Accelerated life tests at higher usage rates

Accelerated life tests are extensively used to provide quickly the information about the life distributions of products. Test units are subjected to elevated stresses which yield shorter lives. For some products whose life is defined by usage, e.g., mileage and cycles, test units are also run at higher usage rates (UR) to compress the test time. This paper presents a method for testing products at both higher stress levels, and UR. Censoring time is pre-determined and fixed, while censoring usage is a function of UR. A UR effect model is proposed to describe the dependence of usage to failure (UTF) on UR. The relationship between UTF, and stress and UR is established, and used to estimate the UTF distribution at design stresses and usual UR. The model parameters are estimated by maximum likelihood method. The best compromise test plans, which choose the UR, stress levels, and sample sizes, are devised by minimizing the asymptotic variance of the estimator of a life percentile at design stresses and usual UR. The efficiency, and sensitivity of the test plans are evaluated. The results show that the test plans are efficient, and robust.     

Accelerated life tests for products of unequal size

This paper considers `estimation of the lifetime distribution' and `optimal design of constant-stress accelerated life test plans' for products of unequal size. The distribution is Weibull with a scale parameter that is a `log-linear function of stress' and a `power function of product size with a size-effect parameter'. Maximum likelihood estimators (MLE) of model parameters are obtained, and their properties are studied. Two stress-level optimal test plans are obtained for products that come in two sizes, and a table useful for finding optimal test plans is given. The sum of asymptotic variances of MLE of a specified quantile of the distributions for products of both sizes is used as the optimality criterion. Optimum plans can be used when the ratio of two sizes is not too large. When the ratio is very large, the preestimate of size effect parameter should be carefully chosen     

Solving inverse problems with piecewise linear estimators: from Gaussian mixture models to structured sparsity

A general framework for solving image inverse problems with piecewise linear estimations is introduced in this paper. The approach is based on Gaussian mixture models, which are estimated via a maximum a posteriori expectation-maximization algorithm. A dual mathematical interpretation of the proposed framework with a structured sparse estimation is described, which shows that the resulting piecewise linear estimate stabilizes the estimation when compared with traditional sparse inverse problem techniques. We demonstrate that, in a number of image inverse problems, including interpolation, zooming, and deblurring of narrow kernels, the same simple and computationally efficient algorithm yields results in the same ballpark as that of the state of the art.     

Jointly registering images in domain and range by piecewise linear comparametric analysis

This paper describes an approach whereby comparametric analysis is used in jointly registering image pairs in their domain and range, i.e., in their spatial coordinates and pixel values, respectively. This is accomplished by approximating a camera's nonlinear comparametric function with a constrained piecewise linear one. The optimal fitting of this approximation to comparagram data is then used in a re-parameterized version of the camera's comparametric function to estimate the exposure difference between images. Doing this allows the inherently nonlinear problem of joint domain and range registration to be performed using a computationally attractive least squares formalism. The paper first presents the range registration process and then describes the strategy for performing the joint registration. The models used allow for the pair-wise registration of images taken from a camera that can automatically adjust its exposure as well as tilt, pan, rotate and zoom about its optical center. Results concerning the joint registration as well as range-only registration are provided to demonstrate the method's effectiveness.     

Predicting hepatitis C virus protease cleavage sites using generalized linear indicator regression models

This paper discusses how to predict hepatitis C virus protease cleavage sites in proteins using generalized linear indicator regression models. The mutual information is used for model-size optimization. Two simulation strategies are adopted, i.e., building a model based on published peptides and building a model based on the published peptides plus newly collected sequences. It is found that the latter outperforms the former significantly. The simulation also shows that the generalized linear indicator regression model far outperforms the multilayer perceptron model.     

高性能分段线性补偿CMOS带隙基准电压源设计

设计了一种具有分段线性补偿的CMOS带隙基准电压源。该电路基于传统带隙基准源,利用MOS晶体管代替双极型晶体管产生正温度系数电流和负温度系数电流,将这两种具有相反温度系数的电流以适当的权重相加到负载电阻,并加入分段补偿电路,在低温阶段,加入一段负温度系数的电流,在高温阶段,抽取部分总电流,从而得到高精度的基准输出电压。在0.5μm CMOS工艺下,使用Cadence Spectre对电路进行仿真,仿真结果表明,在供电电压为5 V时,基准输出电压为1.255 V,在–40～125℃范围内,带隙基准源的温漂系数为1.029×10~(–6)/℃,低频时的电源抑制比(PSRR)低于–75 dB。     

Wavelet-based estimation of a semiparametric generalized linear model of fMRI time-series

This paper addresses the problem of detecting significant changes in fMRI time series that are correlated to a stimulus time course. This paper provides a new approach to estimate the parameters of a semiparametric generalized linear model of fMRI time series. The fMRI signal is described as the sum of two effects: a smooth trend and the response to the stimulus. The trend belongs to a subspace spanned by large scale wavelets. The wavelet transform provides an approximation to the Karhunen-Loève transform for the long memory noise and we have developed a scale space regression that permits to carry out the regression in the wavelet domain while omitting the scales that are contaminated by the trend. In order to demonstrate that our approach outperforms the state-of-the art detrending technique, we evaluated our method against a smoothing spline approach. Experiments with simulated data and experimental fMRI data, demonstrate that our approach can infer and remove drifts that cannot be adequately represented with splines.     

A generalized weighted linear predictor frequency estimation approach for a complex sinusoid

Based on linear prediction and weighted least squares, three simple iterative algorithms for frequency estimation of a complex sinusoid in additive white noise are devised. The proposed approach, which utilizes the first-order as well as higher order linear prediction terms simultaneously but does not require phase unwrapping, can be considered as a generalized version of the weighted linear predictor frequency estimator. In particular, convergence as well as mean and variance analysis of the most computationally efficient frequency estimator, namely, GWLP 2, are provided. Computer simulations are included to contrast the performance of the proposed algorithms with several conventional computationally attractive frequency estimators and Crame/spl acute/r-Rao lower bound for different frequencies, observation lengths, and signal-to-noise ratios.     

Complex TM models in a generalized Goubau line with arbitrary conductivities

The modal equation for the wavenumbers of the complex transverse magnetic (TM) modes of an open circular-cylinder coaxial waveguide with central conductor is studied for the case when the inner and outer materials have arbitrary conductivity. Analytic approximations for the wavenumhers of all of the modes are obtained for large contrast between the inner and outer materials, and simple numerical algorithms for calculating the wavenumbers are obtained for arbitrary contrast. It is shown that when the conductivities are zero, the wavenumbers group together in a set of four complex values, symmetric in the complex plane, but that the symmetry and the grouping can both be destroyed by adding conductivity to the materials. For fixed conductivities, there are principal modes (with no low-frequency cutoffs) and secondary modes (with low-frequency cutoffs) but one type mode can be converted into the other type by changing the conductivities. A numerical study of the modal equation shows how the modes of a Goubau line can be related to those of a coaxial transmission line. It shows also that the values of individual solutions of the modal equation can depend on the history of the conductivity values of the waveguide.     

Performance evaluation of a generalized linear SIC for DS/CDMA signals

The linear successive interference canceler (LSIC) is a multiuser detector that separates code-division multiple-access (CDMA) signals in a multistage manner. In each stage, a user is detected, and its contribution is regenerated and canceled from the input of that stage. A user's spreading sequence is employed for despreading and respreading, and the magnitude of the despreader output is used as the amplitude estimate to reconstruct that user's signal. This paper describes a generalized version of the LSIC (GLSIC) that employs various types of linear filters for the despreading and respreading operations. We analyze the bit error rate (BER), asymptotic multiuser efficiency (AME), and the mean and variance of the amplitude estimates of the GLSIC. It is shown that for certain choices of linear filters, complete cancellation of a user can be achieved, irrespective of the reliability of the symbol estimates. We also demonstrate that, from a BER and AME viewpoint, it is not beneficial to use a linear canceler with a decorrelator or a minimum mean-square-error (MMSE) receiver.     

Phase synthesis of antennas for a given radiation pattern in oneplane using piecewise linear aperture phase distribution

A phase-only method for the synthesis of planar aperture antennas for a given complex radiation pattern in one plane is reported. The problem is reduced to determining an appropriate aperture phase distribution in the form of a ruled function and solved for apertures with rectangular shape and an arbitrary amplitude distribution and for apertures of arbitrary shape and amplitude distribution. This method can be used for controlling the pattern of phased-array antennas. Results of computer modeling are presented     

Plane-wave expansion for arrays of arbitrarily oriented piecewise linear elements and its application in determining the impedance of a single linear antenna in a lossy half-space

An infinite array of arbitrarily oriented identical elements with arbitrary identical currents is considered. The field from this array is expanded into plane inhomogeneous waves, and the mutual impedance between the array elements and an exterior arbitrarily oriented element is derived. The formulation is particularly useful when the array is located adjacent to a dielectric interface. Numerical examples are given and the relationship to earlier formulations pointed out. It is further shown that the impedance of a single element can be obtained as the average of the scan impedance taken over the entire hemisphere (called the array scanning method (ASM)). This technique has a clear physical interpretation which greatly facilitates its uses, which include the moment method solutions of wire antennas as applied to the Sommerfeld integral. Numerical evaluation is straightforward when the dipole is in the lossy half-space, and the utility of the method is demonstrated by the presentation of results for the input impedance of dipoles in a variety of half-space environments. Solution is by Galerkin's method with a piecewise sinusoidal expansion for the current. Computer time is proportional tod^{-1}, wheredis the distance of the dipole to the interface. For conducting media and low frequencies an approximation is made to reduce computation time. The moment method solution of a dipole buried at a depth as small as 1/150000 wavelength in the earth is presented.     

Nonlinear filters for linear models (a robust approach)

We consider the altering problem for linear models where the driving noises may be quite general, nonwhite and non-Gaussian, and where the observation noise may only be known to belong to a finite family of possible disturbances. Using diffusion approximation methods, we show that a certain nonlinear filter minimizes the asymptotic filter variance. This nonlinear filter is obtained by choosing at each moment, on the basis of the observations, one of a finite number of Kalman-type filters driven by a suitable nonlinear transformation of the “innovations”. As a byproduct we obtain also the asymptotic identification of the a priori unknown observation noise disturbance. By yielding an asymptotically efficient filter in face of an unknown observation noise, our approach may also be viewed as a robust approach to filtering for linear models     

Field tests on a MAGLEV with passive guideway linear inductor motortransportation system

A passive guideway linear inductor motor MAGLEV research vehicle intended primarily for urban transportation applications is presented. Solutions for magnetic levitation and propulsion control together with the main sensors (airgap, acceleration, and position) are described. Preliminary field tests on a 4-t 4-m-long research vehicle, named Magnibus-01, are given. Vehicle take-off and landing, response to perturbations in levitation, vehicle acceleration, and electrical braking at low speeds were recorded and are presented     

On replacement models via a fuzzy set theoretic framework

Uncertainty is present in virtually all replacement decisions due to unknown future events, such as revenue streams, maintenance costs, and inflation. Fuzzy sets provide a mathematical framework for explicitly incorporating imprecision into the decision making model, especially when the system involves human subjectivity. This paper illustrates the use of fuzzy sets and possibility theory to explicitly model uncertainty in replacement decisions via fuzzy variables and numbers. In particular, a fuzzy set approach to economic life of an asset calculation as well as a finite-horizon single asset replacement problem with multiple challengers is discussed. Because the use of triangular fuzzy numbers provides a compromise between computational efficiency and realistic modeling of the uncertainty, this discussion emphasizes fuzzy numbers. The algorithms used to determine the optimal replacement policy incorporate fuzzy arithmetic, dynamic programming (DP) with fuzzy rewards, the vertex method, and various ranking methods for fuzzy numbers. A brief history of replacement analysis, current conventional techniques, the basic concepts of fuzzy sets and possibility theory, and the advantages of the fuzzy generalization are also discussed     

Stability tests and performance bounds for a class of 2D linear systems

Repetitive, or multipass, processes are a class of 2D systems characterized by a recursive action with interaction between successive outputs or pass profiles. This interpass interaction is the source of the unique control problem for these processes in that it can cause the output sequence to exhibit oscillations which increase in amplitude from pass to pass. Previous work has developed an abstract stability theory and applied it to subclasses, such as discrete nonunit memory linear processes which are considered here, to produce basic stability tests. This article begins by reviewing the known stability tests and concludes that, at best, they only produce highly qualitative indicators of relative stability and performance. Hence, unlike (say) Bode and Nyquist tests for standard linear systems, they are of limited appeal as a basis for computer-aided control systems design. To remove this difficulty, step response data is used to develop new simulation-based tests which yield, at no extra cost, unique computable performance measures. Further, the undoubted advantages of having such measures available is clearly shown by developing a (virtually) complete solution to controller design for one subclass.     

Surface-wave behavior of a phased array analyzed by the grating-lobe series

A pictorial representation of the behavior of a phased array which supports a surface wave is obtained by using the grating-lobe series. The admittance crater for a slotted array, covered by a dielectric sheet, is derived and plotted showing several unusual properties. From the crater, the variation of array admittance with scan is also computed and a contour plot of reflection coefficient magnitude is presented on thesin thetaplane.     

Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response

We describe an automated method to locate and outline blood vessels in images of the ocular fundus. Such a tool should prove useful to eye care specialists for purposes of patient screening, treatment evaluation, and clinical study. Our method differs from previously known methods in that it uses local and global vessel features cooperatively to segment the vessel network. We evaluate our method using hand-labeled ground truth segmentations of 20 images. A plot of the operating characteristic shows that our method reduces false positives by as much as 15 times over basic thresholding of a matched filter response (MFR), at up to a 75% true positive rate. For a baseline, we also compared the ground truth against a second hand-labeling, yielding a 90% true positive and a 4% false positive detection rate, on average. These numbers suggest there is still room for a 15% true positive rate improvement, with the same false positive rate, over our method. We are making all our images and hand labelings publicly available for interested researchers to use in evaluating related methods.