Viewpoint Of Consistency Research Articles

Boosted nonparametric hazards with time-dependent covariates

Given functional data from a survival process with time-dependent covariates, we derive a smooth convex representation for its nonparametric log-likelihood functional and obtain its functional gradient. From this we devise a generic gradient boosting procedure for estimating the hazard function nonparametrically. An illustrative implementation of the procedure using regression trees is described to show how to recover the unknown hazard. The generic estimator is consistent if the model is correctly specified; alternatively an oracle inequality can be demonstrated for tree-based models. To avoid overfitting, boosting employs several regularization devices. One of them is step-size restriction, but the rationale for this is somewhat mysterious from the viewpoint of consistency. Our work brings some clarity to this issue by revealing that step-size restriction is a mechanism for preventing the curvature of the risk from derailing convergence.

Relationship between three-dimensional microstructure and Avrami exponent for recrystallization in pure iron

We undertook a three-dimensional analysis of the recrystallization that occurs in pure iron from the viewpoint of consistency between the growth direction of the recrystallized ferrite grains and the Johnson-Mehl-Avrami-Kolmogorov (JMAK) theory. Cold-rolled specimens were heated to 550 °C and, then, held at that temperature for a range of durations. The recrystallization behavior during the annealing was investigated both theoretically and experimentally. The formation of subgrains in non-recrystallized ferrite grains was found to occur before the start of recrystallization. Additionally, the fraction that recrystallized increased with the duration at 550 °C, and the slope became gradual after the annealing duration exceeded 60 s. The values of the Avrami exponent in the early and later stages of annealing were 1.86 and 0.37, respectively. Based on the JMAK theory, the growth direction of the recrystallized ferrite grains was assumed to be one-dimensional. On the other hand, the two- and/or three-dimensional growth of the recrystallized ferrite grains was confirmed by the three-dimensional analysis. Using a modified JMAK equation that takes the effect of recovery in recrystallization during annealing into consideration, the experimental data was found to be in good agreement with the modified JMAK plot. Thus, the inconsistency between the theoretical and experimental results could be attributed to the interaction between the recovery and recrystallization.

Grain-boundary-limited carrier mobility in polycrystalline silicon with negative temperature dependence: modeling carrier conduction through grain-boundary traps based on trap-assisted tunneling

Seto’s model based on thermionic emission (TE) theory explains that the grain-boundary (GB)-limited carrier mobility in polycrystalline silicon (poly-Si) has a positive temperature dependence. Although this model is widely accepted as a standard model for GB-limited carrier mobility in poly-Si, many experimental measurements under steady-state conditions support extremely weak or negative temperature dependence. In this report, we formulate carrier conduction through GB traps by utilizing the trap-assisted tunneling (TAT) model based on non-radiative multi-phonon transition theory. Self-consistent calculation of poly-Si under steady-state conditions reveals that TAT current exceeds TE current in regions with high GB potential barriers. In contrast to Seto’s model, our novel model reproduces the negative dependence of GB-limited carrier mobility on temperature. From the viewpoint of consistency with experimental measurements, our model seems to be suitable for describing carrier conduction in poly-Si under steady-state conditions.

A Study on ‘Special Provisions in other Law’ in relation to Article 6 of Personal Information Protection Act and Article 5 of Information Communication Network Act in Viewpoint of Law Consistency

A Study on ‘Special Provisions in other Law’ in relation to Article 6 of Personal Information Protection Act and Article 5 of Information Communication Network Act in Viewpoint of Law Consistency

Random reduction consistency of the Weber set, the core and the anti-core

In this paper we introduce a new consistency condition and provide characterizations for several solution concepts in TU cooperative game theory. Our new consistency condition, which we call the random reduction consistency, requires the consistency of payoff vectors assigned by a solution concept when one of the players is removed with some probability. We show that the random reduction consistency and other standard properties characterize the Weber set, the convex hull of the marginal contribution vectors. Another salient feature of random reduction consistency is that, by slightly changing its definition, we can characterize the core and the anti-core in a parallel manner. Our result enables us to compare the difference between the three solution concepts from the viewpoint of consistency.

Boosting Hazard Regression with Time-Varying Covariates

Consider a left-truncated right-censored failure process whose evolution depends on time-varying covariates. Such a process can be used to model customer transition dynamics for a variety of queuing networks. Given functional data samples from the process, we propose a gradient boosting procedure for estimating its log-intensity function in a flexible manner to capture time-covariate interactions. The estimator is shown to be consistent if the model is correctly specified. Alternatively an oracle inequality can be demonstrated for tree-based models. We use the procedure to shed new light on a question in the operations literature regarding the effect of workload on service rates in an emergency department.To avoid overfitting, boosting employs several regularization devices. One of them is step-size restriction, but the rationale for this is somewhat mysterious from the viewpoint of consistency: In theoretical treatments of classification and regression problems, unrestricted greedy step-sizes appear to suffice. Given that the partial log-likelihood functional for hazard regression has unbounded curvature, our study suggests that step-size restriction might be a mechanism for preventing the curvature of the risk from derailing convergence.

Evolutionary Fuzzy Integral-Based Gaze Control With Preference of Human Gaze

Research on developing human-like gaze control has been carried out to enhance human-robot interaction. From the viewpoint of a large consistency of human gaze, conventional research had focused on predicting where humans usually pay attention to. However, gaze control is a cognitive process that can even produce different scanpaths from the same visual information. In this paper, an evolutionary fuzzy integral-based gaze control algorithm with preference is proposed. It produces various scanpaths according to the preference of human gaze. The proposed gaze control algorithm evaluates each pixel point with fuzzy measures and fuzzy integral, and produces a scanpath through repeated selections considering memory and bio-inspired processes. The produced scanpath is transformed into a fixation map and compared with a scanpath obtained from a human subject by the earth mover’s distance. Based on the comparison, quantum-inspired evolutionary algorithm gradually develops preference of human gaze to produce a scanpath similar to the human scanpath. The effectiveness of the proposed algorithm is demonstrated by comparing a human scanpath with a scanpath produced from the algorithm using the developed preference. The applicability of the proposed algorithm is also demonstrated by applying the developed preference to gaze control for learning from demonstration.

On the robustness of regularized pairwise learning methods based on kernels

Regularized empirical risk minimization including support vector machines plays an important role in machine learning theory. In this paper regularized pairwise learning (RPL) methods based on kernels will be investigated. One example is regularized minimization of the error entropy loss which has recently attracted quite some interest from the viewpoint of consistency and learning rates. This paper shows that such RPL methods and also their empirical bootstrap have additionally good statistical robustness properties, if the loss function and the kernel are chosen appropriately. We treat two cases of particular interest: (i) a bounded and non-convex loss function and (ii) an unbounded convex loss function satisfying a certain Lipschitz type condition.

Kinematic assumptions and their consequences on the structure of field equations in continuum dislocation theory

Continuum Dislocation Theory (CDT) relates gradients of plastic deformation in crystals with the presence of geometrically necessary dislocations. Therefore, the dislocation tensor is introduced as an additional thermodynamic state variable which reflects tensorial properties of dislocation ensembles. Moreover, the CDT captures both the strain energy from the macroscopic deformation of the crystal and the elastic energy of the dislocation network, as well as the dissipation of energy due to dislocation motion. The present contribution deals with the geometrically linear CDT. More precise, the focus is on the role of dislocation kinematics for single and multi-slip and its consequences on the field equations. Thereby, the number of active slip systems plays a crucial role since it restricts the degrees of freedom of plastic deformation. Special attention is put on the definition of proper, well-defined invariants of the dislocation tensor in order to avoid any spurious dependence of the resulting field equations on the coordinate system. It is shown how a slip system based approach can be in accordance with the tensor nature of the involved quantities. At first, only dislocation glide in one active slip system of the crystal is allowed. Then, the special case of two orthogonal (interacting) slip systems is considered and the governing field equations are presented. In addition, the structure and symmetry of the backstress tensor is investigated from the viewpoint of thermodynamical consistency. The results will again be used in order to facilitate the set of field equations and to prepare for a robust numerical implementation.

Calibration of sealed HCl cells used for TCCON instrumental line shape monitoring

Abstract. The TCCON (Total Carbon Column Observing Network) FTIR (Fourier transform infrared) network provides highly accurate observations of greenhouse gas column-averaged dry-air mole fractions. As an important component of TCCON quality assurance, sealed cells filled with approximately 5 mbar of HCl are used for instrumental line shape (ILS) monitoring at all TCCON sites. Here, we introduce a calibration procedure for the HCl cells which employs a refillable, pressure-monitored reference cell filled with C2H2. Using this method, we identify variations of HCl purity between the TCCON cells as a non-negligible disturbance. The new calibration procedure introduced here assigns effective pressure values to each individual cell to account for additional broadening of the HCl lines. This approach will improve the consistency of the network by significantly reducing possible station-to-station biases due to inconsistent ILS results from different HCl cells. We demonstrate that the proposed method is accurate enough to turn the ILS uncertainty into an error source of secondary importance from the viewpoint of network consistency.

An axiomatization of the Hirsch-index without adopting monotonicity

The Hirsch-index is an index for measuring and comparing the output of researchers. Under the condition of monotonicity, Woeginger (7) provides a characterization of the Hirsch-index by three axioms in 2008. Replacing monotonicity by expansion consistency, we characterize the Hirsch-index by only two of Woeginger's axioms. Besides, we also introduce an axiom contraction consistency. It is a dual viewpoint of expansion consistency. Based on contraction consistency, an additional characterization of the Hirsch-index is reported.

Nonparametric empirical Bayes estimator in simultaneous estimation of Poisson means with application to mass spectrometry data

We consider the problem of simultaneous Poisson mean vector estimation and discuss the performance of nonparametric empirical Bayes (NPEB) estimator from the view point of risk consistency. We define the structural uniform risk consistency with respect to some classes of priors and show that the NPEB estimator achieves a structural uniform risk consistency with respect to some class of priors. It is shown that the NPEB estimator performs better than the maximum-likelihood estimator (MLE) and James–Stein estimators from the view point of structural uniform risk consistency. We also present numerical studies which support the asymptotic results and compare with the MLE and James–Stein-type estimators. We provide a real example of mass spectrometry data from a breast cancer study in Sauter et al. [Sauter, E.R., Davis, W., Qin, W., Scanlon, S., Mooney, B., Bromert, K., and Folk, W.R. (2009), ‘Identification of a β-Casein-Like Peptide in Breast Nipple Aspirate Fluid that is Associated with Breast Cancer’, Biomarkers in Medicine, 3, 577–588] with comparison of various estimators.

Method for Condensation of the Macroscopic Transport Cross-Sections for Criticality Analyses of FBR MONJU by the Code NSHEX

The problem with the energy-group approximation effect in the criticality analysis of the FBR MONJU by the discrete-ordinate transport code NSHEX has been studied. In order to reduce the existing energy-group collapsing effect in the 18 and 7-group results for the effective multiplication factor, a new algorithm for condensation of the macroscopic transport cross-sections has been proposed and verified. This work presents the definition of the new collapsing algorithm, results from the verification tests and a short discussion from the viewpoint of consistency of the algorithm with the specific finite-difference method of the code NSHEX. According to the presented results, the new collapsing algorithm can be recommended for condensation of the transport cross-sections from 70 into fewer energy-group structures.

Simplifying hydrozoan classification: inappropriateness of the group Hydroidomedusae in a phylogenetic context

The systematics of Hydrozoa is considered from the viewpoint of logical consistency between phylogeny and classification. The validity of the nominal taxon Hydroidomedusae (including all groups of Hydrozoa except the Siphonophorae) is discussed with regard to its distinctness and inclusive relationships. In general, phylogenetic systematic evidence suggest that the use of the term Hydroidomedusae is inappropriate given our current level of understanding. It is concluded that no new, or resurrected, names are necessary before or until a broader phylogenetic revision of the Hydrozoa is accomplished.

Indicators of renal effects of exposure to cadmium: N-acetyl-beta-D-glucosaminidase and others.

The renal effects of cadmium (Cd) have been studied in industrial workers exposed to Cd and inhabitants of Cd-polluted districts, as the kidney is a critical organ in exposure to Cd. Several biological indicators of Cd have been proposed including N-acetyl-beta-D-glucosaminidase (NAG) and beta 2-microglobulin (BMG) in urine for the detection of early renal effects. The average concentrations of Cd in urine samples were over 10 micrograms/g.creatinine in classic researches. Even in the industrial field, this exposure level is now hardly observed in Japan and western countries. The situation is the same with inhabitants in general living in a Cd-polluted district. From the viewpoint of consistency of the association, the relationship between Cd and NAG has become fairly definite. Stability in the pH change, simplicity, low cost and the reliability of measurements were also satisfactory. NAG is one of the recommended tools for detecting minimum renal effects under 10 micrograms/g.creatinine of Cd.

小学生用ストレス反応尺度の開発

The purposes of this study were to develop the Stress Response Scale for Children(SRS-C) which measures slight stress responses of elementary school children in a daily school life setting, and to examine its reliability and validity. In study I, after selecting items which state stress responses in school, factor analysis of data by 2,160 children revealed that the SRS-C has four main factors; “physical states”, “depressive-anxlous feeling”, “irritated-angry feeling” and “helplessness”. As a result,the SRS-C including 20 items was developed. In study II, psychometric analyses showed that the SRS-C has enough high reliability by test-retest method and split half method, and from the viewpoint of internal consistency. Furthermore, SRS-C scores were compared among three groups; HS-group which showed high stress responses, LS-group which showed low stress responses, and MS-group which showed moderate stress responses. As results of ANOVAs, it was revealed that SRS-C scores of HS-group were higher than other groups. It was suggested that the SRS-C had high clinical validity, content validity, and construct validity. It was also suggested that the SRS-C had enough possibility to measure slight stress responses of elementary school children. Finally, the significance of measuring stress responses in psychological stress studies and possibilities of clinical application of the SRS-C were discussed.

Magnetic Storm Development and Its Quantification for Aims of Modeling.

Using a large sample of storms of different intensity the ring current magnetic field development is followed in terms of varying interplanetary conditions. It is shown that although the storm depression field is associated with energy input into the magnetosphere, the sustained IEF intensity <-5 mV/m as a condition for the occurrence of intense storms appears not to be of general validity. Quantification of the magnetic storm development indicates the role of the actual state of the magnetosphere in the development of its response on interplanetary medium forcing. Ring current energization is considered for some storm models represented by pairs of energy injection rate and time decay parameter. A number of models are juxtaposed quantitatively. The adequacy of modeling of storm profiles and the significance of decay parameter in the magnetic storm development is discussed from the viewpoint of consistency of energy injection rate and energy decay rate and also with regard to an adequate distribution of dissipated energy within the ring current region and auroral ionosphere.

Estimating the Logistic Curve

Abstract In estimating the parameters of the logistic curve when the response at any given dose is binomial, the method of “maximum likelihood” and the method of “minimum logit chi-square” have both been suggested. Computational difficulties formerly associated with the maximum likelihood solution have now largely disappeared. In a comparison of the two methods it is shown that the maximum likelihood estimates, but not the minimum logit chi-square estimates, are sufficient estimators for the parameters. Particular attention is paid to samples where all but one of the responses are zero or 100 per cent. Also, the effects of using the “2n-rule” for handling the minimum logit chi-square estimation problem for cases of zero or 100 per cent kill in any class are examined. The two sets of estimators are also surveyed from the viewpoint of consistency and some remarks made on the criterion of minimum mean square error estimators when sufficient estimators exist.

Estimating the Logistic Curve

Abstract In estimating the parameters of the logistic curve when the response at any given dose is binomial, the method of “maximum likelihood” and the method of “minimum logit chi-square” have both been suggested. Computational difficulties formerly associated with the maximum likelihood solution have now largely disappeared. In a comparison of the two methods it is shown that the maximum likelihood estimates, but not the minimum logit chi-square estimates, are sufficient estimators for the parameters. Particular attention is paid to samples where all but one of the responses are zero or 100 per cent. Also, the effects of using the “2n-rule” for handling the minimum logit chi-square estimation problem for cases of zero or 100 per cent kill in any class are examined. The two sets of estimators are also surveyed from the viewpoint of consistency and some remarks made on the criterion of minimum mean square error estimators when sufficient estimators exist.