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.

<p>This master's thesis explores whether time-frequency techniques can be utilized in a ground penetrating radar system. The system studied is the HUMUS system which has been developed at FOI, and which is used for the detection and classification of buried land mines. </p><p>The objective of this master's thesis is twofold. First of all it is supposed to give a theoretical introduction to the wavelet transform and wavelet packets, and also to introduce general time-frequency transformations. Secondly, the thesis presents and implements an adaptive method, which is used to perform the task of a feature extractor. </p><p>The wavelet theory presented in this thesis gives a first introduction to the concept of time-frequency transformations. The wavelet transform and wavelet packets are studied in detail. The most important goal of this introduction is to define the theoretical background needed for the second objective of the thesis. However, some additional concepts will also be introduced, since they were deemed necessary to include in an introduction to wavelets. </p><p>To illustrate the possibilities of wavelet techniques in the existing HUMUS system, one specific application has been chosen. The application chosen is feature extraction. The method for feature extraction described in this thesis uses wavelet packets to transform theoriginal radar signal into a form where the features of the signal are better revealed. One of the algorithms strengths is its ability to adapt itself to the kind of input radar signals expected. The algorithm will pick the "best" wavelet packet from a large number of possible wavelet packets.</p><p>The method we use in this thesis emanates from a previously publicized dissertation. The method proposed in that dissertation has been modified to the specific environment of the HUMUS system. It has also been implemented in MATLAB, and tested using data obtained by the HUMUS system. The results are promising; even"weak"objects can be revealed using the method.</p>

This master's thesis explores whether time-frequency techniques can be utilized in a ground penetrating radar system. The system studied is the HUMUS system which has been developed at FOI, and which is used for the detection and classification of buried land mines. The objective of this master's thesis is twofold. First of all it is supposed to give a theoretical introduction to the wavelet transform and wavelet packets, and also to introduce general time-frequency transformations. Secondly, the thesis presents and implements an adaptive method, which is used to perform the task of a feature extractor. The wavelet theory presented in this thesis gives a first introduction to the concept of time-frequency transformations. The wavelet transform and wavelet packets are studied in detail. The most important goal of this introduction is to define the theoretical background needed for the second objective of the thesis. However, some additional concepts will also be introduced, since they were deemed necessary to include in an introduction to wavelets. To illustrate the possibilities of wavelet techniques in the existing HUMUS system, one specific application has been chosen. The application chosen is feature extraction. The method for feature extraction described in this thesis uses wavelet packets to transform theoriginal radar signal into a form where the features of the signal are better revealed. One of the algorithms strengths is its ability to adapt itself to the kind of input radar signals expected. The algorithm will pick the "best" wavelet packet from a large number of possible wavelet packets. The method we use in this thesis emanates from a previously publicized dissertation. The method proposed in that dissertation has been modified to the specific environment of the HUMUS system. It has also been implemented in MATLAB, and tested using data obtained by the HUMUS system. The results are promising; even"weak"objects can be revealed using the method.

The ongoing development and increased affordability of hyperspectral sensors are increasing their utilization in a variety of applications, such as agricultural monitoring and decision making. Hyperspectral Automated Target Recognition (ATR) systems typically rely heavily on dimensionality reduction methods, and particularly intelligent reduction methods referred to as feature extraction techniques. This dissertation reports on the development, implementation, and testing of new hyperspectral analysis techniques for ATR systems, including their use in agricultural applications where ground truthed observations available for training the ATR system are typically very limited. This dissertation reports the design of effective methods for grouping and down-selecting Discrete Wavelet Transform (DWT) coefficients and the design of automated Wavelet Packet Decomposition (WPD) filter tree pruning methods for use within the framework of a Multiclassifiers and Decision Fusion (MCDF) ATR system. The efficacy of the DWT MCDF and WPD MCDF systems are compared to existing ATR methods commonly used in hyperspectral remote sensing applications. The newly developed methods’ sensitivity to operating conditions, such as mother wavelet selection, decomposition level, and quantity and quality of available training data are also investigated. The newly developed ATR systems are applied to the problem of hyperspectral remote sensing of agricultural food crop contaminations either by airborne chemical application, specifically Glufosinate herbicide at varying concentrations applied to corn crops, or by biological infestation, specifically soybean rust disease in soybean crops. The DWT MCDF and WPD MCDF methods significantly outperform conventional hyperspectral ATR methods. For example, when detecting and classifying varying levels of soybean rust infestation, stepwise linear discriminant analysis, results in accuracies of approximately 30%-40%, but WPD MCDF methods result in accuracies of approximately 70%-80%.

No description available.

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).

Today's industry uses increasingly complex machines, some with extremely demanding performance criteria. Failed machines can lead to economic loss and safety problems due to unexpected production stoppages. Fault diagnosis in the condition monitoring of these machines is crucial for increasing machinery availability and reliability. Fault diagnosis of machinery is often a difficult and daunting task. To be truly effective, the process needs to be automated to reduce the reliance on manual data interpretation. It is the aim of this research to automate this process using data from machinery vibrations. This thesis focuses on the design, development, and application of an automatic diagnosis procedure for rolling element bearing faults. Rolling element bearings are representative elements in most industrial rotating machinery. Besides, these elements can also be tested economically in the laboratory using relatively simple test rigs. Novel modern signal processing methods were applied to vibration signals collected from rolling element tests to destruction. These included three advanced timefrequency signal processing techniques, best basis Discrete Wavelet Packet Analysis (DWPA), Matching Pursuit (MP), and Basis Pursuit (BP). This research presents the first application of the Basis Pursuit to successfully diagnosing rolling element faults. Meanwhile, Best basis DWPA and Matching Pursuit were also benchmarked with the Basis Pursuit, and further extended using some novel ideas particularly on the extraction of defect related features. The DWPA was researched in two aspects: i) selecting a suitable wavelet, and ii) choosing a best basis. To choose the most appropriate wavelet function and decomposition tree of best basis in bearing fault diagnostics, several different wavelets and decomposition trees for best basis determination were applied and comparisons made. The Matching Pursuit and Basis Pursuit techniques were effected by choosing a powerful wavelet packet dictionary. These algorithms were also studied in their ability to extract precise features as well as their speed in achieving a result. The advantage and disadvantage of these techniques for feature extraction of bearing faults were further evaluated. An additional contribution of this thesis is the automation of fault diagnosis by using Artificial Neural Networks (ANNs). Most of work presented in the current literature has been concerned with the use of a standard pre-processing technique - the spectrum. This research employed additional pre-processing techniques such as the spectrogram and DWPA based Kurtosis, as well as the MP and BP features that were subsequently incorporated into ANN classifiers. Discrete Wavelet Packets and Spectra, were derived to extract features by calculating RMS (root mean square), Crest Factor, Variance, Skewness, Kurtosis, and Matched Filter. Certain spikes in Matching Pursuit analysis and Basis Pursuit analysis were also used as features. These various alternative methods of pre-processing for feature extraction were tested, and evaluated with the criteria of the classification performance of Neural Networks. Numerous experimental tests were conducted to simulate the real world environment. The data were obtained from a variety of bearings with a series of fault severities. The mechanism of bearing fault development was analysed and further modelled to evaluate the performance of this research methodology. The results of the researched methodology are presented, discussed, and evaluated in the results and discussion chapter of this thesis. The Basis Pursuit technique proved to be effective in diagnostic tasks. The applied Neural Network classifiers were designed as multi layer Feed Forward Neural Networks. Using these Neural Networks, automatic diagnosis methods based on spectrum analysis, DWPA, Matching Pursuit, and Basis Pursuit proved to be effective in diagnosing different conditions such as normal bearings, bearings with inner race and outer race faults, and rolling element faults, with high accuracy. Future research topics are proposed in the final chapter of the thesis to provide perspectives and suggestions for advancing research into fault diagnosis and condition monitoring.

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.

Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2009. / ENGLISH ABSTRACT: Brain-Computer Interface (BCI) monitors brain activity by using signals such as EEG, EcOG, and MEG, and attempts to bridge the gap between thoughts and actions by providing control to physical devices that range from wheelchairs to computers. A crucial process for a BCI system is feature extraction, and many studies have been undertaken to find relevant information from a set of input signals. This thesis investigated feature extraction from EEG signals using two different approaches. Wavelet packet decomposition was used to extract information from the signals in their frequency domain, and cepstral analysis was used to search for relevant information in the cepstral domain. A BCI was implemented to evaluate the two approaches, and three classification techniques contributed to finding the effectiveness of each feature type. Data containing two-class motor imagery was used for testing, and the BCI was compared to some of the other systems currently available. Results indicate that both approaches investigated were effective in producing separable features, and, with further work, can be used for the classification of trials based on a paradigm exploiting motor imagery as a means of control. / AFRIKAANSE OPSOMMING: ’n Brein-Rekenaar Koppelvlak (BRK) monitor brein aktiwiteit deur gebruik te maak van seine soos EEG, EcOG, en MEG. Dit poog om die gaping tussen gedagtes en fisiese aksies te oorbrug deur beheer aan toestelle soos rolstoele en rekenaars te verskaf. ’n Noodsaaklike proses vir ’n BRK is die ontginning van toepaslike inligting uit inset-seine, wat kan help om tussen verskillende gedagtes te onderskei. Vele studies is al onderneem oor hoe om sulke inligting te vind. Hierdie tesis ondersoek die ontginning van kenmerk-vektore in EEG-seine deur twee verskillende benaderings. Die eerste hiervan is golfies pakkie ontleding, ’n metode wat gebruik word om die sein in die frekwensie gebied voor te stel. Die tweede benadering gebruik kepstrale analise en soek vir toepaslike inligting in die kepstrale domein. ’n BRK is geïmplementeer om beide metodes te evalueer. Die toetsdata wat gebruik is, het bestaan uit twee-klas motoriese verbeelde bewegings, en drie klassifikasie-tegnieke was gebruik om die doeltreffendheid van die twee metodes te evalueer. Die BRK is vergelyk met ander stelsels wat tans beskikbaar is, en resultate dui daarop dat beide metodes doeltreffend was. Met verdere navorsing besit hulle dus die potensiaal om gebruik te word in stelsels wat gebruik maak van motoriese verbeelde bewegings om fisiese toestelle te beheer.