Search

Modeling global C cycles requires in-depth 'knowledge about small-scale C stocks and turnover processes, yet different soil organic C (SOC) pools reveal considerable spatiotemporal heterogeneity, at the field scale, which is scarcely 'known due to the considerable workload associated with traditional fractionation procedures. We investigated the potential of mid-infrared spectroscopy combined with partial least squares regression (MIRS-PLSR) for rapid assessment of different particulate organic matter (POM) pools and their spatial heterogeneity at the field scale. Locally calibrated prediction models estimated the contents of SOC, POM of three size classes (POMI: 2000-250 [micro]m; POM2: 250-53 [micro]m; and POM3:53-20 [micro]m), and lignin contents for 129 locations in a 1.3-ha test field. Relations between the parameters were described using correlation analysis and fuzzy- [kappa] statistics. All parameters were predicted successfully by applying local calibrations for MIRS-PLSR ([R.sup.2] = 0.77-0.96). The prediction model for POM1 chiefly relied on specific signals of lignin and cellulose; contents of POM2 were estimated by spectral bands assigned to degradation products as aliphatic C-H groups and aromatic moieties; carboxylic groups essentially contributed to the prediction of POM3. There was a close spatial relation between the coarse POM1 and POM2 fractions and lignin ([kappa] = 0.77), which largely also explained variations in bulk SOC. In contrast, POM3 exhibited a less deterministic pattern in the field, thus contributing little to the spatial variation in SOC content. doi: 10.2136/sssaj2009.0195

State covariances of linear systems satisfy certain constraints imposed by the underlying dynamics. These constraints dictate a particular structure of state covariances. However, sample covariances almost always fail to have the required structure. The renewed interest in using state covariances for estimating the power spectra of inputs gives rise to the approximation problem. In this note, the structured covariance least-squares problem is formulated and the Lyapunov-type matricial linear constraint is converted into an equivalent set of trace constraints. Efficient unconstrained maximization methods capable of solving the corresponding dual problem are developed. Index Terms--Convex optimization, least-squares approximation, structured covariances.

Multiple-input-multiple-output (MIMO) receivers with direct-conversion radio-frequency (RF) architecture are investigated in this paper. Direct conversion is a low-cost RF design that requires fewer external components in chip implementation. Nevertheless, it introduces extra RF impairments such as I-Q imbalance and dc offset in addition to frequency offset that is commonly encountered in all RF architectures. This paper proposes to do the joint least squares (LS) estimation of frequency, dc offset, I-Q imbalance, and a channel in MIMO receivers to improve performance; frequency-dependent and frequency-independent I-Q imbalances are included. Previously, RF impairments were separately estimated in MIMO receivers, which leads to inferior performance. In particular, a receiver architecture that facilitates the joint estimation of the frequency, the dc offset, the I-Q imbalance, and the channel is proposed. The LS criterion is then applied to obtain the joint estimators, with a special training-sequence design to reduce complexity. Simplified estimators on the frequency and dc offset are also proposed with almost no loss in performance. Finally, the estimators are shown through analysis to be unbiased and approach the Cramer-Rao lower bound (CRLB) for signal-to-noise ratios (SNRs) of interest. The analysis is verified by computer simulations. Index Terms--Direct-conversion RF architecture, joint least squares (LS) estimations, multiple-input-multiple-output (MIMO) receiver.

This brief addresses the design of the compensation filter of a generalized comb filter (GCF). The proposed method is general and can be applied to different design constraints, i.e., maximally flat, least square, and minimax. The coefficients of the proposed filter for all three cases can be obtained by solving two simple linear equations. The filter operates at a low rate and considerably reduces the passband droop of the GCF. Index Terms--Finite-impulse-response (FIR) filters, generalized comb filters (GCFs), least square, maximally flat, minimax.

A method to assign weights to the measurements obtained through phasor measurement units (PMUs) in a weighted least squares (WLS) state estimation is presented in this paper. The uncertainties for direct measurements are obtained from the manufacturer's specifications. For pseudo-measurements, the uncertainties are evaluated by using the classical uncertainty propagation theory. The propagation of measurement uncertainty as a function of line length and conductor type is also investigated. The lower and upper bounds of the estimated states considering the measurement uncertainties are found by using linear programming. The proposed method is applied on the IEEE 14-, 30-, 57-, and 118-bus test systems, and the state estimation results including the lower and upper bounds of the estimated states are presented. Index Terms--Measurement uncertainty, phasor measurement units, state estimation, total vector error.

This paper deals with the 3-D reconstruction of the coronary tree from a rotational X-ray projection sequence. It describes the following three stages: the reconstruction of the 3-D coronary tree at different phases of the cardiac cycle, the motion estimation, and the motion-compensated tomographic reconstruction of the 3-D coronary tree at one given phase using all the available projections. Our method is tested on a series of simulated images computed from the projection of a segmented dynamic volume sequence acquired in multislice computed tomography imaging. Performances are comparable to those obtained by reconstruction of a statical coronary tree using an algebraic reconstruction technique algorithm. Index Terms--Angiography, B-spline interpolation, deformable model, inverse problem, penalized least squares, rotational X-ray.

The generalized linear least square (GLLS) method can successfully construct unbiased parametric images from dynamic positron emission tomography data. Quantitative dynamic single photon emission computed tomography (SPECT) also has the potential to generate physiological parametric images. However, the high level of noise, intrinsic in SPECT, can give rise to unsuccessful voxelwise fitting using GLLS, resulting in physiologically meaningless estimates. In this paper, we systematically investigated the applicability of our recently proposed approaches to improve the reliability of GLLS to parametric image generation from noisy dynamic SPECT data. The proposed approaches include use of a prior estimate of distribution volume ([V.sub.d]), a bootstrap Monte Carlo (BMC) resampling technique, as well as a combination of both techniques. Full Monte Carlo simulations were performed to generate dynamic projection data, which were then reconstructed with and without resolution recovery, before generating parametric images with the proposed methods. Four experimental clinical datasets were also included in the analysis. The GLLS methods incorporating BMC resampling could successfully and reliably generate parametric images. For high signal-to-noise ratio (SNR) imaging data, the BMC-aided GLLS provided the best estimates of [K.sub.1], while the BMC-[V.sub.d]-aided GLLS proved superior for estimating [V.sub.d]. The improvement in reliability gained with BMC-aided GLLS in low SNR image data came at the expense of some overestimation of Va and increased computation time. Index Terms--Least square methods, parameter estimation, simulation, single photon emission computed tomography (SPECT).

Cardiopulmonary resuscitation (CPR) artifacts caused by chest compressions and ventilations interfere with the rhythm diagnosis of automated external defibrillators (AED). CPR must be interrupted for a reliable diagnosis. However, pauses in chest compressions compromise the defibrillation success rate and reduce perfusion of vital organs. The removal of the CPR artifacts would enable compressions to continue during AED rhythm analysis, thereby increasing the likelihood of resuscitation success. We have estimated the CPR artifact using only the frequency of the compressions as additional information to model it. Our model of the artifact is adaptively estimated using a least mean-square (LMS) filter. It was tested on 89 shockable and 292 nonshockable ECG samples from real out-of-hospital sudden cardiac arrest episodes. We evaluated the results using the shock advice algorithm of a commercial AED. The sensitivity and specificity were above 95% and 85%, respectively, for a wide range of working conditions of the LMS filter. Our results show that the CPR artifact can be accurately modeled using only the frequency of the compressions. These can be easily registered after small changes in the hardware of the CPR compression pads. Index Terms--Automated external defibrillator (AED), cardiopulmonary resuscitation (CPR), least mean-square (LMS) algorithm, sudden cardiac arrest (SCA), ventricular fibrillation (VF).

This paper presents a weighted least squares (WLS) method for IIR digital filter design using a new stability constraint. Utilizing the reweighting technique, an iterative second-order cone programming (SOCP) method is employed to solve the design problem, such that either linear or second-order cone constraints can be further incorporated. In order to guarantee the stability of designed IIR digital filters, a new stability constraint with a prescribed pole radius is derived from the argument principle (AP) of complex analysis. As compared with other frequency-domain stability constraints, the AP-based stability constraint is both sufficient and necessary. Since the derived stability constraint cannot be directly incorporated in the iterative SOCP method, the similar reweighting technique is deployed to approximate the stability constraint in a quadratic form, which is then combined with the WLS iterative design process. Filter design examples are presented to demonstrate the effectiveness of the proposed iterative SOCP method. Index Terms--Argument principle (AP), infinite impulse response (IIR) digital filters, reweighting techniques, second-order cone programming (SOCP), weighted least squares (WLS) approximation.

In this paper, the technique of McClellan transformation is applied to design variable 2-D FIR digital filters. Compared with the conventional transformation, the 2-D transformation subfilter and the 1-D prototype filter are designed such that their frequency characteristics are adjustable. Moreover, they are tunable by the same variable parameter, so the variable characteristics of 1-D prototype filters are coincident with those of 2-D subfilters. Several examples, including variable fan filters, variable circularly symmetric filters, and variable elliptically symmetric filters with arbitrary orientation, are presented to demonstrate the effectiveness and the flexibility of the presented method. Index Terms--Circularly symmetric filter, elliptically symmetric filter, fan filter, least squares approach, McClellan transformation, two-dimensional (2-D) filter, variable digital filter.

The purpose of this research is to develop a classifier capable of state-of-the-art performance in both computational efficiency and generalization ability while allowing the algorithm designer to choose arbitrary loss functions as appropriate for a give problem domain. This is critical in applications involving heavily imbalanced, noisy, or non-Gaussian distributed data. To achieve this goal, a kernel-matching pursuit (KMP) framework is formulated where the objective is margin maximization rather than the standard error minimization. This approach enables excellent performance and computational savings in the presence of large, imbalanced training data sets and facilitates the development of two general algorithms. These algorithms support the use of arbitrary loss functions allowing the algorithm designer to control the degree to which outliers are penalized and the manner in which non-Gaussian distributed data is handled. Example loss functions are provided and algorithm performance is illustrated in two groups of experimental results. The first group demonstrates that the proposed algorithms perform equivalent to several state-of-the-art machine learning algorithms on well-published, balanced data. The second group of results illustrates superior performance by the proposed algorithms on imbalanced, non-Gaussian data achieved by employing loss functions appropriate for the data characteristics and problem domain. Index Terms--Boosting, imbalanced data, iteratively reweighted least squares, kernel machines, kernel-matching pursuits (KMPs), margin maximization, robust classification, robust statistics, unbalanced data.

Byline: Chia-Huei Wu (1), Lung Hung Chen (2), Ying-Mei Tsai (3) Keywords: Satisfaction; Weighting; Importance; Partial least squares Abstract: This study introduced a formative model to investigate the utility of importance weighting on satisfaction scores with partial least squares analysis. Based on the bottom-up theory of satisfaction evaluations, the measurement structure for weighted/unweighted domain satisfaction scores was modeled as a formative model, whereas the measurement structure for global satisfaction scores was modeled as a reflective model according to top-down theory. The purpose was to see if the predictive effect of importance-weighted domain satisfaction scores is stronger than unweighted domain satisfaction scores in predicting global satisfaction scores. Three datasets in life, self, and job satisfaction were analyzed. In the life satisfaction dataset, 237 undergraduates at Central Taiwan University of Science and Technology voluntarily provided their responses. The mean age of respondents was 20.80 years (SD = 1.05). In the self-satisfaction dataset, 269 undergraduates at National Taiwan University provided their responses. The mean age of respondents was 19.78 years (SD = 1.44). Finally, in the job satisfaction dataset, 557 staff members in seven Taiwan provincial hospitals provided their responses. The mean age of respondents was 35.87 years (range from 21 to 65, SD = 8.60). Three measures of domain satisfaction, domain importance, and global satisfaction were collected in each dataset. Partial least squares analysis was used in model estimation. All the results revealed that unweighted domain satisfaction scores have a stronger predictive effect for global satisfaction measures than importance-weighted domain satisfaction scores, indicating that importance weighting on satisfaction scores did not have an empirical benefit. Author Affiliation: (1) Institute of Business and Management, National Chiao Tung University, Hsinchu, Taiwan, ROC (2) Graduate Institute of Physical Education, National Taiwan Sport University, 250, Taoyuan County, Taiwan, ROC (3) Office of Physical Education, Central Taiwan University of Science and Technology, No. 11, Buzih Lane, Beitun District, Taichung City, 40601, Taiwan, ROC Article History: Registration Date: 19/05/2008 Received Date: 03/03/2008 Accepted Date: 15/05/2008 Online Date: 10/06/2008

This paper presents an efficient and robust algorithm for passivity enforcement of S-parameter-based macromodels. The method computes updated values of the model residues by least squares fitting of nonpassive residuals of the scattering matrix. Several examples show that the proposed method yields accurate passive macromodels at a limited computational cost. Index Terms--Least squares fitting, macromodeling, model perturbation, passivity enforcement, vector fitting.

The least squares solution for the entire small-signal equivalent circuit is itself a formidable task. In this paper, a systematic approach comprising the total and conventional least squares method in analytically obtaining the small-signal field-effect transistor (FET) parameters values is introduced. The proposed method eliminates the conventional 'cold FET' and 'hot FET' modeling constraints and allows an ease in inline process tracking. Index Terms--Field-effect transistor (FET), small-signal equivalent circuit.

Multispectral sensors using array of detectors are affected by striping, an artifact that appears as a series of horizontal bright or dark periodic lines in the remotely sensed images. Nonlinearities and memory effect of detectors are the main causes of the striping problem that is not effectively corrected in the onboard or postprocessing calibration phases. In order to clear striping from images, we consider a new procedure based on detector response equalization and apply it to Moderate Resolution Imaging Spectroradiometer data from Terra and Aqua satellites. After identification of the out-of-family detectors, a least squares equalization stage is considered for calibration by using the intrinsic data redundancy caused by the bow-tie effect, where multiple observations of the same field of view are available from different detectors. The main advantage of this method, with respect to others such as the histogram equalization, is due to the independence of the measurements on the scene statistics, which, otherwise, will cause an overestimation or underestimation of the detectors' responses. The new procedure performance is validated using data received at the Mediterranean Agency for Remote Sensing and Environmental Control ground station facility in Benevento--Italy and data downloaded from NASA LAADS Web site. The main results are presented, by showing the effectiveness of the method and the stability of the correction coefficients, at least on one-orbit periods. Index Terms--Calibration, equalization, least squares (LS), Moderate Resolution Imaging Spectroradiometer (MODIS), striping.

The MODerate resolution Imaging Spectrometer MODIS) aboard Terra and Aqua platforms is performing well overall, except for Aqua MODIS band 6. Fifteen of the 20 detectors in Aqua MODIS band 6 are nonfunctional or noisy. Without correction, it will cause problems in the higher MODIS products. This paper develops a restoration algorithm to restore the missing data of Aqua MODIS band 6 by combining a histogram-matching algorithm with local least squares fitting. Histogram matching corrects detector-to-detector striping of the functional detectors. Local least squares fitting restores the missing data of the non-functional detector based on a cubic polynomial derived from the relationship between Aqua MODIS bands 6 and 7. The Aqua MODIS image data used in this research are in digital number format and are not georectified. The proposed restoring algorithm can be used on both 1000- and 500-m pixel resolutions. The algorithm was tested on both Terra and Aqua MODIS images. For Terra MODIS images, results of restoring the synthetic nonfunctional detectors of band 6 demonstrate that local least squares fitting can fill in the missing data with little distortion. For Aqua MODIS images, the results of the restoring algorithm with and without applying histogram matching were compared to evaluate the capability in removing detector-to-detector stripe noise. To evaluate the performance of the proposed method, quantitative and qualitative analyses were carried out by visual inspection and quality index. For all the scenes used in this research, the correlation coefficients were near 0.99 and root mean square error between the original Terra band 6 and its simulated one was 2 x [10.sup.-5]. The proposed algorithm can thus be used satisfactorily for restoring Aqua MODIS band 6. Index Terms--Aqua, band 6, histogram matching, local least squares fitting, MODerate resolution Imaging Spectrometer (MODIS).

Multivariate calibration models based on synthetic single-beam near-infrared spectra are used to demonstrate the ability to maintain viable calibrations over extended time periods. Glucose is studied over the physiological concentration range of 1-30 mM in a buffered aqueous matrix containing varying levels of alanine, ascorbate, lactate, urea, and triacetin. By employing a set of 25 test samples measured 23 times over a period of 325 days, partial least-squares (PLS) calibrations based on synthetic spectra are observed to outperform conventional calibrations that use a set of 64 measured calibration samples. The key to the success of this approach is the use of a set of spectra of phosphate buffer collected on each prediction day to construct synthetic calibration spectra that are specific to that day. This allows the incorporation into the calibration model of nonanalyte spectral variance that is unique to a particular day. In this way, the adverse effects of instrumental drift or other sources of spectral variance on prediction performance can be minimized. Through the application of this methodology, values of the standard error of prediction (SEP) for glucose concentration are maintained to a range of 0.50-0.95 mM and an average of 0.68 mM over the 325 days of the experiment. These results are significantly better than those obtained with conventional models based on measured calibration samples. Over the same time period, a PLS model based on measured calibration spectra in absorbance units produced values of SEP that ranged from 0.41 to 2.02 mM and an average of 1.23 mM.

Helmert's variance component estimation method based on a least-squares adjustment of condition equations is presented, in which the registered area and the coordinates of a cadastral parcel are assumed to be different and independent types of observations with errors in the cadastral parcel area adjustment. The Helmert method is employed for the estimation of variance components of these two types of observations, thus providing a determination of accurate weights between them. At the same time, inconsistencies between the registered and digitized areas of the parcels are adjusted through a least-squares adjustment. The mathematical models for adjusting the boundaries of the parcel areas are derived, incorporating both the area conditions and geometric conditions. An empirical test is conducted and the results are compared to those obtained from the conventional method, assuming that the digitized coordinates are treated as observations while the registered parcel areas are not. The analysis of the results demonstrates that the least-squares adjustment, when based on Helmert's variance component estimates, refinds the weights of the observations more accurately, improves the accuracy of the adjusted coordinates in parcel digitization, and resolves the inconsistencies between the registered areas and digitized areas of the parcels more rigorously. DOI: 10.1061/(ASCE)0733-9453(2009)135:1(19) CE Database subject headings: Spatial data; Variance analysis; Estimation; Least square method; Surveys.

Near infrared spectroscopy (NIR) was developed primarily for applications such as the quantitative determination of nutrients in the agricultural and food industries. Examples include the determination of water, protein, and fat within complex samples such as grain and milk. Because of its useful properties, NIR analysis has spread to other areas such as chemistry and pharmaceutical production. NIR spectra consist of infrared overtones and combinations thereof, making interpretation of the results complicated. It can be very difficult to assign peaks to known constituents in the sample. Thus, multivariate analysis (MVA) has been crucial in translating spectral data into information, mainly for predictive purposes. Orthogonal partial least squares (OPLS), a new MVA method, has prediction and modeling properties similar to those of other MVA techniques, e.g., partial least squares (PLS), a method with a long history of use for the analysis of NIR data. OPLS provides an intrinsic algorithmic improvement for the interpretation of NIR data. In this report, four sets of NIR data were analyzed to demonstrate the improved interpretation provided by OPLS. The first two sets included simulated data to demonstrate the overall principles; the third set comprised a statistically replicated design of experiments (DoE), to demonstrate how instrumental difference could be accurately visualized and correctly attributed to Wood's anomaly phenomena; the fourth set was chosen to challenge the MVA by using data relating to powder mixing, a crucial step in the pharmaceutical industry prior to tabletting. Improved interpretation by OPLS was demonstrated for all four examples, as compared to alternative MVA approaches. It is expected that OPLS will be used mostly in applications where improved interpretation is crucial; one such area is process analytical technology (PAT). PAT involves fewer independent samples, i.e., batches, than would be associated with agricultural applications; in addition, the Food and Drug Adiministration (FDA) demands 'process understanding' in PAT. Both these issues make OPLS the ideal tool for a multitude of NIR calibrations. In conclusion, OPLS leads to better interpretation of spectrometry data (e.g., NIR) and improved understanding facilitates cross-scientific communication. Such improved knowledge will decrease risk, with respect to both accuracy and precision, when using NIR for PAT applications.

The present study addresses the problem of estimating time-varying time constants associated with thermocouple sensors by a set of basis functions. By expanding each time-varying time constant onto a finite set of basis sequences, the time-varying identification problem reduces to a parameter estimation problem of a time-invariant system. The proposed algorithm, to be called as orthogonal least-squares with basis function expansion algorithm, combines the orthogonal least-squares algorithm with an error reduction ratio test to include significant basis functions into the model which results in a parsimonious model structure. The performance of the method was compared with a linear Kalman filter Simulations on engine data have demonstrated that the proposed method performs satisfactorily and is better than the Kalman filter The new technique has been applied in a Stirling cycle compressor The sinusoidal variations in time constant are tracked properly using the new technique, but the linear Kalman filter fails to do so. Both model validation and thermodynamic laws confirm that the new technique gives unbiased estimates and that the assumed thermocouple model is adequate. [DOI: 10.1115/1.3023111]

Since variances in the input variables of the engineering system cause subsequent variances in the product output performance, reliability-based design optimization (RBDO) is getting much attention recently. However, RBDO requires expensive computational time. Therefore, the response surface method is often used for computational efficiency in solving RBDO problems. A method to estimate the effect of the response surface error on the RBDO result is developed in this paper The effect of the error is expressed in terms of the prediction interval, which is utilized as the error metric for the response surface used for RBDO. The prediction interval provides upper and lower bounds for the confidence level that the design engineer specified. Using the prediction interval of the response surface, the upper and lower limits of the reliability are computed. The lower limit of reliability is compared with the target reliability to obtain a conservative optimum design and thus safeguard against the inaccuracy of the response surface. On the other hand, in order to avoid obtaining a design that is too conservative, the developed method also constrains the upper limit of the reliability in the design optimization process. The proposed procedure is combined with an adaptive sampling strategy to refine the response surface. Numerical examples show the usefulness and the efficiency of the proposed method. [DOI: 10.1115/1.2988476] Keywords: reliability-based design optimization, response surface method, prediction interval, moving least squares method

Fourier transform near-infrared (FT-NIR) diffuse reflection spectroscopy was used in combination with principal component analysis and partial least-squares regression to simultaneously determine the physical and the chemical parameters of a porous poly(p-methylstyrene-co-1,2-bis(p-vinylphenyl)ethane) (MS/BVPE) monolithic polymer. Chemical variations during the synthesis of the polymer material can alter the pore volume and pore area distributions within the polymer scaffold. Furthermore, mid-infrared and near-infrared (NIR) spectroscopic chemical imaging was implemented as a tool to assess the uniformity of the samples. The presented study summarizes the comparative results derived from the spectral FT-NIR data combined with chemometric techniques. The relevance of the interrelation of physical and chemical parameters is highlighted whereas the amount of MS/ BVPE (%, v/v) and the quantity (%) of micropores (diameter, d < 6 nm), mesopores (6 nm < d < 50 nm), and macropores (50 nm < d < 200 nm) could be determined with one measurement. For comparison of the quantitative data, the standard error of prediction (SEP) was used. The SEP for determining the MS/BVPE amount in the samples showed 0.35%, for pore volume quantiles 1.42-8.44%, and for pore area quantiles 0.38-1.45%, respectively. The implication of these results is that FT-NIR spectroscopy is a suitable technique for the screening of samples with varying physicochemical properties and to quantitatively determine the parameters simultaneously within a few seconds.

A spreading code-allocation procedure using simple least squares (LS) channel estimation is presented to reduce multiple-access interference (MAI) in dowulink multicarrier code-division multiple-access (MC-CDMA) systems. The spreading codes chosen by the proposed method are in a consistent sequence. Index Terms--Code-selection method, consistent sequence, least squares (LS) channel estimation, multicarrier code-division multiple access (MC-CDMA), multiple-access interference (MAI), spreading codes, Walsh-Hadamard code.

A least-squares (LS) channel estimation (CE) technique for mobile orthogonal frequency-division multiplexing (OFDM) communications over a rapidly time-varying frequency-selective fading channel is investigated in this paper. The proposed technique keeping the comb-type pilot arrangement can achieve a low error probability by accurately estimating channel impulse response (CIR) and effectively tracking rapid CIR time variations. The LS CE technique proposed here is conducted in the time domain (TD). Meanwhile, a generic estimator is serially performed block by block without assistance from a priori channel information and without increasing computational complexity. By taking advantage of linearly frequency-modulated (LFM) or pseudorandom signals transceived for jointly sounding pilot subchannels, the proposed LS CE can inherently perform pseudonoise (PN) matched filtering (MF) to suppress multipath interference (MPI) caused by frequency-selective fading and intercarrier interference (ICI) resulting from data subchannels. The optimality of the proposed technique is verified by taking Cramer-Rao lower bounds (CRLBs) into comparison both on noise-and interference-dominant signal-to-noise ratio (SNR) conditions. In addition, the dual optimality of the LFM and PN pilot symbols is verified for both TD and frequency-domain (FD) CEs. Furthermore, the proposed technique also exhibits good resistance against residual timing errors occurring with the discrete Fourier transform (DFT) demodulation. Extensive computer simulations in conjunction with statistical derivations show the superiority of the proposed technique. Index Terms--Channel estimation (CE), Cramer-Rao lower bounds (CRLBs), least-squares estimation (LSE), linearly frequency modulated (LFM), matched filter (MF), pseudonoise (PN).

This paper proposes a regularized robust recursive least squares (R3LS) method for online estimation of power-system electromechanical modes based on synchronized phasor measurement unit (PMU) data. The proposed method utilizes an autoregressive moving average exogenous (ARMAX) model to account for typical measurement data, which includes low-level pseudorandom probing, ambient, and ringdown data. A robust objective function is utilized to reduce the negative influence from nontypical data, which include outliers and missing data. A dynamic regularization method is introduced to help include a priori knowledge about the system and reduce the influence of under-determined problems. Based on a 17-machine simulation model, it is shown through the Monte Carlo method that the proposed R3LS method can estimate and track electromechanical modes by effectively using combined typical and nontypical measurement data. Index Terms--Autoregressive moving average processes, least squares methods, power system identification, power system measurements, power system monitoring, power system parameter estimation, power system stability, recursive estimation, robustness.

A meshless approach, collocation discrete least square (CDLS) method, is extended in this paper, for solving elasticity problems and grid irregularity effect is assessed. In the present CDLS method, the problem domain is discretized by distributed field nodes. The field nodes are used to construct the trial functions. The moving least-squares interpolant is employed to construct the trial functions. Some collocation points that can be independent of the field nodes are used to form the total residuals of the problem. The least-squares technique is used to obtain the solution of the problem by minimizing the summation of the residuals for the collocation points. The final stiffness matrix is symmetric and therefore can be solved directly via efficient solvers. The boundary conditions are easily enforced by the penalty method. The present method does not require any mesh so it is a truly meshless method. Numerical examples are studied in detail, which show that the present method is stable and possesses good accuracy, high convergence rate and high efficiency for both regular and irregular point distribution. Keywords: Meshless method, MLS, Least square technique, CDLS, Elasticity, Irregular grids, INTRODUCTION The finite element method (FEM) has been the most frequently used numerical method in engineering during the three past decades. It has been used in most fields of applied [...]

Empirical relations for the propagation constant and the field profile parameters of integrated optical diffused channel waveguides have been developed. The field profile used is the evanescent secant-hyperbolic field, which has been shown earlier to be a very good approximation for diffused channel-waveguide modes. Least-square fitting has been used to obtain the empirical relations. The results show that the error in empirical relations for the propagation constant is within 2% for a broad range of waveguide parameters. The obtained empirical relations for the field profile and the propagation constant have been used, as an example, to calculate the coupling length of diffused channel-waveguide-based directional couplers. OCIS codes: 130.2790, 130.3730.

Most Positron Emission Tomography (PET) scanners still partly rely on analog processing to sort out events from the PET detector front-end. Recent all-digital architectures enable the use of more complex algorithms to solve common problems in PET scanners, such as crystal identification and parallax error. Auto-Regressive eXogeneous variable (ARX) algorithms were shown to be among the most powerful methods of crystal identification by Pulse Shape Discrimination (PSD) for parallax mitigation or resolution improvement with phoswich detectors. Although ARX algorithms achieve a nearly 100% discrimination accuracy even in a noisy environment, such methods are computationally expensive and can hardly be implemented in a real time digital PET system. A crystal identification method based on adaptive filter theory using an Auto-Regressive (AR) model is proposed to enable real time crystal identification in a noisy environment. Index Terms--Adaptive filter, auto-regressive (AR) model, crystal identification, PET scanner, real time.

Since multiuser code-division multiple-access (CDMA) communications systems suffer significantly from multiple-access interference (MAI) and from classical white Gaussian noise, it is therefore necessary to consider their impact on the performance of these systems. It is well known that the learning speed of any adaptive filtering algorithm is increased by adding a constraint to it. In this paper, a constrained least-mean-square (LMS) algorithm, which incorporates the knowledge of the number of users, spreading sequence length, and additive noise variance, is developed subject to the new combined constraint comprising the MAI and noise variance for a synchronous downlink direct-sequence CDMA system. The novelty of this constraint resides in the fact that the MAI variance was never used as a constraint. In our approach, a Robbins-Monro algorithm is used to minimize the conventional mean-square-error criterion subject to the variance of the new constraint (MAI plus noise). This constrained optimization technique results in an (MAI plus noise)-constrained LMS (MNCLMS) algorithm. The MNCLMS algorithm is a type of variable step-size LMS algorithm where the step-size rule arises naturally from the constraints on MAI and noise variance. Convergence and tracking analysis of the proposed algorithm are carried out in the presence of MAI. Finally, a number of simulations are conducted to compare the performance of the MNCLMS algorithm with other adaptive algorithms. Index Terms--Constrained optimization, direct sequence-code-division multiple access (DS-CDMA), least mean square (MAI plus noise)-constrained least mean square (LMSMNCLMS) algorithm, multiple-access interference (MAI).

In this paper, a new approach for the identification of a minimum-phase autoregressive (AR) system in the presence of a heavy noise is presented. First, a model, valid for both white noise and periodic impulse-train excitations, for the ramp-cepstrum (RC) of the one-sided autocorrelation function of an AR signal is proposed. A residue-based least-squares optimization technique is then employed in conjunction with the RC model to estimate the AR parameters from a noisy output, with a guaranteed system stability. The proposed ramp-cepstral model fitting combines the good features of both the correlation and cepstral domains, and thus provides a more accurate estimate of the parameters in a noisy environment. Extensive simulations are carried out on synthetic AR systems of different orders in the presence of white as well as colored noise. Simulation results demonstrate quite a satisfactory identification performance even for a signal-to-noise ratio of -5 dB, a level at which most of the existing methods fail to provide accurate estimation. To illustrate the suitability of the proposed technique in practical applications, a spectral estimation of a human vocal-tract system is carried out using noise-corrupted natural speech signals. Index Terms--Autoregressive (AR) system, low signal-to-noise ratio (SNR), ramp-cepstrum (RC), residue-based least-squares (RBLS) optimization, speech analysis.

Nonlinearity of amplifiers and/or loudspeakers gives rise to nonlinear echo in acoustic systems, which seriously degrades the performance of speech and audio communications. Many nonlinear acoustic echo cancellation (AEC) methods have been proposed. In this paper, a simple yet efficient nonlinear echo cancellation scheme is presented by using an adaptable sigmoid function in conjunction with a conventional transversal adaptive filter. The new scheme uses the least mean square (LMS) algorithm to update the parameters of sigmoid function and the recursive least square (RLS) algorithm to determine the coefficient vector of the transversal filter. The proposed AEC is proved to be convergent under some mild assumptions. Computer simulations show that the proposed scheme gives a superior echo cancellation performance over the well known Volterra filter approach when the echo path suffers from the saturation-type nonlinear distortion. More importantly, the new AEC has a much lower computational complexity than the Volterra-filter-based method. Index Terms--Acoustic echo cancellation, RLS algorithm, sigmoid function.

This paper studies the performance and applicability of a novel kernel partial least squares (KPLS) algorithm for nonlinear feature extraction in the context of remote sensing applications. The so-called kernel orthonormalized PLS algorithm with reduced complexity (rKOPLS) has the following two core parts: 1) a kernel version of OPLS (called KOPLS) and 2) a sparse approximation for large-scale data sets, which ultimately leads to the rKOPLS algorithm. The method is theoretically analyzed in terms of computational burden and memory requirements and is tested in common remote sensing applications: multi- and hyperspectral image classification and biophysical parameter estimation problems. The proposed method largely outperforms the traditional (linear) PLS algorithm and demonstrates good capabilities in terms of expressive power of the extracted nonlinear features, accuracy, and scalability as compared to the standard KPLS. Index Terms--Feature extraction, image classification, kernel methods, model inversion, partial least squares (PLS), support vector machine (SVM).

We propose a novel numerical method to simulate transient electromagnetic problems. The time derivatives are still tackled with the customary explicit leapfrog time scheme. But in the space domain, the fields at the collocation points are expanded into a series of radial basis functions and are treated with a meshless method procedure. Our method solves numerically Maxwell's equations with various assigned boundary conditions and current source excitation. Furthermore, the numerical stability condition of our method is obtained through a one-dimensional (l-D) wave equation and thus the relationship between control parameters is accounted for. To verify the accuracy and effectiveness of the new formulation, we compare the results of the proposed method with those of the conventional finite-difference time-domain method through a 1-D case study with different boundary conditions. Index Terms--Least square method (LSM), meshless method (MLM), radial basis function (RBF), shape function, time-domain.

Optimal receiver diversity combining employing linear channel estimation is examined. Based on the statistical properties of least-squares (LS) and minimum mean square error (MMSE) channel estimation, an optimal diversity receiver for wireless systems employing practical linear channel estimation on Rician fading channels is proposed. The new receiver structure includes the conventional maximal ratio combining receiver as a special case. Exact analytical expressions for the symbol error rates (SERs) of LS and MMSE channel estimation aided optimal diversity combining are derived. It is shown that, if an optimal detector is used, an MPSK wireless system with MMSE channel estimation has the same SER when the MMSE channel estimation is replaced by LS estimation. This is an interesting counterexample to the common perception that channel estimation with smaller mean square error leads to smaller SER. Extensive simulation results validate the theoretical results. Index Terms--Diversity receiver, error probability, least-squares channel estimation, minimum mean square error channel estimation, Rician fading.

von Bertalanffy parameters are usually estimated for a species, perhaps by sex, in some well-defined geographical area. An alternative way to estimate von Bertalanffy parameters is to model them in a general fixed-effects nonlinear model. For this model, the length of the ith individual is modeled as [y.sub.i] = f([phi], [t.sub.i], [x.sub.i]) + [[epsilon].sub.i], where [y.sub.i] is the length and [t.sub.i] is the age of the ith specimen at the time of sampling, [phi] are the unknown parameters required to model von Bertalanffy growth, and [x.sub.i1] are covariates associated with the ith specimen that minimally contain sex information (xii), but may also contain additional covariates. Standard nonlinear least squares and associated likelihood methods can be used to estimate parameters for this model. For Pacific ocean perch (Sebastes alutus), we model the effect that depth of collection has on estimated von Bertalanffy growth parameters; for sablefish (Anoplopoma fimbria), we model the effects due to latitude of collection; and for walleye pollock (Theragra chalcogramma) in the eastern Bering Sea, we model the effects due to variations in year classes. Results illustrate how modeling von Bertalanffy growth parameters directly using explanatory variables can be used to describe how growth relates to geographic, environmental, or biological factors. On estime generalement les parametres de von Bertalanffy pour une espece, parfois pour chacun des sexes, dans une region geographique bien definie. Une methode de rechange pour estimer les parametres de von Bertalanffy est de les modeliser dans un modele lineaire general a effets fixes. Dans ce modele, la longueur du ueme individu est calculee d'apres [y.sub.i] = f([phi], [t.sub.i], [x.sub.i]) + [[epsilon].sub.i], dans lequel [y.sub.i] est la longueur et [t.sub.i] est l'age du ueme individu au moment de l'echantillonnage, [phi] les parametres inconnus necessaires pour modeliser la croissance de von Bertalanffy et [x.sub.i] les covariables associees au ueme individu qui contiennent au minimum de l'information sur son sexe (xii), mais qui peuvent aussi comprendre d'autres covariables. La methode standard non lineaire des moindres carres et les methodes associees de vraisemblance peuvent servir a estimer les parametres de ce modele. Chez le sebaste a longue machoire (Sebastes alutus), nous modelisons l'effet de la profondeur de la recolte sur les parametres estimes de croissance de von Bertalanffy; chez la morue charbonniere (Anoplopoma fimbria), nous modelisons les effets causes par la latitude de la recolte; finalement, chez la goberge de l'Alaska (Theragra chalcogramma) dans l'est de la mer de Bering, nous modelisons les effets dus aux variations dans les classes d'age. Ces resultats montrent comment la modelisation directe des parametres de croissance de von Bertalanffy a l'aide de variables explicatives peut servir a decrire comment la croissance est reliee aux facteurs geographiques, environnementaux et biologiques. [Traduit par la Redaction], Introduction The von Bertalanffy growth curve (von Bertalanffy 1938) is perhaps the most widely used model in fisheries science and has been particularly useful in describing growth for many varieties [...]

In multiple-input-multiple-output (MIMO) communication systems, multiple antennas are employed at the transmitter and the receiver. Compared with conventional systems, it has been recognized that MIMO is an important technology in obtaining higher data rate and increasing the system capacity. This paper proposes two new linear multiuser detectors and their adaptive implementations for the synchronous multiuser direct-sequence code division multiple-access systems in a MIMO multipath fading environment. First, we employ the total least squares (TLS) method and the estimation of signal parameters via rotational invariance techniques (ESPRIT) to construct the multiuser detector structures. Second, we use the least mean square algorithm in the TLS-based and ESPRIT-based multiuser detectors to develop four adaptive receivers. We also analyze the probability of bit error of the proposed receivers. Simulation results show the performance comparisons of the proposed receivers. Index Terms--Direct-sequence code division multiple access (DS/CDMA), estimation of signal parameters via rotational invariance techniques (ESPRIT), least mean square (LMS), multiple-input--multiple-output (MIMO), total least squares (TLS).

Kernel principal component analysis (PCA) is a technique to perform feature extraction in a high-dimensional feature space, which is nonlinearly related to the original input space. The kernel PCA formulation corresponds to an eigendecomposition of the kernel matrix: eigenvectors with large eigenvalues correspond to the principal components in the feature space. Starting from the least squares support vector machine (LS-SVM) formulation to kernel PCA, we extend it to a generalized form of kernel component analysis (KCA) with a general underlying loss function made explicit. For classical kernel PCA, the underlying loss function is [L.sub.2]. In this generalized form, one can plug in also other loss functions. In the context of robust statistics, it is known that the [L.sub.2] loss function is not robust because its influence function is not bounded. Therefore, outliers can skew the solution from the desired one. Another issue with kernel PCA is the lack of sparseness: the principal components are dense expansions in terms of kernel functions. In this paper, we introduce robustness and sparseness into kernel component analysis by using an epsilon-insensitive robust loss function. We propose two different algorithms. The first method solves a set of nonlinear equations with kernel PCA as starting points. The second method uses a simplified iterative weighting procedure that leads to solving a sequence of generalized eigenvalue problems. Simulations with toy and real-life data show improvements in terms of robustness together with a sparse representation. Index Terms--Epsilon-insensitive loss function, kernel principal component analysis (PCA), least squares support vector machines (LS-SVM), loss function, robustness, sparseness.