An adaptive IoT management infrastructure for eco transport networks

The complexity associated with fast growing of B2B and the lack of a (complete) suite of open standards makes difficulty to maintain the underlying collaborative processes. Aligned to this challenge, this paper aims to be a contribution to an open architecture of logistics and transport processes management system. A model of an open integrated system is being defined as an open computational responsibility from the embedded systems (on-board) as well as a reference implementation (prototype) of a host system to validate the proposed open interfaces. Embedded subsystem can, natively, be prepared to cooperate with other on-board units and with IT-systems in an infrastructure commonly referred to as a center information system or back-office. In interaction with a central system the proposal is to adopt an open framework for cooperation where the embedded unit or the unit placed somewhere (land/sea) interacts in response to a set of implemented capabilities.

Metalearner based on Dynamic Neural Network for Strategic Bidding in electricity Markets

The restructuring of electricity markets, conducted to increase the competition in this sector, and decrease the electricity prices, brought with it an enormous increase in the complexity of the considered mechanisms. The electricity market became a complex and unpredictable environment, involving a large number of different entities, playing in a dynamic scene to obtain the best advantages and profits. Software tools became, therefore, essential to provide simulation and decision support capabilities, in order to potentiate the involved players’ actions. This paper presents the development of a metalearner, applied to the decision support of electricity markets’ negotiation entities. The proposed metalearner executes a dynamic artificial neural network to create its own output, taking advantage on several learning algorithms implemented in ALBidS, an adaptive learning system that provides decision support to electricity markets’ players. The proposed metalearner considers different weights for each strategy, depending on its individual quality of performance. The results of the proposed method are studied and analyzed in scenarios based on real electricity markets’ data, using MASCEM - a multi-agent electricity market simulator that simulates market players’ operation in the market.

Neural control of an autonomous robot

This article aims to apply the concepts associated with artificial neural networks (ANN) in the control of an autonomous robot system that is intended to be used in competitions of robots. The robot was tested in several arbitrary paths in order to verify its effectiveness. The results show that the robot performed the tasks with success. Moreover, in the case of arbitrary paths the ANN control outperforms other methodologies, such as fuzzy logic control (FLC).

Projecto de Controladores usando Redes Neuronais

Neste documento descreve-se o projeto desenvolvido na unidade curricular de Tese e Dissertação durante o 2º ano do Mestrado de Engenharia Eletrotécnica e de Computadores no ramo de Automação e Sistemas, no Departamento de Engenharia Eletrotécnica (DEE) do Instituto Superior de Engenharia do Porto (ISEP). O projeto escolhido teve como base o uso da tecnologia das redes neuronais para implementação em sistemas de controlo. Foi necessário primeiro realizar um estudo desta tecnologia, perceber como esta surgiu e como é estruturada. Por último, abordar alguns casos de estudo onde as redes neuronais foram aplicadas com sucesso. Relativamente à implementação, foram consideradas diferentes estruturas de controlo, e entre estas escolhidas a do sistema de controlo estabilizador e sistema de referência adaptativo. No entanto, como o objetivo deste trabalho é o estudo de desempenho quando aplicadas as redes neuronais, não se utilizam apenas estas como controlador. A análise exposta neste trabalho trata de perceber em que medida é que a introdução das redes neuronais melhora o controlo de um processo. Assim sendo, os sistemas de controlo utilizados devem conter pelo menos uma rede neuronal e um controlador PID. Os testes de desempenho são aplicados no controlo de um motor DC, sendo realizados através do recurso ao software MATLAB. As simulações efetuadas têm diferentes configurações de modo a tirar conclusões o mais gerais possível. Assim, os sistemas de controlo são simulados para dois tipos de entrada diferentes, e com ou sem a adição de ruído no sensor. Por fim, é efetuada uma análise das respostas de cada sistema implementado e calculados os índices de desempenho das mesmas.

Automatic syllabification for danish text-to-speech systems

In this paper, a rule-based automatic syllabifier for Danish is described using the Maximal Onset Principle. Prior success rates of rule-based methods applied to Portuguese and Catalan syllabification modules were on the basis of this work. The system was implemented and tested using a very small set of rules. The results gave rise to 96.9% and 98.7% of word accuracy rate, contrary to our initial expectations, being Danish a language with a complex syllabic structure and thus difficult to be rule-driven. Comparison with data-driven syllabification system using artificial neural networks showed a higher accuracy rate of the former system.

Sustainability of systems interoperability in dynamic business networks

Dissertação para obtenção do Grau de Doutor em Engenharia Electrotécnica e de Computadores

Distinction of males of the Lutzomyia intermedia (Lutz & Neiva, 1912) species complex by ratios between dimensions and by an artificial neural network (Diptera: Psychodidae, Phlebotominae)

The females of the two species of the Lutzomyia intermedia complex can be easily distinguished, but the males of each species are quite similar. The ratios between the extra-genital and the genital structures of L. neivai are larger than those of L. intermedia s. s., according to ANOVA. An artificial neural network was trained with a set of 300 examples, randomly taken from a sample of 358 individuals. The input vectors consisted of several ratios between some structures of each insect. The model was tested on the remaining 58 insects, 56 of which (96.6%) were correctly identified. This ratio of success can be considered remarkable if one takes into account the difficulty of attaining comparable results using traditional statistical techniques.

Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior

Neural correlates of alerting and orienting impairment in multiple sclerosis patients.

BACKGROUND A considerable percentage of multiple sclerosis patients have attentional impairment, but understanding its neurophysiological basis remains a challenge. The Attention Network Test allows 3 attentional networks to be studied. Previous behavioural studies using this test have shown that the alerting network is impaired in multiple sclerosis. The aim of this study was to identify neurophysiological indexes of the attention impairment in relapsing-remitting multiple sclerosis patients using this test. RESULTS After general slowing had been removed in patients group to isolate the effects of each condition, some behavioral differences between them were obtained. About Contingent Negative Variation, a statistically significant decrement were found in the amplitude for Central and Spatial Cue Conditions for patient group (p<0.05). ANOVAs showed for the patient group a significant latency delay for P1 and N1 components (p<0.05) and a decrease of P3 amplitude for congruent and incongruent stimuli (p<0.01). With regard to correlation analysis, PASAT-3s and SDMT showed significant correlations with behavioral measures of the Attention Network Test (p<0.01) and an ERP parameter (CNV amplitude). CONCLUSIONS Behavioral data are highly correlated with the neuropsychological scores and show that the alerting and orienting mechanisms in the patient group were impaired. Reduced amplitude for the Contingent Negative Variation in the patient group suggests that this component could be a physiological marker related to the alerting and orienting impairment in relapsing-remitting multiple sclerosis. P1 and N1 delayed latencies are evidence of the demyelination process that causes impairment in the first steps of the visual sensory processing. Lastly, P3 amplitude shows a general decrease for the pathological group probably indexing a more central impairment. These results suggest that the Attention Network Test give evidence of multiple levels of attention impairment, which could help in the assessment and treatment of relapsing-remitting multiple sclerosis patients.

Disentangling the attention network test: behavioral, event related potentials, and neural source analyses.

BACKGROUND The study of the attentional system remains a challenge for current neuroscience. The "Attention Network Test" (ANT) was designed to study simultaneously three different attentional networks (alerting, orienting, and executive) based in subtraction of different experimental conditions. However, some studies recommend caution with these calculations due to the interactions between the attentional networks. In particular, it is highly relevant that several interpretations about attentional impairment have arisen from these calculations in diverse pathologies. Event related potentials (ERPs) and neural source analysis can be applied to disentangle the relationships between these attentional networks not specifically shown by behavioral measures. RESULTS This study shows that there is a basic level of alerting (tonic alerting) in the no cue (NC) condition, represented by a slow negative trend in the ERP trace prior to the onset of the target stimuli. A progressive increase in the CNV amplitude related to the amount of information provided by the cue conditions is also shown. Neural source analysis reveals specific modulations of the CNV related to a task-related expectancy presented in the NC condition; a late modulation triggered by the central cue (CC) condition and probably representing a generic motor preparation; and an early and late modulation for spatial cue (SC) condition suggesting specific motor and sensory preactivation. Finally, the first component in the information processing of the target stimuli modulated by the interaction between orienting network and the executive system can be represented by N1. CONCLUSIONS The ANT is useful as a paradigm to study specific attentional mechanisms and their interactions. However, calculation of network effects is based in subtractions with non-comparable experimental conditions, as evidenced by the present data, which can induce misinterpretations in the study of the attentional capacity in human subjects.

Volatility smile extrapolation with an artificial neural network

I use a multi-layer feedforward perceptron, with backpropagation learning implemented via stochastic gradient descent, to extrapolate the volatility smile of Euribor derivatives over low-strikes by training the network on parametric prices.

Validation procedures in radiological diagnostic models. Neural network and logistic regression

The objective of this paper is to compare the performance of twopredictive radiological models, logistic regression (LR) and neural network (NN), with five different resampling methods. One hundred and sixty-seven patients with proven calvarial lesions as the only known disease were enrolled. Clinical and CT data were used for LR and NN models. Both models were developed with cross validation, leave-one-out and three different bootstrap algorithms. The final results of each model were compared with error rate and the area under receiver operating characteristic curves (Az). The neural network obtained statistically higher Az than LR with cross validation. The remaining resampling validation methods did not reveal statistically significant differences between LR and NN rules. The neural network classifier performs better than the one based on logistic regression. This advantage is well detected by three-fold cross-validation, but remains unnoticed when leave-one-out or bootstrap algorithms are used.

Quality coding by neural populations in the early olfactory pathway: analysis using information theory

In this article, we analyze the ability of the early olfactory system to detect and discriminate different odors by means of information theory measurements applied to olfactory bulb activity images. We have studied the role that the diversity and number of receptor neuron types play in encoding chemical information. Our results show that the olfactory receptors of the biological system are low correlated and present good coverage of the input space. The coding capacity of ensembles of olfactory receptors with the same receptive range is maximized when the receptors cover half of the odor input space - a configuration that corresponds to receptors that are not particularly selective. However, the ensemble's performance slightly increases when mixing uncorrelated receptors of different receptive ranges. Our results confirm that the low correlation between sensors could be more significant than the sensor selectivity for general purpose chemo-sensory systems, whether these are biological or biomimetic.

Nonlinear inverse dynamic models of gas sensing systems based on chemical sensor arrays for quantitative measurements

Gas sensing systems based on low-cost chemical sensor arrays are gaining interest for the analysis of multicomponent gas mixtures. These sensors show different problems, e.g., nonlinearities and slow time-response, which can be partially solved by digital signal processing. Our approach is based on building a nonlinear inverse dynamic system. Results for different identification techniques, including artificial neural networks and Wiener series, are compared in terms of measurement accuracy.

Synchronizability of EEG-Based Functional Networks in Early Alzheimer's Disease.

Recently graph theory and complex networks have been widely used as a mean to model functionality of the brain. Among different neuroimaging techniques available for constructing the brain functional networks, electroencephalography (EEG) with its high temporal resolution is a useful instrument of the analysis of functional interdependencies between different brain regions. Alzheimer's disease (AD) is a neurodegenerative disease, which leads to substantial cognitive decline, and eventually, dementia in aged people. To achieve a deeper insight into the behavior of functional cerebral networks in AD, here we study their synchronizability in 17 newly diagnosed AD patients compared to 17 healthy control subjects at no-task, eyes-closed condition. The cross-correlation of artifact-free EEGs was used to construct brain functional networks. The extracted networks were then tested for their synchronization properties by calculating the eigenratio of the Laplacian matrix of the connection graph, i.e., the largest eigenvalue divided by the second smallest one. In AD patients, we found an increase in the eigenratio, i.e., a decrease in the synchronizability of brain networks across delta, alpha, beta, and gamma EEG frequencies within the wide range of network costs. The finding indicates the destruction of functional brain networks in early AD.