Using regression trees to classify fault-prone software modules

Software faults are defects in software modules that might cause failures. Software developers tend to focus on faults, because they are closely related to the amount of rework necessary to prevent future operational software failures. The goal of this paper is to predict which modules are fault-prone and to do it early enough in the life cycle to be useful to developers. A regression tree is an algorithm represented by an abstract tree, where the response variable is a real quantity. Software modules are classified as fault-prone or not, by comparing the predicted value to a threshold. A classification rule is proposed that allows one to choose a preferred balance between the two types of misclassification rates. A case study of a very large telecommunications systems considered software modules to be fault-prone, if any faults were discovered by customers. Our research shows that classifying fault-prone modules with regression trees and the using the classification rule in this paper, resulted in predictions with satisfactory accuracy and robustness.     

Confidence intervals for regression (MEM) spectral estimates

The probability density and confidence intervals for the maximum entropy (or regression) method (MEM) of spectral estimation are derived using a Wishart model for the estimated covariance. It is found that the density for the estimated transfer function of the regression filter may be interpreted as a generalization of the student's t distribution. Asymptotic expressions are derived which are the same as those of Akaike. These expressions allow a direct comparison between the performance of the maximum entropy (regression) and maximum likelihood methods under these asymptotic conditions. Confidence intervals are calculated for an example consisting of several closely space tones in a background of white noise. These intervals are compared with those for the maximum likelihood method (MLM). It is demonstrated that, although the MEM has higher peak to background ratios than the MLM, the confidence intervals are correspondingly larger. Generalizations are introduced for frequency wavenumber spectral estimation and for the joint density at different frequencies.     

The rates of convergence of kernel regression estimates and classification rules

Both nonrecursive and recursive nonparametric regression estimates are studied. The rates of weak and strong convergence of kernel estimates, as well as corresponding multiple classification errors, are derived without assuming the existence of the density of the measurements. An application of the obtained results to a nonparametric Bayes predication is presented.     

一种稳定激光器输出光强的新方法

介绍一种采用数字PID控制技术稳定激光器输出光强的新方法。利用输出光强变化,通过数字PID调节器反馈控制激光管电流可获得较为稳定的激光输出。采用单片机控制,使得控制电路简化,控制精度提高,整机工作更加稳定可靠。     

Adaptive visual servo control to simultaneously stabilize image and pose error

A novel, Lyapunov-based visual servo controller is presented that stabilizes both the entire image and pose error vectors simultaneously, rather than a subset of the errors. Furthermore, the controller uses adaptive depth estimation to eliminate the need to measure depth or obtain knowledge of the scene. A stability proof is presented. Simulation and experimental results compare the performance of the proposed method to PBVS, IBVS and 2.5D VS approaches.     

Using Gaussian-process regression for meta-analytic neuroimaging inference based on sparse observations

The purpose of neuroimaging meta-analysis is to localize the brain regions that are activated consistently in response to a certain intervention. As a commonly used technique, current coordinate-based meta-analyses (CBMA) of neuroimaging studies utilize relatively sparse information from published studies, typically only using (x,y,z) coordinates of the activation peaks. Such CBMA methods have several limitations. First, there is no way to jointly incorporate deactivation information when available, which has been shown to result in an inaccurate statistic image when assessing a difference contrast. Second, the scale of a kernel reflecting spatial uncertainty must be set without taking the effect size (e.g., Z-stat) into account. To address these problems, we employ Gaussian-process regression (GPR), explicitly estimating the unobserved statistic image given the sparse peak activation "coordinate" and "standardized effect-size estimate" data. In particular, our model allows estimation of effect size at each voxel, something existing CBMA methods cannot produce. Our results show that GPR outperforms existing CBMA techniques and is capable of more accurately reproducing the (usually unavailable) full-image analysis results.     

Application of the surface harmonic expansions for modeling thehuman torso

A method is described to represent the human-torso geometry, as obtained from, e.g. MR imaging, in terms of the surface harmonic expansion. Three specific torso geometries, two male and one female, were reconstructed with the root-mean-square (rms) error <5 mm using 168 and 248 parameters, respectively. The method can be used in radiation therapy and enhances the accuracy of forward and inverse modeling in electrocardiology     

A novel approach to stabilize contact resistance of electrically conductive adhesives on lead-free alloy surfaces

Electrically conductive adhesive (ECA) is an alternative for the toxic lead-based solders. However, unstable electrical conductivity has long been a haunting problem. Galvanic corrosion at the ECA/pad interface has recently been found to be the major mechanism for this decay. Applying a more active metal or alloy on a dissimilar metal couple in contact can prohibit galvanic corrosion. In this study, powders of aluminum, magnesium, zinc, and two aluminum alloys were added in an ECA and applied on five pad surfaces. The aging of the bulk resistivity and contact resistance of the ECA/metal surface pairs were studied. The two alloys significantly suppressed the increase of the contact resistance on all tested metal surfaces.     

Use of plasma tube impedance variations to frequency stabilize a CO2laser

A method for stabilizing the frequency of a single-J- value CO2laser to the center of its output power versus frequency curve based upon the variation of the impedance of the plasma tube with the optical power extracted is described. Frequency modulation of the laser produces an ac component of voltage drop across the plasma tube, which is synchronously detected to generate a frequency-error signal.     

Effect of torso boundaries on electric potential and magnetic fieldof a dipole

A numerical model of a human torso was used to study and compare the effect of outer torso, lung, and intracavitary blood mass boundaries on the body surface distribution of electric potential and normal component of magnetic field due to a single current dipole placed at various locations in the heart. Results are presented in the form of isopotential and isofield maps and are also compared to the maps of a dipole in a semi-infinite homogenous model in the context of single dipole inverse solutions. The inclusion of the boundaries has a large effect on the magnitudes of the maps and modest effects on their topology. The electric and magnetic maps show similar responses to the boundaries for X (leftward) and Y (upward) directed dipoles. The electric maps of Z (back-to-front) dipoles are comparatively unaffected by the boundaries, unlike the magnetic maps of Z dipoles, to which the outer boundary makes a substantial contribution. The results indicate electric and magnetic maps have complementary sensitivities for certain dipole components in the presence of realistic boundaries     

Use of the finite element method to determine epicardial from body surface potentials under a realistic torso model

This paper presents a new method of solution for the inverse problem in electrocardiography using the finite element procedure. It is an application of the authors' earlier work which derived a solution method by means of an integral equation under a generalized configuration of geometry and conductivity of the torso. Based on prior geometry information, the human torso region is discretized into a series offinite elements and, then, electric fields are computed when a set of linearly independent functions chosen as a basis is imposed on the epicardial surface. The set of these forward solutions defines the forward transfer coefficients which relate epicardial to body surface potentials. By the use of the forward transfer coefficients, a constrained least-squares estimate of the epicardial potential distribution can be obtained from measured body surface potentials. The solution method is examined through numerical experiments carried out for a realistic model of the human torso. It is demonstrated that the rapid decrease in voltage far from the heart generator makes this inverse problem ill conditioned and, as a result, the accuracy of the inverse epicardial potentials calculated depends greatly upon both the signal-to-noise ratio and the number of lead points in measuring the body surface potentials.     

脑卒中发病率的多元回归模型研究

脑卒中俗称脑中风,是一种严重威胁人类健康和生命的常见病,已成为我国重大的公共卫生问题。因此了解脑卒中的危险因素和发病机制对于有效的预防和治疗脑卒中都具有十分重要的意义。首先,我们对数据进行统计处理,得出了各年份各月人员发病人数及发病率,以及不同性别,年龄段,职业的发病数据。发现男性发病率比女性大;60—89岁年龄段的人最容易得病;农民的发病率最高。其次,我们对前面得出的数据进行整合处理,得到了四年各月平均气压、气压差、平均温度、温差、平均湿度及发病率数据,用多元逐步回归分析法建立数学模型。最后,根据以上数据,总结得出脑卒中的发病原因并对高危人群提出了预警方案。     

Design and development of a mechatronic infant torso simulator for respiratory physiotherapy learning

Currently, constraint-free realistic context training is nonexistent in infant physiotherapy. In order to enhance the vocational learning of novices, in close collaboration with expert physiotherapists, we designed an innovative simulator dedicated to the training of infant respiratory physiotherapy. This paper describes the simulator’s functionalities and the method used to design its physical structure and the learning paradigm. Firstly, regarding a cognitive approach, relevant vocational and didactic criteria were defined in order to characterize the gesture and determine its limits for a nondangerous practice. Subsequently, we chose physical parameters to assess the criteria and define the specifications of the simulator. The mechatronic functions arose from a didactic transposition of the expected simulation-based functionalities. A 6-month-old infant torso physical structure has been designed with the use of finite element simulations. Its mechanical behaviour provides the possibility to deform the mannequin like a real infant during physiotherapy manoeuvres. A prototype has been realized and validated.     

Variance of Bayes estimates

This paper contains an analysis of the performance of Bayes conditional-mean parameter estimators. The main result is that on a finite parameter space such estimates exhibit a mean-square error that diminishes exponentially with the number of observations, the observations being assumed to be independent. Two situations are discussed: true parameter included in the parameter space and true parameter not included in the parameter space. In the former instance only very general assumptions are required to demonstrate the exponential convergence rate. In the latter case the existence of an information function must be invoked. Comments on the continuous-parameter-space realization of the estimator and a discussion of the convergence mechanism are also included.     

Some estimates pertaining to sensitivity and robust stability of input-output systems

The estimates derived in this paper strengthen the available results on sensitivity and robust stability of input-output systems. Two types of estimates are discussed: the “sensitivity type”, which establishes a bound for the output change when the system is perturbed but the input remains the same, and the “robustness type”, which gives a bound for the output change when the input changes but the perturbation does not. First, estimates for general systems over abstract extended spaces are derived; these results are then applied to (1) two frequently used control configurations, and (2) systems governed by vector integral and differential equations on the time domain [0, ∞). The applications of the estimates are illustrated by several examples. This research was supported by the National Science Foundation under Grant #DMS-9102910     

Evaluation of WindSat wind vector performance with respect to QuikSCAT estimates

The WindSat instrument was launched on January 6, 2003 as part of a risk reduction effort to assess the potential of using spaceborne fully polarimetric radiometry to measure the marine wind vector. Microwave radiometry on the Special Sensor Microwave/Imager onboard the Defense Meteorological Satellite Program satellites has long provided wind speed measurements. Fully polarimetric radiometry offers the additional possibility of obtaining wind direction as well. By contrast, the QuikSCAT satellite uses active microwave measurements to estimate the wind vector from space. It represents the most comprehensive satellite dataset against which to compare WindSat measurements. In this paper, we systematically compare temporally and spatially coincident WindSat and QuikSCAT wind vector measurements against the design goals of the WindSat instrument, taking into consideration expected differences related to instrument precision and the spatial and temporal variability of the wind field.     

实用型光纤陀螺系统工作点的选定和稳定技术的试验研究

介绍了实用型中低精度开环光纤陀螺系统中如何实时并准确地测量陀螺系统的工作点的方法和技术方案,并且从理论上分析了开环的光纤陀螺系统的工作点的选择依据。通过对实验结果的对比测试分析,提出了进一步提高光纤陀螺精度和稳定度的途径和设想。     

Constrained estimates of multipath covariance

When multipath propagation occurs, the covariance among signals traveling along rays emanating from a common source is expected to be larger than the covariance between signals generated by independent sources. Several data adaptive constrained estimates of the covariance are derived by the author as bilinear forms and some simulations are presented. The ability of a bilinear form to distinguish a 0-dB (relative to uncorrelated noise) correlated arrival pair from a 0-dB independent source is studied using an expected narrowband cross-spectral matrix corresponding to a simulated acoustic field with a 32-element line array at Nyquist spacing. An adaptive set of filter vectors obtained from the classical minimum variance problem are found to minimize sidelobe interference to 2 dB above the background noise level at the cost of reduced peaks having an 18-dB output above the uncorrelated background     

Optimization of Barron density estimates

We investigate a nonparametric estimator of the probability density introduced by Barron (1988, 1989). Earlier papers established its consistency in a strong sense, e.g., in the expected information divergence or expected chi-square divergence. This paper pays main attention to the expected chi-square divergence criterion. We give a new motivation of the Barron estimator by showing that a maximum-likelihood estimator (MLE) of a density from a family important in practice is consistent in expected information divergence but not in expected chi-square divergence. We also present new and practically applicable conditions of consistency in the expected chi-square divergence. Main attention is paid to optimization (in the sense of the mentioned criterion) of the two objects specifying the Barron estimator: the dominating probability density and the decomposition of the observation space into finitely many bins. Both problems are explicitly solved under certain regularity assumptions about the estimated density. A simulation study illustrates the results in exponential, Rayleigh, and Weibull families