Search

Mediation analysis is widely used to study whether the effect of an independent variable on an outcome is transmitted through a mediator. Bayesian methods have become increasingly popular for mediation analysis. However, limited research has been done on formal Bayesian hypothesis testing of mediation. Although hypothesis testing using Bayes factor for a single path is readily available, how to integrate the Bayes factors of two paths (from input to mediator and from mediator to outcome) while incorporating prior beliefs on the two paths and/or mediation is under-studied. In the current study, we propose a general approach to Bayesian hypothesis testing of mediation. The proposed approach allows researchers to specify prior odds based on the substantive research context and can be used in mediation modeling with latent variables. The impact of prior odds specifications on Bayesian hypothesis test of mediation is demonstrated via both real and hypothetical data examples. Both R functions and a user-friendly R web app are provided for the implementation of the proposed approach. Our study can add to researchers' toolbox of mediation analysis and raise researchers' awareness of the importance of prior odds specifications in Bayesian hypothesis testing of mediation. [This is the online version of an article published in "Behavioral Research Methods."]

We present quantum algorithms, for Hamiltonians of linear combinations of local unitary operators, for Hamiltonian matrix-vector products and for preconditioning with the inverse of shifted reduced Hamiltonian operator that contributes to the diagonal matrix elements only. The algorithms implement a convergent series of approximations towards the exact solution of the full CI (configuration interaction) problem. The algorithm scales with O(m^5 ), with m the number of one-electron orbitals in the case of molecular electronic structure calculations. Full CI results can be obtained with a scaling of O(nm^5 ), with n the number of electrons and a prefactor on the order of 10 to 20. With low orders of Hamiltonian matrix-vector products, a whole repertoire of approximations widely used in modern electronic structure theory, including various orders of perturbation theory and/or truncated CI at different orders of excitations can be implemented for quantum computing for both routine and benchmark results at chemical accuracy. The lowest order matrix-vector product with preconditioning, basically the second-order perturbation theory, is expected to be a leading algorithm for demonstrating quantum supremacy for Ab Initio simulations, one of the most anticipated real world applications. The algorithm is also applicable for the hybrid variational quantum eigensolver.

End-to-end Spoken Language Understanding (SLU) models are made increasingly large and complex to achieve the state-ofthe-art accuracy. However, the increased complexity of a model can also introduce high risk of over-fitting, which is a major challenge in SLU tasks due to the limitation of available data. In this paper, we propose an attention-based SLU model together with three encoder enhancement strategies to overcome data sparsity challenge. The first strategy focuses on the transferlearning approach to improve feature extraction capability of the encoder. It is implemented by pre-training the encoder component with a quantity of Automatic Speech Recognition annotated data relying on the standard Transformer architecture and then fine-tuning the SLU model with a small amount of target labelled data. The second strategy adopts multitask learning strategy, the SLU model integrates the speech recognition model by sharing the same underlying encoder, such that improving robustness and generalization ability. The third strategy, learning from Component Fusion (CF) idea, involves a Bidirectional Encoder Representation from Transformer (BERT) model and aims to boost the capability of the decoder with an auxiliary network. It hence reduces the risk of over-fitting and augments the ability of the underlying encoder, indirectly. Experiments on the FluentAI dataset show that cross-language transfer learning and multi-task strategies have been improved by up to 4:52% and 3:89% respectively, compared to the baseline., Comment: will be presented in INTERSPEECH 2020

The major scientific goals of DArk Matter Particle Explorer (DAMPE) are to study cosmic-ray electrons (including positrons) and gamma rays from 5 GeV to 10 TeV and nuclei from Z = 1 to 26 up to 100 TeV. The deposited energy measured by the Bismuth Germanate Oxide (BGO) calorimeter of DAMPE is affected by fluorescence attenuation in BGO crystals that are 600 mm long. In this work, an in-orbit attenuation calibration method is reported, and energy correction of the sensitive detector unit of the BGO calorimeter is also presented.

This paper proposes a new two-stage network mediation method based on the use of a latent network approach -- model-based eigenvalue decomposition -- for analyzing social network data with nodal covariates. In the decomposition stage of the observed network, no assumption on the metric of the latent space structure is required. In the mediation stage, the most important eigenvectors of a network are used as mediators. This method further offers an innovative way for controlling for the conditional covariates and it only considers the information left in the network. We demonstrate this approach in a detailed tutorial R code provided for four separate cases -- unconditional and conditional model-based eigenvalue decompositions for either a continuous outcome or a binary outcome -- to show its applicability to empirical network data.

Reducing the lateral scale of two-dimensional (2D) materials to one-dimensional (1D) has attracted substantial research interest not only to achieve competitive electronic device applications but also for the exploration of fundamental physical properties. Controllable synthesis of high-quality 1D nanoribbons (NRs) is thus highly desirable and essential for the further study. Traditional exploration of the optimal synthesis conditions of novel materials is based on the trial-and-error approach, which is time consuming, costly and laborious. Recently, machine learning (ML) has demonstrated promising capability in guiding material synthesis through effectively learning from the past data and then making recommendations. Here, we report the implementation of supervised ML for the chemical vapor deposition (CVD) synthesis of high-quality 1D few-layered WTe2 nanoribbons (NRs). The synthesis parameters of the WTe2 NRs are optimized by the trained ML model. On top of that, the growth mechanism of as-synthesized 1T' few-layered WTe2 NRs is further proposed, which may inspire the growth strategies for other 1D nanostructures. Our findings suggest that ML is a powerful and efficient approach to aid the synthesis of 1D nanostructures, opening up new opportunities for intelligent material development.

Differential and angle-integrated cross sections for the $^{10}$B($n, {\alpha}$)$^{7}$Li, $^{10}$B($n, {\alpha}$$_{0}$)$^{7}$Li and $^{10}$B($n, {\alpha}$$_{1}$)$^{7}$Li$^{*}$ reactions have been measured at CSNS Back-n white neutron source. Two enriched (90%) $^{10}$B samples 5.0 cm in diameter and ~85.0 ${\mu}$g/cm$^{2}$ in thickness each with an aluminum backing were prepared, and back-to-back mounted at the sample holder. The charged particles were detected using the silicon-detector array of the Light-charged Particle Detector Array (LPDA) system. The neutron energy E$_{n}$ was determined by TOF (time-of-flight) method, and the valid ${\alpha}$ events were extracted from the E$_{n}$-Amplitude two-dimensional spectrum. With 15 silicon detectors, the differential cross sections of ${\alpha}$-particles were measured from 19.2{\deg} to 160.8{\deg}. Fitted with the Legendre polynomial series, the ($n, {\alpha}$) cross sections were obtained through integration. The absolute cross sections were normalized using the standard cross sections of the $^{10}$B($n, {\alpha}$)$^{7}$Li reaction in the 0.3 - 0.5 MeV neutron energy region. The measurement neutron energy range for the $^{10}$B($n, {\alpha}$)$^{7}$Li reaction is 1.0 eV $\le$ En < 2.5 MeV (67 energy points), and for the $^{10}$B($n, {\alpha}$$_{0}$)$^{7}$Li and $^{10}$B($n, {\alpha}$$_{1}$)$^{7}$Li$^{*}$ reactions is 1.0 eV $\le$ En < 1.0 MeV (59 energy points). The present results have been analyzed by the resonance reaction mechanism and the level structure of the $^{11}$B compound system, and compared with existing measurements and evaluations., Comment: 19 pages, 34 figures, to be published in Chinese Physics C

For manufacturing Micromegas detectors, the "bulk" method based on photoetching, was successfully developed and widely used in nuclear and particle physics experiments. However, the complexity of the method requires a considerable number of advanced instruments and processing, limiting the accessibility of this method for production of Micromegas detectors. In view of these limitations with the bulk method, a new method based on thermal bonding technique (TBM) has been developed to manufacture Micromegas detectors in a much simplified and efficient way without etching. This paper describes the TBM in detail and presents performance of the Micromegas detectors built with the TBM. The effectiveness of this method was investigated by testing Micromegas detector prototypes built with the method. Both X-rays and electron beams were used to characterize the prototypes in a gas mixture of argon and CO2 (7%). A typical energy resolution of ~16% (full width at half maximum, FWHM) and an absolute gain greater than 10^4 were obtained with 5.9 keV X-rays. Detection efficiency greater than 98% and a spatial resolution of ~65 {\mu}m were achieved using a 5 GeV electron beam at the DESY test-beam facility. The gas gain of a Micromegas detector could reach up to 10^5 with a uniformity of better than 10% when the size of the avalanche gap was optimized thanks to the flexibility of the TBM in defining the gap. Additionally, the TBM facilitates the exploration of new detector structures based on Micromegas owing to the much-simplified operation with the method., Comment: 15 pages, 17 figures

Structural equation modeling (SEM) is a widely used technique for studies involving latent constructs. While covariance-based SEM (CB-SEM) permits estimating the regression relationship among latent constructs, the parameters governing this relationship do not apply to that among the scored values of the constructs, which are needed for prediction, classification and/or diagnosis of individuals/participants. In contrast, the partial-least squares approach to SEM (PLS-SEM) first obtains weighted composites for each case and then estimates the structural relationship among the composites. Consequently, PLS-SEM is a preferred method in predicting and/or classifying individuals. Nevertheless, properties of PLS-SEM still depend on how the composites are formulated. Herman Wold proposed to use mode A to compute the scores for constructs with reflective indicators. However, Yuan and Deng recently showed that composites under mode B enjoy better psychometric properties. The authors thus proposed a structured transformation from mode A to mode B, denoted as mode BA. This chapter further studies properties of the three modes of PLS SEM. Analytical and numerical results show that 1) Mode A does not possess any solid statistical or psychometric properties, 2) Mode B possesses good theoretical properties but is over sensitive to sampling errors, and 3) Mode BA possesses good theoretical properties as well as numerical stability. The performances of the three modes are also illustrated with two real data examples. [This chapter was published in: "Partial least squares path modeling: Basic concepts, methodological issues, and applications, 2nd edition," edited by H. Latan et al., Springer.]