Latent Domain Research Articles

A Robust joint coverless image steganography scheme based on two independent modules

With the development of deep learning technology, great progress has been made in the field of coverless steganography based on deep learning technology, including some selection-based steganography methods that use deep learning technology and all generation-based steganography methods, however both of which have their limitations. The former is difficult to meet actual communication requirements in terms of communication capacity and completeness due to the limit of the algorithm. Due to the irreversibility of the process of generating secret images from message codeword, the recovery accuracy of the latter is very poor. To this end, this paper designs a robust joint coverless image steganography scheme called Joint Coverless Image Steganography (JoCS). Firstly, this paper proposes the Semantic Factorization Fitting module (SeFF) and the Transform Domain Steganography module (TrDS). The former adds the secret message to the input vector of the low resolution layer in the StyleGAN generator network, which establishs a mapping rule between message codeword and the coarse feature of the generated image, and then the extractor is used to fit the above mapping rule, which has excellent robustness and completeness; the latter encodes the main content area of the image based on the encoder in VQGAN, and then adds secret message to the latent vector of the encoded image, which achieves the steganography in the latent domain of the image. Secondly, we demonstrate the independence between two modules and the advantages of connecting two modules. By using the image generated in the SeFF module as the cover image in the TrDS module, secondary steganography of a single image is achieved, based on which we design the JoCS scheme. The results show that our scheme breaks through the communication capacity limit in the selection-based coverless methods while guaranteeing 100% completeness, excellent image quality and outstanding robustness against various image attacks. Moreover, our scheme exhibits strong security against detection by multiple steganalysis tools and excellent practicality in practical communication. Finally, this paper also discusses the following three points as further elaboration of the scheme: (1) the advantages of the mapping rule in the SeFF module (2) the verification of the independence between the two modules (3) the flexibility of the joint steganography scheme.

Improving the Parameterization of Complex Subsurface Flow Properties With Style‐Based Generative Adversarial Network (StyleGAN)

AbstractRepresenting and preserving complex (non‐Gaussian) spatial patterns in aquifer flow properties during model calibration are challenging. Conventional parameterization methods that rely on linear/Gaussian assumptions are not suitable for representation of property maps with more complex spatial patterns. Deep learning techniques, such as Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN), have recently been proposed to address this difficulty by learning complex spatial patterns from prior training images and synthesizing similar realizations using low‐dimensional latent variables with Gaussian distributions. The resulting Gaussian latent variables lend themselves to calibration with the ensemble Kalman filter‐based updating schemes that are suitable for parameters with Gaussian distribution. Despite their superior performance in generating complex spatial patterns, these generative models may not provide desirable properties that are needed for parameterization of model calibration problems, including robustness, smoothness in the latent domain, and reconstruction fidelity. This paper introduces the second generation of style‐based Generative Adversarial Networks (StyleGAN) for parameterization of complex subsurface flow properties and compares its model calibration properties and performance with those of the convolutional VAE and GAN architectures. Numerical experiments involving model calibration with the Ensemble Smoother with Multiple Data Assimilation (ES‐MDA) in single‐phase and two‐phase fluid flow examples are used to assess the capabilities and limitations of these methods. The results show that parameterization with StyleGANs provides superior performance in terms of reconstruction fidelity and flexibility, underscoring its potential for improving the representation and reconstruction of complex spatial patterns in subsurface flow model calibration problems.

Normalizing flow sampling with Langevin dynamics in the latent space

AbstractNormalizing flows (NF) use a continuous generator to map a simple latent (e.g. Gaussian) distribution, towards an empirical target distribution associated with a training data set. Once trained by minimizing a variational objective, the learnt map provides an approximate generative model of the target distribution. Since standard NF implement differentiable maps, they may suffer from pathological behaviors when targeting complex distributions. For instance, such problems may appear for distributions on multi-component topologies or characterized by multiple modes with high probability regions separated by very unlikely areas. A typical symptom is the explosion of the Jacobian norm of the transformation in very low probability areas. This paper proposes to overcome this issue thanks to a new Markov chain Monte Carlo algorithm to sample from the target distribution in the latent domain before transporting it back to the target domain. The approach relies on a Metropolis adjusted Langevin algorithm whose dynamics explicitly exploits the Jacobian of the transformation. Contrary to alternative approaches, the proposed strategy preserves the tractability of the likelihood and it does not require a specific training. Notably, it can be straightforwardly used with any pre-trained NF network, regardless of the architecture. Experiments conducted on synthetic and high-dimensional real data sets illustrate the efficiency of the method.

Dual-branch teacher-student with noise-tolerant learning for domain adaptive nighttime segmentation

While significant progress has been achieved in the field of image semantic segmentation, the majority of research has been primarily concentrated on daytime scenes. Semantic segmentation of nighttime images is equally critical for autonomous driving; however, this task presents greater challenges due to inadequate lighting and difficulties associated with obtaining accurate manual annotations. In this paper, we introduce a novel method called the Dual-Branch Teacher-Student (DBTS) framework for unsupervised nighttime semantic segmentation. Our approach combines domain alignment and knowledge distillation in a mutually reinforcing manner. Firstly, we employ a photometric alignment module to dynamically generate target-like latent images, bridging the appearance gap between the source domain (daytime) and the target domain (nighttime). Secondly, we establish a dual-branch framework, where each branch enhances collaboration between the teacher and student networks. The student network utilizes adversarial learning to align the target domain with another domain (i.e., source or latent domain), while the teacher network generates reliable pseudo-labels by distilling knowledge from the latent domain. Furthermore, recognizing the potential noise present in pseudo-labels, we propose a noise-tolerant learning method to mitigate the risks associated with overreliance on pseudo-labels during domain adaptation. When evaluated on benchmark datasets, the proposed DBTS achieves state-of-the-art performance. Specifically, DBTS, using different backbones, outperforms established baseline models by approximately 25% in mIoU on the Zurich dataset and by over 26% in mIoU on the ACDC dataset, demonstrating the effectiveness of our method in addressing the challenges of domain-adaptive nighttime segmentation.

Identifying neurofunctional domains across substance use disorders

ABSTRACT Background: Substance use disorders (SUDs) are heterogeneous across multiple functional domains. Various frameworks posit that domains (e.g., executive function) contribute to the persistence of SUDs; however, the domains identified in different studies vary. Objectives: We used factor analysis to identify the underlying latent domains present in a large sample (N = 5,244, 55.8% male) with a variety of SUDs to yield findings more generalizable than studies with a narrower focus. Method: Participants (1,384 controls and 3,860 participants with one or more SUDs including alcohol, cocaine, cannabis, and/or opioid use disorders) completed the Semi-Structured Assessment for Drug Dependence and Alcoholism, the NEO Personality Inventory, and the Wisconsin Card Sorting Test. Exploratory factor analysis (EFA) and fit indices (root mean-squared error of approximation (RMSEA), Comparative Fit Index (CFI), and Tucker-Lewis Index (TLI)) were used to examine different latent variable models. A multiple indicators, multiple causes (MIMIC) approach-tested associations of the latent variables with sociodemographics, substance use, and a history of abuse/neglect. Results: A six-factor model (predominant alcohol, predominant cocaine, predominant opioid, externalizing, personality, and executive function) provided the best fit [RMSEA = 0.063 (90% CI 0.060, 0.066), CFI = 0.98, TLI = 0.96]. All factors were moderately correlated (coefficient = 0.25–0.55, p < .05) with the exception of executive function. MIMIC analysis revealed different patterns of associations (all p < .0001) with sociodemographics, substance use, and a history of abuse/neglect among the factors. Conclusions: The domains identified, particularly executive function, were parallel to those observed previously. These factors underscore the heterogeneous nature of SUDs and may be useful in developing more targeted clinical interventions.

A novel causal feature learning-based domain generalization framework for bearing fault diagnosis with a mixture of data from multiple working conditions and machines

Data distribution shift usually deteriorates the performance of traditional supervised learning-based fault diagnosis models. Such issue can be well addressed by domain generalization fault diagnosis methods even if the test data are unavailable in training stage. However, most of these methods are designed and validated only for a single device, and also require the domain labels being provided, which hampers their further application. Therefore, this paper focuses a more realistic scenario, where the source training set is a mixture of data from multiple operation conditions and devices with domain information unavailable. First, a causal analysis is made for the task of domain generalization fault diagnosis, and a structural causal model (SCM) that describes the data generation process is constructed based on the relationships among different variables. A new learning rule for domain generalization, named object-conditional domain invariant (Obj-DI) rule, is also elicited. Then, to achieve domain generalization fault diagnosis, a three-stage based method named LOODG is proposed. Potential domains are mined and samples are given domain labels in latent domain discovery stage. Samples belonging to same object but different domains are explored in object discovery stage. In Obj-DI based causal feature learning stage, generalizable causal features are learned to finally obtain a generalized model. Experiments are conducted on tasks designed from three datasets, and the results demonstrate the superiority of the proposed method.

Cross-domain knowledge collaboration for blending-target domain adaptation

Unsupervised domain adaptation (UDA) avoids expensive data annotation for the unlabeled target domains by fully utilizing the knowledge of existing source domain. In practice, the target data are usually highly heterogeneous that mix multiple latent domains. And sometimes the source data involve the user private information which is forbidden to access directly. To this end, this paper tackles the blending-target data under the source-available setting, and for the first time under the source-free setting. Specifically, we devise a novel Cross-domain Knowledge Collaboration (CdKC) framework, which mainly includes a prediction network and an adaptation network. The complementarity of two networks are exploited to explore the intrinsic structure in targets. Specifically, CdKC is capable of learning domain-invariant space, and disentangling domain-specific feature simultaneously to boost the UDA performance greatly. A total of 12 tasks are conducted on three visual datasets to verify the superior performance of CdKC by comparing with the state-of-the-art models designed under 4 different UDA settings. The experiments demonstrate that the accuracy of CdKC model still exceeds D-CGCT 0.4% on Office dataset and 1.2% on Office–Home dataset although D-CGCT can access source data and domain labels of targets that CdKC cannot do. It verifies the effectiveness of CdKC although under much looser source and target domain restrictions.

Translation and Validation of the Malay Version of Modified Vaccine Hesitancy Scale (MVHS-M) for Assessment of Parental Vaccine Hesitancy

INTRODUCTION: Parental hesitancy towards routine childhood vaccines has been recognized as one of the public health threats. Since the uptake of child vaccination remains inconsistent, there is a need for a reliable and validated tool to measure this phenomenon. MATERIALS AND METHODS: A cross-sectional study was conducted at government health clinics in Kelantan between April 2023 to July 2023. A permission to use the original version of Modified Vaccine Hesitancy Scale (MVHS) was obtained and translated into the Malay version (MVHS-M) based on established guidelines. Parents who have at least one child aged 7 years or less were recruited by using systematic random sampling to validate the MVHS-M. A confirmatory factor analysis (CFA) was used to confirm the latent domain, while reliability was measured by composite reliability and test-retest. The data were analysed using IBM SPSS Version 26 and Mplus version 8. RESULTS: A total of 270 parents who fulfilled the study criteria were selected and completed the survey. The CFA showed a good fit index: RMSEA = 0.057 (90% CI 0.031, 0.082), CFI = 0.970, TLI = 0.957, and SRMR = 0.031. The composite reliability for the domain "lack of confidence" was 0.93 (95% CI 0.91, 0.94), while the domain "risk" showed a reliability of 0.74 (95% CI 0.69, 0.79). The test-retest reliability, as measured by the Intra-class Correlation Coefficient (ICC), was 0.77 (95% CI 0.59, 0.87), indicating good stability. CONCLUSION: MVHS-M is a valid and reliable tool that will be useful in identifying parental vaccine hesitancy in Malaysia.

Latent domain knowledge distillation for nighttime semantic segmentation

Despite significant progress made in image semantic segmentation, most research has primarily focused on daytime scenes. Semantic segmentation of nighttime images is equally critical for autonomous driving; however, this task poses more challenges due to inadequate lighting and difficulties associated with obtaining accurate manual annotations. In this paper, we propose a novel method called Latent Domain Knowledge Distillation (LDKD) for accurate nighttime semantic segmentation. Within a teacher-student framework, our LDKD combines domain alignment and knowledge distillation in a mutually reinforcing manner. First, we introduce a bidirectional photometric alignment module capable of generating daytime-like and nighttime-like latent images in real-time. This module effectively bridges the appearance gap between the source domain (daytime) and the target domain (nighttime). Second, we enhance collaboration between the teacher and student networks. The student network unifies image-level and feature-level domain alignment, while the teacher network generates reliable pseudo-labels by distilling knowledge from the latent domain. Furthermore, to account for potential noise in pseudo-labels, we propose a noise-tolerant learning method aimed at mitigating the risks associated with overreliance on pseudo-labels during model training. Extensive experiments on Dark Zurich and ACDC datasets show that our LDKD achieves state-of-the-art performance, demonstrating the effectiveness of our method for nighttime semantic segmentation.

Prompt-driven Latent Domain Generalization for Medical Image Classification.

Deep learning models for medical image analysis easily suffer from distribution shifts caused by dataset artifact bias, camera variations, differences in the imaging station, etc., leading to unreliable diagnoses in real-world clinical settings. Domain generalization (DG) methods, which aim to train models on multiple domains to perform well on unseen domains, offer a promising direction to solve the problem. However, existing DG methods assume domain labels of each image are available and accurate, which is typically feasible for only a limited number of medical datasets. To address these challenges, we propose a unified DG framework for medical image classification without relying on domain labels, called Prompt-driven Latent Domain Generalization (PLDG). PLDG consists of unsupervised domain discovery and prompt learning. This framework first discovers pseudo domain labels by clustering the bias-associated style features, then leverages collaborative domain prompts to guide a Vision Transformer to learn knowledge from discovered diverse domains. To facilitate cross-domain knowledge learning between different prompts, we introduce a domain prompt generator that enables knowledge sharing between domain prompts and a shared prompt. A domain mixup strategy is additionally employed for more flexible decision margins and mitigates the risk of incorrect domain assignments. Extensive experiments on three medical image classification tasks and one debiasing task demonstrate that our method can achieve comparable or even superior performance than conventional DG algorithms without relying on domain labels. Our code is publicly available at https://github.com/SiyuanYan1/PLDG/tree/main.

Factorial structure of quality of life, satisfaction with caregiving and caregiver burden in palliative care: A systematic review.

The aim of this research is to identify the main approaches and domains of palliative care quality assessment through three questionnaires used for this purpose. Systematic review. The proposed analysis process consists of three stages from 2000 to 2020: (i) massive literature search, (ii) text mining and (iii) systematic reviews carried out on the QLQ C30, Zarit Burden Interview and FAMCARE questionnaires. The Preferred Reporting Items for Systematic Reviews (PRISMA-P) have guided our research. Sixteen papers were included in our study. The main findings have been summarised using a descriptive narrative synthesis approach. Systematic reviews evidenced that such tools present variable factor structures or latent domains. The results obtained are generally representative of the evidence supporting the factor structure of the QLQ-C30 in the general cancer population. The factor structure of the Zarit Burden Interview remains ambiguous, although the idea of a unifactorial structure predominates. In the case of FAMCARE, most of the factor structures differ from the initial proposal of Kristjanson. The categorisation of the main subjective assessment approaches could be useful for the construction of a coherent system of indicators to be used in nursing practice. For its part, the variability in the latent dimensionality of the questionnaires analysed could be due to: (i) the characteristics of the sample, (ii) the population studied, (iii) cross-cultural variability, (iv) the design of the questionnaire and (v) the analysis techniques employed.

Mini-Batch Alignment: A Deep-Learning Model for Domain Factor-Independent Feature Extraction for Wi-Fi–CSI Data

Unobtrusive sensing (device-free sensing) aims to embed sensing into our daily lives. This is achievable by re-purposing communication technologies already used in our environments. Wireless Fidelity (Wi-Fi) sensing, using Channel State Information (CSI) measurement data, seems to be a perfect fit for this purpose since Wi-Fi networks are already omnipresent. However, a big challenge in this regard is CSI data being sensitive to ‘domain factors’ such as the position and orientation of a subject performing an activity or gesture. Due to these factors, CSI signal disturbances vary, causing domain shifts. Shifts lead to the lack of inference generalization, i.e., the model does not always perform well on unseen data during testing. We present a domain factor-independent feature-extraction pipeline called ‘mini-batch alignment’. Mini-batch alignment steers a feature-extraction model’s training process such that it is unable to separate intermediate feature-probability density functions of input data batches seen previously from the current input data batch. By means of this steering technique, we hypothesize that mini-batch alignment (i) absolves the need for providing a domain label, (ii) reduces pipeline re-building and re-training likelihood when encountering latent domain factors, and (iii) absolves the need for extra model storage and training time. We test this hypothesis via a vast number of performance-evaluation experiments. The experiments involve both one- and two-domain-factor leave-out cross-validation, two open-source gesture-recognition datasets called SignFi and Widar3, two pre-processed input types called Doppler Frequency Spectrum (DFS) and Gramian Angular Difference Field (GADF), and several existing domain-shift mitigation techniques. We show that mini-batch alignment performs on a par with other domain-shift mitigation techniques in both position and orientation one-domain leave-out cross-validation using the Widar3 dataset and DFS as input type. When considering a memory-complexity-reduced version of the GADF as input type, mini-batch alignment shows hints of recuperating performance regarding a standard baseline model to the extent that no additional performance due to weight steering is lost in both one-domain-factor leave-out and two-orientation-domain-factor leave-out cross-validation scenarios. However, this is not enough evidence that the mini-batch alignment hypothesis is valid. We identified pitfalls leading up to the hypothesis invalidation: (i) lack of good-quality benchmark datasets, (ii) invalid probability distribution assumptions, and (iii) non-linear distribution scaling issues.

Investigating a Common Structure of Personality Pathology and Attachment

Critical theoretical intersections between adult insecure attachment and personality disorders (PDs) suggest that they may overlap, but a lack of empirical analysis to date has limited further interpretation. The current study used a large sample ( N = 812) of undergraduates ( N = 355) and adults receiving psychological treatment ( N = 457) to test whether a joint hierarchical factor structure of personality pathology and insecure attachment is tenable. Results suggested that attachment and PD indicators load together on latent domains of emotional lability, detachment, and vulnerability, but antagonistic, impulsigenic, and psychosis-spectrum factors do not subsume attachment indicators. This solution was relatively consistent across treatment status but varied across gender, potentially suggesting divergent socialization of interpersonal problems. Although further tests are needed, if attachment and PDs prove to be unitary, combining them has exciting potential for providing an etiologic-developmental substrate to the classification of interpersonal dysfunction.

Texture representation via analysis and synthesis with generative adversarial networks

We investigate data-driven texture modeling via analysis and synthesis with generative adversarial networks. For network training and testing, we have compiled a diverse set of spatially homogeneous textures, ranging from stochastic to regular. We adopt StyleGAN3 for synthesis and demonstrate that it produces diverse textures beyond those represented in the training data. For texture analysis, we propose GAN inversion using a novel latent domain reconstruction consistency criterion for synthesized textures, and iterative refinement with a sliced Wasserstein loss for real-world textures. We propose perceptual procedures for evaluating network capabilities, exploring the global and local behavior of latent space trajectories, and comparing with existing texture analysis-synthesis techniques.

Cross-Country (Brazil and Iran) Invariance of Fractionation of Executive Functions in Early Adolescence

ABSTRACT Cultural background can influence cognition, including executive functions (EFs), abilities that encompass skills responsible for self-regulation of thoughts and behavior. The seminal unity and diversity model of EFs proposes the existence, in adulthood, of at least three correlated but separable EF latent (shared variance in more than one task/indicator) domains: inhibition, updating and shifting. However, evidence of the cross-cultural generality of this framework is lacking, especially in adolescence, an age during which these domains become more clearly separable. We tested whether this EF fractionation could be observed in early adolescents (9- to 15-year-olds) from metropolitan areas in Brazil (São Paulo) and Iran (Tehran) (total sample: 739; 407 Iranians; 358 girls). Participants carried out two open-access tasks that are representative of each EF domain and that were adapted to each cultural context. Seven latent model configurations were tested. The three-correlated latent factor structure had adequate fit, and multiple-group confirmatory factor analysis invariance testing showed invariance for country at the level of the latent factor structure (configural), factor loadings (metric), and partial invariance at the intercept (scalar) level. Iranians had higher scores in all domains. Multiple indicators multiple causes invariance testing showed model invariance across age (except for one task) and parental education. Performance in all domains improved with age and only minimally with parental schooling. We conclude that EF fractionation into three domains is present in the first half of adolescence in two samples from underrepresented populations in the literature, suggesting a potential generality of EF latent unity/diversity development at this age.

Pediatric ACEs and related life event screener (PEARLS) latent domains and child health in a safety-net primary care practice

BackgroundResearch examining the connections between individual adverse childhood experiences (ACEs) and how groupings of interrelated adversities are linked with subsequent health is scarce, limiting our understanding of risk during a period of rapid expansion of ACE screening in clinical practice. The study objective was to conduct a psychometric analysis to derive latent domains of ACEs and related life events and assess the association between each domain and health outcome.MethodsParticipants (3 months-11 years) were recruited from the University of California San Francisco Benioff’s Children Hospital Oakland Primary Care Clinic. Children were screened with the Pediatric ACEs and Related Life Events Screener (PEARLS) (n = 340), which assessed 17 total ACEs and related life events, including forms of abuse, household challenges, and social risks. Domains were constructed using confirmatory factor analysis and associations between the three identified domains and 14 health outcomes were assessed using multivariable linear and logistic regression models.ResultsThree PEARLS domains were identified: Maltreatment (ω = 0.73, ɑ=0.87), Household Challenges (ω = 0.70, ɑ=0.82), and Social Context (ω = 0.55, ɑ=0.70). Measurement invariance was supported across both gender and screening format. All domains were associated with poorer general and behavioral health and stomachaches. Maltreatment and Social Context were additionally associated with eczema while only Social Context was associated with increased odds of reporting headaches and somatic symptoms.ConclusionIn an underserved, urban west-coast pediatric population, the PEARLS found three adversity domains of Maltreatment, Household Challenges, and Social Context that all had an independent statistically significant association with poorer child health. The results provide a timely and more nuanced representation of risk that can inform clinical practice and policy using more targeted resources and interventions.

Airfoil GAN: encoding and synthesizing airfoils for aerodynamic shape optimization

Abstract The current design of aerodynamic shapes, like airfoils, involves computationally intensive simulations to explore the possible design space. Usually, such design relies on the prior definition of design parameters and places restrictions on synthesizing novel shapes. In this work, we propose a data-driven shape encoding and generating method, which automatically learns representations from existing airfoils and uses the learned representations to generate new airfoils. The representations are then used in the optimization of synthesized airfoil shapes based on their aerodynamic performance. Our model is built upon VAEGAN, a neural network that combines Variational Autoencoder with Generative Adversarial Network and is trained by the gradient-based technique. Our model can (1) encode the existing airfoil into a latent vector and reconstruct the airfoil from that, (2) generate novel airfoils by randomly sampling the latent vectors and mapping the vectors to the airfoil coordinate domain, and (3) synthesize airfoils with desired aerodynamic properties by optimizing learned features via a genetic algorithm. Our experiments show that the learned features encode shape information thoroughly and comprehensively without predefined design parameters. By interpolating/extrapolating feature vectors or sampling from Gaussian noises, the model can automatically synthesize novel airfoil shapes, some of which possess competitive or even better aerodynamic properties as compared to airfoils used for model training purposes. By optimizing shapes on the learned latent domain via a genetic algorithm, synthesized airfoils can evolve to target aerodynamic properties. This demonstrates an efficient learning-based airfoil design framework that encodes and optimizes the airfoil on the latent domain and synthesizes promising airfoil candidates for required aerodynamic performance.

Latent Domain Generation for Unsupervised Domain Adaptation Object Counting

Unsupervised cross-domain crowd counting has recently received great attention in computer vision, which generalizes the model from the source domain to the unlabeled target domain. However, it is an extremely challenging task because only unlabeled data is available from the target domain and the domain gap between two domains is implicit in crowd counting. In this paper, we propose a latent domain generation method to improve the generalization ability of unsupervised domain adaptation crowd counting by generating a latent domain. To this end, we propose a domain generator with random perturbations to learn a new latent distribution derived from the original source distribution. The latent domain generator can extract target information sampled in its stochastic latent representation, which preserves the original target information and enhances the variational ability. Meanwhile, to ensure that the generated latent domain is consistent with the source domain in counting performance, we introduce a consistency loss to encourage similar output from latent and source domains. Moreover, to enhance the adaptation ability of the generated latent domain, we apply the adversarial loss to achieve alignment between the latent and target domains. The domain generator with the adversarial loss and consistency loss ensures that the generated domain is aligned to the target while also improving the robustness of the original source domain model. The experiment indicates that our framework can effortlessly extend to scenarios with different objects (crowd, cars). The experiments also demonstrate the effectiveness of our method on unsupervised realistic-to-realistic crowd counting problems.

Health Assessment of Rotating Equipment With Unseen Conditions Using Adversarial Domain Generalization Toward Self-Supervised Regularization Learning

Traditional health assessment models work well under the assumption that the test and training samples obey a similar distribution. However, it is practically impossible to eliminate domain shifts between different tasks. Thus, most work tries to establish a data-driven approach via domain adaptation to accomplish transfer learning between different operating conditions. Sufficient target data are needed to participate in the training, which may not normally be available due to most working scenarios being unseen. An adversarial domain generalization framework with regularization learning (ADGR) is proposed for the health assessment to mine latent domains. Also, the latent domain is expanded to the unseen domain as possible. More specifically, the diversity of the sample distribution is augmented by adversarial training and the maximization of the domain discrepancy between the latent and source domains. Meanwhile, self-supervised interdomain regularization and semantical consistent regularization are proposed to mitigate the feature drift of the domain classifier and semantic divergence between source and latent domains. The case study shows that the ADGR-based health assessment approach achieves competitive prediction accuracy under unseen conditions, demonstrating its potential as a diagnostic solution.

Fractionation of executive functions in adolescents from Iran: invariance across age and socioeconomic status

AbstractExecutive functions (EFs) are cognitive skills that regulate thoughts and behavior. The seminal EF unity and diversity theoretical framework proposes the existence of three correlated EF latent domains (inhibition, updating, and switching) that become distinguishable from a certain moment during adolescence, but it is unclear how age and socioeconomic status (SES) affect these abilities. Here, we assessed 407 9-15-year-old Iranians of variable SES using an open-access battery of executive function tests that includes two tasks of each EF domain and allows for sociocultural adaptations regarding language and stimuli. Various EF model configurations proposed in the literature were tested (one, two and three EF latent factor, nested and bifactor-S-1 models) using confirmatory factor analyses. In addition, to explore the unbiased effects of age and SES, we performed invariance testing (across age and SES) using multiple indicators multiple causes (MIMIC) model to the best fitting model solution. The three-correlated EF factor model had the best fit and was mostly invariant across age and SES, with all three EF latent traits improving with age, while SES exerted only minimal positive effects on shifting and updating. We concluded that the three separable EF domains, found in adults and adolescents of other ages from different populations, can already be detected from the beginning of adolescence when culturally and psychometrically appropriate EF tasks are used. Additionally, these abilities continue to improve with age and are little affected by SES, suggesting that the unity and diversity framework is useful to study the cross-country generality of EF development.