A contribution to semantic description of images and videos: an application of soft biometrics

Humans have a high ability to extract visual data information acquired by sight. Trought a learning process, which starts at birth and continues throughout life, image interpretation becomes almost instinctively. At a glance, one can easily describe a scene with reasonable precision, naming its main components. Usually, this is done by extracting low-level features such as edges, shapes and textures, and associanting them to high level meanings. In this way, a semantic description of the scene is done. An example of this, is the human capacity to recognize and describe other people physical and behavioral characteristics, or biometrics. Soft-biometrics also represents inherent characteristics of human body and behaviour, but do not allow unique person identification. Computer vision area aims to develop methods capable of performing visual interpretation with performance similar to humans. This thesis aims to propose computer vison methods which allows high level information extraction from images in the form of soft biometrics. This problem is approached in two ways, unsupervised and supervised learning methods. The first seeks to group images via an automatic feature extraction learning , using both convolution techniques, evolutionary computing and clustering. In this approach employed images contains faces and people. Second approach employs convolutional neural networks, which have the ability to operate on raw images, learning both feature extraction and classification processes. Here, images are classified according to gender and clothes, divided into upper and lower parts of human body. First approach, when tested with different image datasets obtained an accuracy of approximately 80% for faces and non-faces and 70% for people and non-person. The second tested using images and videos, obtained an accuracy of about 70% for gender, 80% to the upper clothes and 90% to lower clothes. The results of these case studies, show that proposed methods are promising, allowing the realization of automatic high level information image annotation. This opens possibilities for development of applications in diverse areas such as content-based image and video search and automatica video survaillance, reducing human effort in the task of manual annotation and monitoring.

Improving drug discovery using a neural networks based parallel scoring function

Virtual Screening (VS) methods can considerably aid clinical research, predicting how ligands interact with drug targets. Most VS methods suppose a unique binding site for the target, but it has been demonstrated that diverse ligands interact with unrelated parts of the target and many VS methods do not take into account this relevant fact. This problem is circumvented by a novel VS methodology named BINDSURF that scans the whole protein surface to find new hotspots, where ligands might potentially interact with, and which is implemented in massively parallel Graphics Processing Units, allowing fast processing of large ligand databases. BINDSURF can thus be used in drug discovery, drug design, drug repurposing and therefore helps considerably in clinical research. However, the accuracy of most VS methods is constrained by limitations in the scoring function that describes biomolecular interactions, and even nowadays these uncertainties are not completely understood. In order to solve this problem, we propose a novel approach where neural networks are trained with databases of known active (drugs) and inactive compounds, and later used to improve VS predictions.

Delays in activity based neural networks

In this paper we study the effect of two distinct discrete delays on the dynamics of a Wilson-Cowan neural network. This activity based model describes the dynamics of synaptically interacting excitatory and inhibitory neuronal populations. We discuss the interpretation of the delays in the language of neurobiology and show how they can contribute to the generation of network rhythms. First we focus on the use of linear stability theory to show how to destabilise a fixed point, leading to the onset of oscillatory behaviour. Next we show for the choice of a Heaviside nonlinearity for the firing rate that such emergent oscillations can be either synchronous or anti-synchronous depending on whether inhibition or excitation dominates the network architecture. To probe the behaviour of smooth (sigmoidal) nonlinear firing rates we use a mixture of numerical bifurcation analysis and direct simulations, and uncover parameter windows that support chaotic behaviour. Finally we comment on the role of delays in the generation of bursting oscillations, and discuss natural extensions of the work in this paper.

Depolarization induced suppression of excitation and the emergence of ultra-slow rhythms in neural networks

Ultra-slow fluctuations (0.01-0.1 Hz) are a feature of intrinsic brain activity of as yet unclear origin. We propose a candidate mechanism based on retrograde endocannabinoid signaling in a synaptically coupled network of excitatory neurons. This is known to cause depolarization-induced suppression of excitation (DISE), which we model phenomenologically. We construct emergent network oscillations in a globally coupled network and show that for strong synaptic coupling DISE can lead to a synchronized population burst at the frequencies of resting brain rhythms.

Photovoltaic power forecast modeling with artificial neural networks

Dissertação de Mestrado, Engenharia Eletrónica e Telecomunicações, Faculdade de Ciências e Tecnologia, Universidade do Algarve, 2016

An incremental meta-cognitive-based scaffolding fuzzy neural network

The idea of meta-cognitive learning has enriched the landscape of evolving systems, because it emulates three fundamental aspects of human learning: what-to-learn; how-to-learn; and when-to-learn. However, existing meta-cognitive algorithms still exclude Scaffolding theory, which can realize a plug-and-play classifier. Consequently, these algorithms require laborious pre- and/or post-training processes to be carried out in addition to the main training process. This paper introduces a novel meta-cognitive algorithm termed GENERIC-Classifier (gClass), where the how-to-learn part constitutes a synergy of Scaffolding Theory - a tutoring theory that fosters the ability to sort out complex learning tasks, and Schema Theory - a learning theory of knowledge acquisition by humans. The what-to-learn aspect adopts an online active learning concept by virtue of an extended conflict and ignorance method, making gClass an incremental semi-supervised classifier, whereas the when-to-learn component makes use of the standard sample reserved strategy. A generalized version of the Takagi-Sugeno Kang (TSK) fuzzy system is devised to serve as the cognitive constituent. That is, the rule premise is underpinned by multivariate Gaussian functions, while the rule consequent employs a subset of the non-linear Chebyshev polynomial. Thorough empirical studies, confirmed by their corresponding statistical tests, have numerically validated the efficacy of gClass, which delivers better classification rates than state-of-the-art classifiers while having less complexity.

New inequality-based approach to passivity analysis of neural networks with interval time-varying delay

This paper is concerned with the problem of passivity analysis of neural networks with an interval time-varying delay. Unlike existing results in the literature, the time-delay considered in this paper is subjected to interval time-varying without any restriction on the rate of change. Based on novel refined Jensen inequalities and by constructing an improved Lyapunov-Krasovskii functional (LKF), which fully utilizes information of the neuron activation functions, new delay-dependent conditions that ensure the passivity of the network are derived in terms of tractable linear matrix inequalities (LMIs) which can be effectively solved by various computational tools. The effectiveness and improvement over existing results of the proposed method in this paper are illustrated through numerical examples.

Passivity analysis of memristor-based complex-valued neural networks with time-varying delays

In this paper, the model of memristor-based complex-valued neural networks (MCVNNs) with time-varying delays is established and the problem of passivity analysis for MCVNNs is considered and extensively investigated. The analysis in this paper employs results from the theory of differential equations with discontinuous right-hand side as introduced by Filippov. By employing the appropriate Lyapunov–Krasovskii functional, differential inclusion theory and linear matrix inequality (LMI) approach, some new sufficient conditions for the passivity of the given MCVNNs are obtained in terms of both complex-valued and real-value LMIs, which can be easily solved by using standard numerical algorithms. Numerical examples are provided to illustrate the effectiveness of our theoretical results.

Optimal control of non-linear systems through hybrid cell-mapping/artificial-neural-networks techniques

In this paper, a real-time optimal control technique for non-linear plants is proposed. The control system makes use of the cell-mapping (CM) techniques, widely used for the global analysis of highly non-linear systems. The CM framework is employed for designing approximate optimal controllers via a control variable discretization. Furthermore, CM-based designs can be improved by the use of supervised feedforward artificial neural networks (ANNs), which have proved to be universal and efficient tools for function approximation, providing also very fast responses. The quantitative nature of the approximate CM solutions fits very well with ANNs characteristics. Here, we propose several control architectures which combine, in a different manner, supervised neural networks and CM control algorithms. On the one hand, different CM control laws computed for various target objectives can be employed for training a neural network, explicitly including the target information in the input vectors. This way, tracking problems, in addition to regulation ones, can be addressed in a fast and unified manner, obtaining smooth, averaged and global feedback control laws. On the other hand, adjoining CM and ANNs are also combined into a hybrid architecture to address problems where accuracy and real-time response are critical. Finally, some optimal control problems are solved with the proposed CM, neural and hybrid techniques, illustrating their good performance.

Application of artificial neural networks in linear profile monitoring

In many quality control applications the quality of process or product is characterized and summarized by a relation (profile) between a response variable and one or more explanatory variables. Such profiles can be modeled using linear or nonlinear regression models. In this paper we use artificial neural networks to detect and classify the shifts in linear profiles. Three monitoring methods based on artificial neural networks are developed to monitor linear profiles. Their efficacies are assessed using average run length criterion. © 2010 Elsevier Ltd. All rights reserved.

Exponential stability of non-autonomous neural networks with heterogeneous time-varying delays and destabilizing impulses

In this paper, the problem of global exponential stability analysis of a class of non-autonomous neural networks with heterogeneous delays and time-varying impulses is considered. Based on the comparison principle, explicit conditions are derived in terms of testable matrix inequalities ensuring that the system is globally exponentially stableunder destabilizing impulsive effects. Numerical examples are given to demonstrate the effectiveness of the obtained results.

Exponential stabilization of non-autonomous delayed neural networks via Riccati equations

This paper concerns with the problem of exponential stabilization for a class of non-autonomous neural networks with mixed discrete and distributed time-varying delays. Two cases of discrete time-varying delay, namely (i) slowly time-varying; and (ii) fast time-varying, are considered. By constructing an appropriate Lyapunov-Krasovskii functional in case (i) and utilizing the Razumikhin technique in case (ii), we establish some new delay-dependent conditions for designing a memoryless state feedback controller which stabilizes the system with an exponential convergence of the resulting closed-loop system. The proposed conditions are derived through solutions of some types of Riccati differential equations. Applications to control a class of autonomous neural networks with mixed time-varying delays are also discussed in this paper. Some numerical examples are provided to illustrate the effectiveness of the obtained results.

On global dissipativity of nonautonomous neural networks with multiple proportional delays

This brief addresses the problem of global dissipativity analysis of nonautonomous neural networks with multiple proportional delays. By using a novel constructive approach based on some comparisontechniques for differential inequalities, new explicit delay-independentconditions are derived using M-matrix theory to ensure the existence ofgeneralized exponential attracting sets and the global dissipativity of thesystem. The method presented in this brief is also utilized to derive ageneralized exponential estimate for a class of Halanay-type inequalitieswith proportional delays. Finally, three numerical examples are given toillustrate the effectiveness and improvement of the obtained results.

Reachable sets bounding for generalized neural networks with interval time-varying delay and bounded disturbances

This paper deals with the problem of finding outer bound of forwards reachable sets and interbound of backwards reachable sets of generalized neural network systems with interval nondifferentiable time-varying delay and bounded disturbances. Based on constructing a suitable Lyapunov–Krasovskii functional and utilizing some improved Jensen integral-based inequalities, two sufficient conditions are derived for the existence of: (1) the smallest possible outer bound of forwards reachable sets and (2) the largest possible interbound of backwards reachable sets. These conditions are delay dependent and in the form of matrix inequalities, which therefore can be efficiently solved by using existing convex algorithms. Three numerical examples with simulation results are provided to demonstrate the effectiveness of our results.