Revendo os códigos hamming e CRC para tratar com erros na transmissão de dados

This article has the purpose to review the main codes used to detect and correct errors in data communication specifically in the computer's network. The Hamming's code and the Ciclic Redundancy Code (CRC) are presented as the focus of this article as well as CRC hardware implementation. Each code is reviewed in details in order to fill the gaps in the literature and to make it accessible to the computer science and engineering students as well as to anyone who may be interested in learning the technique to treat error in data communication.

Redes neurais aplicadas em processos de usinagem da madeira

Pós-graduação em Engenharia Mecânica - FEG

SMAC multi-hop mesh routing protocol using IEEE 802.15.4

This paper discusses some aspects related to Wireless Sensor Networks over the IEEE 802.15.4 standard, and proposes, for the very first time, a mesh network topology with geographic routing integrated to the open Freescale protocol (SMAC - Simple Medium Access Control). For this is proposed the SMAC routing protocol. Before this work the SMAC protocol was suitable to perform one hop communications only. However, with the developed mechanisms, it is possible to use multi-hop communication. Performance results from the implemented protocol are presented and analyzed in order to define important requirements for wireless sensor networks, such as robustness, self-healing property and low latency. (c) 2011 Elsevier Ltd. All rights reserved.

A neuro-mechanical model for interpersonal coordination

The present study investigates the coordination between two people oscillating handheld pendulums, with a special emphasis on the influence of the mechanical properties of the effector systems involved. The first part of the study is an experiment in which eight pairs of participants are asked to coordinate the oscillation of their pendulum with the other participant's in an in-phase or antiphase fashion. Two types of pendulums, A and B, having different resonance frequencies (Freq A=0.98 Hz and Freq B=0.64 Hz), were used in different experimental combinations. Results confirm that the preferred frequencies produced by participants while manipulating each pendulum individually were close to the resonance frequencies of the pendulums. In their attempt to synchronize with one another, participants met at common frequencies that were influenced by the mechanical properties of the two pendulums involved. In agreement with previous studies, both the variability of the behavior and the shift in the intended relative phase were found to depend on the task-effector asymmetry, i.e., the difference between the mechanical properties of the effector systems involved. In the second part of the study, we propose a model to account for these results. The model consists of two cross-coupled neuro-mechanical units, each composed of a neural oscillator driving a wrist-pendulum system. Taken individually, each unit reproduced the natural tendency of the participants to freely oscillate a pendulum close to its resonance frequency. When cross-coupled through the vision of the pendulum of the other unit, the two units entrain each other and meet at a common frequency influenced by the mechanical properties of the two pendulums involved. The ability of the proposed model to address the other effects observed as a function of the different conditions of the pendulum and intended mode of coordination is discussed.

Inteligência coletiva e gestão do conhecimento: uma aplicação na rede social Facebook

Social networks rely on concepts such as collaboration, cooperation, replication, flow, speed, interaction, engagement, and aim the continuous sharing and resharing of information in support of the permanent social interaction. Facebook, the largest social network in the world, reached, in May 2016, the mark of 1.09 billion active users daily, draining 161.7 million hours of users’ attention to the website every day. These users share 4.75 billion units of content daily. The research presented in this dissertation aims to investigate the management of knowledge and collective intelligence, from the introduction of mechanisms that aim to enable users to manage and organize current information in the feeds from Facebook groups in which they participate, turning Facebook into a collective knowledge and information management device that goes far beyond mere interaction and communication among people. The adoption of Design Science Research methodology is intended to instill the "genes" of collective intelligence, as presented in the literature, in the computational artifact being developed, so that intelligence can be managed and used to create even more knowledge and intelligence to and by the group. The main theoretical contribution of this dissertation is to discuss knowledge management and collective intelligence in a complementary and integrated manner, showing how efforts to obtain one also contribute to leveraging the other.

Visualization of learning in multilayer perceptron networks using principal component analysis

This paper is concerned with the use of scientific visualization methods for the analysis of feedforward neural networks (NNs). Inevitably, the kinds of data associated with the design and implementation of neural networks are of very high dimensionality, presenting a major challenge for visualization. A method is described using the well-known statistical technique of principal component analysis (PCA). This is found to be an effective and useful method of visualizing the learning trajectories of many learning algorithms such as back-propagation and can also be used to provide insight into the learning process and the nature of the error surface.

Comparison of classification ability of hyperball algorithms to neural network and k-nearest neighbour algorithms

The main focus of this thesis is to evaluate and compare Hyperbalilearning algorithm (HBL) to other learning algorithms. In this work HBL is compared to feed forward artificial neural networks using back propagation learning, K-nearest neighbor and 103 algorithms. In order to evaluate the similarity of these algorithms, we carried out three experiments using nine benchmark data sets from UCI machine learning repository. The first experiment compares HBL to other algorithms when sample size of dataset is changing. The second experiment compares HBL to other algorithms when dimensionality of data changes. The last experiment compares HBL to other algorithms according to the level of agreement to data target values. Our observations in general showed, considering classification accuracy as a measure, HBL is performing as good as most ANn variants. Additionally, we also deduced that HBL.:s classification accuracy outperforms 103's and K-nearest neighbour's for the selected data sets.

Real-Time software control of neural stimulation in a closed loop Animat system

A recent area for investigation into the development of adaptable robot control is the use of living neuronal networks to control a mobile robot. The so-called Animat paradigm comprises a neuronal network (the ‘brain’) connected to an external embodiment (in this case a mobile robot), facilitating potentially robust, adaptable robot control and increased understanding of neural processes. Sensory input from the robot is provided to the neuronal network via stimulation on a number of electrodes embedded in a specialist Petri dish (Multi Electrode Array (MEA)); accurate control of this stimulation is vital. We present software tools allowing precise, near real-time control of electrical stimulation on MEAs, with fast switching between electrodes and the application of custom stimulus waveforms. These Linux-based tools are compatible with the widely used MEABench data acquisition system. Benefits include rapid stimulus modulation in response to neuronal activity (closed loop) and batch processing of stimulation protocols.

A reconfigurable neural environment on active networks

This paper proposes the deployment of a neural network computing environment on Active Networks. Active Networks are packet-switched computer networks in which packets can contain code fragments that are executed on the intermediate nodes. This feature allows the injection of small pieces of codes to deal with computer network problems directly into the network core, and the adoption of new computing techniques to solve networking problems. The goal of our project is the adoption of a distributed neural network for approaching tasks which are specific of the computer network environment. Dynamically reconfigurable neural networks are spread on an experimental wide area backbone of active nodes (ABone) to show the feasibility of the proposed approach.

A forward constrained selection algorithm for probabilistic neural network

A new probabilistic neural network (PNN) learning algorithm based on forward constrained selection (PNN-FCS) is proposed. An incremental learning scheme is adopted such that at each step, new neurons, one for each class, are selected from the training samples arid the weights of the neurons are estimated so as to minimize the overall misclassification error rate. In this manner, only the most significant training samples are used as the neurons. It is shown by simulation that the resultant networks of PNN-FCS have good classification performance compared to other types of classifiers, but much smaller model sizes than conventional PNN.

Cross-situational learning of object-word mapping using Neural Modeling Fields

The issue of how children learn the meaning of words is fundamental to developmental psychology. The recent attempts to develop or evolve efficient communication protocols among interacting robots or Virtual agents have brought that issue to a central place in more applied research fields, such as computational linguistics and neural networks, as well. An attractive approach to learning an object-word mapping is the so-called cross-situational learning. This learning scenario is based on the intuitive notion that a learner can determine the meaning of a word by finding something in common across all observed uses of that word. Here we show how the deterministic Neural Modeling Fields (NMF) categorization mechanism can be used by the learner as an efficient algorithm to infer the correct object-word mapping. To achieve that we first reduce the original on-line learning problem to a batch learning problem where the inputs to the NMF mechanism are all possible object-word associations that Could be inferred from the cross-situational learning scenario. Since many of those associations are incorrect, they are considered as clutter or noise and discarded automatically by a clutter detector model included in our NMF implementation. With these two key ingredients - batch learning and clutter detection - the NMF mechanism was capable to infer perfectly the correct object-word mapping. (C) 2009 Elsevier Ltd. All rights reserved.

How language can help discrimination in the Neural Modelling Fields framework

The relationship between thought and language and, in particular, the issue of whether and how language influences thought is still a matter of fierce debate. Here we consider a discrimination task scenario to study language acquisition in which an agent receives linguistic input from an external teacher, in addition to sensory stimuli from the objects that exemplify the overlapping categories that make up the environment. Sensory and linguistic input signals are fused using the Neural Modelling Fields (NMF) categorization algorithm. We find that the agent with language is capable of differentiating object features that it could not distinguish without language. In this sense, the linguistic stimuli prompt the agent to redefine and refine the discrimination capacity of its sensory channels. (C) 2007 Elsevier Ltd. All rights reserved.

A multi-GPU algorithm for large-scale neuronal networks

Large-scale simulations of parts of the brain using detailed neuronal models to improve our understanding of brain functions are becoming a reality with the usage of supercomputers and large clusters. However, the high acquisition and maintenance cost of these computers, including the physical space, air conditioning, and electrical power, limits the number of simulations of this kind that scientists can perform. Modern commodity graphical cards, based on the CUDA platform, contain graphical processing units (GPUs) composed of hundreds of processors that can simultaneously execute thousands of threads and thus constitute a low-cost solution for many high-performance computing applications. In this work, we present a CUDA algorithm that enables the execution, on multiple GPUs, of simulations of large-scale networks composed of biologically realistic Hodgkin-Huxley neurons. The algorithm represents each neuron as a CUDA thread, which solves the set of coupled differential equations that model each neuron. Communication among neurons located in different GPUs is coordinated by the CPU. We obtained speedups of 40 for the simulation of 200k neurons that received random external input and speedups of 9 for a network with 200k neurons and 20M neuronal connections, in a single computer with two graphic boards with two GPUs each, when compared with a modern quad-core CPU. Copyright (C) 2010 John Wiley & Sons, Ltd.

A proposed neural control for the trajectory tracking of a nonholonomic mobile robot with disturbances

In this paper, a trajectory tracking control problem for a nonholonomic mobile robot by the integration of a kinematic neural controller (KNC) and a torque neural controller (TNC) is proposed, where both the kinematic and dynamic models contains disturbances. The KNC is a variable structure controller (VSC) based on the sliding mode control theory (SMC), and applied to compensate the kinematic disturbances. The TNC is a inertia-based controller constituted of a dynamic neural controller (DNC) and a robust neural compensator (RNC), and applied to compensate the mobile robot dynamics, and bounded unknown disturbances. Stability analysis with basis on Lyapunov method and simulations results are provided to show the effectiveness of the proposed approach. © 2012 Springer-Verlag.

Stochastic competitive learning in complex networks

Competitive learning is an important machine learning approach which is widely employed in artificial neural networks. In this paper, we present a rigorous definition of a new type of competitive learning scheme realized on large-scale networks. The model consists of several particles walking within the network and competing with each other to occupy as many nodes as possible, while attempting to reject intruder particles. The particle's walking rule is composed of a stochastic combination of random and preferential movements. The model has been applied to solve community detection and data clustering problems. Computer simulations reveal that the proposed technique presents high precision of community and cluster detections, as well as low computational complexity. Moreover, we have developed an efficient method for estimating the most likely number of clusters by using an evaluator index that monitors the information generated by the competition process itself. We hope this paper will provide an alternative way to the study of competitive learning.