Página 10 dos resultados de 435 itens digitais encontrados em 0.010 segundos

‣ Procedimentos avançados em codificação wavelet adaptada à geometria para tratamento e compressão de imagens; Advanced procedures in geometry adapted wavelet coding for image processing and compression

Ricardo Barroso Leite
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Tese de Doutorado Formato: application/pdf
Publicado em 03/07/2014 Português
Relevância na Pesquisa
27.15793%
Muitas áreas de pesquisa utilizam imagens digitais e outros arranjos multidimensionais de dados, que para serem transmitidos e armazenados de forma mais eficiente passam por um processo de filtragem e compressão. A transformada wavelet isotrópica é tradicionalmente usada e considerada um método rápido e eficiente para compressão. Por agregar as vantagens de representação multirresolução e a localização dos contornos, as bandelets têm sido consideradas estado-da-arte em várias aplicações de processamento de imagens. Neste trabalho é apresentado um novo método para processamento e compressão de imagens baseado na transformada bandelet. Em nosso método, uma estimativa é feita de forma a reduzir o espaço de busca e tornar o processamento da imagem assintoticamente mais rápido. Os resultados mostram que pode ser feito um compromisso entre qualidade da imagem e tempo computacional, tornando o esquema mais atrativo para uma ampla gama de aplicações. Dentre as áreas beneficiadas por esse método estão transmissão de imagens e vídeo (TV digital e dispositivos móveis), imagens médicas e modelagem 3D.; Many research areas use digital images and other multi-dimensional arrays of data which to be transmitted and stored more efficiently pass through a filtering process and compression. The isotropic wavelet transform is traditionally used and considered a fast and efficient method for compression. By adding the advantages of multi-resolution representation and location of edges...

‣ Contribuições ao problema de extração de tempo musical; Contributions to the problem of musical tempo extraction

Antonio Carlos Lopes Fernandes Junior
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Tese de Doutorado Formato: application/pdf
Publicado em 27/02/2015 Português
Relevância na Pesquisa
27.15793%
A deteção de tempo em um sinal musical é uma tarefa muito importante em diversas aplicações. A presente tese apresenta os resultados da detecção de andamento usando uma nova abordagem baseada na extração de atributos de um conjunto de funções de detecção de periodicidade e aprendizado de máquina. Para isto a transformada wavelet foi utilizada para separar o sinal musical em diferentes resoluções e o domínio complexo retificado foi aplicado para a construção de funções de deteccão de onsets. Em seguida, as funções de deteccão de periodicidade para cada nível wavelet foram geradas por operações de autocorrelação. Descritores de áudio clássicos foram adaptados e extraídos de cada função de periodicidade e foram usados como entradas para a máquina de aprendizado que mapeia os descritores para o tempo da música. As máquinas utilizadas foram o perceptron de múltiplas camadas e a máquina de aprendizado extremo, com propostas diferenciadas de configuração. Um método para classificação e avaliação dos descritores foi proposto. Também, neste trabalho, um novo descritor foi proposto. Um método de seleção forward de atributos via Gram-Schmidt foi aplicado para a escolha do melhor subconjunto para o treinamento da máquina. Foi ainda aplicado um método de clustering via K-means para a partilha de observações entre os conjuntos de treinamento...

‣ Aplicação de tecnologias analíticas de processo e inteligência artificial para monitoramento e controle de processo de recobrimento de partículas em leito fluidizado; Application of process analytical technologies and artificial intelligence to monitor and control a fluidized bed coating process

Carlos Alexandre Moreira da Silva
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Tese de Doutorado Formato: application/pdf
Publicado em 25/02/2015 Português
Relevância na Pesquisa
27.15793%
As indústrias química, alimentícia e farmacêutica têm empregado extensivamente a operação de fluidização em inúmeros processos, devido às suas características bastante atrativas, que possibilitam um contato efetivo entre a fase sólida e fluida, o que reflete na geração de altas taxas de transferência de calor e de massa. No entanto, o regime de fluidização borbulhante, o qual é condição de partida dos processos que envolvem esta operação, frequentemente é afetado pelas condições operacionais. As temperaturas elevadas, o conteúdo de umidade excessivo das partículas e a introdução de líquidos no leito fluidizado podem conduzir a instabilidades no regime fluidodinâmico e provocar o colapso parcial ou total do leito, reduzindo a eficiência do processo. A manutenção de condições estáveis do regime de fluidização durante processos de recobrimento de partículas em leitos fluidizados é de fundamental importância para garantir uma eficiência de recobrimento favorável e evitar a formação de zonas sem movimentação e aglomeração das partículas no leito, pois estes fatores indesejáveis comprometem a mistura entre as fases e conseqüentemente a qualidade do produto final. Dentro deste contexto...

‣ Classification of events in distribution networks using autonomous neural models

Lazzaretti, Andre Eugênio; Ferreira, Vitor Hugo; Vieira Neto, Hugo; Riella, Rodrigo Jardim; Omori, Julio Shigeaki
Fonte: International Conference on Intelligent System Applications to Power Systems; Curitiba Publicador: International Conference on Intelligent System Applications to Power Systems; Curitiba
Tipo: Conferência ou Objeto de Conferência
Português
Relevância na Pesquisa
27.15793%
This paper presents a method for automatic classification of faults and events related to quality of service in electricity distribution networks. The method consists in preprocessing event oscillographies using the wavelet transform and then classifying them using autonomous neural models. In the preprocessing stage, the energy present in each sub-band of the wavelet domain is computed in order to compose input feature vectors for the classification stage. The classifiers investigated are based in Multi-Layer Perceptron (MLP) feed-forward artificial neural networks and Support Vector Machines (SVM), which automatically promote input selection and structure complexity control simultaneously. Experiments using simulated data show promising results for the proposed application.; 5000

‣ Autonomous neural models for the classification of events in power distribution networks

Lazzaretti, Andre Eugênio; Ferreira, Vitor Hugo; Vieira Neto, Hugo; Riella, Rodrigo Jardim; Omori, Julio Shigeaki
Fonte: Journal of Control, Automation and Electrical Systems; Curitiba Publicador: Journal of Control, Automation and Electrical Systems; Curitiba
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
27.15793%
This paper presents a method for automatic classification of faults and transients in power distribution networks, based on voltage oscillographies of the distribution networks feeders. For signal preprocessing, the discrete wavelet transform was used with the performances of several families of wavelet functions being compared. In the classification stage, three neural models were assessed: multilayer perceptrons, radial basis function networks, and support vector machines. The models were trained autonomously, i.e., using automatic model selection and complexity control. Promising results were obtained using a set of simulations generated using the Alternative Transients Program (ATP). Initial results obtained for real data acquired from a set of oscillograph loggers installed in a distribution network are also presented.; 5000

‣ Detecção de fadiga neuromuscular em pessoas com lesão medular completa utilizando transformada wavelet

Krueger, Eddy
Fonte: Curitiba Publicador: Curitiba
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
27.15793%
Introduction: People with spinal cord injury (SCI) may have the paralyzed muscles activated through functional electrical stimulation (FES) on neural pathways present below the skin. These electrical stimulations are important to restore the neuromuscular trophism or during the movement control using neural prostheses. However, prolonged FES application causes fatigue, which decreases the contraction strength, mainly due the neuromuscular hypotrophy in this population. The acquisition of myofibers’ vibration is recognized by mechanomyography (MMG) system and does not suffer electrical interference from the FES system. Objective: To characterize the rectus femoris muscle vibration during electrically evoked neuromuscular fatigue protocol in complete spinal cord injury subjects. Methods: As sample, 24 limbs (right and left) from 15 male participants (age: 27±5 y.o.) and ranked as A and B according to American Spinal Injury Impairment Scale) were selected. An electrical stimulator operating as voltage source, specially developed for research, was configured as: pulse frequency set to 1 kHz (20% duty cycle) and burst (modulating) frequency set to 70 Hz (20% active period). The triaxial [X (transverse), Y (longitudinal) and Z (perpendicular)] MMG signal of rectus femoris muscle was processed with a third-order 5-50 Hz bandpass Butterworth filter. A load cell was used to register the force. The stimulator output voltage was increased (~3 V/s to avoid motoneuron adaptation/habituation) until the maximal electrically-evoked extension (MEEE) of the knee joint. After the load cell placement...

‣ Segmentação, classificação e detecção de novas classes de eventos em oscilografias de redes de distribuição de energia elétrica

Lazzaretti, André Eugenio
Fonte: Curitiba Publicador: Curitiba
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
27.15793%
This work presents new approaches for two of the fundamental steps in automatic waveform analysis in electrical distribution systems: transient time detection and its classification. Two datasets were used to compare and validate the proposed methods. The first is composed by simulated waveforms, by using the Alternative Transient Program, while the second is formed by real data from a monitoring system developed for overhead distribution power lines. The real data present a set of relevant events for the analysis proposed here, mainly due to the variety of events, including lightning-related transients. Regarding transient detection (waveform segmentation), the experiments involve usual segmentation methods, such as Kalman filtering, standard Discrete Wavelet Transform, and autoregressive models, besides two new techniques based on the Teager Energy Operator and Support Vector Data Description. The results obtained on both simulated and real world data demonstrate that the method based on Support Vector Data Description outperforms other methods in the transient identification task. Regarding the automatic waveform classification, a new approach including the detection of classes not defined in the training stage (called novelties) is presented. Also...

‣ Classificação de falhas em maquinas eletricas usando redes neurais, modelos wavelet e medidas de informação

Silva, Lyvia Regina Biagi
Fonte: Cornelio Procopio Publicador: Cornelio Procopio
Tipo: Dissertação de Mestrado
Português
Relevância na Pesquisa
27.15793%
This work presents a methodology for diagnosis and classification of faults in three-phase induction motors connected directly to the power grid. The proposed method is based on the analysis of the stator current signals, with and without the presence of faults in the bearings, stator and rotor. These faults cause the presence of specific frequency components that are related to the machine rotational speed. The signals were analyzed using wavelet-packet decomposition, which allows a multiresolution evaluation of the signals. Using this decomposition, we estimated some predictability measures, such as relative entropy, predictive power and normalized error variance, obtained with the predictability component analysis. With this measures, we verified which were the most predictable components. In this work, normalized error variance and the predictive power were used as inputs to three topologies of artificial neural networks used as classifiers: multilayer perceptron, radial basis function and Kohonen self-organizing maps. We tested six different input vectors to the artificial neural networks, in which we vary the predictability measures and the number of elements of the vectors. The studies were performed considering samples of signals from different motors...

‣ The wavelet transforms and time-scale analysis of signals

Gopinath, Ramesh Ambat
Fonte: Universidade Rice Publicador: Universidade Rice
Português
Relevância na Pesquisa
27.15793%
Orthonormal wavelet bases provide an alternative technique for the analysis of non-stationary signals. Unlike the Gabor representation, the basis functions in the wavelet representation all have the same band width on a logarithmic scale. This thesis develops a general framework for the time-scale analysis of signals. In this context, the ON wavelets form a subclass of DWT wavelets. Efficient algorithms for the computation of the wavelet transforms are also developed. As an application, we discuss the problem of detection of (wideband) signals subjected to scale-time perturbations. The probable unknown parameters for scale-time perturbed signals are the gain, and the scale and time perturbations. This problem is set in the context of classical composite hypothesis testing with unknown parameters, and depending on what the unknown parameters are, one of the wavelet transforms, developed is shown to naturally lead to a detector.

‣ Transformada wavelet aplicada a análise de falhas em rolamentos; Wavelet transform applied on bearing's fault detection

Thiago Augusto Bento da Silva Camargo
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 21/07/2011 Português
Relevância na Pesquisa
27.15793%
Neste trabalho, foram feitas avaliações da utilização da transformada wavelet aplicada, principalmente, na identificação de falhas em rolamentos de esferas com contato angular. Como essa transformada pode ser comparada a transformada de Fourier, foi feito, primeiramente, um estudo comparativo entre a transformada wavelet contínua e a transformada de Fourier com sinais variantes no tempo. Posterior a essa avaliação, a transformada Wavelet discreta foi aplicada em diferentes métodos de identificação de presença de falhas em rolamentos como os métodos da porcentagem de energia, contagem de WZC (Wavelet Zero Crossing) e distancia euclidiana avaliados comparativamente entre sinais simulados de rolamento considerado bom e outro considerado ruim, para cada banda de freqüência. E, em seguida, a transformada wavelet contínua foi comparada através da avaliação dos resultados da identificação de origem de falhas pelo método do envelope, sendo utilizada como filtro em substituição ao filtro passa banda de Butterworth comumente utilizado. Os resultados mostraram que a transformada Wavelet consegue identificar a variação de freqüência em sinais variantes no tempo e a transformada de Fourier não. Os métodos que utilizaram a transformada wavelet discreta puderam fazer a identificação positiva da presença de falha em rolamentos...

‣ Uma proposta imuno-inspirada para segmentação de imagens com texturas usando transformada wavelet packet; An immune-inspired proposal for textured image segmentation using wavelet packet transform

Karinne Saraiva da Silva
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 14/04/2010 Português
Relevância na Pesquisa
27.15793%
Segmentação de texturas é um ponto crucial em muitas aplicações da área de visão computacional e processamento digital de imagens. Muitas são as aplicações que utilizam imagens com texturas, como: sensoriamento remoto, análise de imagens médicas, inspeção industrial, etc. Para análise de texturas, é essencial o uso de um extrator de características capaz de representar bem cada textura presente na imagem. A transformada wavelet packet fornece a caracterização necessária para discriminação de texturas, oferecendo também uma representação multi-escala, ferramenta muito importante na análise de texturas. Outro ponto importante neste trabalho, é o fato da metodologia aqui proposta ser não supervisionada. Para tal, é utilizado o algoritmo de clusterização ARIA, que determina automaticamente o número de clusters presentes no conjunto de dados. A eficiência do método desenvolvido é comprovada aplicando-o em diversas imagens, como: mosaicos de Brodatz, imagens naturais, imagens médicas e outras aplicações; Texture segmentation is a crucial aspect in many computer vision and digital image processing applications. Several of these applications use texture images, such as remote sensing, medical image analysis...

‣ Multi-marcação de vídeo baseada em marca d'água LWT-SVD usando abordagem lateral

Fung, Charles Way Hun
Fonte: Curitiba Publicador: Curitiba
Tipo: Dissertação de Mestrado
Português
Relevância na Pesquisa
27.15793%
Digital videos have become the most used way to communicate, however these data are easily copied and distributed. That happen due the growing number of tools that are create with this goal, causing breach of copyright and illegal distribution of content. The most studied solution that can solve this problem are the digital watermarks that provide security like authentication and tamper detection. In this work, we developed a new method of embedding and extracting watermarks in a video using a process called side view. This process allows watermark a block of frames. The several watermarks embedded can be used like redundance to grow the robustness of the method against attacks. The tests followed the standard benchmarks Vidmark and Stirmark that show the performance of the method in keep the watermark even after attacks.; CAPES; Vídeos digitais se tornaram uma forma de comunicação altamente utilizada na rede, entretanto estes dados são facilmente copiados e distribuídos. Isto se deve ao crescente número de ferramentas que surgiram com este objetivo, causando quebra dos direitos autorais e distribuição ilegal de conteúdo. A solução mais estudada para este problema são as marcas d'água digitais, que provêm segurança em forma de autenticação e verificação de violação. Neste trabalho...

‣ Factoring Pseudoidentity Matrix Pairs

Sebert, Florian M.; Zou, Yi Ming
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 19/01/2011 Português
Relevância na Pesquisa
27.15793%
The problem of factorization and parametrization of compactly supported biorthogonal wavelets was reduced to that of pseudoidentity matrix pairs by Resnikoff, Tian, and Wells in their 2001 paper. Based on a conjecture on the pseudoidentity matrix pairs of rank 2 stated in the same paper, they proved a theorem which gives a complete factorization result for rank 2 compactly supported biorthogonal wavelets. In this paper, we first provide examples to show that the conjecture is not true, then we prove a factorization theorem for pseudoidentity matrix pairs of rank $m\ge 2$. As a consequence, our result shows that a slightly modified version of the factorization theorem in the rank 2 case given by Resnikoff, Tian, and Wells holds. We also provide a concrete constructive method for the rank 2 case which is determined by applying the Euclidean algorithm to two polynomials.; Comment: To appear in SIAM Journal on Mathematical Analysis

‣ Coorbit spaces and wavelet coefficient decay over general dilation groups

Führ, Hartmut
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
27.15793%
We study continuous wavelet transforms associated to matrix dilation groups giving rise to an irreducible square-integrable quasi-regular representation on ${\rm L}^2(\mathbb{R}^d)$. We first prove that these representations are integrable as well, with respect to a wide variety of weights, thus allowing to consistently quantify coefficient decay via coorbit space norms. We then show that these spaces always admit an atomic decomposition in terms of bandlimited Schwartz wavelets. We exhibit spaces of Schwartz functions densely contained in (most of) the coorbit spaces. We also present an example showing that for a consistent definition of coorbit spaces, the irreducibility requirement cannot be easily dispensed with. We then address the question how to predict wavelet coefficient decay from vanishing moment assumptions. To this end, we introduce a new condition on the open dual orbit associated to a dilation group: If the orbit is temperately embedded, it is possible to derive rather general weighted ${\rm L}^{p,q}$-estimates for the wavelet coefficients from vanishing moment conditions on the wavelet and the analyzed function. These estimates have various applications: They provide very explicit admissibility conditions for wavelets and integrable vectors...

‣ Symmetries in projective multiresolution analyses

Røysland, Kjetil
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 26/09/2007 Português
Relevância na Pesquisa
27.15793%
We give an equivariant version of Packer and Rieffel's theorem on sufficient conditions for the existence of orthonormal wavelets in projective multiresolution analyses. The scaling functions that generate a projective multiresolution analysis are supposed to be invariant with respect to some finite group action. We give sufficient conditions for the existence of wavelets with similar invariance.

‣ Invertible Orientation Scores of 3D Images

Janssen, Michiel; Duits, Remco; Breeuwer, Marcel
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 28/05/2015 Português
Relevância na Pesquisa
27.15793%
The enhancement and detection of elongated structures in noisy image data is relevant for many biomedical applications. To handle complex crossing structures in 2D images, 2D orientation scores were introduced, which already showed their use in a variety of applications. Here we extend this work to 3D orientation scores. First, we construct the orientation score from a given dataset, which is achieved by an invertible coherent state type of transform. For this transformation we introduce 3D versions of the 2D cake-wavelets, which are complex wavelets that can simultaneously detect oriented structures and oriented edges. For efficient implementation of the different steps in the wavelet creation we use a spherical harmonic transform. Finally, we show some first results of practical applications of 3D orientation scores.; Comment: ssvm 2015 published version in LNCS contains a mistake (a switch notation spherical angles) that is corrected in this arxiv version

‣ On stable reconstructions from nonuniform Fourier measurements

Adcock, Ben; Gataric, Milana; Hansen, Anders C.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
27.15793%
We consider the problem of recovering a compactly-supported function from a finite collection of pointwise samples of its Fourier transform taking nonuniformly. First, we show that under suitable conditions on the sampling frequencies - specifically, their density and bandwidth - it is possible to recover any such function $f$ in a stable and accurate manner in any given finite-dimensional subspace; in particular, one which is well suited for approximating $f$. In practice, this is carried out using so-called nonuniform generalized sampling (NUGS). Second, we consider approximation spaces in one dimension consisting of compactly supported wavelets. We prove that a linear scaling of the dimension of the space with the sampling bandwidth is both necessary and sufficient for stable and accurate recovery. Thus wavelets are up to constant factors optimal spaces for reconstruction.

‣ Wavelets and Information-preserving Transformations

Kim, Y. S.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 13/10/1996 Português
Relevância na Pesquisa
27.15793%
The underlying mathematics of the wavelet formalism is a representation of the inhomogeneous Lorentz group or the affine group. Within the framework of wavelets, it is possible to define the ``window'' which allows us to introduce a Lorentz-covariant cut-off procedure. The window plays the central role in tackling the problem of photon localization. It is possible to make a transition from light waves to photons through the window. On the other hand, the windowed wave function loses analyticity. This loss of analyticity can be measured in terms of entropy difference. It is shown that this entropy difference can be defined in a Lorentz-invariant manner within the framework of the wavelet formalism.; Comment: 8 pages, latex, no figures; presented at the 3rd International Conference on Quantum Communications and Measurements (Fiji-Hakone Land, Japan, September, 1996), to be published in the Proceedings

‣ Three-way tiling sets in two dimensions

Larson, David; Massopust, Peter; Olafsson, Gestur
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 18/10/2007 Português
Relevância na Pesquisa
27.15793%
In this article we show that there exist measurable sets W in the plane with finite measure that tile the plane in a measurable way under the action of a expansive matrix A, an affine Weyl group W, and a full rank lattice G. This note is follow-up research to the earlier article "Coxeter groups and wavelet sets" by the first and second authors, and is also relevant to the earlier article "Coxeter groups, wavelets, multiresolution and sampling" by M. Dobrescu and the third author. After writing these two articles, the three authors participated in a workshop at the Banff Center on "Operator methods in fractal analysis, wavelets and dynamical systems," December 2 -- 7, 2006, organized by O. Bratteli, P. Jorgensen, D. Kribs, G. Olafsson, and S. Silvestrov, and discussed the interrelationships and differences between the articles, and worked on two open problems posed in the Larson-Massopust article. We solved part of Problem 2, including a surprising positive solution to a conjecture that was raised, and we present our results in this article.

‣ Extended object reconstruction in adaptive-optics imaging: the multiresolution approach

Gallé, Roberto Baena; Núñez, Jorge; Gladysz, Szymon
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 25/10/2012 Português
Relevância na Pesquisa
27.15793%
We propose the application of multiresolution transforms, such as wavelets (WT) and curvelets (CT), to the reconstruction of images of extended objects that have been acquired with adaptive optics (AO) systems. Such multichannel approaches normally make use of probabilistic tools in order to distinguish significant structures from noise and reconstruction residuals. Furthermore, we aim to check the historical assumption that image-reconstruction algorithms using static PSFs are not suitable for AO imaging. We convolve an image of Saturn taken with the Hubble Space Telescope (HST) with AO PSFs from the 5-m Hale telescope at the Palomar Observatory and add both shot and readout noise. Subsequently, we apply different approaches to the blurred and noisy data in order to recover the original object. The approaches include multi-frame blind deconvolution (with the algorithm IDAC), myopic deconvolution with regularization (with MISTRAL) and wavelets- or curvelets-based static PSF deconvolution (AWMLE and ACMLE algorithms). We used the mean squared error (MSE) and the structural similarity index (SSIM) to compare the results. We discuss the strengths and weaknesses of the two metrics. We found that CT produces better results than WT, as measured in terms of MSE and SSIM. Multichannel deconvolution with a static PSF produces results which are generally better than the results obtained with the myopic/blind approaches (for the images we tested) thus showing that the ability of a method to suppress the noise and to track the underlying iterative process is just as critical as the capability of the myopic/blind approaches to update the PSF.; Comment: In revision in Astronomy & Astrophysics. 19 pages...