Video target tracking by using competitive neural networks

A target tracking algorithm able to identify the position and to pursuit moving targets in video digital sequences is proposed in this paper. The proposed approach aims to track moving targets inside the vision field of a digital camera. The position and trajectory of the target are identified by using a neural network presenting competitive learning technique. The winning neuron is trained to approximate to the target and, then, pursuit it. A digital camera provides a sequence of images and the algorithm process those frames in real time tracking the moving target. The algorithm is performed both with black and white and multi-colored images to simulate real world situations. Results show the effectiveness of the proposed algorithm, since the neurons tracked the moving targets even if there is no pre-processing image analysis. Single and multiple moving targets are followed in real time.

Robust and fast vowel recognition using optimum-path forest

The applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy. ©2010 IEEE.

Classificação de sinais acústicos utilizando a transformada wavelet discreta e a decomposição de modo empírico: aplicações na área de alimentos

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Classificação de níveis de desgaste de dressadores de ponta única utilizando sinais de emissão acústica e redes neurais artificiais

Pós-graduação em Engenharia Elétrica - FEB

Aplicação de redes neurais artificiais no monitoramento da operação de dressagem

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Um método não-limiar para redução de ruído em sinais de voz no domínio wavelet

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Tool Condition Monitoring of Single-Point Dresser Using Acoustic Emission and Neural Networks Models

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Reconhecimento de voz para aplicações em automação implementado em FPGA

In many movies of scientific fiction, machines were capable of speaking with humans. However mankind is still far away of getting those types of machines, like the famous character C3PO of Star Wars. During the last six decades the automatic speech recognition systems have been the target of many studies. Throughout these years many technics were developed to be used in applications of both software and hardware. There are many types of automatic speech recognition system, among which the one used in this work were the isolated word and independent of the speaker system, using Hidden Markov Models as the recognition system. The goals of this work is to project and synthesize the first two steps of the speech recognition system, the steps are: the speech signal acquisition and the pre-processing of the signal. Both steps were developed in a reprogrammable component named FPGA, using the VHDL hardware description language, owing to the high performance of this component and the flexibility of the language. In this work it is presented all the theory of digital signal processing, as Fast Fourier Transforms and digital filters and also all the theory of speech recognition using Hidden Markov Models and LPC processor. It is also presented all the results obtained for each one of the blocks synthesized e verified in hardware

Utilização da instrumentação virtual em Labview para criação da interface gráfica do amplificador lock-in utilizado em estudos fisiológicos a partir da comunicação via porta serial

This work presents the development of a graphical interface to the Lock-in Amplifier, which is used in physiological studies on the motility of the gastrointestinal tract in rats and signal processing. With a simple and low cost instrumentation, the resources offered by the virtual interface of LabVIEW software allows the creation of commands similar to the actual instrument that, through communication via standard serial port, transmits data between a PC and peripheral device performing specific and particular needs in the amplifier. Created for the lock-in amplifier model SR830 Stanford Research Systems, the remote manipulation gives the user greater accessibility in the process of configuration and calibration. And, since the software is installed, there is the advantage of eliminating the need of purchase new devices to upgrade the system. The commands created were made to perform six basic modifications that are used in routine of the Biomagnetism Laboratory. The instrumentation developed has the following controls: Amplitude, Frequency, Time Constant, slope low pass filter, sensitivity and offset

Tool condition monitoring of aluminum oxide grinding wheel in dressing operation using acoustic emission and neural networks

The grinding operation gives workpieces their final finish, minimizing surface roughness through the interaction between the abrasive grains of a tool (grinding wheel) and the workpiece. However, excessive grinding wheel wear due to friction renders the tool unsuitable for further use, thus requiring the dressing operation to remove and/or sharpen the cutting edges of the worn grains to render them reusable. The purpose of this study was to monitor the dressing operation using the acoustic emission (AE) signal and statistics derived from this signal, classifying the grinding wheel as sharp or dull by means of artificial neural networks. An aluminum oxide wheel installed on a surface grinding machine, a signal acquisition system, and a single-point dresser were used in the experiments. Tests were performed varying overlap ratios and dressing depths. The root mean square values and two additional statistics were calculated based on the raw AE data. A multilayer perceptron neural network was used with the Levenberg-Marquardt learning algorithm, whose inputs were the aforementioned statistics. The results indicate that this method was successful in classifying the conditions of the grinding wheel in the dressing process, identifying the tool as "sharp''(with cutting capacity) or "dull''(with loss of cutting capacity), thus reducing the time and cost of the operation and minimizing excessive removal of abrasive material from the grinding wheel.

Disintegration of magnetic tablets in human stomach evaluated by alternate current biosusceptometry

Oral administration is the most convenient route for drug therapy. The knowledge of the gastrointestinal transit and specific site for drug delivery is a prerequisite for development of dosage forms. The aim of this work was to demonstrate that is possible to monitor the disintegration process of film-coated magnetic tablets by multi-sensor alternate current Biosusceptometry (ACB) in vivo and in vitro. This method is based on the recording of signals produced by the magnetic tablet using a seven sensors array and signal-processing techniques. The disintegration was confirmed by signals analysis in healthy human volunteers' measurements and in vitro experiments. Results showed that ACB is efficient to characterize the disintegration of dosage forms in the stomach, being a research tool for the development of new pharmaceutical dosage forms.

Comparison of different analysis techniques for the determination of muscle onset in individuals with patellofemoral pain syndrome

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Análise da fadiga muscular localizada em atletas e sedentários através de parâmetros de freqüência do sinal eletromiográfico

Embora a análise no domínio da freqüência do sinal eletromiográfico (EMG) seja empregada na caracterização do processo de fadiga muscular localizada, sua aplicação, especificamente a da freqüência mediana (Fmed), é pouco explorada no âmbito esportivo. O objetivo do presente estudo foi verificar a viabilidade da aplicação do sinal EMG, através de sua análise no domínio da freqüência, como parâmetro para determinação e diferenciação no comportamento da fadiga muscular localizada. Dois grupos de sujeitos, um caracterizado como atletas (n =12) e outro como sedentários (n =12), foram submetidos a análises baseadas em procedimentos executados em três diferentes situações experimentais, todos envolvendo a modalidade de exercício isométrico: i) teste máximo para determinação da contração isométrica voluntária máxima (CIVM); ii) teste de fadiga, sustentado por 35 seg. a 80% da CIVM; iii) teste de recuperação, sustentado por 10 seg. a 80% da CIVM; neste ultimo foi monitorado o comportamento da Fmed nos três primeiros (Fmedi) e três últimos segundos (Fmedf) do sinal EMG no músculo tibial anterior durante o teste de fadiga. Durante os 10 segundos do teste de recuperação foi calculada a Fmed referente a todo o período (Fmedr). parâmetro utilizado no cálculo do índice de recuperação muscular (IRM). Os resultados apontam que a Fmedf apresentou valor menor em relação à Fmedi em ambos os grupos (p < 0,05). Quando comparado com o grupo de sedentários, o grupo de atletas apresentou valores maiores de Fmedi e Fmedf (p < 0,05). O valor médio e desvio-padrão do IRM para o grupo de atletas foram de 62,1% ± 28,7 e, para o grupo de sedentários, de 55,2% ± 27,8 (p > 0,05). Dessa forma, os resultados apresentados neste estudo permitem inferir a viabilidade na aplicação de parâmetros no domínio da freqüência do sinal EMG para a determinação e diferenciação do comportamento da fadiga muscular localizada.

Comparison of the Polar S810i monitor and the ECG for the analysis of heart rate variability in the time and frequency domains

The aim of the present study was to compare heart rate variability (HRV) at rest and during exercise using a temporal series obtained with the Polar S810i monitor and a signal from a LYNX® signal conditioner (BIO EMG 1000 model) with a channel configured for the acquisition of ECG signals. Fifteen healthy subjects aged 20.9 ± 1.4 years were analyzed. The subjects remained at rest for 20 min and performed exercise for another 20 min with the workload selected to achieve 60% of submaximal heart rate. RR series were obtained for each individual with a Polar S810i instrument and with an ECG analyzed with a biological signal conditioner. The HRV indices (rMSSD, pNN50, LFnu, HFnu, and LF/HF) were calculated after signal processing and analysis. The unpaired Student t-test and intraclass correlation coefficient were used for data analysis. No statistically significant differences were observed when comparing the values analyzed by means of the two devices for HRV at rest and during exercise. The intraclass correlation coefficient demonstrated satisfactory correlation between the values obtained by the devices at rest (pNN50 = 0.994; rMSSD = 0.995; LFnu = 0.978; HFnu = 0.978; LF/HF = 0.982) and during exercise (pNN50 = 0.869; rMSSD = 0.929; LFnu = 0.973; HFnu = 0.973; LF/HF = 0.942). The calculation of HRV values by means of temporal series obtained from the Polar S810i instrument appears to be as reliable as those obtained by processing the ECG signal captured with a signal conditioner.

Multidimensional polynomial powers of sigmoid (PPS) Wavelet neural networks

Wavelet functions have been used as the activation function in feedforward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural network have been developed and reported in the literature. However, most of the aforementioned reports impose many restrictions in the classical backpropagation algorithm, such as low dimensionality, tensor product of wavelets, parameters initialization, and, in general, the output is one dimensional, etc. In order to remove some of these restrictions, a family of polynomial wavelets generated from powers of sigmoid functions is presented. We described how a multidimensional wavelet neural networks based on these functions can be constructed, trained and applied in pattern recognition tasks. As an example of application for the method proposed, it is studied the exclusive-or (XOR) problem.