present a brain ventricles fast reconstruction method. The method is based on the processing of brain sections and establishing a fixed number of landmarks onto those sections to reconstruct the ventricles 3D surface. Automated landmark extraction is accomplished through the use of the self-organising network, the growing neural gas (GNG), which is able to topographically map the low dimensionality of the network to the high dimensionality of the contour manifold without requiring a priori knowledge of the input space structure. Moreover, our GNG landmark method is tolerant to noise and eliminates outliers. Our method accelerates the classical surface reconstruction and filtering processes. The proposed method offers higher accuracy compared to methods with similar efficiency as Voxel Grid.

Protein deiminases: new players in the developmentally regulated loss of neural regenerative ability

Spinal cord regenerative ability is lost with development, but the mechanisms underlying this loss are still poorly understood. In chick embryos, effective regeneration does not occur after E13, when spinal cord injury induces extensive apoptotic response and tissue damage. As initial experiments showed that treatment with a calcium chelator after spinal cord injury reduced apoptosis and cavitation, we hypothesized that developmentally regulated mediators of calcium-dependent processes in secondary injury response may contribute to loss of regenerative ability. To this purpose we screened for such changes in chick spinal cords at stages of development permissive (E11) and non-permissive (E15) for regeneration. Among the developmentally regulated calcium-dependent proteins identified was PAD3, a member of the peptidylarginine deiminase (PAD) enzyme family that converts protein arginine residues to citrulline, a process known as deimination or citrullination. This post-translational modification has not been previously associated with response to injury. Following injury, PAD3 up-regulation was greater in spinal cords injured at E15 than at E11. Consistent with these differences in gene expression, deimination was more extensive at the non-regenerating stage, E15, both in the gray and white matter. As deimination paralleled the extent of apoptosis, we investigated the effect of blocking PAD activity on cell death and deiminated-histone 3, one of the PAD targets we identified by mass-spectrometry analysis of spinal cord deiminated proteins. Treatment with the PAD inhibitor, Cl-amidine, reduced the abundance of deiminated-histone 3, consistent with inhibition of PAD activity, and significantly reduced apoptosis and tissue loss following injury at E15. Altogether, our findings identify PADs and deimination as developmentally regulated modulators of secondary injury response, and suggest that PADs might be valuable therapeutic targets for spinal cord injury.

A Fuzzy-Wavelet Neural Network Model for the Detection of Meat Spoilage using an Electronic Nose

Food product safety is one of the most promising areas for the application of electronic noses. The performance of a portable electronic nose has been evaluated in monitoring the spoilage of beef fillet stored aerobically at different storage temperatures (0, 4, 8, 12, 16 and 20°C). This paper proposes a fuzzy-wavelet neural network model which incorporates a clustering pre-processing stage for the definition of fuzzy rules. The dual purpose of the proposed modeling approach is not only to classify beef samples in the respective quality class (i.e. fresh, semi-fresh and spoiled), but also to predict their associated microbiological population directly from volatile compounds fingerprints. Comparison results indicated that the proposed modeling scheme could be considered as a valuable detection methodology in food microbiology