Search

Recent advances in electron, scanning probe, optical, and chemical imaging and spectroscopy yield bespoke data sets containing the information of structure and functionality of complex systems. In many cases, the resulting data sets are underpinned by low-dimensional simple representations encoding the factors of variability within the data. The representation learning methods seek to discover these factors of variability, ideally further connecting them with relevant physical mechanisms. However, generally, the task of identifying the latent variables corresponding to actual physical mechanisms is extremely complex. Here, we present an empirical study of an approach based on conditioning the data on the known (continuous) physical parameters and systematically compare it with the previously introduced approach based on the invariant variational autoencoders. The conditional variational autoencoder (cVAE) approach does not rely on the existence of the invariant transforms and hence allows for much greater flexibility and applicability. Interestingly, cVAE allows for limited extrapolation outside of the original domain of the conditional variable. However, this extrapolation is limited compared to the cases when true physical mechanisms are known, and the physical factor of variability can be disentangled in full. We further show that introducing the known conditioning results in the simplification of the latent distribution if the conditioning vector is correlated with the factor of variability in the data, thus allowing us to separate relevant physical factors. We initially demonstrate this approach using 1D and 2D examples on a synthetic data set and then extend it to the analysis of experimental data on ferroelectric domain dynamics visualized via piezoresponse force microscopy. [ABSTRACT FROM AUTHOR]

Time-domain spectroscopy encompasses a wide range of techniques, such as Fourier-transform infrared, pump–probe, Fourier-transform Raman, and two-dimensional electronic spectroscopies. These methods enable various applications, such as molecule characterization, excited state dynamics studies, or spectral classification. Typically, these techniques rarely use sampling schemes that exploit the prior knowledge scientists typically have before the actual experiment. Indeed, not all sampling coordinates carry the same amount of information, and a careful selection of the sampling points may notably affect the resulting performance. In this work, we rationalize, with examples, the various advantages of using an optimal sampling scheme tailored to the specific experimental characteristics and/or expected results. We show that using a sampling scheme optimizing the Fisher information minimizes the variance of the desired parameters. This can greatly improve, for example, spectral classifications and multidimensional spectroscopy. We demonstrate how smart sampling may reduce the acquisition time of an experiment by one to two orders of magnitude, while still providing a similar level of information. [ABSTRACT FROM AUTHOR]

We present a novel approach for systematically exploring the conformational space of small molecules with multiple internal torsions. Identifying unique conformers through a systematic conformational search is important for obtaining accurate thermodynamic functions (e.g., free energy), encompassing contributions from the ensemble of all local minima. Traditional geometry optimizers focus on one structure at a time, lacking transferability from the local potential-energy surface (PES) around a specific minimum to optimize other conformers. In this work, we introduce a physics-driven meta-Gaussian processes (meta-GPs) method that not only enables efficient exploration of target PES for locating local minima but, critically, incorporates physical surrogates that can be applied universally across the optimization of all conformers of the same molecule. Meta-GPs construct surrogate PESs based on the optimization history of prior conformers, dynamically selecting the most suitable prior mean function (representing prior knowledge in Bayesian learning) as a function of the optimization progress. We systematically benchmarked the performance of multiple GP variants for brute-force conformational search of amino acids. Our findings highlight the superior performance of meta-GPs in terms of efficiency, comprehensiveness of conformer discovery, and the distribution of conformers compared to conventional non-surrogate optimizers and other non-meta-GPs. Furthermore, we demonstrate that by concurrently optimizing, training GPs on the fly, and learning PESs, meta-GPs exhibit the capacity to generate high-quality PESs in the torsional space without extensive training data. This represents a promising avenue for physics-based transfer learning via meta-GPs with adaptive priors in exploring torsional conformer space. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a novel dual inertial Tseng's extragradient method for solving variational inequality problems in real Hilbert spaces, particularly those involving pseudomonotone and Lipschitz continuous operators. Our secondary method incorporates variable step‐size, updated at each iteration based on some previous iterates. A notable advantage of these algorithms is their ability to operate without prior knowledge of Lipschitz‐type constants and without the need for any line‐search procedure. We establish the convergence theorem of the proposed algorithms under mild assumptions. To illustrate the numerical behavior of the algorithms and to make comparisons with other methods, we conduct several numerical experiments. The results of these evaluations are showcased and thoroughly examined to exemplify the practical significance and effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

We present a versatile and robust framework to render implicit surfaces defined by black‐box functions that only provide function value queries. We assume that the input function is locally Lipschitz continuous; however, we presume no prior knowledge of its Lipschitz constants. Our pre‐processing step generates a discrete acceleration structure, a Lipschitz field, that provides data to infer local and directional Lipschitz upper bounds. These bounds are used to compute safe step sizes along rays during rendering. The Lipschitz field is constructed by generating local polynomial approximations to the input function, then bounding the derivatives of the approximating polynomials. The accuracy of the approximation is controlled by the polynomial degree and the granularity of the spatial resolution used during fitting, which is independent from the resolution of the Lipschitz field. We demonstrate that our process can be implemented in a massively parallel way, enabling straightforward integration into interactive and real‐time modelling workflows. Since the construction only requires function value evaluations, the input surface may be represented either procedurally or as an arbitrarily filtered grid of function samples. We query the original implicit representation upon ray trace, as such, we preserve the geometric and topological details of the input as long as the Lipschitz field supplies conservative estimates. We demonstrate our method on both procedural and discrete implicit surfaces and compare its exact and approximate variants. [ABSTRACT FROM AUTHOR]

Interruptions are often pervasive and require attentional shifts from the primary task. Limited data are available on the factors influencing individuals' efficiency in resuming from interruptions during digital reading. The reported investigation--conducted using the InteRead dataset--examined whether individual differences in visuo-spatial working memory capacity (vsWMC) and prior knowledge could influence resumption lag times during interrupted reading. Participants' vsWMC capacity was assessed using the symmetry span (SSPAN) task, while a pre-test questionnaire targeted their background knowledge about the text. While reading an extract from a Sherlock Holmes story, they were interrupted six times and asked to answer an opinion question. Our analyses revealed that the interaction between vsWMC and prior knowledge significantly predicted the time needed to resume reading following an interruption. The results from our analyses are discussed in relation to theoretical frameworks of task resumption and current research in the field. [ABSTRACT FROM AUTHOR]

AbstractIn this paper, we study the transfer learning problem in functional classification, aiming to improve the classification accuracy of the target data by leveraging information from related source datasets. To facilitate transfer learning, we propose a novel transferability function tailored for classification problems, enabling a more accurate evaluation of the similarity between source and target dataset distributions. Interestingly, we find that a source dataset can offer more substantial benefits under certain conditions than another dataset with an identical distribution to the target dataset. This observation renders the commonly-used debiasing step in the parameter-based transfer learning algorithm unnecessary under some circumstances to the classification problem. In particular, we propose two adaptive transfer learning algorithms based on the functional Distance Weighted Discrimination (DWD) classifier for scenarios with and without prior knowledge regarding informative sources. Furthermore, we establish the upper bound on the excess risk of the proposed classifiers, providing the statistical gain via transfer learning mathematically provable. Simulation studies are conducted to thoroughly examine the finite-sample performance of the proposed algorithms. Finally, we implement the proposed method to Beijing air-quality data, and significantly improve the prediction of the PM 2.5 level of a target station by effectively incorporating information from source datasets. [ABSTRACT FROM AUTHOR]

Different process-object frameworks have been used to describe the structure and sequence of acquisition of knowledge about mathematical concepts in the sense that operational (i.e. process-related) knowledge should be acquired before structural (i.e. object-related) knowledge. This approach has previously been used to investigate the structure of knowledge about the concept of derivative from a qualitative perspective. In this article, we apply a process-object framework to investigate the acquisition of knowledge about the concept of derivative quantitatively. Data was collected from N = 176 grade 10/11 students in Germany using a test instrument that has been specifically developed to measure operational and structural knowledge about the concept of derivative. In a second study, interviews were conducted with a selected subsample of the same students to ensure the validity of the test and the compatibility of our items to the theoretical model. Our results show that knowledge about the concept of derivative can be seen as psychometrically two-dimensional reflecting operational and structural aspects of knowledge. Additionally, our results indicate that a majority of students might only have acquired pseudostructural knowledge about the concept of derivative. Lastly, implications for research specifically for the role of prior knowledge are discussed. [ABSTRACT FROM AUTHOR]

With recent advances in multi-color super-resolution light microscopy, it is possible to simultaneously visualize multiple subunits within biological structures at nanometer resolution. To optimally evaluate and interpret spatial proximity of stainings on such an image, colocalization analysis tools have to be able to integrate prior knowledge on the local geometry of the recorded biological complex. We present MultiMatch to analyze the abundance and location of chain-like particle arrangements in multi-color microscopy based on multi-marginal optimal unbalanced transport methodology. Our object-based colocalization model statistically addresses the effect of incomplete labeling efficiencies enabling inference on existent, but not fully observable particle chains. We showcase that MultiMatch is able to consistently recover existing chain structures in three-color STED images of DNA origami nanorulers and outperforms geometry-uninformed triplet colocalization methods in this task. MultiMatch generalizes to an arbitrary number of color channels and is provided as a user-friendly Python package comprising colocalization visualizations. MultiMatch performs geometry-informed colocalization analysis for multi-color microscopy based on multi-marginal optimal unbalanced transport methodology. [ABSTRACT FROM AUTHOR]

In the rapidly evolving field of medical image analysis utilizing artificial intelligence (AI), the selection of appropriate computational models is critical for accurate diagnosis and patient care. This literature review provides a comprehensive comparison of vision transformers (ViTs) and convolutional neural networks (CNNs), the two leading techniques in the field of deep learning in medical imaging. We conducted a survey systematically. Particular attention was given to the robustness, computational efficiency, scalability, and accuracy of these models in handling complex medical datasets. The review incorporates findings from 36 studies and indicates a collective trend that transformer-based models, particularly ViTs, exhibit significant potential in diverse medical imaging tasks, showcasing superior performance when contrasted with conventional CNN models. Additionally, it is evident that pre-training is important for transformer applications. We expect this work to help researchers and practitioners select the most appropriate model for specific medical image analysis tasks, accounting for the current state of the art and future trends in the field. [ABSTRACT FROM AUTHOR]

Integrative analysis has emerged as a prominent tool in biomedical research, offering a solution to the "small n$$ n $$ and large p$$ p $$" challenge. Leveraging the powerful capabilities of deep learning in extracting complex relationship between genes and diseases, our objective in this study is to incorporate deep learning into the framework of integrative analysis. Recognizing the redundancy within candidate features, we introduce a dedicated feature selection layer in the proposed integrative deep learning method. To further improve the performance of feature selection, the rich previous researches are utilized by an ensemble learning method to identify "prior information". This leads to the proposed prior assisted integrative deep learning (PANDA) method. We demonstrate the superiority of the PANDA method through a series of simulation studies, showing its clear advantages over competing approaches in both feature selection and outcome prediction. Finally, a skin cutaneous melanoma (SKCM) dataset is extensively analyzed by the PANDA method to show its practical application. [ABSTRACT FROM AUTHOR]

AbstractRooted in signaling theory and attribution theory, this research investigated how destination social responsibility (DSR) strategy (ability-oriented vs. effort-oriented) impacts residents’ quality of life (QOL) and support for tourism. A mixed-method approach combining semi-structured interviews and scenario-based experiments was conducted. The results revealed that effort-oriented DSR strategies increaseed residents’ QOL and support for tourism more than ability-oriented DSR strategies, in which perceived warmth and communal relationship play a serial mediation effect. Furthermore, the study identifies a key boundary condition: DSR disclosure entity. The relative dominance of effort-oriented DSR strategies weakens when DSR messages are self-disclosed rather than third-party disclosed. These findings advance prior knowledge on DSR and resident QOL and offer destination managers useful guidance on how to adopt DSR strategies to effectively enhance residents’ QOL and support for tourism. Future research could examine a wider range of outcomes, participant groups, and boundary conditions to build on this study’s conclusions. [ABSTRACT FROM AUTHOR]

Atomic‐resolution scanning transmission electron microscopy (STEM) characterization requires precise tilting of the specimen to a high symmetric zone axis, which is usually processed in reciprocal space by following the diffraction patterns. However, for small‐sized nanocrystalline materials, their diffraction patterns are often too faint to guide the tilting process. Here, a simple and effective tilting method is developed based on the diffraction contrast change of the shadow image in the Ronchigram. The misorientation angle of the specimen can be calculated and tilted to the zone axis based on the position of the shadow image with lowest intensity. This method requires no prior knowledge of the sample and the maximum misorientation angle that can be corrected is >±6.9° with sub‐mrad accuracy. It operates in real space, without recording the diffraction patterns of the specimens, making it particularly effective for nanocrystalline materials. Combined with the scripting to control the microscope, the sample can be automatically tilted to the zone axis under low dose conditions (<0.17 e− Å−2 s−1), facilitating the imaging of beam sensitive materials such as zeolites or metal‐organic frameworks. This automated tilting method can significantly contribute to the atomic‐scale characterization of the nanocrystalline materials by STEM imaging. [ABSTRACT FROM AUTHOR]

Time‐lapse images carry out important information about dynamic changes in Earth's interior, which can be inferred using different full waveform inversion schemes. The estimation process is performed by manipulating more than one seismic dataset, associated with the baseline and monitors surveys. The time‐lapse variations can be so minute and localized that quantifying the uncertainties becomes fundamental to assessing the reliability of the results. The Bayesian formulation of the full waveform inversion problem naturally provides confidence levels in the solution, but evaluating the uncertainty of time‐lapse seismic inversion remains a challenge due to the ill‐posedness and high dimensionality of the problem. The Hamiltonian Monte Carlo can effectively sample over high‐dimensional distributions with affordable computational efforts. In this context, we explore the sequential approach in a Bayesian fashion for time‐lapse full waveform inversion using the Hamiltonian Monte Carlo method. The idea relies on integrating the baseline survey information as prior knowledge to the monitor estimation. We compare this methodology with a parallel scheme in perfect and a simple perturbed acquisition geometry scenario considering the Marmousi and a typical Brazilian pre‐salt velocity model. We also investigate the correlation effect between baseline and monitor samples on the propagated uncertainties. The results show that samples between different surveys are weakly correlated in the sequential case, while the parallel strategy provides time‐lapse images with lower dispersion. Our findings demonstrate that both methodologies are robust in providing uncertainties even in non‐repeatable scenarios. [ABSTRACT FROM AUTHOR]

Compositional analysis (CA)—identification and quantification of the system constituents—is the most fundamental and decisive approach for investigating the system of interest. Pyrolysis mass spectrometry (MS) with a high resolution of over 10 000 is very effective for chemical identification and is directly applicable to polymer materials regardless of their solubilities. However, it is less helpful for quantification, especially when the references, i.e., pure constituents, are unknown, non-isolable and thus cannot be prepared. To compensate for this weakness, herein we propose reference-free quantitative mass spectrometry (RQMS) with enhanced quantification accuracy assisted by synchronized thermogravimetry (TG). The key to success lies in correlating the instantaneous weight loss from TG with the MS signal, enabling the quantitative evaluation of the distinct ionization efficiency for each fragment individually. The determined ionization efficiencies allow the conversion of MS signal intensities of pyrolyzed fragments into weight abundances. In a benchmark test using ternary polymer systems, this new framework named TG-RQMS demonstrates accurate CA within ±1.3 wt% errors without using any prior knowledge or spectra of the references. This simple yet accurate and versatile CA method would be an invaluable tool to investigate polymer materials whose composition is hardly accessible via other analytical methods. [ABSTRACT FROM AUTHOR]

An international movement is underway to promote the recognition of prior learning (RPL) as a means of social justice, especially for disadvantaged populations. This article examines the duration of the RPL pathway towards the upper secondary VET diploma from a social justice perspective. Grounded in the Sen's capability approach (CA) and using survival analysis with administrative data, the results show that, under certain conditions, the RPL helps promote access to an upper secondary vocational education and training (VET) diploma, especially for experienced workers without a diploma. Indeed, some personal (e.g. immigration status) and social conversion factors (e.g. involvement of employers in the RPL pathway) are associated with the time until graduation through RPL. The discussion highlights the relevance of using survival analysis when examining the association between conversion factors and the RPL pathway. The conclusion sheds light on the relevance of incorporating a temporal dimension when analysing pathway in RPL and under CA framework. [ABSTRACT FROM AUTHOR]

In this work, we propose an approach for assessing sensitivity to unobserved confounding in studies with multiple outcomes. We demonstrate how prior knowledge unique to the multi-outcome setting can be leveraged to strengthen causal conclusions beyond what can be achieved from analyzing individual outcomes in isolation. We argue that it is often reasonable to make a shared confounding assumption, under which residual dependence amongst outcomes can be used to simplify and sharpen sensitivity analyses. We focus on a class of factor models for which we can bound the causal effects for all outcomes conditional on a single sensitivity parameter that represents the fraction of treatment variance explained by unobserved confounders. We characterize how causal ignorance regions shrink under additional prior assumptions about the presence of null control outcomes, and provide new approaches for quantifying the robustness of causal effect estimates. Finally, we illustrate our sensitivity analysis workflow in practice, in an analysis of both simulated data and a case study with data from the National Health and Nutrition Examination Survey (NHANES). for this article are available online. [ABSTRACT FROM AUTHOR]

The high dimensionality of genetic data poses many challenges for subgroup identification, both computationally and theoretically. This paper proposes a double-penalized regression model for subgroup analysis and variable selection for heterogeneous high-dimensional data. The proposed approach can automatically identify the underlying subgroups, recover the sparsity, and simultaneously estimate all regression coefficients without prior knowledge of grouping structure or sparsity construction within variables. We optimize the objective function using the alternating direction method of multipliers with a proximal gradient algorithm and demonstrate the convergence of the proposed procedure. We show that the proposed estimator enjoys the oracle property. Simulation studies demonstrate the effectiveness of the novel method with finite samples, and a real data example is provided for illustration. [ABSTRACT FROM AUTHOR]

The detection of anomalies in dam deformation is paramount for evaluating structural integrity and facilitating early warnings, representing a critical aspect of dam health monitoring (DHM). Conventional data-driven methods for dam anomaly detection depend extensively on historical data; however, obtaining annotated data is both expensive and labor-intensive. Consequently, methodologies that leverage unlabeled or semi-labeled data are increasingly gaining popularity. This paper introduces a spatiotemporal contrastive learning pretraining (STCLP) strategy designed to extract discriminative features from unlabeled datasets of dam deformation. STCLP innovatively combines spatial contrastive learning based on temporal contrastive learning to capture representations embodying both spatial and temporal characteristics. Building upon this, a novel anomaly detection method for dam deformation utilizing STCLP is proposed. This method transfers pretrained parameters to targeted downstream classification tasks and leverages prior knowledge for enhanced fine-tuning. For validation, an arch dam serves as the case study. The results reveal that the proposed method demonstrates excellent performance, surpassing other benchmark models. [ABSTRACT FROM AUTHOR]

Image stitching aims to construct a wide field of view with high spatial resolution, which cannot be achieved in a single exposure. Typically, conventional image stitching techniques, other than deep learning, require complex computation and are thus computationally expensive, especially for stitching large raw images. In this study, inspired by the multiscale feature of fluid turbulence, we developed a fast feature point detection algorithm named local-peak scale-invariant feature transform (LP-SIFT), based on the multiscale local peaks and scale-invariant feature transform method. By combining LP-SIFT and RANSAC in image stitching, the stitching speed can be improved by orders compared with the original SIFT method. Benefiting from the adjustable size of the interrogation window, the LP-SIFT algorithm demonstrates comparable or even less stitching time than the other commonly used algorithms, while achieving comparable or even better stitching results. Nine large images (over 2600 × 1600 pixels), arranged randomly without prior knowledge, can be stitched within 158.94 s. The algorithm is highly practical for applications requiring a wide field of view in diverse application scenes, e.g., terrain mapping, biological analysis, and even criminal investigation. [ABSTRACT FROM AUTHOR]

The objective of image super-resolution is to reconstruct a high-resolution (HR) image with the prior knowledge from one or several low-resolution (LR) images. However, in the real world, due to the limited complementary information, the performance of both single-frame and multi-frame super-resolution reconstruction degrades rapidly as the magnification increases. In this paper, we propose a novel two-step image super resolution method concatenating multi-frame super-resolution (MFSR) with single-frame super-resolution (SFSR), to progressively upsample images to the desired resolution. The proposed method consisting of an L0-norm constrained reconstruction scheme and an enhanced residual back-projection network, integrating the flexibility of the variational model-based method and the feature learning capacity of the deep learning-based method. To verify the effectiveness of the proposed algorithm, extensive experiments with both simulated and real world sequences were implemented. The experimental results show that the proposed method yields superior performance in both objective and perceptual quality measurements. The average PSNRs of the cascade model in set5 and set14 are 33.413 dB and 29.658 dB respectively, which are 0.76 dB and 0.621 dB more than the baseline method. In addition, the experiment indicates that this cascade model can be robustly applied to different SFSR and MFSR methods. [ABSTRACT FROM AUTHOR]

The present study investigated multilevel models posited to predict student approaches to homework. Participants were 1,072 middle school students in China. Results revealed that deep and surface approaches were positively associated with performance-approach. Furthermore, deep approach to homework was associated negatively with homework cost, yet positively with mastery-approach, homework expectancy, and prior knowledge. Surface approach to homework was associated positively with homework cost and parent education, yet negatively with homework expectancy and mastery-approach. Females were less likely to use surface approach to homework than males. At the class level, surface approach to homework was negatively associated with parent education. Implications for homework practice and future investigation are discussed in terms of these results. [ABSTRACT FROM AUTHOR]

The aim of this study was to examine which topic- and learning-related knowledge and motivational beliefs predict the use of specific deep-level learning strategies during an independent learning task. Participants included 335 Estonian fourth- and sixth-grade students who were asked to read about light processes and seasonal changes. The study was completed electronically. Topic-related knowledge was assessed via an open question about seasonal changes, and learning-related knowledge was assessed via scenario-based tasks. Expectancies, interest, and utility values related to learning astronomy and using deep-level learning strategies were assessed via questions based on the Situated Expectancy-Value Theory. Deep-level learning strategies (using drawings in addition to reading and self-testing) were assessed while completing the reading task. Among topic-related variables, prior knowledge and utility value—but not interest or expectancy in learning astronomy—were related to using deep-level learning strategies. Among learning-related variables, interest and utility value of effective learning—but not metacognitive knowledge of learning strategies or expectancy in using deep-level learning strategies—were related to using deep-level learning strategies. This study confirms that it is not enough to examine students' knowledge and skills in using learning strategies with general or hypothetical questions, instead, it is of crucial importance to study students in real learning situations. [ABSTRACT FROM AUTHOR]

Imagination-to-learn is a specific learning strategy that has been studied in many academic fields. The present study investigated whether imagination is beneficial overall for learning compared to conventional study strategies, while also identifying moderator factors affecting the global effect. A meta-analysis was conducted by scientifically rigorous experiments comparing the learning outcomes of students who were asked to form a mental image of the events described in learning material while reading (imagination condition) or were given no imagination instructions (control condition). A total of 21 experimental studies published on the PsycINFO, Web of Science, ProQuest Dissertations and Theses, ERIC and Google Scholar databases were included, yielding 70 pair-wise comparisons with N = 2625 participants. An overall positive effect of imagination-to-learn was found for both retention (g+ = 0.40, 95% CI [0.23, 0.58], z = 4.63, p <.001) and transfer (g+ = 0.51, 95% CI [0.22, 0.43, z = 3.43, p <.001]) performance. However, analysis of the funnel plots showed that publication bias was present in the reporting of learning outcomes. Analysis of the moderators indicated that the effect sizes differed significantly only with respect to learners' prior knowledge for transfer performance and their educational level for retention scores. Based on these findings, the present study provides important directions for future research and practices. [ABSTRACT FROM AUTHOR]

To address the issue of weak model generalization caused by processing long texts, hierarchical coding structures, and long-tailed distributions in international classification of diseases (ICD) automatic coding methods, this paper proposed the PromptHP method for few-shot ICD automatic coding, leveraging medical pre-trained language models. Firstly, the PromptHP method combined coding descriptions and clinical texts into the prompt template to improve the model's comprehension of clinical texts. Then, it utilized the pre-trained language model's prior knowledge for initial prediction. Next, it introduced the hypersphere prototypical onto the output representation of the pre-trained language model for category modeling and metric classification, while fine-tuning the network on the medical dataset to incorporate the data knowledge and improve the model's performance on few-shot ICD coding classification tasks. Finally, it obtained the coding prediction results by integrating and weighting the two parts of the prediction results. Experimental results on the publicly available medical dataset MIMIC-III demonstrate that PromptHP outperforms state-of-the-art baseline methods, increasing the macro-AUC, micro-AUC, macro-F1, and micro-F1 of few-shot coding by 1.77%, 1.54%, 14.22%, and 15.01%, respectively. The experimental results validate the effectiveness of the PromptHP method in few-shot coding classification tasks. [ABSTRACT FROM AUTHOR]

Leadership in Early Childhood Education and Care (ECEC) is changing globally. We investigated ECEC leadership and leaders’ interpretations of power and its realization between leaders and followers, a little researched topic in the field. Our theoretical framework consists of ECEC contextual knowledge and prior research attached with Michel Foucault’s and Mary Parker Follet’s perceptions of power as positive, relational and discursive microphenomenon. Our essay data (N = 46) was written by ECEC center leaders before participating in educational leaders in-service training. The method of analysis was Greimas’ actantial analysis (1979), which enabled us to build two actantial models of leaders’ perspectives and relation to power. Findings indicate that power is a leader-centered, unstructured and hiding concept needing conscious reframing and integration of positional and non-positional leader roles in the community. [ABSTRACT FROM AUTHOR]

Usually, detailed impact simulation models within flexible multibody systems have to be set up manually rather than being generated automatically. This is because the process requires prior knowledge of the time and location of the impact, as well as the element resolution within the contact area. If the penalty method is used to determine the occurring contact forces, the corresponding penalty factor also needs to be determined manually. This work, however, presents an adaptive algorithm to simulate impacts within flexible multibody systems fully automatically using reduced isogeometric analysis models, the floating frame of reference formulation, and quasistatic contact models for an efficient but still accurate simulation. The adaptive algorithm detects impacts in the system, determines the contact locations on the bodies, refines the contact area, and determines the penalty factor, and therefore automatically simulates impacts. The work shows how to automatically simulate impacts in flexible multibody systems without user action or prior knowledge of impact location and size. The first application example simulates significant elastodynamic effects within a long flexible rod. The goal is to validate the algorithm by preserving the wave propagation and energy of the system. The second application example simulates the impacts of two flexible double pendulums. This setup is a suitable benchmark for the complete adaptive impact analysis procedure as the flexible double pendulums undergo large rigid body motions. [ABSTRACT FROM AUTHOR]

Mastery‐based assignments typically provide students with multiple opportunities to improve their performance, but getting students to take advantage of these opportunities is difficult. We report on the implementation of a two‐part series of nudges designed to improve students' engagement with and performance on mastery‐based assignments in high‐enrollment, introductory undergraduate courses. Students received one or two email‐based nudges for each assignment, providing both decision information and decision assistance. Delivered via email by a digital coaching system that provides tailored support to students, we evaluated the effectiveness of viewing versus not viewing these personalized nudges across introductory courses in mathematics, computer science and engineering over five terms at our large, research‐intensive university. We used multilevel modelling with a sample of 30,693 assignment scores nested within 79 assignments and 5349 undergraduate students to explore the relationship between students' viewing the nudges and their scores while controlling for performance in other courses and students' baseline proclivities to read email from the coaching system. We find that viewing versus not viewing nudges is significantly related to improved outcomes. Viewing the first of the two‐part nudge series is associated with a 3% increase in scores on average. Importantly, we found a significant interaction with prior academic performance such that students with the lowest average academic performance across all courses are predicted to benefit the most—up to 9%—from nudging. Positive impacts are observed in most courses where nudges were implemented and are found to be most impactful for later versus earlier assignments within a term. We discuss the implications of these results for supporting students' decision‐making within mastery‐based assignment schemes and suggest future research for tailored nudges to support student success. Practitioner notesWhat is already known about this topic Nudges are known to be broadly effective, but heterogeneity is observed especially in education where the research base is relatively limited.Mastery‐based grading is an alternative approach to grading that, among other features, emphasizes learning through an explicit feedback cycle of struggle and revision without penalty.What this paper adds This study assesses the effectiveness of personalized nudges in the context of mastery‐based grading in undergraduate STEM courses.We examined the efficacy of viewing versus not viewing nudges in the real learning settings of three STEM courses enrolling more than 5000 students.We found the nudges to be effective overall, correlated with improvements of approximately 3% in students' assignment scores and most impactful for students with the lowest average academic performance.Implications for practice and/or policy Nudging by email or text message has a low overhead cost and yet may provide materially significant gains in students' assessment scores.Nudges can be effectively targeted to specific subsets of students and tailored based on students' prior and concurrent learning analytics data. [ABSTRACT FROM AUTHOR]

Initial teacher education programs have been criticised for their failure to deliver classroom-ready graduates. Problems of concern for preservice teachers (PSTs) identified in the literature are insufficient time in the classroom, lack of confidence, inadequate pedagogical knowledge and a theory practice divide. This research examines a school–university partnership approach to science teacher education from the perspective of PSTs, school students, teachers and teacher educators where university tutorials were conducted in a school environment. This research is underpinned by practice architectures theory, it follows collaborative participatory action research methodology using mixed methods of data collection including surveys, interviews and focus groups. The research findings revealed how the program built on PSTs' pedagogical knowledge and confidence and connected theory with practice. Teachers observed high level student engagement and students building on their prior science knowledge in innovative science lessons. The research provides rich data that illuminate aspects in this school–university partnership approach from a range of perspectives. [ABSTRACT FROM AUTHOR]

The present study tested the efficacy of an intervention on thinking dispositions on multiple-text comprehension performance. The participants in the study were 75 undergraduate students. First, participants completed pretest assessment tests (prior beliefs and knowledge, thinkinPromoting multiple-text comprehension through thinking dispositions: a randomized controlled trialg dispositions). Second, the participants were randomly assigned to the experimental (n = 36) or control condition (n = 35). In each condition they were asked to read instructional material about critical thinking when reading from multiple texts. The experimental group students were specifically instructed on the definition and functioning of thinking dispositions. Third, participants read two texts about the controversial topic of red meat consumption, answered to a comprehension test, and wrote an argumentative essay (coded by length and argumentative quality). Overall, the thinking disposition intervention was effective in promoting a higher engagement with the task and a higher level of argumentative quality. [ABSTRACT FROM AUTHOR]

Lung cancer screening (LCS) has the potential to decrease mortality from lung cancer by 20%. Yet, more than a decade since LCS was established as an evidence-based practice, < 20% of the eligible population in the United States has been screened. This review focuses on critically appraising interventions that have been designed to increase the initial uptake of LCS, including how they address known barriers to LCS and their effectiveness in overcoming these barriers. Studies were categorized based on the primary barriers that they addressed: (1) identifying eligible patients (including enhancing awareness through smoking history collection, outreach, and education), (2) shared decision-making-related interventions, and (3) patient navigation interventions. Four of the studies included multicomponent interventions, which often included patient navigation as one of the components. Overall, the effectiveness of the studies reviewed at improving LCS uptake generally was modest and was limited by the multilevel barriers that need to be overcome. Multicomponent interventions generally were more effective at improving LCS uptake, but most studies still had relatively low completion of screening. Improving uptake of LCS requires learning from prior interventions to design multilevel interventions that address barriers to LCS at key steps and identifying which components of these interventions are effective and generalizable. [ABSTRACT FROM AUTHOR]

How do task experiences support proximal and longer‐term desires to reengage? Central to this question is the interplay between perceptions of task difficulty and the situational interest. This interplay is increasingly researched but not yet well understood. Micro‐analytic, latent studies are important tools for replicating past findings and extending our understanding in this area. This study aimed to extend our understanding of the interplay between readiness (prior knowledge and individual interest), a sequence of mathematics task experiences (situational interest and perceived difficulty) and reengagement beyond the set of tasks (i.e. optional follow‐up engagement). Participants (ages 20–49; n = 301) completed a series of maths tasks online, self‐reporting their task experiences after each task. Participants were offered an optional opportunity to follow‐up with the task content as a measure of their continued interest. Both readiness components assessed were important predictors of future situational interest (positive) and perceptions of task difficulty (negative). Persistent interconnections between the task experience components across time supported past evidence regarding the important role of situational interest and the challenges of perceived difficulty for sustained engagement. Modelling indicated that task success (β = 0.36), situational interest (β = 0.16) and perceptions of task difficulty (β = 0.21) can converge on choices to reengage with an object going forward. [ABSTRACT FROM AUTHOR]

Due to time, budget, and/or technical constraints, geotechnical site investigation data from a specific site are often limited and sparse, leading to a long-lasting challenge in characterization of spatially varying geotechnical properties. During preliminary stages of site characterization, geotechnical data from neighboring sites or sites with similar geological conditions are often collected and used as valuable prior knowledge in geotechnical engineering practice. Nevertheless, existing methods for spatial variability characterization often rely solely on site-specific data and cannot effectively incorporate prior knowledge or existing databases. To address this issue, this study proposes a novel machine learning method that systematically combines sparsely measured data at a specific site with existing data from neighboring sites or sites with similar geological settings for characterization of property spatial variability in a data-driven manner. The proposed method starts with the construction of a dictionary that draws the dominant spatially varying patterns from a property measured at sites with similar geology under a dictionary learning framework. Leveraging the developed dictionary, the spatial variability of a property is interpreted from sparse site-specific measurements using Bayesian learning. The effectiveness of the proposed method is demonstrated using real data, and improved performance over existing methods is observed. [ABSTRACT FROM AUTHOR]

We present an approach to autonomous drone racing inspired by how a human pilot learns a race track. Human pilots drive around the track multiple times to familiarise themselves with the track and find key points that allow them to complete the track without the risk of collision. This paper proposes a three-stage approach: exploration, navigation, and refinement. Our approach does not require prior knowledge about the race track, such as the number of gates, their positions, and their orientations. Instead, we use a trained neural pilot called DeepPilot to return basic flight commands from camera images where a gate is visible to navigate an unknown race track and a Single Shot Detector to visually detect the gates during the exploration stage to identify points of interest. These points are then used in the navigation stage as waypoints in a flight controller to enable faster flight and navigate the entire race track. Finally, in the refinement stage, we use the methodology developed in stages 1 and 2, to generate novel data to re-train DeepPilot, which produces more realistic manoeuvres for when the drone has to cross a gate. In this sense, similar to the original work, rather than generating examples by flying in a full track, we use small tracks of three gates to discover effective waypoints to be followed by the waypoint controller. This produces novel training data for DeepPilot without human intervention. By training with this new data, DeepPilot significantly improves its performance by increasing its flight speed twice w.r.t. its original version. Also, for this stage 3, we required 66 % less training data than in the original DeepPilot without compromising the effectiveness of DeepPilot to enable a drone to autonomously fly in a racetrack. [ABSTRACT FROM AUTHOR]

Physics-informed neural networks formulation allows the neural network to be trained by both the training data and prior domain knowledge about the physical system that models the data. In particular, it has a loss function for the data and the physics, where the latter is the deviation from a partial differential equation describing the system. Conventionally, both loss functions are combined by a weighted sum, whose weights are usually chosen manually. It is known that balancing between different loss terms can make the training process more efficient. In addition, it is necessary to find the optimal architecture of the neural network in order to find a hypothesis set in which is easier to train the PINN. In our work, we propose a multi-objective optimization approach to find the optimal value for the loss function weighting, as well as the optimal activation function, number of layers, and number of neurons for each layer. We validate our results on the Poisson, Burgers, and advection-diffusion equations and show that we are able to find accurate approximations of the solutions using optimal hyperparameters. [ABSTRACT FROM AUTHOR]

Multi-agent encirclement with collision avoidance constitutes a common challenge in the multi-agent confrontation domain, wherein the focus lies in the development of cooperative strategies among agents. Previous studies encountered difficulties in addressing the dynamic encirclement of faster prey in obstacles environment. This paper introduces a novel multi-agent deep reinforcement learning approach based on prior knowledge. It is dedicated to exploring the multi-agent encirclement with collision avoidance task involving slower multiple pursuers collaboratively encircling faster prey in an obstacles environment. Firstly, the utilization of the classic Apollonius circle theory as prior knowledge guides agent action selection, narrows the exploratory action space, and accelerates the learning of strategies. Subsequently, the variance descriptor restricts the motion direction of pursuers, thus ensuring that pursuers continuously narrow the encirclement until the prey is successfully encircled. Finally, experiments in an obstacles environment were conducted to validate the proposed method. The results indicate that our method can acquire an effective encirclement strategy, with an encirclement success rate exceeding that of previous methods by more than 10%, and simulation experiment results demonstrate the effectiveness and practicability of our method. [ABSTRACT FROM AUTHOR]

• A failed innovation may signal that line of research must be abandoned. • But on the other hand this line of research could be fruitful if further pursued. • In this case a failure is not a reliable signal that this line should be abandoned. • We show that the latter case is especially relevant in complex technologies. This paper explores whether failures in innovation projects at the firm level contribute to strengthening firms' innovative activities and the odds of future innovation. Building on the literature on NK fitness landscapes, our paper focuses on technological complexity as a key factor that influences the response to innovation failures, guiding whether to discontinue the current path or, alternatively, to leverage the failure as a foundation for future innovation success. We then test the hypothesis derived from our model using a panel data set constituted by ten waves of the Community Innovation Survey held in the Netherlands from 1996 to 2014. Our findings show the fundamental relevance of the different forms of learning that are available to the firm. In particular, we highlight the positive role of learning after a previous innovation project has been abandoned. Previous failure in innovating produces some forms of learning inside the firms, and this learning positively contributes to subsequent successful innovation. Moreover, by differentiating between radical and incremental innovation, and between complex and less-complex innovation landscapes, we highlight the role of incremental innovation over the whole spectrum of landscape complexity, while the role of radical innovation appears to be more limited to less turbulent technological landscapes. [ABSTRACT FROM AUTHOR]

This paper tackles the problem of trajectory tracking for wheeled mobile robots subject to time-varying input delay and bounded external disturbances. First, we establish a dynamic model for a wheeled mobile robot under sliding and skidding conditions, and determine the maximum allowable input delay that maintains system stability using Razumikhin-type stability analysis without prior knowledge of the variation in delay. The proposed adaptive robust controller combined with super-twisting sliding mode control is resilient to disturbances such as input delay, system uncertainty, and parameter variation. The proposed adaptive law enables real-time modification of switching gain based on tracking error without predefined knowledge of uncertainty bounds. Compared with traditional sliding mode control strategies, the super-twisting algorithm can eliminate chattering phenomenon while combined robust methods further reduce modeling uncertainties' influence on system performance. Finally, we select an appropriate Lyapunov function to analyze and prove uniformly ultimately bounded of the closed-loop system. MATLAB simulation comparison results demonstrate that this approach achieves high tracking accuracy, faster response speed, and robustness. [ABSTRACT FROM AUTHOR]

The vision enhancement of autonomous underwater vehicle (AUV) has received increasing attention and rapid development in recent years. However, existing methods based on prior knowledge struggle to adapt to all scenarios, while learning-based approaches lack paired datasets from real-world scenes, limiting their enhancement capabilities. Consequently, this severely hampers their generalization and application in AUVs. Besides, the existing deep learning-based methods largely overlook the advantages of prior knowledge-based approaches. To address the aforementioned issues, a novel architecture called CodeUNet is proposed in this paper. Instead of relying on physical scattering models, a real-world scene vision enhancement network based on a codebook prior is considered. First, the VQGAN is pretrained on underwater datasets to obtain a discrete codebook, encapsulating the underwater priors (UPs). The decoder is equipped with a novel feature alignment module that effectively leverages underwater features to generate clean results. Then, the distance between the features and the matches is recalibrated by controllable matching operations, enabling better matching. Extensive experiments demonstrate that CodeUNet outperforms state-of-the-art methods in terms of visual quality and quantitative metrics. The testing results of geometric rotation, SIFT salient point detection, and edge detection applications are shown in this paper, providing strong evidence for the feasibility of CodeUNet in the field of autonomous underwater vehicles. Specifically, on the full reference dataset, the proposed method outperforms most of the 14 state-of-the-art methods in four evaluation metrics, with an improvement of up to 3.7722 compared to MLLE. On the no-reference dataset, the proposed method achieves excellent results, with an improvement of up to 0.0362 compared to MLLE. Links to the dataset and code for this project can be found at: https://github.com/An-Shunmin/CodeUNet. [ABSTRACT FROM AUTHOR]

Traditional methods for object detection typically necessitate a substantial amount of training data, and creating high-quality training data is time-consuming. We propose a novel Few-Shot Object Detection network (FSODv2) in this paper that aims to detect objects from previously unseen categories using only a few annotated examples. Attention RPN, Multi-Relation Detector, and Contrastive Training strategy are central to our method (Fan et al., in: CVPR, 2020), which exploit similarity between few shot support set and query set to detect novel objects while suppressing false detection in the background. We also contribute a new dataset, FSOD-1k, which contains 1000 categories of various objects with high-quality annotations to train our network. To the best of our knowledge, this is one of the first datasets designed for few-shot object detection. This paper improves our FSOD model through well-designed model calibration in three areas: (1) we propose an improved FPN with multi-scale support inputs to calibrate the multi-scale support-query feature matching by exploiting multi-scale features from the same support image with different input scales; (2) we introduce a support classification supervision branch to calibrate the support feature supervision, aligning to the query feature training supervision; (3) we propose backbone calibration to preserve prior knowledge while alleviating backbone bias toward base classes by employing classification dataset to help our model calibration procedure, where such dataset has previously only been used for pre-training in other related works. Besides, we propose a Fast Attention RPN to improve evaluation speed and save computational memory during inference. Once trained, our few-shot network can detect objects from previously unseen categories without further training or fine-tuning, resulting in new state-of-the-art performance on different datasets in the few-shot setting. Our method is general in scope and has numerous potential applications. The dataset link is https://github.com/fanq15/Few-Shot-Object-Detection-Dataset. [ABSTRACT FROM AUTHOR]

In this paper, we undertake a novel two-pronged investigation into the human recognition of deepfake speech, addressing critical gaps in existing research. First, we pioneer an evaluation of the impact of prior information on deepfake recognition, setting our work apart by simulating real-world attack scenarios where individuals are not informed in advance of deepfake exposure. This approach simulates the unpredictability of real-world deepfake attacks, providing unprecedented insights into human vulnerability under realistic conditions. Second, we introduce a novel metric to evaluate the quality of deepfake audio. This metric facilitates a deeper exploration into how the quality of deepfake speech influences human detection accuracy. By examining both the effect of prior knowledge about deepfakes and the role of deepfake speech quality, our research reveals the importance of these factors, contributes to understanding human vulnerability to deepfakes, and suggests measures to enhance human detection skills. [ABSTRACT FROM AUTHOR]

Although teachers have opportunities to learn about many things through teaching experience, we know little about how they develop science subject matter knowledge in this setting. With both limited opportunities to learn science subject matter knowledge before becoming teachers and minimal science professional development available while working as a teacher, it is important to understand the extent to which elementary teachers develop science subject matter knowledge in their regular classroom practice and the factors that influence that development. In this longitudinal, mixed methods study we collected both quantitative and qualitative data before and following their final field experience, which was their first opportunity to have significant teaching experience. Findings suggest two important factors for subject matter knowledge development: time for considering science subject matter and a learning setting that values science. In contrast, indicators of learner capacity (i.e., prior knowledge) and time teaching the topics were not associated with teacher subject matter knowledge development. [ABSTRACT FROM AUTHOR]

AbstractAccording to cognitive load theory, an expert learner can access prior knowledge to interpret a diagram with minimum effort. A novice learner who lacks prior knowledge, in contrast, would experience a high level of cognitive load when processing a diagram, which would interfere with learning. On learning to solve percentage problems, we investigated the effect of approach (non-algebra vs. algebra), with and without diagram support for two levels of learner expertise. Participants were 218 Asian students whose mean age was 15.00 (SD = 0.18). Contrary to our hypothesis, the presence or absence of a diagram may bore little, if any, benefit for students who were more knowledgeable. Considering two levels of learner expertise together, as hypothesized, performance outcomes favoring more knowledgeable students were greater for the unitary-pictorial approach than the equation-pictorial approach. Interestingly, the impact of a diagram was more pronounced for more knowledgeable students; however, with relevant prior algebra knowledge, the presence of a diagram (e.g., equation-pictorial approach) can also be helpful for less knowledgeable students. Overall, then, our research undertaking has yielded important implications for teaching and research purposes. [ABSTRACT FROM AUTHOR]

Various robot navigation methods have been developed, but they are mainly based on Simultaneous Localization and Mapping (SLAM), reinforcement learning, etc., which require prior map construction or learning. In this study, we consider the simplest method that does not require any map construction or learning, and execute open-vocabulary navigation of robots without any prior knowledge to do this. We applied an omnidirectional camera and pre-trained vision-language models to the robot. The omnidirectional camera provides a uniform view of the surroundings, thus eliminating the need for complicated exploratory behaviors including trajectory generation. By applying multiple pre-trained vision-language models to this omnidirectional image and incorporating reflective behaviors, we show that navigation becomes simple and does not require any prior setup. Interesting properties and limitations of our method are discussed based on experiments with the mobile robot Fetch. [ABSTRACT FROM AUTHOR]

Image denoising aims to remove noise from images and improve the quality of images. However, most image denoising methods heavily rely on pairwise training strategies and strict prior knowledge about image structure or noise distribution. While these methods exhibit significant results when handling known types of noise, their generalization performance diminishes when confronted with images containing unknown noise distributions. To address this issue, a two‐stage approach is introduced for enhancing the generalizability of image denoising. The proposed method does not rely on a large amount of paired data or prior knowledge of the noise type and level. Instead, it constructs a denoising pipeline with improved generalizability through an MLP‐based denoiser and generative diffusion prior. Specifically, in the first stage, an initial denoised image is predicted with a structure resembling that of the underlying clean image by introducing an MLP‐based U‐shaped denoising network aided by an implicit structural prior. In the second stage, the generalizability and quality of the denoiser are further enhanced by conditioning the result obtained from the previous stage on the pretrained denoising diffusion null‐space model. Extensive experimentation on multiple datasets demonstrates that this method exhibits better denoising performance and generalizability than other image denoising methods. [ABSTRACT FROM AUTHOR]

Police in England and Wales are invested with specific legal powers to detain a person—who is not under arrest—and search them or their vehicle for unlawful items. The exercise of this coercive power has long been a source of tension and mistrust, particularly among minoritised and other marginalised communities, and has been repeatedly implicated among the causes of serious public disorder. Although concerns about the misuse of stop and search have created a recurring cycle of crisis and reform—stretching back over more than four decades—the fundamental problem remains unchanged. How did this happen and what should now be done about it? These questions will be addressed by considering how the policy problem has been framed over time, reviewing evidence on the impact of stop and search and identifying policy challenges associated with regulating the powers, including lessons that can be learnt from previous attempts at reform. [ABSTRACT FROM AUTHOR]

Postgraduate medical education in clinical settings poses many challenges secondary to the large volume of knowledge to be acquired, competing clinical responsibilities, and fatigue. To address these challenges, a microlearning curriculum using flipped classroom methodologies was created to facilitate the mastering of fundamental physiology formulas by pediatric critical care medicine fellows. Forty physiology formulas were distilled into 5-minute microlearning sessions. Fellows were provided the weekly formula and encouraged to self-study prior to the face-to-face learning. The 5-minute session took place at the beginning of a regularly scheduled clinical care conference where normal values, explanatory diagrams, and board-like questions were discussed. A faculty or fellow facilitator then provided a more in-depth explanation and shared clinical pearls related to the formula. Following the session, an e-mail summarizing the learning points was sent. The curriculum was well received by fellows and faculty. Over 5 years, the curriculum evolved through phases of active development, implementation, minor modifications, transition to a virtual platform, shift to senior fellow-led instruction, and harmonization with other curricular activities. Engagement and sustainability were addressed with a fully flipped classroom, where senior fellows served as teachers to junior fellows. Microlearning in a multimodal manner is an excellent method for teaching busy postgraduate clinical trainees fundamental physiology formulas that underpin pediatric critical care decision-making. The gradual transition from individual learning to a flipped classroom taught by peers with faculty support was well tolerated and consistent with adult learning theories. The transition was essential to ensure the sustainability of the curriculum. [ABSTRACT FROM AUTHOR]

Simulated data play an important role in SAR target recognition, particularly under zero-shot learning (ZSL) conditions caused by the lack of training samples. The traditional SAR simulation method is based on manually constructing target 3D models for electromagnetic simulation, which is costly and limited by the target's prior knowledge base. Also, the unavoidable discrepancy between simulated SAR and measured SAR makes the traditional simulation method more limited for target recognition. This paper proposes an innovative SAR simulation method based on a visual language model and generative diffusion model by extracting target semantic information from optical remote sensing images and transforming it into a 3D model for SAR simulation to address the challenge of SAR target recognition under ZSL conditions. Additionally, to reduce the domain shift between the simulated domain and the measured domain, we propose a domain adaptation method based on dynamic weight domain loss and classification loss. The effectiveness of semantic information-based 3D models has been validated on the MSTAR dataset and the feasibility of the proposed framework has been validated on the self-built civilian vehicle dataset. The experimental results demonstrate that the first proposed SAR simulation method based on a visual language model and generative diffusion model can effectively improve target recognition performance under ZSL conditions. [ABSTRACT FROM AUTHOR]