Smoothing

Receiving of remote sensed data's signals in urban space information reception centers is usually difficult, because of complex electromagnetic situation in cities and insufficient EMC. Traditional methods for digital reconstruction of images use smoothing and autoregressive forecasting. In this case anomalous spikes on the image are lost. Alternative method based on Kolmogorov-Wiener's filters and fractal properties of satellite images is

In this paper, we combine the well-established technique of Wiener filtering with an efficient method for robust smoothing: channel smoothing. The main parameters to choose in channel smoothing are the number of channels and the averaging filter. Whereas the number of channels has a natural lower bound given by the noise level and should for the sake of speed be as small as possible, the averaging filter is a less obvious choice. Based on the linear behavior of channel smoothing for inlier noise, we derive a Wiener filter applicable for averaging the channels of an image. We show in some experiments that our method compares favorable with established methods.

The Regional Ocean Modeling System (ROMS) is used to systematically investigate equilibrium conditions and seasonal variations of the Benguela system at a resolution of 9 km, including both the large-scale offshore flow regime and the economically and ecologically important coastal upwelling regime. A shelf-edge poleward flow exists in the northern Benguela region (i.e., north of ∼28°S) and is driven primarily by the wind stress curl via the Sverdrup relation. As such, it is strongly seasonal and is most intense during spring and summer, when the wind stress curl is most negative. The poleward flow deepens as it moves southward; between ∼25° and 27°S, much of it veers offshore because of the nature of the wind stress curl and its interaction with the northwestward path of the Benguela Current, which is influenced by alongshore topographical variations. The Benguela Current is driven by nonlinear interactions of passing Agulhas rings and eddies and does not have a striking seasonal s...

In order to measure the D structure of a number of objects a comparably new technique in computer vision exists, namely time of flight (TOF) cameras. The overall principle is rather easy and has been applied using sound or light for a long time in all kind of sonar and lidar systems. However in this approach one uses modulated light waves and receives the signals by a parallel pixel array structure. Out of the travelling time at each pixel one can estimate the depth structure of a distant object. The technique requires measuring the intensity differences and ratios of several pictures with extremely high accuracy; therefore one faces in practice rather high noise levels. Object features as reflectance and roughness influence the measurement results. This leads to partly high noise levels with variances dependent on the illumination and material parameters. It can be shown that a reciprocal relation between the variance of the phase and the squared amplitude of the signals exists. On...

The problem of predicting a future value of a time series is considered in this paper. If the series follows a stationary Markov process, this can be done by nonparametric estimation of the autoregression function. Two forecasting algorithms are introduced. They only differ in the nonparametric kernel-type estimator used: the Nadaraya-Watson estimator and the local linear estimator. There are three major issues in the implementation of these algorithms: selection of the autoregressor variables; smoothing parameter selection and computing prediction intervals. These have been tackled using recent techniques borrowed from the nonparametric regression estimation literature under dependence. The performance of these nonparametric algorithms has been studied by applying them to a collection of 43 well-known time series. Their results have been compared to those obtained using classical Box-Jenkins methods. Finally, the practical behaviour of the methods is also illustrated by a detailed analysis of two data sets.

University of California, Davis This paper provides a data analysis and some methodological ad-vances which contribute to an ongoing scientific debate about the patterns of aging. One of the problems we address is how to estimate a hazard function when only aggregated ...

The present article discusses various preprocessing techniques suitable for dealing with time series data for environmental science-related studies. The errors or noises due to electronic sensor fault, fault in the communication channel, etc., are considered here. Such errors or glitches that occur during the data acquisition or transmission phases need to be eliminated before it fed to the forecasting or classification systems. Computationally simple and efficient techniques are discussed here so that they can even be adopted for a hard real-time system environment. While adopting these techniques, we may also end up with some of the real genuine values, which may consider as an outlier. A special indicator function, the moving Inter Quartile Range (MIQR) algorithm, is proposed to overcome such special cases.

Conflict cannot be avoided since it is an inevitable aspect of work teams. Conflict may be defined as a struggle or contest between people with opposing needs, ideas, beliefs, values, or goals. Conflict on teams is inevitable; however, the results of conflict are not predetermined. Conflict might escalate and lead to nonproductive results, or conflict can be beneficially resolved and lead to quality final products. Therefore, learning to manage conflict is integral to a high-performance team. Although very few people go looking for conflict, more often than not. Conflict management involves acquiring skills related to conflict resolution, selfawareness about conflict modes, conflict communication skills, and establishing a structure for management of conflict in organizational environment. This paper presents types of conflict describe the benefits and detriments of conflict and present the causes of conflict. Strategies are also presented to prevent and to effectively manage conflict.

Statistical analysis of relationships between time series of data exhibiting seasonal variation is often of great interest in environmental monitoring and assessment. The present study focused on regression models with timevarying intercept and slope parameters. In particular, we derived and tested semiparametric models in which rapid interannual and interseasonal variation in the intercept were penalized in the search for a model that combined a good ®t to data with smoothly varying parameters. Furthermore, we developed a software package for ef®cient estimation of the parameters of such models. Test runs on time series of runoff data and riverine loads of nutrients and chloride in the Rhine River showed that the proposed smoothing methods were particularly useful for analysis of time-varying linear relationships between time series of data with both seasonal variation and temporal trends. The predictivity of the semiparametric models was superior to that of conventional parametric models. In addition, normalization of observed annual loads to mean or minimum runoff produced smooth curves that provided convincing evidence of human impact on water quality.

—We present a continuous time state estimation framework that unifies traditionally individual tasks of smoothing , tracking, and forecasting (STF), for a class of targets subject to smooth motion processes, e.g., the target moves with nearly constant acceleration or affected by insignificant noises. Fundamentally different from the conventional Markov transition formulation, the state process is modeled by a continuous trajec-tory function of time (FoT) and the STF problem is formulated as an online data fitting problem with the goal of finding the trajectory FoT that best fits the observations in a sliding time-window. Then, the state of the target, whether the past (namely, smoothing), the current (filtering) or the near-future (forecasting), can be inferred from the FoT. Our framework releases stringent statistical modeling of the target motion in real time, and is applicable to a broad range of real world targets of significance such as passenger aircraft and ships which move on scheduled, (segmented) smooth paths but little statistical knowledge is given about their real time movement and even about the sensors. In addition, the proposed STF framework inherits the advantages of data fitting for accommodating arbitrary sensor revisit time, target maneuvering and missed detection. The proposed method is compared with state of the art estimators in scenarios of either maneuvering or non-maneuvering target.

The Canny edge detector is a very popular and effective edge feature detector that is used as a pre-processing step in many computer vision algorithms. It is a multi-step detector which performs smoothing and filtering, non-maxima suppression, followed by a connected-component analysis stage to detect "true" edges, while suppressing "false" non edge filter responses. While there have been previous (partial) implementations of the Canny and other edge detectors on GPUs, they have been focussed on the old style GPGPU computing with programming using graphical application layers. Using the more programmer friendly CUDA framework, we are able to implement the entire Canny algorithm. Details are presented along with a comparison with CPU implementations. We also integrate our detector in to MAT-LAB, a popular interactive simulation package often used by researchers. The source code will be made available as open source.

A fingerprint classification procedure using a computer is described. It classifies the prints into one of ten defined types. The procedure is implemented using PICAP (picture array processor). The picture processing system includes a TV camera input and a special picture processor. The first part of the procedure is a transformation of the original print to a sampling matrix, where the dominant direction of the ridges for each subpicture is indicated. After smoothing, the lines in this pattern are traced out and converted to strings of symbols. Finally, a syntactic approach is adopted to make the type classification based on this string of symbols.

A novel color image histogram equalization approach is proposed that exploits the correlation between color components and it is enhanced by a multi-level smoothing technique borrowed from statistical language engineering. Multi-level smoothing aims at dealing efficiently with the problem of unseen color values, either considered independently or in combination with others. It is applied here to the HSI color space for the probability of intensity and the probability of saturation given the intensity, while the hue is left unchanged. Moreover, the proposed approach is extended by an empirical technique, which is based on a hue preserving non-linear transformation, in order to eliminate the gamut problem. This is the second method proposed in the paper. The equalized images by the two methods are compared to those produced by other well-known methods. The better quality of the images equalized by the proposed methods is judged in terms of their visual appeal and objective figures of merit, such as the entropy and the Kullback–Leibler divergence estimates between the resulting color histogram and the multivariate uniform probability density function.

This study describes a methodology of recovery of the Earth's gravity field from CHAMP and GRACE satellites data in Pakistan using least squares collocation (LSC) based downward continuation technique. The CHAMP height anomalies and GRACE gravity disturbances derived from the observed satellite data have been used in combination solution using LSC with observed gravity values at the Earth surface. The combined covariance functions of height anomalies and/or gravity disturbances at satellite altitudes and observed gravity anomalies at Earth surface have been used as the basis for combination and downward continuation solution. The variance of predicted gravity anomalies from GRACE gravity disturbances is relatively lower than the corresponding results of gravity anomalies from CHAMP height anomalies. This fact may be attributed partly to the amplification of noise and partly to the unstable inverse transformation process of height anomalies to gravity anomalies. The impact of data error variance has been studied in the context of smoothing and noise reduction in the final solution of downward continuation using least squares collocation. The raising of data error suppresses the noise and as a result a smooth final solution is obtained. The prediction results appear to be dependent on the quality of data and goodness of combined covariance function, which are fairly comparable for the CHAMP and GRACE data. The recovered gravity field from satellite data appears to contribute mainly to medium and long wavelength parts of total gravity field spectrum. Due to flexibility of data handling in least squares collocation, this procedure is applicable to any observable of gravity field being at different altitudes and with different data spacing.

Smoothing algorithms for maneuvering target tracking with nonlinear target dynamic and measurement equations are described and investigated. Target motion is represented using a multiple model approach. Techniques based on the interacting multiple model filter (IMMF), hypothesis pruning and maximum a posteriori (MAP) estimation of the maneuvering mode are described. All three techniques are based on the use of the unscented transformation with an augmented state model. A procedure for selecting the sigma points which exploits the partial lineairty of the augmented state model is used. The performances of the algorithms are analysed using a scenario involving a target which undergoes coordinated turn maneuvers. In this scenario, for a sufficiently large number of smoothing lags, the MAP approach and the pruning algorithm have almost equal performance and significanty superior performance to the augmented state IMMF. The MAP approach has the benefit of a reduced computational expense.

Overcoming the resolution-LER-sensitivity trade-off is a key challenge for the development of novel resists and processes that are able to achieve the ITRS targets for future lithography nodes. Here, we describe a process that treats lithographic patterns with aqueous solutions of block copolymers to facilitate a reduction in LER. A detailed understanding of parameters affecting adhesion and smoothing is gained by first investigating the behavior of the polymers on planar smooth and rough surfaces. Once healing was established in these model systems the methodology is tested on lithographically printed features where significant healing is observed, making this a promising technology for LER remediation.

In spite of extensive research on fitting parametric surfaces, the published 'standard' solutions often fail, when data points are irregularly distributed over topologically irregular domains, high accuracy is required and the free quantities of least squares fitting-such as the number and placement of knots, the weights of the smoothing functionals and the best parametrisation of the data points-must be set without user assistance. Further difficulties arise when the fitted surface needs to be extended in a natural way and hole loops without underlying point data need to be covered smoothly. This paper attempts to analyse the above difficulties and provide practical solutions to overcome these. Main results include algorithms to compute a good initial parametrisation, a fitting strategy to maintain tight tolerances and smoothness simultaneously, to handle weakly defined control points and a shape dependent knot refinement procedure. A few examples and suggestions for future work conclude the paper.

We propose a new sketch parsing and beautification method that converts digitally created design sketches into beautified line drawings. Our system uses a trainable, sequential bottom-up and top-down stroke clustering method that learns how to parse input pen strokes into groups of strokes each representing a single curve, followed by point-cloud ordering that facilitates curve fitting and smoothing. This approach enables greater conceptual freedom during visual ideation activities by allowing designers to develop their sketches using multiple, casually drawn strokes without requiring them to indicate the separation between different stroke groups. With the proposed method, raw sketches are seamlessly converted into vectorized geometric models, thus facilitating downstream assessment and editing activities.

The frequency of a sinusoidal signal is a well defined quantity. However, often in practice, signals are not truly sinusoidal, or even aggregates of sinusoidal components. Nonstationary signals in particular do not lend themselves well to decomposition into sinusoidal components. For such signals, the notion of frequency loses its effectiveness, and one needs to use a parameter which accounts for the time-varying nature of the process. This need has given rise to the idea of instantaneous frequency.

We are concerned with the initial-boundary problem associated to the Korteweg de Vries Kawahara perturbed by a dispersive term which appears in several fluids dynamics problems. We obtain local smoothing effects that are uniform with respect to the size of the interval. We also propose a simple finite different scheme for the problem and prove its unconditional stability. Finally we give some numerical examples.

In this paper we investigate the commonly used autoregressive filter method of adjusting appraisal-based real estate returns to correct for the perceived biases induced in the appraisal process. Since the early work by Geltner (1989), many papers have been written on this topic but remarkably few have considered the relationship between smoothing at the individual property level and the amount of persistence in the aggregate appraised-based index.

Income smoothing has become a phenomenon. It when companies report large profits, people become asked whether this is really real profit or profit that is intentionally made for a particular purpose. Departing from this, we made a study of income smoothing in the mining sector. Mining sector is one sector that is classified as profitable for people; this sector can be called an opportunist and opportunist sector often associated with earnings management and income smoothing. Our research is quantitative research. We use secondary data, financial statements of mining companies for the past five years. We use path analysis for the analysis tools in this study. We use three moderator variables, namely: institutional ownership, managerial ownership and audit committee. We examine the three moderator variables whether they can moderate profitability and leverage on income smoothing. The results of our study state that profitability influences income smoothing. In addition managerial ownership is able to moderate profitability and leverage, while the audit committee is only able to moderate profitability on income smoothing.

This paper promotes a novel numerical approach to static, free vibration and buckling analyses of laminated composite plates by an edge-based smoothed finite method (ES-FEM). In the present ES-FEM formulation, the system stiffness matrix is established by using the strain smoothing technique over the smoothing domains associated with the edges of the triangular elements. A discrete shear gap (DSG3) technique without shear locking is combined into the ES-FEM to give a so-called edge-based smoothed discrete shear gap method (ES-DSG3) for analysis of laminated composite plates. The present method uses only linear interpolations and its implementation into finite element programs is quite simple. Numerical results for analysis of laminated composite plates show that the ES-DSG3 performs quite well compared to several other published approaches in the literature.

The PROMETHEUS model is a spatially explicit, deterministic fire growth model, praised for being beneficial in various aspects of fire management. Our goal is to build on this success, applying statistical smoothing to alleviate some computational difficulties and to increase accuracy; a pleasant by-product is the opportunity to introduce stochasticity to the model using a residual-based block bootstrap. Copyright © 2008 John Wiley & Sons, Ltd.

This paper presents analyses of different methods of postprocessing lines that have resulted from the raster-to-vector conversion of black and white line drawing. Special attention was paid to the borders of connected components of maps. These methods are implemented with compression and smoothing algorithms. Smoothing algorithms can enhance accuracy, so using both smoothing and compression algorithms in succession gives a more accurate result than using only a compression algorithm. The paper also shows that a map in vector format may require more memory than a map in raster format. The Appendix contains a detailed description of the new smoothing method (continuous local weighted averaging) suggested by the authors.

The problem of evaluating an averaged functional magnetic resonance imaging (fMRI) response for repeated block design experiments was considered within a semiparametric regression model with autocorrelated residuals. We applied functional data analysis (FDA) techniques that use a least-squares fitting of B-spline expansions with Tikhonov regularization. To deal with the noise autocorrelation, we proposed a regularization parameter selection method based on the idea of combining temporal smoothing with residual whitening. A criterion based on a generalized 2 -test of the residuals for white noise was compared with a generalized cross-validation scheme. We evaluated and compared the performance of the two criteria, based on their effect on the quality of the fMRI response. We found that the regularization parameter can be tuned to improve the noise autocorrelation structure, but the whitening criterion provides too much smoothing when compared with the cross-validation criterion. The ultimate goal of the proposed smoothing techniques is to facilitate the extraction of temporal features in the hemodynamic response for further analysis. In particular, these FDA methods allow us to compute derivatives and integrals of the fMRI signal so that fMRI data may be correlated with behavioral and physiological models. For example, positive and negative hemodynamic responses may be easily and robustly identified on the basis of the first derivative at an early time point in the response. Ultimately, these methods allow us to verify previously reported correlations between the hemodynamic response and the behavioral measures of accuracy and reaction time, showing the potential to recover new information from fMRI data.

The Canny edge detector is a very popular and effective edge feature detector that is used as a pre-processing step in many computer vision algorithms. It is a multi-step detector which performs smoothing and filtering, non-maxima suppression, followed by a connected-component analysis stage to detect "true" edges, while suppressing "false" non edge filter responses. While there have been previous (partial) implementations of the Canny and other edge detectors on GPUs, they have been focussed on the old style GPGPU computing with programming using graphical application layers. Using the more programmer friendly CUDA framework, we are able to implement the entire Canny algorithm. Details are presented along with a comparison with CPU implementations. We also integrate our detector in to MAT-LAB, a popular interactive simulation package often used by researchers. The source code will be made available as open source.

We study energy minimizing properties of the function u=limλj→1+uλju=limλj→1+uλj, where uλjuλj is the solution to the pλj(⋅)pλj(⋅)-Laplacian Dirichlet problem with prescribed boundary values. Here p:Ω→[1,∞) is a variable exponent and pλj(x)=max{p(x),λj}pλj(x)=max{p(x),λj} for λj>1λj>1. This problem leads in a natural way to a mixture of Sobolev and total variation norms. The main results are obtained under the assumption that p is strongly log-Hölder continuous and bounded. To motivate our approach we also consider the one-dimensional case and give examples which justify our assumptions. The results can be applied in the analysis of a model for image restoration combining total variation and isotropic smoothing.

Abstraet--'Endpoint error' describes the erratic behavior at the beginning and end of the computed acceleration data which is commonly observed after smoothing and differentiating raw displacement data. To evaluate endpoint error produced by four popular smoothing and differentiating techniques, Lanshammar's (1982, J. Biomechanics 15, 99-105) modification of the Pezzack et al. (1977, J. Biomechanics, 10, 377-382) raw angular displacement data set was truncated at three different locations corresponding to the major peaks in the criterion acceleration curve. Also, for each data subset, three padding conditions were applied. Each data subset was smoothed and differentiated using the Butterworth digital filter, cubic spline, quintic spline, and Fourier series to obtain acceleration values. RMS residual errors were calculated between the computed and criterion accelerations in the endpoint regions. Although no method completely eliminated endpoint error, the results demonstrated clear superiority of the quintic spline over the other three methods in producing accurate acceleration values close to the endpoints of the modified Pezzack et al. (1977) data set. In fact, the quintic spline performed best with non-padded data (cumulative error = 48.0 rad s-2). Conversely, when applied to non-padded data, the Butterworth digital filter produced wildly deviating values beginning more than the 10 points from the terminal data point (cumulative error = 226.6 rad s-2). Each of the four methods performed better when applied to data subsets padded by linear extrapolation (average cumulative error = 68.8 fads -2) than when applied to analogous subsets padded by reflection (average cumulative error = 86.1 rads-2).

Minerals have unique spectral signatures that can be used for their identification similar to a fingerprint. Although some minerals have extremely similar compositions thus comparable signatures, they can be differentiated through remote sensing. Therefore, a derivative spectrum was used in this study, which enhanced the subtle spectral discrepancies to help determine whether a special order of a derivative spectrum is applicable in discrimination of these mineral targets. Second, we investigated whether derivative spectra in higher orders can be applied to discriminate between mineral targets using those in five orders as an input for a similarity measure (Jeffries-Matusita distance). Results of this study have shown that the best derivative order selection for each target is a target-specific problem. The first and fourth derivative orders were the bests for alunite and quartz minerals, respectively. As spectral smoothing is a preliminary process of derivative analysis, its bandwidth influence on derivative spectra was then investigated, and a smoothing window size of five sampling points was considered. Based on the results of this study, we recommend the introduction of high-order derivative spectra as the input for many detectors or classifiers in remote sensing especially for differentiation of minerals such as phengite, muscovite, and sericite.

The use of principal component methods to analyze functional data is appropriate in a wide range of different settings. In studies of "functional data analysis," it has often been assumed that a sample of random functions is observed precisely, in the continuum and without noise. While this has been the traditional setting for functional data analysis, in the context of longitudinal data analysis a random function typically represents a patient, or subject, who is observed at only a small number of randomly distributed points, with nonnegligible measurement error. Nevertheless, essentially the same methods can be used in both these cases, as well as in the vast number of settings that lie between them. How is performance affected by the sampling plan? In this paper we answer that question. We show that if there is a sample of n functions, or subjects, then estimation of eigenvalues is a semiparametric problem, with root-n consistent estimators, even if only a few observations are made of each function, and if each observation is encumbered by noise. However, estimation of eigenfunctions becomes a nonparametric problem when observations are sparse. The optimal convergence rates in this case are those which pertain to more familiar function-estimation settings. We also describe the effects of sampling at regularly spaced points, as opposed to random points. In particular, it is shown that there are often advantages in sampling randomly. However, even in the case of noisy data there is a threshold sampling rate (depending on the number of functions treated) above which the rate of sampling (either randomly or regularly) has negligible impact on estimator performance, no matter whether eigenfunctions or eigenvectors are being estimated. 1.1. Connections between FDA and LDA. Advances in modern technology, including computing environments, have facilitated the collection and analysis of

Kernel density estimation for multivariate, circular data has been formulated only when the sample space is the sphere, but theory for the torus would also be useful. For data lying on a d-dimensional torus (d ≥ 1), we discuss kernel estimation of a density, its mixed partial derivatives, and their squared functionals. We introduce a specific class of product kernels whose order is suitably defined in such a way to obtain L2-risk formulas whose structure can be compared to their euclidean counterparts. Our kernels are based on circular densities, however we also discuss smaller bias estimation involving negative kernels which are functions of circular densities. Practical rules for selecting the smoothing degree, based on cross-validation, bootstrap and plug-in ideas are derived. Moreover, we provide specific results on the use of kernels based on the von Mises density. Finally, real-data examples and simulation studies illustrate the findings.

A very important aspect of virtually any kind of systematic investigation is to be able to identify whether two entities are different, and, almost equivalently, whether they are the same. We need to be sure that measurements made at different time in different places by different experimenters are equivalent. To do this in the social sciences, the procedure of equating is necessary to be able to compare measurements made using different instruments. Small sample sizes can lead to apparent jaggedness in the formulae for equating two quantities, and some kind of smoothing procedure is frequently necessary when dealing with relatively small samples. A large-sample formula is developed for the standard error of moving average smoothed equipercentile equating on a single sample. An example is given of the application in equating two versions of a reading test, and the results are verified using a bootstrap procedure. The large sample formula gives a result that is close to the bootstrap procedure, except at very sparse frequencies.

There is a pressing need to develop effective techniques for structural health monitoring, so that the safety and integrity of the composite structures can be improved. The main objective of this study is to evaluate dynamics-based damage detection techniques for composite laminated plates using smart piezoelectric materials and modern instrumentation like scanning laser vibrometer (SLV). The study comprises of testing an E-glass/epoxy composite plate with an embedded delamination using two different actuator–sensor systems: (1) SLV with PZT (lead–zirconate–titanate) actuators (PZT-SLV), and (2) polyvinylidenefluoride (PVDF) sensors with PZT actuators (PZT-PVDF). The numerical finite element (FE) analysis is also performed to complement the damage detection. The experimental and numerical curvature mode shapes are primarily used to detect the presence, location, and size of the delamination. Three relatively new damage detection algorithms (i.e., simplified gapped smoothing method (GSM), generalized fractal dimension (GFD), and strain energy method (SEM)) are employed to analyze the experimental and numerical curvature mode shape data and uniform load surface (ULS) curvatures. From the damage detection outcomes, it is observed that the PZT-SLV system proves to be more convenient and effective, and it is capable of scanning a large number of points over the entire plate specimens; while the PZT-PVDF system, in which the curvature mode shapes are directly acquired, exhibits good sensitivity to damage. The damage detection algorithms like GSM, GFD and SEM based on the utilization of three consecutive mode curvatures (modes 3–5) and resulting ULS curvature successfully identify the presence, location, and relative size of delamination in the composite plate.

The Cox proportional hazards (PH) model usually assumes linearity of the covariates on the log hazard function, which may be violated because linearity cannot always be guaranteed. We propose a partially linear single-index proportional hazards regression model, which can model both linear and nonlinear covariate effects on the log hazard in the proportional hazards model. We adopt a polynomial spline smoothing technique to model the structured nonparametric single-index component for the nonlinear covariate effects. This method can reduce the dimensionality of the covariates being modeled, while, at the same time, can provide efficient estimates of the covariate effects. A two-step iterative algorithm to estimate the nonparametric component and the covariate effects is used for facilitating implementation. Asymptotic properties of the estimators are derived. Monte Carlo simulation studies are presented to compare the new method with the standard Cox linear PH model and some other comparable models. A case study with clinical trial data is presented for illustration.

This paper examines the use of two kinds of context to improve the results of content-based music taggers: the relationships between tags and between the clips of songs that are tagged. We show that users agree more on tags applied to clips temporally "closer" to one another; that conditional restricted Boltzmann machine models of tags can more accurately predict related tags when they take context into account; and that when training data is "smoothed" using context, support vector machines can better rank these clips according to the original, unsmoothed tags and do this more accurately than three standard multi-label classifiers.

We present a new class of methods for high-dimensional nonparametric regression and classification called sparse additive models (SpAM). Our methods combine ideas from sparse linear modeling and additive nonparametric regression. We derive an algorithm for fitting the models that is practical and effective even when the number of covariates is larger than the sample size. SpAM is essentially a functional version of the grouped lasso of Yuan and Lin . SpAM is also closely related to the COSSO model of , but decouples smoothing and sparsity, enabling the use of arbitrary nonparametric smoothers. We give an analysis of the theoretical properties of sparse additive models, and present empirical results on synthetic and real data, showing that SpAM can be effective in fitting sparse nonparametric models in high dimensional data.