Parameter Restrictions Research Articles

Deep Learning for Concrete Crack Detection and Measurement

Concrete structures inevitably experience cracking, which is a common form of damage. If cracks are left undetected and allowed to worsen, catastrophic failures, with costly implications for human life and the economy, can occur. Traditional image processing techniques for crack detection and measurement have several limitations, which include complex parameter selection and restriction to measuring cracks in pixels, rather than more practical units of millimetres. This paper presents a three-stage approach that utilises deep learning and image processing for crack classification, segmentation and measurement. In the first two stages, custom CNN and U-Net models were employed for crack classification and segmentation. The final stage involved measuring crack width in millimetres by using a novel laser calibration method. The classification and segmentation models achieved 99.22% and 96.54% accuracy, respectively, while the mean absolute error observed for crack width measurement was 0.16 mm. The results demonstrate the adequacy of the developed crack detection and measurement method, and shows the developed deep learning and laser calibration method promotes safer, quicker inspections that are less prone to human error. The method’s ability to measure cracks in millimetres provides a more insightful assessment of structural damage, which is, in comparison to traditional pixel-based measurement methods, a significant improvement for practical field applications.

To use, or not to use the spatial Durbin model? – that is the question

ABSTRACT The spatial Durbin model (SDM) is one of the most widely used models in spatial econometrics. It originated as a generalisation of the spatial error model (SEM) under a non-linear parametric restriction (see Anselin (1988, pp. 110–111)). This restriction should be tested to select an appropriate model between SDM and SEM. Perhaps, due to the complexity of executing a test for a non-linear hypothesis, this restriction is rarely tested in practice, though see Burridge (1981), Mur and Angulo (2006) and LeSage and Pace (2009, p. 164). This paper considers an alternative linear hypothesis to test the suitability of the SDM. To achieve this, we first use Rao’s score (RS) testing principle and then Bera and Yoon (1993)’s methodology to robustify the original RS tests. The robust tests that require only ordinary least squares (OLS) estimation are able to identify the specific source(s) of departure(s) from the baseline linear regression model. An extensive Monte Carlo study provides evidence that our suggested tests possess excellent finite sample properties, both in terms of size and power. Our empirical illustrations, with two real data sets, attest that the tests developed in this paper could be very useful in judging the suitability of the SDM for the spatial data in hand.

Optical solitons for the dispersive concatenation model with spatio-temporal dispersion having multiplicative white noise

This investigation of the current work presents the dispersive concatenation model that integrates the spatio-temporal dispersion and the effect of multiplicative white noise in the Itô sense. The study aims to secure stochastic optical soliton solutions within this framework. To achieve this purpose, we implemented the enhanced Kudryashov technique and the new projective Riccati equations strategy. Initially, the traveling wave transform hypothesis was applied to convert the stochastic model into its nonlinear ordinary differential equation form, encompassing real and imaginary components with emerging the related parametric restrictions. Subsequently, we introduced the enhanced Kudryashov and the new projective Riccati equations techniques successfully employed in analyzing the generated nonlinear ordinary differential equation. By utilizing the appropriate solution sets, which encompass variables with unknown values and necessary transformations, we have derived many stochastic optical soliton-type solutions for the model. Detailed discussions for the dynamics of some selected soliton solutions are presented with the supporting of the 3D and 2D graphs that illustrate the white noise effect on these solitons.

Partial identification and inference in duration models with endogenous censoring

AbstractThis paper studies identification and inference in transformation models with endogenous censoring. Many kinds of duration models, such as the accelerated failure time model, proportional hazard model, and mixed proportional hazard model, can be viewed as transformation models. We allow the censoring of a duration outcome to be arbitrarily correlated with observed covariates and unobserved heterogeneity. We impose no parametric restrictions on either the transformation function or the distribution function of the unobserved heterogeneity. In this setting, we develop bounds on the regression parameters and the transformation function, which are characterized by conditional moment inequalities involving U‐statistics. Subsequently, we provide inference methods for them by constructing an inference approach for conditional moment inequality models in which the sample analogs of moments are U‐statistics. We apply the proposed inference methods to evaluate the effect of unemployment insurance on duration of joblessness using data from the Current Population Survey's Displaced Workers Supplements.

Quiescent Optical Solitons for the Concatenation Model Having Nonlinear Chromatic Dispersion with Differential Group Delay

This study recovers quiescent optical solitons within a complex concatenation model featuring nonlinear chromatic dispersion and differential group delay. It employs the sine-Gordon equation approach and the projective Riccati equation scheme. The results include the successful recovery of soliton solutions and the identification of parameter restrictions for their existence. The novelty lies in the application of these methods to this specific problem, offering valuable insights for optical communication system design.

Bifurcations of a three-species prey-predator system with scavenger

In this paper, we explore the existence of fixed points, local dynamical characteristics at fixed points, the existence of bifurcation sets at fixed points, and bifurcations of a three-species discrete prey-predator system with the scavenger. More specifically, it is proved that for all parameters, the discrete system has trivial and boundary fixed points; two more boundary fixed points, and an interior fixed point under a certain model's parametric restriction(s). Further, by the theory of linear stability, we examined local dynamics at fixed points. In order to understand the dynamics of the understudied system thoroughly, we studied the occurrence of certain bifurcations at fixed points by the bifurcation theory. Finally, theoretical results are numerically verified.

On statistical inference with high-dimensional sparse CCA.

We consider asymptotically exact inference on the leading canonical correlation directions and strengths between two high-dimensional vectors under sparsity restrictions. In this regard, our main contribution is developing a novel representation of the Canonical Correlation Analysis problem, based on which one can operationalize a one-step bias correction on reasonable initial estimators. Our analytic results in this regard are adaptive over suitable structural restrictions of the high-dimensional nuisance parameters, which, in this set-up, correspond to the covariance matrices of the variables of interest. We further supplement the theoretical guarantees behind our procedures with extensive numerical studies.

Columnar-to-equiaxed transition and grain refinement by solute interaction effects

The effects of single solute on grain refinement of binary alloys during casting have been revealed with supercooling parameter (P) and growth restriction factor (Q) theory in the literature. However, multiple-solute effects are still not clear due to the interaction between different solutes. In this work, we proposed a method to make remarkable grain refinement effects with minor Ti and C solutes. In addition, a novel method for columnar-to-equiaxed transition and grain refinement was also put forward based on solute interaction effects between multiple solute elements. Two solutes were designed first by considering (a) both segregated in solid-liquid interfaces with partition coefficients <1 and (b) with properly strong interaction energy. The interaction effect between the solutes enhances build-ups ahead of the solid-liquid interface and generate stronger constitutional supercooling, which leads to significant grain refinement in the selected model metals of Ni and Fe.

Learning ability of interpolating deep convolutional neural networks

It is frequently observed that overparameterized neural networks generalize well. Regarding such phenomena, existing theoretical work mainly devotes to linear settings or fully-connected neural networks. This paper studies the learning ability of an important family of deep neural networks, deep convolutional neural networks (DCNNs), under both underparameterized and overparameterized settings. We establish the first learning rates of underparameterized DCNNs without parameter or function variable structure restrictions presented in the literature. We also show that by adding well-defined layers to a non-interpolating DCNN, we can obtain some interpolating DCNNs that maintain the good learning rates of the non-interpolating DCNN. This result is achieved by a novel network deepening scheme designed for DCNNs. Our work provides theoretical verification of how overfitted DCNNs generalize well.

Parameter Restrictions for the Sake of Identification: Is There Utility in Asserting That Perhaps a Restriction Holds?

Parameter Restrictions for the Sake of Identification: Is There Utility in Asserting That Perhaps a Restriction Holds?

The multiple double-pole solitons and multiple negaton-type solitons in the space-shifted nonlocal nonlinear Schrödinger equation

This letter focuses on the constructions and dynamics of multiple double-pole soliton solutions and multiple negaton-type soliton solutions of the space-shifted nonlocal nonlinear Schrödinger equation. These solutions are derived from multiple bright soliton solutions through long-wave limits with specific parameter restrictions, and their explicit expressions are presented in determinants with matrix elements expressed as simple algebraic forms. The waveforms of multiple double-pole solitons are symmetric about their intersection point. The negaton-type solitons are partly influenced by the space-shifting parameter x0 included in the space-shifted nonlocal nonlinear Schrödinger equation. The dynamics of these two types of solitons are studied analytically and exhibited graphically.

Event-triggered impulse control on reaction–diffusion Gilpin–Ayala competition model with multiple stationary solutions

In previous literature, the parameter restrictions for the reaction–diffusion Gilpin–Ayala competition ecosystem were limited to the control of the first eigenvalue of the Laplace operator. This paper considers extending the parameter to the control of the second eigenvalue. However, exceeding the first eigenvalue results in a loss of compactness in the energy functional of the determined ecosystem. Consequently, this paper discusses the orthogonal decomposition of a given Sobolev space and variational techniques, obtaining the existence of multiple equilibrium points. The presence of multiple equilibrium points is a common phenomenon in real-world ecosystems and implies that the system cannot be globally stable under normal circumstances. However, this study develops an effective event-triggered impulse mechanism (ETIM) that achieves global stability for the positive equilibrium solution in the ecosystem. Notably, the newly designed ETIM not only eliminates Zeno behaviour but also reduces the cost of impulse control. This is achieved by removing some unnecessary impulses in the fixed impulsive instants mechanism associated with the ecosystem in previous literature. Finally, a numerical simulation validates the effectiveness of the proposed method.

Multivariate reference and tolerance regions based on conditional transformation models: Application to glycemic markers.

The reference interval is the most widely used medical decision-making, constituting a central tool in determining whether an individual is healthy or not. When the results of several continuous diagnostic tests are available for the same patient, their clinical interpretation is more reliable if a multivariate reference region (MVR) is available rather than multiple univariate reference intervals. MVRs, defined as regions containing 95% of the results of healthy subjects, extend the concept of the reference interval to the multivariate setting. However, they are rarely used in clinical practice owing to difficulties associated with their interpretability and the restrictions inherent to the assumption of a Gaussian distribution. Further statistical research is thus needed to make MVRs more applicable and easier for physicians to interpret. Since the joint distribution of diagnostic test results may well change with patient characteristics independent of disease status, MVRs adjusted for covariates are desirable. The present work introduces a novel formulation for MVRs based on multivariate conditional transformation models (MCTMs). Additionally, we take into account the estimation uncertainty of such MVRs by means of tolerance regions. These conditional MVRs imply no parametric restriction on the response, and potentially nonlinear continuous covariate effects can be estimated. MCTMs allow the estimation of the effects of covariates on the joint distribution of multivariate response variables and on these variables' marginal distributions, via the use of most likely transformation estimation. Our contributions proved reliable when tested with simulated data and for a real data application with two glycemicmarkers.

Analysis of the existing approaches to in-flight aircraft rerouting

Currently, the large number of aircraft accidents is associated with the loss of control in flight and a controlled flight into terrain. It frequently occurs due to a change of flight conditions, relatively which a preparation for departure was carried out, and involves the necessity to reroute efficiently in the conditions of increased psychophysiological load and time constraint for decisionmaking. Generated thunderstorm cells on route, artificial or natural obstacles, not considered while planning a route, can result in amending a flight plan, which was earlier accepted and implemented in the automatic, flight director or manual modes of control. The lack of comprehensive situational awareness is fairly a frequent cause of aviation accidents for general aviation aircraft. Aviation accidents of transport category aircraft are typically associated with incorrect crew actions when dangerous flight zones are detected along the route. The article represents an overview and analyzes modern onboard facilities to detect obstacles, as well as required pilot actions to reroute a flight for in-flight detected obstacle avoidance. The current level of avionics development provides situational awareness necessary for obstacles avoidance but requires timely, correct and sometimes non-obvious flight crew rerouting decisions. The algorithms used with robotic packages of various applications in related fields ensure the automatic rerouting for obstacle avoidance. They cannot be directly used or adapted for the implementation on board an aircraft due to the lack of consideration for aircraft specific features when obstacle avoidance routing, i.e., restrictions of control parameters (an angle of attack, overload, roll angle), capabilities of a control system (available rate of overload, available and maximally allowable angular rolling velocity, etc.). Therefore, the issue to develop a system to support pilot decisions for obstacle avoidance is relevant. It encompasses the synthesis of safe alternatives for obstacle avoidance which are optimal by a pilot-assigned criterion (minimum loss of time, minimum additional fuel consumption, etc.).

Bayesian modeling via discrete nonparametric priors

The availability of complex-structured data has sparked new research directions in statistics and machine learning. Bayesian nonparametrics is at the forefront of this trend thanks to two crucial features: its coherent probabilistic framework, which naturally leads to principled prediction and uncertainty quantification, and its infinite-dimensionality, which exempts from parametric restrictions and ensures full modeling flexibility. In this paper, we provide a concise overview of Bayesian nonparametrics starting from its foundations and the Dirichlet process, the most popular nonparametric prior. We describe the use of the Dirichlet process in species discovery, density estimation, and clustering problems. Among the many generalizations of the Dirichlet process proposed in the literature, we single out the Pitman–Yor process, and compare it to the Dirichlet process. Their different features are showcased with real-data illustrations. Finally, we consider more complex data structures, which require dependent versions of these models. One of the most effective strategies to achieve this goal is represented by hierarchical constructions. We highlight the role of the dependence structure in the borrowing of information and illustrate its effectiveness on unbalanced datasets.

Autonomous and non-autonomous modified Leslie-type stochastic predator-prey model with foraging arena scheme.

This paper aims to investigate how the external random noise affects the dynamics of the predator-prey model with a modified Leslie and foraging arena scheme. The autonomous and non-autonomous systems are both considered. First, some asymptotic behaviors of two species are explored including the threshold point. Then, the existence of an invariant density is deduced, based on the theory elaborated in Pike and Luglato (1987). Moreover, the famous LaSalle-type theorem is applied to investigate weak extinction, which requires weaker parametric restrictions. A numerical study is conducted to illustrate our theory.

Fully modified least squares estimation and inference for systems of cointegrating polynomial regressions

We consider fully modified least squares estimation for systems of cointegrating polynomial regressions, i.e., systems of regressions that include deterministic variables, integrated processes and their powers as regressors. The errors are allowed to be correlated across equations, over time and with the regressors. Whilst, of course, fully modified OLS and GLS estimation coincide – for any regular weighting matrix – without restrictions on the parameters and with the same regressors in all equations, this equivalence breaks down, in general, in case of parameter restrictions and/or different regressors across equations. Consequently, we discuss in detail restricted fully modified GLS estimators and inference based upon them.

Sequential Image Recovery Using Joint Hierarchical Bayesian Learning

Recovering temporal image sequences (videos) based on indirect, noisy, or incomplete data is an essential yet challenging task. We specifically consider the case where each data set is missing vital information, which prevents the accurate recovery of the individual images. Although some recent (variational) methods have demonstrated high-resolution image recovery based on jointly recovering sequential images, there remain robustness issues due to parameter tuning and restrictions on the type of sequential images. Here, we present a method based on hierarchical Bayesian learning for the joint recovery of sequential images that incorporates prior intra- and inter-image information. Our method restores the missing information in each image by “borrowing” it from the other images. More precisely, we couple sequential images by penalizing their pixel-wise difference. The corresponding penalty terms (one for each pixel and pair of subsequent images) are treated as weakly-informative random variables that favor small pixel-wise differences but allow occasional outliers. As a result, all of the individual reconstructions yield improved accuracy. Our method can be used for various data acquisitions and allows for uncertainty quantification. Some preliminary results indicate its potential use for sequential deblurring and magnetic resonance imaging.

Hybrid adaptive bionic fuzzy control method for MIMO systems with dead-zone input

In this research, a hybrid adaptive bionic fuzzy control strategy is developed for a class of complicated nonlinear multiple-input-multiple-output (MIMO) systems with dead-zone input. The first component of the bionic adaptive controller is a general phrase for tunning system parameters depending on the present state, and the second component is a trend-based compensation for adjusting the system parameters. This technique makes the system more intelligent and boosts its anti-interference capabilities. The stability and convergence are analyzed using the Lyapunov synthetic method, and thus the parameter restrictions of the MIMO system are provided. Finally, the strong anti-interference of the system is verified by the simulations.

Quiescent optical solitons with complex Ginzburg–Landau equation having a dozen forms of self–phase modulation

The current study focuses on the recovery of quiescent optical solitons through the use of the complex Ginzburg–Landau equation when the chromatic dispersion is rendered to be nonlinear. A dozen forms of self-phase modulation structures are taken into consideration. The utilization of the enhanced Kudryashov's scheme has led to the emergence of singular, dark, and bright soliton solutions. The existence of such solitons is subject to certain parametric restrictions, which are also discussed in this paper.