Data Segmentation Algorithm Research Articles

Basis approach to estimate the instantaneous frequencies in multicomponent AM-FM signals

Abstract In this paper, an analytical approach to estimate the instantaneous frequencies of a multicomponent signal is presented. A non-stationary signal composed of oscillation modes or resonances is described by a multicomponent AM-FM model. The proposed method has two main stages. At first, the signal is decomposed into its oscillation components. Afterwards, the instantaneous frequency of each component is estimated. The decomposition stage is performed through the basis expansion exploiting orthogonal rational functions in the complex plane. Orthogonal rational bases are generalized to expand linear time-varying systems. To decompose the non-stationary signal, its equivalent time-varying system is sought. The time-varying poles of this system are required to construct appropriate basis functions. An adaptive data segmentation algorithm is provided for this purpose. The effect of noise is scrutinized analytically and evaluated experimentally to verify the robustness of the new method. The performance of this method in extraction of embedded instantaneous frequencies is asserted by simulations on both synthetic data and real-world audio signal.

INTEGRAL/SPI data segmentation to retrieve source intensity variations

The INTEGRAL/SPI, X-gamma-ray spectrometer (20 keV - 8 MeV) is an instrument for which recovering source intensity variations is not straightforward and can constitute a difficulty for data analysis. In most cases, determining the source intensity changes between exposures is largely based on a priori information. We propose techniques that help to overcome the difficulty related to source intensity variations, which make this step more rational. In addition, the constructed "synthetic" light curves should permit us to obtain a sky model that describes the data better and optimizes the source signal-to-noise ratios. For this purpose, the time intensity variation of each source was modeled as a combination of piecewise segments of time during which a given source exhibits a constant intensity. To optimize the signal-to-noise ratios, the number of segments was minimized. We present a first method that takes advantage of previous time series that can be obtained from another instrument on-board the INTEGRAL observatory. A data segmentation algorithm was then used to synthesize the time series into segments. The second method no longer needs external light curves, but solely SPI raw data. For this, we developed a specific algorithm that involves the SPI transfer function. The time segmentation algorithms that were developed solve a difficulty inherent to the SPI instrument, which is the intensity variations of sources between exposures, and it allows us to obtain more information about the sources' behavior.

Engineering and algorithm design for an image processing Api: a technical report on ITK--the Insight Toolkit.

We present the detailed planning and execution of the Insight Toolkit (ITK), an application programmers interface (API) for the segmentation and registration of medical image data. This public resource has been developed through the NLM Visible Human Project, and is in beta test as an open-source software offering under cost-free licensing. The toolkit concentrates on 3D medical data segmentation and registration algorithms, multimodal and multiresolution capabilities, and portable platform independent support for Windows, Linux/Unix systems. This toolkit was built using current practices in software engineering. Specifically, we embraced the concept of generic programming during the development of these tools, working extensively with C++ templates and the freedom and flexibility they allow. Software development tools for distributed consortium-based code development have been created and are also publicly available. We discuss our assumptions, design decisions, and some lessons learned.

Comparison of Retinal Nerve Fiber Layer and Central Macular Thickness Measurements Among Five Different Optical Coherence Tomography Instruments in Patients With Multiple Sclerosis and Optic Neuritis

To compare the mean central macular thickness (CMT) and the mean average optic nerve retinal nerve fiber layer (RNFL) thickness in the eyes of patients with a history of optic neuritis and/or multiple sclerosis (MS) using 5 commercially available optical coherence tomography (OCT) instruments. Cross-sectional study including 46 patients (92 eyes) with a history of optic neuritis and/or MS. Both eyes were imaged on the same day with 5 OCT instruments: 1 time-domain OCT (Stratus) and 4 different Fourier-domain (spectral-domain) OCT (3D OCT-1000, Cirrus, RTVue-100, and Spectralis). Twenty-five patients (50 eyes) were included in the final analysis after excluding patients with diabetes, glaucoma, ocular hypertension, or retinal pathology and inadequate scan quality. Randomized block analysis of variance revealed statistically significant differences across instruments (P < 0.001) for both eyes for mean CMT and mean average optic nerve RNFL. When testing for significant differences in measurements from instrument to instrument, some difference was noted between the right and left eyes. Statistically significant differences exist among commercially available OCT instruments in measuring mean CMT and mean average RNFL thickness in patients with optic neuritis and/or MS. These findings likely result from the differences in data acquisition and segmentation algorithm software among OCT instruments. Awareness of these variations among OCT instruments will be important in using these instruments for clinical trials and management of patients with optic neuritis and/or MS.

Radial Basis Function Network for Ore Grade Estimation

This paper highlights the performance of a radial basis function (RBF) network for ore grade estimation in an offshore placer gold deposit. Several pertinent issues including RBF model construction, data division for model training, calibration and validation, and efficacy of the RBF network over the kriging and the multilayer perceptron models have been addressed in this study. For the construction of the RBF model, an orthogonal least-square algorithm (OLS) was used. The efficacy of this algorithm was testified against the random selection algorithm. It was found that OLS algorithm performed substantially better than the random selection algorithm. The model was trained using training data set, calibrated using calibration data set, and finally validated on the validation data set. However, for accurate performance measurement of the model, these three data sets should have similar statistical properties. To achieve the statistical similarity properties, an approach utilizing data segmentation and genetic algorithm was applied. A comparative evaluation of the RBF model against the kriging and the multilayer perceptron was then performed. It was seen that the RBF model produced estimates with the R2 (coefficient of determination) value of 0.39 as against of 0.19 for the kriging and of 0.18 for the multilayer perceptron.

Construction of a radial basis function network using an evolutionary algorithm for grade estimation in a placer gold deposit

This paper presents a study highlighting the predictive performance of a radial basis function (RBF) network in estimating the grade of an offshore placer gold deposit. In applying the radial basis function network to grade estimation of the deposit, several pertinent issues regarding RBF model construction are addressed in this study. One of the issues is the selection of the RBF network along with its center and width parameters. Selection was done by an evolutionary algorithm that utilizes the concept of cooperative coevolutions of the RBFs and the associated network. Furthermore, the problem of data division, which arose during the creation of the training, calibration and validation of data sets for the RBF model development, was resolved with the help of an integrated approach of data segmentation and genetic algorithms (GA). A simulation study conducted showed that nearly 27% of the time, a bad data division would result if random data divisions were adopted in this study. In addition, the efficacy of the RBF network was tested against a feed-forward network and geostatistical techniques. The outcome of this comparative study indicated that the RBF model performed decisively better than the feed-forward network and the ordinary kriging (OK).

Convergent Smoothing and Segmentation of Noisy Range Data in Multiscale Space

With few exceptions, most of the existing noise reduction and data segmentation algorithms are only suited to image data. Therefore, an adaptive smoothing algorithm, with model-based masks, within a scale space framework is proposed for range data in this paper. This algorithm smoothes range data that conform to predefined, geometric models, while leaving other data points unaffected. The convergence of the algorithm in yielding dominant features is shown based on its compliance with the anisotropic diffusion concept. The weights of the smoothing masks are adaptively calculated according to the Mahalanobis distances between range data and model-based predictions. These behave as the diffusion coefficient in the anisotropic diffusion equation, thus satisfying the requirements of the causality criterion that no new features are introduced from fine to coarse scales. The computational complexity of this algorithm is examined and compared to that of the well-known RANSAC feature extraction algorithm. Unlike RANSAC, it has the advantage that the computational complexity is less affected by increasing the order of the model, and is independent of the number of model outliers. The proposed algorithm can be used to smooth range data in multiscale space by increasing the number of smoothing iterations. Robust, robot-occlusion-invariant features are then easily extracted from the smoothed data by least squares fitting algorithms.

Range image segmentation using surface selection criterion

In this paper, we address the problem of recovering the true underlying model of a surface while performing the segmentation. First, and in order to solve the model selection problem, we introduce a novel criterion, which is based on minimising strain energy of fitted surfaces. We then evaluate its performance and compare it with many other existing model selection techniques. Using this criterion, we then present a robust range data segmentation algorithm capable of segmenting complex objects with planar and curved surfaces. The presented algorithm simultaneously identifies the type (order and geometric shape) of each surface and separates all the points that are part of that surface. This paper includes the segmentation results of a large collection of range images obtained from objects with planar and curved surfaces. The resulting segmentation algorithm successfully segments various possible types of curved objects. More importantly, the new technique is capable of detecting the association between separated parts of a surface, which has the same Cartesian equation while segmenting a scene. This aspect is very useful in some industrial applications of range data analysis.

Data Segmentation and Genetic Algorithms for Sparse Data Division in Nome Placer Gold Grade Estimation Using Neural Network and Geostatistics

Ore reserve estimation, based on sparse drill hole data, was conducted for a placer gold property in Nome, Alaska. A problem with sparse data is that random subdivision of the data into modelling and evaluation subsets (as is commonly done) becomes a problem, as random selection may result in biased/skewed subsets. Therefore, a technique that combined data segmentation with genetic algorithms (GA) was applied to divide the samples into three equivalent subsets: training, validation and testing. Data segmentation was done on the basis of the distribution of gold values. Neural network and a variety of kriging techniques were used to estimate gold grades. A multi-layer feed forward neural network along with “early/quick stop” training was used for neural network modelling. A comparative evaluation of kriging and neural network methods was then performed. The results revealed that neural network was generally superior to the kriging techniques for gold grade estimation in the Nome deposit.

Model Selection Techniques and Merging Rules for Range Data Segmentation Algorithms

The problem of model selection is relevant to many areas of computer vision. Model selection criteria have been used in the vision literature and many more have been proposed in statistics, but the relative strengths of these criteria have not been analyzed in vision. More importantly, suitable extensions to these criteria must be made to solve the problems unique to computer vision. Using the problem of surface reconstruction as our context, we analyze existing criteria using simulations and sensor data, introduce new criteria from statistics, develop novel criteria capable of handling unknown error distributions and outliers, and extend model selection criteria to apply to the surface merging problem. The new and existing model selection criteria and merging rules are tested (over a wide range of experimental conditions using both synthetic and sensor data. The new surface merging rules improve upon previous results and work well, even at small step heights (h=2σ) and at crease discontinuities. Our results show that a Bayesian criterion and its bootstrapped variant perform the best, although for time-sensitive applications, a variant of the Akaike criterion may be a better choice. Unfortunately, none of the criteria work reliably for small region sizes, implying that model selection and surface merging should be avoided unless the region size is sufficiently large.

An iterative approach to multisensor sea ice classification

Characterizing the variability in sea ice in the polar regions is fundamental to an understanding of global climate and the geophysical processes governing climate changes. Sea ice can be grouped into a number of general classes with different characteristics. Multisensor data from NSCAT, ERS-2, and SSM/I are reconstructed into enhanced resolution imagery for use in ice-type classification. The resulting twelve-dimensional data set is linearly transformed through principal component analysis to reduce data dimensionality and noise levels. An iterative statistical data segmentation algorithm is developed using maximum likelihood (ML) and maximum a posteriori (MAP) techniques. For a given ice type, the conditional probability distributions of observed vectors are assumed to be Gaussian. The cluster centroids, covariance matrices, and a priori distributions are estimated from the classification of a previous temporal image set. An initial classification is produced using centroid training data and a weighted nearest-neighbor classifier. Though validation is limited, the algorithm results in an ice classification that is judged to be superior to a conventional k-means approach.