Search

Marginal maximum likelihood, a common estimation method for item response theory models, is not inherently a Bayesian procedure. However, due to estimation difficulties, Bayesian priors are often applied to the likelihood when estimating 3PL models, especially with small samples. Little focus has been placed on choosing the priors for marginal maximum estimation. In this study, using sample sizes of 1,000 or smaller, not using priors often led to extreme, implausible parameter estimates. Applying prior distributions to the c -parameters alleviated the estimation problems with samples of 500 or more; for the samples of 100, priors on both the a -parameters and c -parameters were needed. Estimates were biased when the mode of the prior did not match the true parameter value, but the degree of the bias did not depend on the strength of the prior unless it was extremely informative. The root mean squared error (RMSE) of the a -parameters and b -parameters did not depend greatly on either the mode or the strength of the prior unless it was extremely informative. The RMSE of the c -parameters, like the bias, depended on the mode of the prior for c. [ABSTRACT FROM AUTHOR]

The purpose of this work is to analyze the impact of reinforced Al2O3–LM6 aluminum composite made with dual mixed slurry for semi-solid casting with stirring, which is documented according to microstructure and wear properties. Under dry sliding pin-on-disk conditions, the composition and surface morphology of worn surfaces were carefully examined for the 10 N applied force, 1.2 m/s sliding speed, and sliding distances up to 750 m. Experimental findings indicate that Al2O3 reinforcement with semi-solid dual slurry effects give outstanding resistance against the adhesive wear. Microstructure, EDS, and XRD results from worn surface evaluation all show evidence of protective layers, which helps explain the reason for the rate of wear decreased due to processing. In this experiment, LM6 serves as the matrix material and Al2O3 as reinforcement. Al2O3–LM6 semi-solid cast composite was created via a dual mixed slurry technique with temperature control close to the solidus line for varying compositions. This work reports a substantial relationship between metallurgical and mechanical parameters. Mechanical properties and wear characteristics have been investigated. [ABSTRACT FROM AUTHOR]

En l'última dècada, la traducció automàtica (TA) ha augmentat la seva presència no només en el sector de la traducció sinó també en el conjunt de la societat, en part pels bons resultats de qualitat obtinguts per la traducció automàtica neuronal (TAN). Actualment, els models massius de llenguatge (MML) com ara GPT (Generic Pre-trained Transformer) poden generar text sobre una infinitat de temes diferents i també traduir documents tenint en compte un context més ampli. Tot i així, per a idiomes estretament relacionats, com ara l'espanyol i el català, la traducció automàtica basada en regles (TABR) s'utilitza diàriament per traduir milers de paraules. Aquest article estudia la TAN, TABR i GPT del castellà al català, dues llengües romàniques amb una estructura molt semblant en les quals els sistemes de TABR han demostrat un bon rendiment. Utilitzem un challenge test set centrat en la resolució d'anàfores, específicament els pronoms febles, un grup de pronoms que no tenen una correlació directa entre les dues llengües. Com que els models de TABR només tenen en compte la informació a nivell de frase, només estudiem les aparicions intraoracionals. L'objectiu és avaluar un fenomen sintàctic complex que ens pot ajudar a entendre quin dels tres sistemes tradueix més bé els elements contextuals. Els resultats mostren que els dos models GPT provats són els que produeixen el nombre més baix d'errors, seguit dels sistemes de TAN. Tot i així, el nombre de traduccions errònies en el millor sistema és del 47%, cosa que contrasta amb els bons resultats d'avaluació generals que s'obtenen per a aquest parell de llengües.

A mantra often repeated in the introductory material to psychometrics and Item Response Theory (IRT) is that a Rasch model is a probabilistic version of a Guttman scale. The idea comes from the observation that a sigmoidal item response function provides a probabilistic version of the characteristic function that models an item response in the Guttman scale. It appears, however, more difficult to reconcile the assumption of local independence, which traditionally accompanies the Rasch model, with the item dependence existing in a Guttman scale. In recent work, an alternative probabilistic version of a Guttman scale was proposed, combining Knowledge Space Theory (KST) with IRT modeling, here referred to as KST-IRT. The present work has, therefore, a two-fold aim. Firstly, the estimation of the parameters involved in KST-IRT models is discussed. More in detail, two estimation methods based on the Expectation Maximization (EM) procedure are suggested, i.e., Marginal Maximum Likelihood (MML) and Gibbs sampling, and are compared on the basis of simulation studies. Secondly, for a Guttman scale, the estimates of the KST-IRT models are compared with those of the traditional combination of the Rasch model plus local independence under the interchange of the data generation processes. Results show that the KST-IRT approach might be more effective in capturing local dependence as it appears to be more robust under misspecification of the data generation process, but it comes with the price of an increased number of parameters.

A mantra often repeated in the introductory material to psychometrics and Item Response Theory (IRT) is that a Rasch model is a probabilistic version of a Guttman scale. The idea comes from the observation that a sigmoidal item response function provides a probabilistic version of the characteristic function that models an item response in the Guttman scale. It appears, however, more difficult to reconcile the assumption of local independence, which traditionally accompanies the Rasch model, with the item dependence existing in a Guttman scale. In recent work, an alternative probabilistic version of a Guttman scale was proposed, combining Knowledge Space Theory (KST) with IRT modeling, here referred to as KST-IRT. The present work has, therefore, a two-fold aim. Firstly, the estimation of the parameters involved in KST-IRT models is discussed. More in detail, two estimation methods based on the Expectation Maximization (EM) procedure are suggested, i.e., Marginal Maximum Likelihood (MML) and Gibbs sampling, and are compared on the basis of simulation studies. Secondly, for a Guttman scale, the estimates of the KST-IRT models are compared with those of the traditional combination of the Rasch model plus local independence under the interchange of the data generation processes. Results show that the KST-IRT approach might be more effective in capturing local dependence as it appears to be more robust under misspecification of the data generation process, but it comes with the price of an increased number of parameters. [ABSTRACT FROM AUTHOR]

Ti-6Al-4V (an α + β titanium alloy) pins were slid against the SS316L disc in a pin-on-disc apparatus at different temperatures under vacuum and ambient conditions. Tribological characterization was performed using a field emission scanning electron microscope (FESEM) equipped with energy dispersive X-ray (EDAX) analysis and X-ray diffraction. The worn pin surfaces of Ti-6Al-4V were investigated in order to identify the effect of frictional heating at the interface of tribo-pair. To investigate the effects of frictional heating on mechanically mixed layer (MML), experiments were performed under vacuum conditions (2 × 1 0 − 4 Torr) by varying the temperature from 25°C to 400°C at a constant sliding speed of 0.01 ms − 1 and at constant normal load of 137 N. The material was found to transfer from the counter-face to the worn pin surface of alloy where an MML and tribo-oxide (TO) layer were observed to developed on the worn pin surfaces under both the experimental environments. Moreover, a new mechanism, called the "debris burial mechanism" during the formation of the MML at different temperatures was obtained at the interface. The rate of wear was observed to decreased with the increase in frictional heating at the interface resulting to the progressive formation of thicker MML over the worn pin surface. The wear resistances in Ti–6Al–4V alloy decrease rapidly due to loosening the generated MML on the sliding surface. [ABSTRACT FROM AUTHOR]

The emergence of the novel severe acute respiratory syndrome Coronavirus 2 (SARS-CoV-2) rapidly evolved into a worldwide pandemic of Coronavirus Disease 2019 (COVID-19). The pandemic had a major operational impact upon the US military, requiring interventions to mitigate transmission risk resulting in DoD-wide disruption of daily operations, restriction of movement, and delays in training. Development of a rapid mobile COVID-19 testing strategy was pursued as a means to allow service members to complete critical missions in select settings. In this report, we describe the first of its kind mobile medical laboratory (MML) that allowed for testing of approximately 4,000 soldiers of the 1/34th Armored Brigade Combat Team (1/34th ABCT), 34th Infantry Division, prior to deployment for validation exercises to the National Training Center, Fort Irwin, CA. We describe the utilizing of the MML, COVID-19 testing workflow, clinical symptom data/cycle threshold (Ct) data from positive patients, and outcomes from this testing mission. [ABSTRACT FROM AUTHOR]

Mechanical stir casting is utilized to produce an artificially aged Al-Si-Mg alloy, whereas halide slat (K2TiF6 and KBF4) synthesis is utilized to produce Al-Si-Mg/TiB2 aluminum matrix composites. The dry sliding pin on disc wear test was conducted using a DUCOM/TR-20LE-PHM-200 machine to simulate an automobile application (Piston-Ring assembly). Where pistons are made of aluminum alloy (for the Pin) and rings are made of grey cast iron (for the disc material). At room temperature, a wear test was conducted by altering the ageing time (3, 6, 9, 12), sliding speed (2, 2.5 m/s), and applied load (14.71, 19.62, 24.52 N) with the disc speed (500 rpm) held constant (10 min). The results indicate that the aluminum matrix composite (AMC) wear rate is reduced by 37 percent at higher sliding speeds (2.5 m/s) and by 4 percent at lower sliding speeds (2.0 m/s) compared to the base alloy. Field emission scanning electron microscope-energy dispersive spectroscopy (FESEM-EDS) and X-ray photoelectron spectroscopy (XPS) analysis revealed that the formation of the mechanically mixed layer (MML) or oxidative layers on the worn surfaces reduces the wear rate under conditions of longer ageing time, higher sliding speed, and lower applied load. The research demonstrates that composite wear is a function of sliding velocity, aging period, and applied force. As sliding speed rose from 2 m/s to 2.5 m/s, the wear rate of composites dropped reasonably, yet composites are softer than basic alloys. It is conceivable due to the presence of a considerable amount of MML and the formation of oxidative layers between pins and their equivalents. [ABSTRACT FROM AUTHOR]

Mechanical stir casting is utilized to produce an artificially aged Al-Si-Mg alloy, whereas halide slat (K2TiF6 and KBF4) synthesis is utilized to produce Al-Si-Mg/TiB2 aluminum matrix composites. The dry sliding pin on disc wear test was conducted using a DUCOM/TR-20LE-PHM-200 machine to simulate an automobile application (Piston-Ring assembly). Where pistons are made of aluminum alloy (for the Pin) and rings are made of grey cast iron (for the disc material). At room temperature, a wear test was conducted by altering the ageing time (3, 6, 9, 12), sliding speed (2, 2.5 m/s), and applied load (14.71, 19.62, 24.52 N) with the disc speed (500 rpm) held constant (10 min). The results indicate that the aluminum matrix composite (AMC) wear rate is reduced by 37 percent at higher sliding speeds (2.5 m/s) and by 4 percent at lower sliding speeds (2.0 m/s) compared to the base alloy. Field emission scanning electron microscope-energy dispersive spectroscopy (FESEM-EDS) and X-ray photoelectron spectroscopy (XPS) analysis revealed that the formation of the mechanically mixed layer (MML) or oxidative layers on the worn surfaces reduces the wear rate under conditions of longer ageing time, higher sliding speed, and lower applied load. The research demonstrates that composite wear is a function of sliding velocity, aging period, and applied force. As sliding speed rose from 2 m/s to 2.5 m/s, the wear rate of composites dropped reasonably, yet composites are softer than basic alloys. It is conceivable due to the presence of a considerable amount of MML and the formation of oxidative layers between pins and their equivalents. [ABSTRACT FROM AUTHOR]

Background: Tetraploid cotton plants serve as prime natural fiber source for the textile industry. Although various omics studies have revealed molecular basis for fiber development, a better understanding of transcriptional regulation mechanism regulating lint fiber initiation is necessary to meet global natural fiber demand. Results: Here, we aimed to perform transcriptome sequencing to identify DEGs (differentially expressed genes) in ovules of the cotton variety Xu142 and its fibreless mutant Xu142fl during early lint fiber initiation period. Totally, 5516 DEGs including 1840 upregulated and 3676 downregulated were identified. GO enrichment analysis revealed that the downregulated DEGs were mainly associated with biological processes such as transcription related biosynthesis and metabolism, organic cyclic compound biosynthesis and metabolism, photosynthesis, and plant cell wall organization, with molecular functions involving transcription related binding, organic cyclic compound binding, and dioxygenase activity, while the upregulated DEGs were associated with DNA replication and phospholipid biosynthetic related processes. Among the 490 DEGs annotated as transcription factor genes, 86.5% were downregulated in the mutant including the Malvaceae-specific MMLs, expression patterns of which were confirmed during the central period of lint fiber initiation. Investigation of the 16 genes enriched in the cell wall organization revealed that 15 were EXPA coding genes. Conclusions: Overall, our data indicate that lint fiber initiation is a complicated process involving cooperation of multiple transcription factor families, which might ultimately lead to the reorganization of the cell wall and terminated cell division of the differentiating fiber initials. [ABSTRACT FROM AUTHOR]

Mechanical and tribological investigation of obtained nanocomposites is presented in this paper. As matrix material, well known tribological zinc-aluminium alloy, ZA-27 was used. Nanocomposites were obtained by compocasting procedure, while as reinforcement Al2O3 nanoparticles with average size of 20-30 nm was used. Nanocomposites with three different volume fractions were obtained. In order to get insight in structure and mechanical properties of obtained nanocomposites density and hardness measurements were performed. Tribological properties of tested materials were investigated using block-on-disc tribometer in dry sliding conditions with variation three different values of sliding speed and normal load. Wear tracks that were generated as a result of dry sliding process were analysed using optical and scanning electron with EDS microscope.

This article presents a short research report on the relationship between perceived antagonism in social relations measured using the Belief in a Zero-Sum Game (BZSG) scale, life satisfaction, and positive and negative affect. Given that individuals who believe that life is like a zero-sum game are likely to perceive their daily interactions with others as unfair, we expected that individuals with high BZSG experience more negative affect and fewer positive one, resulting in a lower satisfaction with life. In addition, we examined whether country-level BZSG may play a moderating role in these associations. Data were collected from student samples (N = 7146) in 35 countries. Multilevel modelling revealed that perceived social antagonism in social relations is negatively associated with satisfaction with life and that this relationship is mediated by both positive and negative affect at the individual level. The relation of individual BZSG and negative affect on satisfaction with life were weaker in societies with higher country-level BZSG, suggesting that the effects of BZSG may be less detrimental in these countries. These findings extend previous knowledge about predictors of life satisfaction and suggest that social beliefs might also be an important factor that influences subjective well-being. The contribution of the study is that the separate treatment of life satisfaction and positive and negative affect may be helpful in many research situations, particularly from a cross-cultural perspective. [ABSTRACT FROM AUTHOR]

The multinomial distribution has been widely used to model count data. To increase clustering efficiency, we use an approximation to the Fisher scoring algorithm, which is more robust regarding the choice of initial parameter values. Then, we use a novel approach to estimate the optimal number of components, based on minimum message length criterion. Moreover, we consider a generalization of the multinomial model obtained by introducing the Dirichlet as prior, yielding the Dirichlet Compound Multinomial (DCM). Even though DCM can address the burstiness phenomenon of count data, the presence of Gamma function in its density function usually leads to undesired complications. In this article, we use two alternative representations of DCM distribution to perform clustering based on finite mixture models, where the mixture parameters are estimated using the minorization–maximization framework. To evaluate and compare the performance of our proposed models, we have considered three challenging real‐world applications that involve high‐dimensional count vectors, namely, sentiment analysis, facial expression recognition, and human action recognition. The results show that the proposed algorithms increase the clustering efficiency of their respective models remarkably, and the best results are achieved by the second parametrization of DCM, which can accommodate over‐dispersed count data. [ABSTRACT FROM AUTHOR]

Medical Markup Language (MML) is a standard format for exchange of healthcare data among healthcare providers. Following the last major update (version 3), we developed new modules and discussed the requirements for the next major updates. Subsequently, in 2016 we released MML version 4 and used it to obtain clinical data from healthcare providers for a nationwide electronic health records (EHR) system. In this article we provide an overview of this major update of MML version 4 and discuss its interoperability for clinical data. [ABSTRACT FROM AUTHOR]

Strict Minimum Message Length (SMML) is an information-theoretic statistical inference method widely cited (but only with informal arguments) as providing estimations that are consistent for general estimation problems. It is, however, almost invariably intractable to compute, for which reason only approximations of it (known as MML algorithms) are ever used in practice. Using novel techniques that allow for the first time direct, non-approximated analysis of SMML solutions, we investigate the Neyman-Scott estimation problem, an oft-cited showcase for the consistency of MML, and show that even with a natural choice of prior neither SMML nor its popular approximations are consistent for it, thereby providing a counterexample to the general claim. This is the first known explicit construction of an SMML solution for a natural, high-dimensional problem. [ABSTRACT FROM AUTHOR]

Abstract Manufacturing industry is an important part of economic development. Recognizing the sustainable development of regional manufacturing has an important guiding role in the formulation of environmental policies. Based on the meta-frontier Malmquist-Luenberger (MML) productivity index, this paper uses Chinese provincial panel data (2003–2015) to measure the green total factor productivity (TFP) of China's manufacturing. It is decomposed into the following: efficiency change (EC), change of the best practice gap ratio (BPC) and change of technical gap ratio (TGC). We compared the regional differences in green TFP growth in manufacturing in all provinces, analyzed regional and time differences in green TFP and the decomposition of manufacturing between regions and identified innovative regions. The results show that: (1) The average annual growth rate of green TFP in Chinese manufacturing is 0.85% with technological progress playing a key role. (2) There are differences in the causes of the increase in green TFP in all regions. The eastern region and the western region are driven by technological progress while the central region depends on technology catch-up effects. (3) Guangdong and Qinghai are two different types of global innovation regions with Guangdong driven by technological innovation and Qinghai driven by strict environmental protection systems. [ABSTRACT FROM AUTHOR]

EDCM, the Exponential-family approximation to the Dirichlet Compound Multinomial (DCM), proposed by Elkan (2006), is an efficient statistical model for high-dimensional and sparse count data. EDCM models take into account the burstiness phenomenon correctly while being many times faster than DCM. This work proposes the use of Minimum Message Length (MML) criterion for determining the number of components that best describes the data with a finite EDCM mixture model. Parameters estimation is based on the previously proposed Deterministic Annealing Expectation-Maximization (DAEM) approach. The validation of the proposed unsupervised algorithm involves different real applications: text document modeling, topic novelty detection and hierarchical image clustering. A comparison with results obtained for other information-theory based selection criteria is provided. [ABSTRACT FROM AUTHOR]

Although considerable developments have been added to the cognitive diagnosis modeling literature recently, most have been conducted for dichotomous responses only. This research proposes a general cognitive diagnosis model for polytomous responses—the general polytomous diagnosis model (GPDM), which combines the G-DINA modeling process for dichotomous responses with the item-splitting process for polytomous responses. The polytomous items are specified similar to dichotomous items in the Q-matrix, and the MML estimation is implemented using an EM algorithm. Under the general framework, different saturated forms, and some reduced forms, can be transformed linearly. Model assessment and adjustment under the dichotomous context can be extended to polytomous responses. This simulation study demonstrates the effectiveness of the model when comparing the two response types. The real-data example further illustrates how the proposed model can make a difference in practice.

Although considerable developments have been added to the cognitive diagnosis modeling literature recently, most have been conducted for dichotomous responses only. This research proposes a general cognitive diagnosis model for polytomous responses—the general polytomous diagnosis model (GPDM), which combines the G-DINA modeling process for dichotomous responses with the item-splitting process for polytomous responses. The polytomous items are specified similar to dichotomous items in the Q-matrix, and the MML estimation is implemented using an EM algorithm. Under the general framework, different saturated forms, and some reduced forms, can be transformed linearly. Model assessment and adjustment under the dichotomous context can be extended to polytomous responses. This simulation study demonstrates the effectiveness of the model when comparing the two response types. The real-data example further illustrates how the proposed model can make a difference in practice. [ABSTRACT FROM AUTHOR]

Anodizing is a widely used method for increasing the wear and corrosion resistance of aluminum alloys. However, it is known that the porous brittle alumina layer can easily crack during tribological stresses, which results in the detachment of large particles from the worn surface. Electroplating, on the other hand, can produce a compact ductile metallic coating with enough wear resistance, though a specific pretreatment like the zincate process is needed for an aluminum substrate. In this paper, a combination of the two methods, anodizing and electroplating, is applied on the surface of pure aluminum intending to improve the wear resistance. Anodizing was performed in oxalic acid by applying a constant current density of 2 A/dm2. The anodized samples were then immersed in phosphoric acid for up to 10 h to increase the diameter of the pores. Nickel electroplating was carried out on the anodized samples at a current density of 0.5 A/dm2 in a Watts solution. Cross-sectional studies show that there is an optimum pore widening time that establishes a good adhesion between nickel and anodic oxide layers, while the structure of the oxide film is largely preserved. Sliding wear tests were performed on the samples using a ball-on-disk reciprocating tribometer. The results show much higher wear life for all Ni/Al 2 O 3 composite coatings as compared with the alumina layer. The maximum wear life was obtained for the sample etched for an optimum pore widening time of 4 h. • Nickel was electrodeposited on the surface of the anodized aluminum samples. • The coefficient of friction trend was analyzed through wear surface and subsurface studies. • Nickel plating largely improves the wear life of the anodized aluminum. • The coefficient of friction was reduced once the coatings were tribologically damaged. • Alumina and nickel fragments and the aluminum substrate were mechanically mixed to form an MML. [ABSTRACT FROM AUTHOR]

This paper presents basic tribological properties of A356/10SiC/1Gr hybrid composites in conditions with lubrication. Hybrid composite specimen is obtained by compocasting procedure. A356 aluminium alloy is used as a base matrix alloy, reinforced with 10wt% of SiC and 1wt% of graphite. Tribological tests are done on advanced and computer supported tribometer with block‐on‐ disc contact pair. By the experimental plan, test is conducted under three different values of sliding speed, three different values of normal load, different sliding distances, and also different lubricants. SEM and EDS are used for wear analysis. The analysis has shown the presence of MML, which means that there was transfer of material from steel disc to composite block.

This study compared several parameter estimation methods for multi-unidimensional graded response models using their corresponding statistical software programs and packages. Specifically, we compared two marginal maximum likelihood (MML) approaches (Bock-Aitkin expectation-maximum algorithm, adaptive quadrature approach), four fully Bayesian algorithms (Gibbs sampling, Metropolis-Hastings, Hastings-within-Gibbs, blocked Metropolis), and the Metropolis-Hastings Robbins-Monro (MHRM) algorithm via the use of IRTPRO, BMIRT, and MATLAB. Simulation results suggested that, when the intertrait correlation was low, these estimation methods provided similar results. However, if the dimensions were moderately or highly correlated, Hastings-within-Gibbs had an overall better parameter recovery of item discrimination and intertrait correlation parameters. The performances of these estimation methods with different sample sizes and test lengths are also discussed. [ABSTRACT FROM AUTHOR]

Marginal maximum likelihood estimation based on the expectation–maximization algorithm (MML/EM) is developed for the one-parameter logistic model with ability-based guessing (1PL-AG) item response theory (IRT) model. The use of the MML/EM estimator is cross-validated with estimates from NLMIXED procedure (PROC NLMIXED) in Statistical Analysis System. Numerical data are provided for comparisons of results from MML/EM and PROC NLMIXED. [ABSTRACT FROM AUTHOR]

Highlights: [•] We develop a method for learning the parameters of multidimensional asymmetric generalized Gaussian mixtures (AGGM). [•] We describe and illustrate an online algorithm, based on the developed AGGM, for pedestrian detection using infrared images. [•] We implement a multiple-target tracking (MTT) framework using AGGM. [•] We demonstrate the importance of the fusion of both visible and thermal images for MTT. [ABSTRACT FROM AUTHOR]

Abstract: Inherently complex problems from many scientific disciplines require a multiscale modeling approach. Yet its practical contents remain unclear and inconsistent. Moreover, multiscale models can be very computationally expensive, and may have potential to be executed on distributed infrastructure. In this paper we propose firm foundations for multiscale modeling and distributed multiscale computing. Useful interaction patterns of multiscale models are made predictable with a submodel execution loop (SEL), four coupling templates, and coupling topology properties. We enhance a high-level and well-defined Multiscale Modeling Language (MML) that describes and specifies multiscale models and their computational architecture in a modular way. The architecture is analyzed using directed acyclic task graphs, facilitating validity checking, scheduling distributed computing resources, estimating computational costs, and predicting deadlocks. Distributed execution using the multiscale coupling library and environment (MUSCLE) is outlined. The methodology is applied to two selected applications in nanotechnology and biophysics, showing its capabilities. [Copyright &y& Elsevier]