Life would be much easier if there were no typing involved in preparing a document, typing an email, paying online bills, entering credit card details, booking flights, hotels or car rentals online. Imagine a system that would recognize speech and convert it into another form to do these functions automatically. The fact that most people can speak faster than they can type gives a good reason to have a speech recognizer. This thesis concentrates on developing a speaker independent, speech recognizer using Wavelet Packet Transform. Speech corpus in the form of phonemes is collected from an American male and an Indian Female. The subjects chosen for phoneme recognition vary in a number of factors like the accent, gender, age, microphone used to record speech, environment in which phonemes are recorded, etc. These factors increase the complexity of speech recognition. We also assume that the emotions of the speakers are the same and the speakers are stationary while recording phonemes.

Orientador: Jozue Vieira Filho / Resumo: Neste trabalho aplica-se a Transformada Wavelet Packet para a identificação de faixas de frequência para detecção de danos em sistemas de monitoramento de integridade estrutural baseados no princípio da impedância eletromecânica no domínio do tempo. Assim, foram verificadas e determinadas as faixas de frequências que melhor representam as variações no conjunto PZT/estrutura por meio de informações obtidas da Transformada Wavelet Packet aplicada no sinal de resposta do conjunto PZT/estrutura, obtendo uma metodologia viável, fácil e simples para escolher a faixa mais sensível para a detecção de danos. Os resultados indicam que a entropia dos coeficientes wavelet é uma importante referência na seleção da banda mais apropriada para a detecção de danos. / Abstract: This work applies the Wavelet Packet Transform in the identification of frequency bands for damage detection in structural health monitoring systems based on the principle of electromechanical impedance in the time domain. Thus, the frequency bands that best represent the variations in the set PZT/structure were obtained and determined by means of the information obtained from the Wavelet Packet Transform applied to response signal obtained from PZT/structure, which is an easy, simple and viable methodology for choosing the more sensitive frequency bands for damage detection. Results indicate that the entropy of wavelet coefficients is an important reference in selecting the most appropriate band for damage detection. / Mestre

Submitted by PATRÍCIA GABRIEL VIEIRA null (vieiragpatricia@gmail.com) on 2017-01-23T20:36:55Z No. of bitstreams: 1 Patricia_G_Vieira_Dissertação_Final_2016.pdf: 1483125 bytes, checksum: 78eb2fa98b77bc55ffb7c6344532d7a9 (MD5) / Approved for entry into archive by LUIZA DE MENEZES ROMANETTO (luizamenezes@reitoria.unesp.br) on 2017-01-26T13:40:48Z (GMT) No. of bitstreams: 1 vieira_pg_me_ilha.pdf: 1483125 bytes, checksum: 78eb2fa98b77bc55ffb7c6344532d7a9 (MD5) / Made available in DSpace on 2017-01-26T13:40:48Z (GMT). No. of bitstreams: 1 vieira_pg_me_ilha.pdf: 1483125 bytes, checksum: 78eb2fa98b77bc55ffb7c6344532d7a9 (MD5) Previous issue date: 2016-12-19 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Neste trabalho aplica-se a Transformada Wavelet Packet para a identificação de faixas de frequência para detecção de danos em sistemas de monitoramento de integridade estrutural baseados no princípio da impedância eletromecânica no domínio do tempo. Assim, foram verificadas e determinadas as faixas de frequências que melhor representam as variações no conjunto PZT/estrutura por meio de informações obtidas da Transformada Wavelet Packet aplicada no sinal de resposta do conjunto PZT/estrutura, obtendo uma metodologia viável, fácil e simples para escolher a faixa mais sensível para a detecção de danos. Os resultados indicam que a entropia dos coeficientes wavelet é uma importante referência na seleção da banda mais apropriada para a detecção de danos. / This work applies the Wavelet Packet Transform in the identification of frequency bands for damage detection in structural health monitoring systems based on the principle of electromechanical impedance in the time domain. Thus, the frequency bands that best represent the variations in the set PZT/structure were obtained and determined by means of the information obtained from the Wavelet Packet Transform applied to response signal obtained from PZT/structure, which is an easy, simple and viable methodology for choosing the more sensitive frequency bands for damage detection. Results indicate that the entropy of wavelet coefficients is an important reference in selecting the most appropriate band for damage detection.

Yes / Recent studies suggest that multicarrier systems using wavelets outperform conventional OFDM systems using the FFT, in that they have well-contained side lobes, improved spectral efficiency and BER performance, and they do not require a cyclic prefix. Here we study the wavelet packet and discrete wavelet transforms, comparing the BER performance of wavelet transform-based multicarrier systems and Fourier based OFDM systems, for multipath Rayleigh channels with AWGN. In the proposed system zero-forcing channel estimation in the frequency domain has been used. Results confirm that discrete wavelet-based systems using Daubechies wavelets outperform both wavelet packet transform- based systems and FFT-OFDM systems in terms of BER. Finally, Alamouti coding and maximal ratio combining schemes were employed in MIMO environments, where results show that the effects of multipath fading were greatly reduced by the antenna diversity.

Yes / Aiming to detect concrete defects, we propose a new identification method based on stochastic configuration networks. The presented model has been trained by time-domain and frequency-domain features which are extracted from filtering and decomposing ultrasonic detection signals. This method was applied to ultrasonic detection data collected from 5 mm, 7 mm, and 9 mm penetrating holes in C30 class concrete. In particular, wavelet packet transform (WPT) was then used to decompose the detected signals, thus the information in different frequency bands can be obtained. Based on the data from the fundamental frequency nodes of the detection signals, we calculated the means, standard deviations, kurtosis coefficients, skewness coefficients and energy ratios to characterize the detection signals. We also analyzed their typical statistical features to assess the complexity of identifying these signals. Finally, we used the stochastic configuration networks (SCNs) algorithm to embed four-fold cross-validation for constructing the recognition model. Based upon the experimental results, the performance of the presented model has been validated and compared with the genetic algorithm based BP neural network model, where the comparison shows that the SCNs algorithm has superior generalization abilities, better fitting abilities, and higher recognition accuracy for recognizing defect signals. In addition, the test and analysis results show that the proposed method is feasible and effective in detecting concrete hole defects. / This work was supported in part by the Zhejiang Provincial Natural Science Foundation (ZJNSF) project under Grant (No. LY18F030012), the National Natural Science Foundation of China projects (NSFC) under Grant (No. 61403356, 61573311).

Yes / This paper presents a fault detection method in three-phase induction motors using Wavelet Packet Transform (WPT). The proposed algorithm takes a frame of samples from the three-phase supply current of an induction motor. The three phase current samples are then combined to generate a single current signal by computing the Root Mean Square (RMS) value of the three phase current samples at each time stamp. The resulting current samples are then divided into windows of 64 samples. Each resulting window of samples is then processed separately. The proposed algorithm uses two methods to create window samples, which are called non-overlapping window samples and moving/overlapping window samples. Non-overlapping window samples are created by simply dividing the current samples into windows of 64 sam-ples, while the moving window samples are generated by taking the first 64 current samples, and then the consequent moving window samples are generated by moving the window across the current samples by one sample each time. The new window of samples consists of the last 63 samples of the previous window and one new sample. The overlapping method reduces the fault detection time to a single sample accuracy. However, it is computationally more expensive than the non-overlapping method and requires more computer memory. The resulting window sam-ples are separately processed as follows: The proposed algorithm performs two level WPT on each resulting window samples, dividing its coefficients into its four wavelet subbands. Infor-mation in wavelet high frequency subbands is then used for fault detection and activating the trip signal to disconnect the motor from the power supply. The proposed algorithm was first implemented in the MATLAB platform, and the Entropy power Energy (EE) of the high frequen-cy WPT subbands’ coefficients was used to determine the condition of the motor. If the induction motor is faulty, the algorithm proceeds to identify the type of the fault. An empirical setup of the proposed system was then implemented, and the proposed algorithm condition was tested under real, where different faults were practically induced to the induction motor. Experimental results confirmed the effectiveness of the proposed technique. To generalize the proposed meth-od, the experiment was repeated on different types of induction motors with different working ages and with different power ratings. Experimental results show that the capability of the pro-posed method is independent of the types of motors used and their ages.

El análisis de Fourier es el método fundamental para la medida de armónicos e interarmónicos en señales eléctricas y es el principio de análisis que establece la International Electrotechnical Commission para los instrumentos de medida. Con el objetivo de superar las limitaciones que lo hacen poco efectivo en determinadas condiciones se han propuesto otras técnicas de análisis como las wavelets. En esta tesis doctoral se explora esta alternativa en el campo de la calidad del suministro de energía eléctrica.Como aportación principal se presenta un nuevo método de medida de armónicos e interarmónicos basado en la Transformada Wavelet Packet compatible con el estándar de medida IEC 61000-4-7 de 2002. El método propuesto utiliza un árbol de descomposición wavelet, que en sus distintos niveles suministra la medida de armónicos e interarmónicos de la señal, así como su contenido subarmónico e información de sus variaciones en el dominio temporal.Se exponen las características principales del método en cuanto a la elección de la función wavelet madre, el banco de filtros que implementa el árbol de descomposición wavelet y el postprocesado que posibilita la compatibilidad con el estándar de medida. Se analizan las prestaciones del método en la medida de armónicos e interarmónicos, tanto en condiciones estacionarias como en el caso de pérdida de sincronía por variación de la frecuencia fundamental o variación de la ventana de muestreo de la señal, presencia de componentes no síncronas con la frecuencia de la red o presencia de componentes de amplitud variable. Por último, se expone la información que aporta el método para la estimación temporal de las componentes frecuenciales medidas.El método desarrollado junto con el método de IEC, se ha implementado sobre un equipo electrónico para adquisición y procesado de señal utilizando técnicas de instrumentación virtual. Se expone la estructura y características del hardware utilizado y del software desarrollado así como los resultados obtenidos en la medida del espectro frecuencial de señales de diferente naturaleza.Por último se resumen las conclusiones obtenidas y se proponen futuras líneas de investigación motivadas por la realización de esta tesis doctoral. / Fourier analysis is the fundamental method for the measurement of harmonics and interharmonics in electrical power systems and is the method proposed by the International Electrotechnical Commission (IEC) for standard measurement instruments. With the objective of overcoming the limitations in certain conditions, other techniques of analysis such as wavelets have been proposed. This doctoral thesis investigates alternatives in the field of the quality of the provision of electrical energy. The main contribution of this thesis is the proposal of a new method of measurement of harmonics and interharmonics based on the Wavelet Packet Transform compatible with the standard IEC 61000-4-7 of 2002. The method proposed simultaneously uses different levels of the same wavelet decomposition tree for the measurement of harmonic, interharmonic and subharmonic components in the input signal as well as their time evolution.The basic characteristics of the method in terms of the choice of the mother wavelet function, the bank of filters that implements the wavelet decomposition tree and the postprocessing to make the method compatible with the measurement standard are explained. The benefits of the method in the measurement of harmonics and interharmonics are analyzed, both in stationary conditions and in the case of loss of synchrony due to variation of the base frequency or variation of the sampling window of the signal, presence of nonsynchronous components with the frequency of the network or presence of components of variable amplitude. Finally, the information that the method provides about the temporal estimation of the measured frequencial components is described.The method developed and the IEC method have been implemented on a virtual instrument. The hardware used and the software developed are explained studying the performance of the instrument under different measurement conditions.Finally the conclusions obtained are summarized and future lines of investigation motivated by this doctoral thesis are proposed.

Submitted by RAFAEL RUBIATI SCALVENZI (rafaelrubiati@yahoo.com) on 2018-08-23T14:58:47Z No. of bitstreams: 1 Dissertacao Rafael Rubiati.pdf: 3684917 bytes, checksum: 933c9cd1b163eaf62189c9f2bcfcdd2f (MD5) / Approved for entry into archive by Elza Mitiko Sato null (elzasato@ibilce.unesp.br) on 2018-08-23T19:34:48Z (GMT) No. of bitstreams: 1 scalvenzi_rr_me_sjrp_.pdf: 3684917 bytes, checksum: 933c9cd1b163eaf62189c9f2bcfcdd2f (MD5) / Made available in DSpace on 2018-08-23T19:34:48Z (GMT). No. of bitstreams: 1 scalvenzi_rr_me_sjrp_.pdf: 3684917 bytes, checksum: 933c9cd1b163eaf62189c9f2bcfcdd2f (MD5) Previous issue date: 2018-07-20 / A área na qual a música está inserida requer, para sua compreensão, considerável abstração. Neste âmbito, a análise matemático-computacional possui papel importante, principalmente para planejar a interatividade entre aluno e computador, potencializando o aprendizado musical. Embora um número considerável de estudos em diferentes contextos sejam dedicados à classificação das estruturas sonoras, os procedimentos de análise em um grande conjunto de sinais podem tornar-se uma tarefa difícil e exaustiva. Diante do exposto, este trabalho tem como objetivo a proposição e a implementação de um método capaz de reconhecer e classificar sinais musicais em tempo real, visando auxiliar os aprendizes. No método proposto, um conjunto relevante de eventos musicais é inspecionado por meio da análise de multirresolução baseada na Transformada Wavelet-Packet, escolhida em função da característica multidimensional encontrada na música, a qual permite isolar diferentes eventos musicais em níveis de decomposição wavelet distintos. Apoiado por um processo de autocorrelação e uma rede neural artificial, cada padrão sônico é associado ao seu respectivo evento musical. Testes envolvendo centenas de sinais permitiram obter uma acurácia quase plena com um tempo relativamente bastante pequeno de análise em função da baixa ordem de complexidade computacional do algoritmo implementado, reafirmando a sua aplicabilidade / Music belongs to an area which requires a considerable piece of abstraction for its understanding. In this domain, computational and mathematical analyses play an important role, particularly for planning human-machine interaction and enhancing learning. Although a considerable number of studies in different musical contexts are dedicated to the classification of the structures present in sound signals, the inspection of long clips is a challenge. Thus, this work proposes and implements a method capable of identifying and classifying musical signals in real-time, helping music students. Specifically, multiresolution analysis using the Wavelet-Packet Transform is adopted, allowing for different musical events to be isolated in distinct wavelet levels of decomposition. Based on an autocorrelation and an artificial neural network, each sonic pattern is associated with a respective musical event. Tests using hundreds of music clips exhibit almost full accuracy with relatively very short time consumption as a function of the algorithm low level of computational complexity, reassuring its applicability.

The radar transmitter identification problem involves the identification of a specific radar transmitter based on a received pulse. The radar transmitters are of identical make and model. This makes the problem challenging since the differences between radars of identical make and model will be solely due to component tolerances and variation. Radar pulses also vary in time and frequency which means that the problem is non-stationary. Because of this fact, time-frequency representations such as shift-invariant quadratic time-frequency representations (Cohen’s class) and wavelets were used. A model for a radar transmitter was developed. This consisted of an analytical solution to a pulse-forming network and a linear model of an oscillator. Three signal classification algorithms were developed. A signal classifier was developed that used a radially Gaussian Cohen’s class transform. This time-frequency representation was refined to increase the classification accuracy. The classification was performed with a support vector machine classifier. The second signal classifier used a wavelet packet transform to calculate the feature values. The classification was performed using a support vector machine. The third signal classifier also used the wavelet packet transform to calculate the feature values but used a Universum type classifier for classification. This classifier uses signals from the same domain to increase the classification accuracy. The classifiers were compared against each other on a cubic and exponential chirp test problem and the radar transmitter model. The classifier based on the Cohen’s class transform achieved the best classification accuracy. The classifier based on the wavelet packet transform achieved excellent results on an Electroencephalography (EEG) test dataset. The complexity of the wavelet packet classifier is significantly lower than the Cohen’s class classifier. Copyright / Dissertation (MEng)--University of Pretoria, 2010. / Electrical, Electronic and Computer Engineering / unrestricted

No description available.