Search

The analysis of survey data is a frequently arising issue in clinical trials, particularly when capturing quantities which are difficult to measure. Typical examples are questionnaires about patient's well‐being, pain, or consent to an intervention. In these, data is captured on a discrete scale containing only a limited number of possible answers, from which the respondent has to pick the answer which fits best his/her personal opinion. This data is generally located on an ordinal scale as answers can usually be arranged in an ascending order, for example, "bad", "neutral", "good" for well‐being. Since responses are usually stored numerically for data processing purposes, analysis of survey data using ordinary linear regression models are commonly applied. However, assumptions of these models are often not met as linear regression requires a constant variability of the response variable and can yield predictions out of the range of response categories. By using linear models, one only gains insights about the mean response which may affect representativeness. In contrast, ordinal regression models can provide probability estimates for all response categories and yield information about the full response scale beyond the mean. In this work, we provide a concise overview of the fundamentals of latent variable based ordinal models, applications to a real data set, and outline the use of state‐of‐the‐art‐software for this purpose. Moreover, we discuss strengths, limitations and typical pitfalls. This is a companion work to a current vignette‐based structured interview study in pediatric anesthesia. [ABSTRACT FROM AUTHOR]

Ordinal data such as Likert items, ratings or generic ordered variables are widespread in psychology. These variables are usually analysed using metric models (e.g., standard linear regression) with important drawbacks in terms of statistical inference (reduced power and increased type‐1 error) and prediction. One possible reason for not using ordinal regression models could be difficulty in understanding parameters or conducting a power analysis. The tutorial aims to present ordinal regression models using a simulation‐based approach. Firstly, we introduced the general model highlighting crucial components and assumptions. Then, we explained how to interpret parameters for a logit and probit model. Then we proposed two ways for simulating data as a function of predictors showing a 2 × 2 interaction with categorical predictors and the interaction between a numeric and categorical predictor. Finally, we showed an example of power analysis using simulations that can be easily extended to complex models with multiple predictors. The tutorial is supported by a collection of custom R functions developed to simulate and understand ordinal regression models. The code to reproduce the proposed simulation, the custom R functions and additional examples of ordinal regression models can be found on the online Open Science Framework repository (https://osf.io/93h5j). [ABSTRACT FROM AUTHOR]

There are numerous methods in the literature for Direction-of-Arrival (DOA) estimation, including both classical and machine learning-based approaches that jointly estimate the Number of Sources (NOS) and DOA. However, most of these methods do not fully leverage the potential synergies between these two tasks, which could yield valuable shared information. To address this limitation, in this article, we present a multi-task Convolutional Neural Network (CNN) capable of simultaneously estimating both the NOS and the DOA of the signal. Through experiments on simulated data, we demonstrate that our proposed model surpasses the performance of state-of-the-art methods, especially in challenging environments characterized by high noise levels and dynamic conditions. [ABSTRACT FROM AUTHOR]

This study proposes an interpretable neural network-based nonproportional odds model (N3POM) for ordinal regression. N3POM is different from conventional approaches to ordinal regression with nonproportional models in several ways: (a) N3POM is defined for both continuous and discrete responses, whereas standard methods typically treat the continuous variables as if they were discrete, (b) instead of estimating response-dependent finite-dimensional coefficients of linear models from discrete responses as is done in conventional approaches, we train a nonlinear neural network to serve as a coefficient function. Thanks to the neural network, N3POM offers flexibility while preserving the interpretability of conventional ordinal regression. We establish a sufficient condition under which the predicted conditional cumulative probability locally satisfies the monotonicity constraint over a user-specified region in the covariate space. Additionally, we provide a monotonicity-preserving stochastic (MPS) algorithm for effectively training the neural network. We apply N3POM to several real-world datasets. for this article are available online. [ABSTRACT FROM AUTHOR]

Human dimensions research is valuable to managing human‐wildlife interactions, especially in urban environments where such interactions are common. Survey data, which commonly contain Likert scales and questions, are useful in this field; however, these data can be difficult to analyze with formal modeling approaches. We demonstrate one approach, based on hierarchical Bayesian ordinal regression, to evaluate human‐coyote relationships in Rhode Island, USA. We implemented a survey to collect demographic and sociocultural characteristics of Rhode Island residents and information related to their knowledge of and experiences with coyotes. Our objectives were to assess how these characteristics affected respondents' valuation of and interactions (sightings and incidents) with coyotes. We analyzed 980 surveys from October to December 2020. We found that respondents who had fear of coyotes or experienced an incident between an owned animal and coyote, had the lowest valuation of coyotes. The same demographic of respondents also reported the highest sightings of and incidents with coyote. These results indicate that fearful residents, in addition to pet and livestock owners, are priority targets for disseminating information or programming about coyotes. Our analyses and findings demonstrate how Bayesian ordinal regression can provide clear and appropriate inference from survey data on how groups of people vary in their relationship with wildlife. These results are important in effectively and efficiently allocating resources towards mitigation, education, and management of human‐wildlife interactions. [ABSTRACT FROM AUTHOR]

In the field of autofocus for optical systems, although passive focusing methods are widely used due to their cost-effectiveness, fixed focusing windows and evaluation functions in certain scenarios can still lead to focusing failures. Additionally, the lack of datasets limits the extensive research of deep learning methods. In this work, we propose a neural network autofocus method with the capability of dynamically selecting the region of interest (ROI). Our main work is as follows: first, we construct a dataset for automatic focusing of grayscale images; second, we transform the autofocus issue into an ordinal regression problem and propose two focusing strategies: full-stack search and single-frame prediction; and third, we construct a MobileViT network with a linear self-attention mechanism to achieve automatic focusing on dynamic regions of interest. The effectiveness of the proposed focusing method is verified through experiments, and the results show that the focusing MAE of the full-stack search can be as low as 0.094, with a focusing time of 27.8 ms, and the focusing MAE of the single-frame prediction can be as low as 0.142, with a focusing time of 27.5 ms. [ABSTRACT FROM AUTHOR]

This article aims to analyze locals' attitudes toward tax allocation in the tourism sphere in the Republic of Uzbekistan. The analysis is based on the survey data taken from 505 respondents. We explored the impact of the frequency of travelling, age, the importance of travelling, and total family income on people's attitudes toward public financing of touri sm using the ordinal logistic regression. The results show that increasing the frequency of travelling of each respondent increases the odds of people's approval of financing tourism from taxes by two times. At the same time, surprisingly, the increase in family income reduces the probability of approving tourism's budget financing. In brief, the research contributes to the state - of-the-art literature by analyzing factors affecting people's opinions on tourism financing from tax inflow, which might play a crucial role in the development of tourism development strategies. [ABSTRACT FROM AUTHOR]

Label noise poses a significant challenge to supervised learning algorithms. Extensive research has been conducted on classification and regression tasks, but label noise filtering methods specifically designed for ordinal regression are lacking. In this paper, we propose a set of ordinal label noise filtering frameworks by theoretically exploring the generalization error bound in noisy environments. Besides, we present a robust label noise estimation method voted by inter-class distance. It takes into account the nonuniformity of ordinal labels and the reliability of the base model. This estimator is integrated into our framework in the proposed Inter-Class Distance-based Filtering (ICDF) algorithm. We empirically demonstrate the effectiveness of ICDF in identifying label noise and achieving improved generalization performance. Our experiments conducted on benchmark and real age estimation datasets show the superiority of ICDF over the existing filters in ordinal label noise cleaning. [ABSTRACT FROM AUTHOR]

Previous work has found mentally simulating events of helping others can enhance prosocial intentions. However, to date, this "prosocial simulation effect" (PSE) has only been demonstrated in North America. We provide the first preregistered replication of PSE outside of North America in a New Zealand sample, following existing protocols (Experiment 1: N = 40) and with modifications to rule out an additional confound (Experiment 2: N = 40). Moreover, given evidence that metric models are problematic for assessing ordinal data, we conducted cumulative link model (CLM)-based analyses. Both experiments provide statistically robust support for the PSE outside of North America, lending greater credence to this effect. We also show that, relative to CLM-based analyses, metric models can underestimate effects in ordinal data, yielding inconsistent results across near-identical experimental designs. We consider this issue against the backdrop of the replication crisis and recommend the use of CLM-based analyses in all research reliant on ordinal scales. General Audience Summary: Can imagination increase intentions to help others? Recent evidence suggests it can act to increase one's willingness to help a stranger in need. Thus, imagination could be a key tool for increasing prosocial intentions in people across the globe. However, existing studies demonstrating this effect are primarily from the United States, so it remains unknown whether imagination has the same effect on prosocial intentions across nations and cultures. This is critical because, even within Western countries, baseline levels of prosociality vary, with the United States being at one extreme. We conducted the first preregistered examination of this effect outside of North America with participants from New Zealand. Furthermore, we used statistical approaches more appropriate for the type of data collected in these studies. Across two experiments, we demonstrate that the enhancing effect of imagination on prosocial intentions is statistically robust and evident cross-nationally. Future work is needed to translate these findings to real-world contexts to increase cooperation as modern society deals with significant global challenges. [ABSTRACT FROM AUTHOR]

Semi-supervised ordinal regression (S2OR) has been recognized as a valuable technique to improve the performance of the ordinal regression (OR) model by leveraging available unlabeled samples. The balancing constraint is a useful approach for semi-supervised algorithms, as it can prevent the trivial solution of classifying a large number of unlabeled examples into a few classes. However, rapid training of the S2OR model with balancing constraints is still an open problem due to the difficulty in formulating and solving the corresponding optimization objective. To tackle this issue, we propose a novel form of balancing constraints and extend the traditional convex–concave procedure (CCCP) approach to solve our objective function. Additionally, we transform the convex inner loop (CIL) problem generated by the CCCP approach into a quadratic problem that resembles support vector machine, where multiple equality constraints are treated as virtual samples. As a result, we can utilize the existing fast solver to efficiently solve the CIL problem. Experimental results conducted on several benchmark and real-world datasets not only validate the effectiveness of our proposed algorithm but also demonstrate its superior performance compared to other supervised and semi-supervised algorithms [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Emotional understanding and expression plays a critical role in social interaction. To analyze children's emotional interaction automatically, this study focuses on developing a novel network architecture and a reliable algorithm for expression intensity estimation to measure children's facial expression responses to emotional stimuli. The facial expression intensity variation provides temporal dynamic information of facial behavior, which is critical to interpreting the meaning of expression. In order to avoid laborious manual annotations for expression intensity, existing unsupervised methods attempt to identify relative intensity using ordinal information within a facial expression sequence; however, they fail to estimate absolute intensity accurately. Moreover, appropriate features are needed to represent the continuous appearance changes caused by expression intensity to improve the model's ability to distinguish subtle differences in expression. This study therefore presents a novel semi-supervised method to estimate expression intensity using salient deep learning features. First, the facial expression is represented by the difference response of the convolutional neural network backbone between the target expression and its responding neutral expression, with the goal of suppressing the effects of expression-unrelated features on expression intensity estimation. Then, the pairwise data constructed with ordinal information is input into a Siamese network with a combined hinge loss that guides learning the relative intensity on unlabeled pairwise frames, the absolute intensity of a few labeled key frames, and the intensity range of most unlabeled frames. The average pearson correlation coefficient, intraclass correlation coefficient, and mean absolute error are 0.7683, 0.7405, and 0.1698 on the extended Cohn-Kanade dataset (CK+), and 0.7804, 0.6684, and 0.1864 on the Binghamton University 4D Facial Expression Dataset using the proposed method, results that are superior to the state of the art. The cross-dataset experiment indicates that the proposed method is promising for the analysis of children's emotional interactions. [ABSTRACT FROM AUTHOR]

Context. The strategic management of pigs raised in an intensive system has been conducted, in general, according to the average weight of piglets after weaning. Different models using morphometric parameters to predict the probability of any of the three weight classes (light, medium, and heavy) occurring post-weaning present themselves as an alternative to help the producer conduct these strategic managements. Aims. This study aimed to evaluate the development of suckling piglets by using morphometric parameters. Methods. A thousand simple samples were extracted at random from 268 piglets for the training data, which represent 70% of the original data set (384 piglets). The remaining 116 piglets (test data) were excluded from the analysis so as to verify the performance of the prediction (probability of each weight class to occur). Afterwards, the results were compared with the real weight class of the piglet at weaning. The variables in this research were birth weight (PWB), lactation length (Lac), and morphometric parameters of body length (BL), heart girth (HG), body mass index (BMI), ponderal index (PI), surface:mass ratio (SM), and parity order (PO). Different models were developed to predict the probability of any of the three weight classes (light, <3.967 kg; medium, 3.967-5.095 kg; and heavy, >5.095 kg) occurring at piglet weaning on the basis of their parameters 1 day postpartum. An adjustment of the ordinal regression was proposed to predict the weight classifications. Key results. The model with a significant effect of the Lac variables was selected. Conclusions and implications. One day after birth, light-weight and heavy-weight piglets, regardless of their morphometry, have a high likelihood of remaining in the same weight class at weaning. However, this does not apply to medium-sized piglets with diverse morphometry. [ABSTRACT FROM AUTHOR]

Facial expression intensity estimation has promising applications in health care and affective computing, such as monitoring patients’ pain feelings. However, labeling facial expression intensity is a specialized and time-consuming task. Ordinal regression (OR)-based methods address this issue to some extent by estimating the relative intensity but failing to estimate the absolute intensity due to lack of exploring useful information from noisy labels caused by manual and automatic labeling biases. Inspired by label distribution learning (LDL) to resist the noisy labels, this paper introduces the label-distribution-learning-enhanced OR (LDL-EOR) approach for facial expression intensity estimation. This design aims to utilize LDL to improve the accuracy of absolute intensity estimation while keeping the cost of manual labeling low. The label distribution is converted into a continuous intensity value by calculating the mathematical expectation, which makes the prediction results meet both relative and absolute intensity constraints. Ensuring the feasibility of LDL-EOR in different supervised settings, this paper presents a unified label distribution generation framework to automatically relabel training data frame by frame. The generated soft labels are used to supervise the LDL-EOR model and enhance its robustness to the noise existing in the original labels. Numerous experiments were conducted on three public expression datasets (CK+, BU-4DFE, and PAIN) to validate the superiority of LDL-EOR relative to other state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

In spite of the established literature-based evidence regarding the consequences of large truck accidents, limited body of research has been done on the characteristics and risk factors of such road accidents in Iraqi cities and governorates. According to national statistics, there has been a steady increase in the number of trucks and truck-related crashes over the past ten years. This paper aims to investigate the characteristics and risk factors associated with accidents involving large trucks in Al-Najaf governorate. A sample of 400 truck drivers were randomly selected and interviewed to collect the needed accident data. Four generalized linear models have been built; ordinal regression model for total injuries, binary logistic model for fatal accident occurrence, multinomial logit model for accident frequency, and ordinal regression model for accident cost. The analysis results revealed several influential predictors including truck driver age, education level, type of collision, truck speed, truck type, and street lighting condition. The obtained findings should be enlightening and helpful for government organizations looking to promote safety measures for sustainable freight truck transport. [ABSTRACT FROM AUTHOR]

Within the framework of the life trajectory paradigm, factors of poor health in older age may include ethnicity, as well as migration history of an individual. Estonia, with a large share of the Russian population, is a good example to analyze the impact of migration and changes in the ethnic environment on health throughout the life course. The purpose of the study is to assess differences in self–rated health of the older population (50+) living in Estonia and Russia, and identify reasons for these differences. The empirical basis of the study was data of the SHARE survey conducted in Estonia in 2010-2011 and the SAGE survey conducted in Russia in 2007-2010. The sample includes urban population aged 50+ in private households: 2,655 Estonians living in Estonia, 1,478 Russians living in Estonia, and 2,446 Russians living in Russia. The tested ordinal regression models show that the native-born in Estonia have a 39% higher chance of rating their health as good compared to Russians in Estonia, which is associated with differences in educational level in the population aged 50-64, while in the population aged 65+ it is associated with differences in living standards between the native-born and immigrants of the first and subsequent generations. At the same time, Russians from Russia are 70% (population aged 50-64) or 60% (population 65+) less likely to rate their health as good, which is related to the lifestyle and loneliness. Russians aged 65+ in Estonia who moved to the country at the age of 25+ have the same chances. The study negatives the healthy migrant effect identified in young immigrants, and also indicates health behavior and poor quality of social connections as possible reasons for poor health of the older Russian residents. [ABSTRACT FROM AUTHOR]

Silent pauses are a natural part of speech production and have consequences for speech perception. However, studies have shown mixed results regarding whether listeners process pauses in native and non-native speech similarly or differently. A possible explanation for these mixed results is that perceptual consequences of pauses differ depending on the type of processing that listeners engage in: a focus on the content/meaning of the speech versus style/form of the speech. Thus, the present study examines the effect of silent pauses of listeners' perception of native and non-native speech in two different tasks: the perceived credibility and the perceived fluency of the speech. Specifically, we ask whether characteristics of silent pauses influence listeners' perception differently for native versus non-native speech, and whether this pattern differs when listeners are rating the credibility versus the fluency of the speech. We find that while native speakers are rated as more fluent than non-native speakers, there is no evidence that native speakers are rated as more credible. Our findings suggest that the way a non-native accent and disfluency together impact speech perception differs depending on the type of processing that listeners are engaged in when listening to the speech. [ABSTRACT FROM AUTHOR]

Within the framework of the life trajectory paradigm, factors of poor health in older age may include ethnicity, as well as migration history of an individual. Estonia, with a large share of the Russian population, is a good example to analyze the impact of migration and changes in the ethnic environment on health throughout the life course. The purpose of the study is to assess differences in self–rated health of the older population (50+) living in Estonia and Russia, and identify reasons for these differences. The empirical basis of the study was data of the SHARE survey conducted in Estonia in 2010-2011 and the SAGE survey conducted in Russia in 2007-2010. The sample includes urban population aged 50+ in private households: 2,655 Estonians living in Estonia, 1,478 Russians living in Estonia, and 2,446 Russians living in Russia. The tested ordinal regression models show that the native-born in Estonia have a 39% higher chance of rating their health as good compared to Russians in Estonia, which is associated with differences in educational level in the population aged 50-64, while in the population aged 65+ it is associated with differences in living standards between the native-born and immigrants of the first and subsequent generations. At the same time, Russians from Russia are 70% (population aged 50-64) or 60% (population 65+) less likely to rate their health as good, which is related to the lifestyle and loneliness. Russians aged 65+ in Estonia who moved to the country at the age of 25+ have the same chances. The study negatives the healthy migrant effect identified in young immigrants, and also indicates health behavior and poor quality of social connections as possible reasons for poor health of the older Russian residents. [ABSTRACT FROM AUTHOR]

This paper presents a class of regression models with cumulative logistic functions that are chiefly designed to analyse spatially dependent ordinal data. In contrast to previous works, the proposed model requires neither the sites to be regularly spaced nor the assumption of an underlying continuous variable. It belongs to a more general class of Markov random field models, and can be considered an extension of the ordinal regression model with the proportional odds link function. Our proposed model allows practitioners to interpret the model parameters using odds ratios. Apart from the theoretical developments, this work also highlights the practical aspects of model fitting, including parameterisation, selection of neighbourhood, and calculation of standard errors. Simulation studies with regularly and irregularly spaced sites were conducted. Modelling strategies including pseudo-likelihood methods were found to be useful in both settings. The proposed model and the non-spatial counterpart were applied to the daily air quality index measured in the United Kingdom. The results indicate the presence of spatial effects and the incorporation of spatial effects led to better model performance in terms of various goodness-of-fit measures. [ABSTRACT FROM AUTHOR]

Motivated by data measuring progression of leishmaniosis in a cohort of US dogs, we develop a Bayesian longitudinal model with autoregressive errors to jointly analyze ordinal and continuous outcomes. Multivariate methods can borrow strength across responses and may produce improved longitudinal forecasts of disease progression over univariate methods. We explore the performance of our proposed model under simulation, and demonstrate that it has improved prediction accuracy over traditional Bayesian hierarchical models. We further identify an appropriate model selection criterion. We show that our method holds promise for use in the clinical setting, particularly when ordinal outcomes are measured alongside other variables types that may aid clinical decision making. This approach is particularly applicable when multiple, imperfect measures of disease progression are available. [ABSTRACT FROM AUTHOR]

Accurate maturity identification of permanent teeth for children and adolescents using orthopantomogram (OPG) images is crucial in pediatric dentistry.Although recent advancements in deep learning have shown promising outcomes in maturity staging of third molars and mandibular permanent dentition, limited research has focused on assessing the entire dentition. Furthermore, accurate performance is hindered due to variations in tooth appearance and similarities between adjacent stages. This paper develops an automatic methodology to identify the tooth maturity stages of the full permanent dentition. Specifically, a tooth localization model based on YOLOv3 is presented to detect and number each candidate permanent tooth. Subsequently, we propose a novel symmetric and ordinal staging network (SOS-Net) for the precise maturity identification of each tooth. SOS-Net incorporates a symmetric feature combination block (SFC Block) based on bilateral facial symmetry to enhance discriminative feature representation in order to improve performance, while minimizing increases in model parameters. Additionally, we introduce an auxiliary regression branch with a novel loss called adjacent stage aware (ASA) loss to provide information in the order of maturity levels and effectively reduce misclassification between adjacent stages. The proposed methodology is evaluated on a private OPG image dataset collected from individuals aged 3 to 14 years. The ablation studies and visual analysis of SOS-Net verified the effectiveness and interpretability of the SFC block and ASA loss, with a F1-score improvement of 3.77 % . Moreover, comparative experiments demonstrate the good performance of the proposed methodology compared to state-of-the-art methods in maturity staging and age estimation. [ABSTRACT FROM AUTHOR]

Background: Oral health knowledge forms part of oral health literacy that enables individuals to inform appropriate oral health decisions and actions. Oral health-related quality of life (OHRQoL) characterizes self-perception of well-being influenced by oral health. This study aimed to examine the relationship between oral health knowledge and OHRQoL. Methods: A random sample of 19-to-24-year-old first-year undergraduate students (n = 372) in Minnesota, United States of America was used. Each student was assessed with an online survey using the Comprehensive Measure of Oral Health Knowledge (CMOHK) and the OHRQoL items of the World Health Organization (WHO) Oral Health Questionnaire for Adults. Relationships between OHRQoL parameters and CMOHK together with other covariates were assessed using ordinal regression models. Associations between OHRQoL parameters were examined with the Kendall's tau-b method. Results: Dry mouth (45%) was the most reported OHRQoL issue. The respondents showing good oral health knowledge were less likely to experience speech or pronunciation difficulty (β=-1.12, p = 0.0006), interrupted sleep (β=-1.43, p = 0.0040), taking days off (β=-1.71, p = 0.0054), difficulty doing usual activities (β=-2.37, p = 0.0002), or reduced participation in social activities due to dental or oral issues (β=-1.65, p = 0.0078). Conclusions: This study suggested a protective effect of better oral health knowledge on specific OHRQoL issues. In addition to provision of affordable dental services, university-wide oral health education can be implemented to improve OHRQoL in undergraduate students. [ABSTRACT FROM AUTHOR]

The paper focuses on the issue of motivation for military service in the Czech Armed Forces. It aims to map the Institutional-Occupational (I-O) motivations of the generation of Czech recruits currently starting their military career. The research sample consisted of 1557 recruits. Institutional preference was confirmed. The influence of gender, age, education, partner life and parenthood on these factors were also analyzed. From an institutional point of view, significant influence of age and education was found. From an occupational point of view, results showed, that again age, education and type of partnership cohabitation have a significant influence. [ABSTRACT FROM AUTHOR]

Estimates of resident satisfaction with public education have great utility in public administration, especially among decision makers in shrinking small communities. But such estimates are typically obtained via surveys, which are costly and often unreliable at high spatial resolutions given low response rates. Our study found that satisfaction with public schools among residents of small communities can be reasonably estimated at the community level using public data. Several models generalized adequately to unseen data—these models typically included the following covariates: state student assessment scores, school reorganizations, net open enrollment, and the cost of educational outcomes relative to neighboring districts. Our findings thus amount to a cost‐effective survey alternative for gauging satisfaction with public schools in small Iowa communities. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is a chronic complication of diabetes that damages the retinal blood vessels, leading to impaired vision and even blindness, and is one of the top three eye diseases causing human blindness. An effective DR grading algorithm can help ophthalmologists to diagnose patients and improve efficiency. Therefore, we propose a fusion network based on transformer and convolutional neural network (CNN) to perform DR grading. The proposed approach addresses two critical issues in the task: i) The CNN-based DR classification method has a small receptive field, so the range of available information is limited. The Transformer-based DR classification method has a large receptive field, but it is easy to lose local details; ii) Existing approaches treat DR grading as a traditional multiclass classification task, which ignores ordinal information between DR of different levels. To address i), we fuse the multi-level features of CNN and Transformer at different stages, and realize the enhancement and interaction of local and global information through the fusion module. To address ii), we propose a KC loss by formulating DR grading as a joint ordinal regression and multiclass classification problem, and obtain both category-supervised information and ordinal supervised information. Extensive qualitative and quantitative assessments have shown that our approach achieves superior performance on publicly available DeepDR and IDRiD datasets. [ABSTRACT FROM AUTHOR]

Offshore wind farms are increasingly part of the modern coastal landscape and are often the reason for public opposition. To inform policymakers and to facilitate public participation strategies, the present study examines public opinion concerning offshore wind energy projects on the Belgian coast, its evolution over time and significant determinants. Public opinion is compared for three moments in time. A significant increase in acceptance was found between 2002 (planning phase prior to construction) and 2009 (turbines operational and more under construction). Acceptance remained at a high level from 2009 to 2019 with expansion still ongoing. Familiarization led to a reduction in negative attitudes. In the current population (2019), the visibility of the turbines has no influence on attitudes. Support for wind energy can be ensured when the facilities are perceived as part of the coast's identity and when perceived impacts can be kept low. [ABSTRACT FROM AUTHOR]

Cities are home to a significant proportion of the population in the EU, providing access to job opportunities and public services and, subsequently, driving economic growth. However, cities also face social and environmental challenges such as poverty, prohibitively high housing costs, discrimination, crime, excessive noise and air pollution. This raises the issue of how residents in European cities perceive their lives and assess their overall well-being and satisfaction with the amenities in their city. A U-shaped relationship between life satisfaction and age is tested in a sample of European cities using data from the Quality of Life in European Cities survey, with higher levels of satisfaction expected among younger and older individuals. The results supported the hypothesis and provided evidence for the importance of considering age in the analysis of well-being in urban settings. Subjective well-being is not only influenced by personal factors such as age and individual experiences but also by the quality of the urban environment. The second part employs ordinal logistic regression to analyse individual and contextual factors of well-being in four Czech and Slovak cities, namely Prague, Ostrava, Bratislava, and Košice. [ABSTRACT FROM AUTHOR]

The study presents the economic, managerial, and societal perspectives on corporate social responsibility (CSR) as a basis for adding value to enterprises. It investigates the interplay between the digitalisation of activities and the management of Bulgarian financial enterprises, with a focus on HRM and CSR initiatives in a pandemic situation. The study tests the hypothesis that, in pandemic conditions, the CSR of Bulgarian financial enterprises is positively correlated with the digitalisation of general and human resource management. To assess the level of engagement of financial enterprises with CSR causes during the pandemic, the study employs a methodology comprising descriptive statistics and ordinal regression. The main conclusion, based on a nationally representative survey of Bulgarian financial enterprises, is that banks and insurers that heavily invest in digitalisation have demonstrated a higher level of commitment to CSR causes during the COVID-19 pandemic, while conservative and less digitally advanced financial enterprises have had limited CSR activity. By adopting fintech and insurtech solutions directed towards societal needs, market demands, and customer satisfaction, financial enterprises increase their efficiency. Our analysis confirms the interplay between the digitalisation of financial enterprises and support for CSR causes. [ABSTRACT FROM AUTHOR]

National uniform legislation exists in federations to implement national reforms where the central government does not have the direct authority to legislate under the Constitution. The State jurisdictions must work together on legislation to address urgent issues of national concern, national uniform legislation. Developing and drafting national uniform legislation are complicated and complex because they require the cooperation of many units with asymmetrical knowledge, competing priorities, limited budgets and timeframes, and at times irreconcilable differences. Empirical data analysis and statistics could provide an aid for decision-making in these circumstances. On examination of a large body of legal information on the 69 most significant Australian national reforms, this article finds factors that inhibit or promote sustainable uniformity of enacted legislation by using ordinal regression for the first time. This work provides significant evidence-based insights into the process of harmonisation in federations. Overall, our findings contradict the general belief that the uniformity is mostly dependent on structures alone (referred, applied, mirror, and hybrid). If sustainable uniformity is the goal,the decision-makers must allow resources for establishing the national regulator, ensure maximum uptake by the majority of the nine Australian jurisdictions, support the development of national uniform legislation through the National Cabinet, and be prepared for the second wave of national reforms through consecutive reforms. These findings have valuable strategic implications for policymakers, law reform agencies, and legislative drafters who intend to rely on evidence for future decision-making in terms of the most important national reforms. This paper provides recommendations for governments intending to ensure the sustainability of uniformity and adaptability of the Australian legislation for any future changes without losing the important consensus that has been achieved. The findings are also important for other federations seeking to implement harmonised legislation. [ABSTRACT FROM AUTHOR]

In recent times, deep neural networks achieved outstanding predictive performance on various classification and pattern recognition tasks. However, many real-world prediction problems have ordinal response variables, and this ordering information is ignored by conventional classification losses such as the multi-category cross-entropy. Ordinal regression methods for deep neural networks address this. One such method is the CORAL method, which is based on an earlier binary label extension framework and achieves rank consistency among its output layer tasks by imposing a weight-sharing constraint. However, while earlier experiments showed that CORAL's rank consistency is beneficial for performance, it is limited by a weight-sharing constraint in a neural network's fully connected output layer, which may restrict the expressiveness and capacity of a network trained using CORAL. We propose a new method for rank-consistent ordinal regression without this limitation. Our rank-consistent ordinal regression framework (CORN) achieves rank consistency by a novel training scheme. This training scheme uses conditional training sets to obtain the unconditional rank probabilities through applying the chain rule for conditional probability distributions. Experiments on various datasets demonstrate the efficacy of the proposed method to utilize the ordinal target information, and the absence of the weight-sharing restriction improves the performance substantially compared to the CORAL reference approach. Additionally, the suggested CORN method is not tied to any specific architecture and can be utilized with any deep neural network classifier to train it for ordinal regression tasks. [ABSTRACT FROM AUTHOR]

In many medical applications, interpretable models with high prediction performance are sought. Often, those models are required to handle semistructured data like tabular and image data. We show how to apply deep transformation models (DTMs) for distributional regression that fulfill these requirements. DTMs allow the data analyst to specify (deep) neural networks for different input modalities making them applicable to various research questions. Like statistical models, DTMs can provide interpretable effect estimates while achieving the state‐of‐the‐art prediction performance of deep neural networks. In addition, the construction of ensembles of DTMs that retain model structure and interpretability allows quantifying epistemic and aleatoric uncertainty. In this study, we compare several DTMs, including baseline‐adjusted models, trained on a semistructured data set of 407 stroke patients with the aim to predict ordinal functional outcome three months after stroke. We follow statistical principles of model‐building to achieve an adequate trade‐off between interpretability and flexibility while assessing the relative importance of the involved data modalities. We evaluate the models for an ordinal and dichotomized version of the outcome as used in clinical practice. We show that both tabular clinical and brain imaging data are useful for functional outcome prediction, whereas models based on tabular data only outperform those based on imaging data only. There is no substantial evidence for improved prediction when combining both data modalities. Overall, we highlight that DTMs provide a powerful, interpretable approach to analyzing semistructured data and that they have the potential to support clinical decision‐making. [ABSTRACT FROM AUTHOR]

Morphology often reflects ecology, enabling the prediction of ecological roles for taxa that lack direct observations, such as fossils. In comparative analyses, ecological traits, like diet, are often treated as categorical, which may aid prediction and simplify analyses but ignores the multivariate nature of ecological niches. Furthermore, methods for quantifying and predicting multivariate ecology remain rare. Here, we ranked the relative importance of 13 food items for a sample of 88 extant carnivoran mammals and then used Bayesian multilevel modeling to assess whether those rankings could be predicted from dental morphology and body size. Traditional diet categories fail to capture the true multivariate nature of carnivoran diets, but Bayesian regression models derived from living taxa have good predictive accuracy for importance ranks. Using our models to predict the importance of individual food items, the multivariate dietary niche, and the nearest extant analogs for a set of data-deficient extant and extinct carnivoran species confirms long-standing ideas for some taxa but yields new insights into the fundamental dietary niches of others. Our approach provides a promising alternative to traditional dietary classifications. Importantly, this approach need not be limited to diet but serves as a general framework for predicting multivariate ecology from phenotypic traits. [ABSTRACT FROM AUTHOR]

Label distribution learning achieved promising results on ordinal regression tasks such as facial age and attractiveness estimation, especially using deep label distribution learning (DLDL) methods, introducing the label distribution learning into deep convolutional neural networks. However, existing DLDL methods have an inconsistency between the training objectives and the evaluation metric, so they may be suboptimal. In addition, these methods always adopt image classification or face recognition models with a large amount of parameters, which carry expensive computation cost and storage overhead. In this paper, we firstly analyze the essential relationship between two state-of-the-art methods (ranking CNN and DLDL) and show that the ranking method is in fact learning label distribution implicitly. This result thus firstly unifies two existing popular state-of-the-art methods into the DLDL framework. Second, in order to alleviate the inconsistency and reduce resource consumption, we design a lightweight network architecture and propose a unified framework which can jointly learn label distribution and regress expectation value. The effectiveness of our approach has been demonstrated on typical ordinal regression tasks including facial age and attractiveness estimation. Our method achieves new state-of-the-art results using the single model with 36× fewer parameters and 3× faster inference speed. [ABSTRACT FROM AUTHOR]

The paper examines state-level trends in Bihar for determining patterns in farm diversification for the period 1990-91 to 2018-19, using the Simpson Index of Diversification (SID) and ordinal linear regression analysis to analyse the determinants. The study, conducted in the year 2022, reported that the cropping system at the state level is transforming from food grains to different high-value crops and allied farming sectors. The transformation was not uniform across the regions. The SID values have demonstrated how the agricultural economy has been more diverse over time, with some variations in the production of food and non-food crops. The result of multiple regressions has revealed earning members, social work participation, and government donations to be the major determinants of farm diversification, and various constraints were identified using the Garrett ranking method. Hence, the study suggests that policy support for the development of dairy farmers should be more focused on increased cropping intensity, insurance protection, investments in agricultural research and education, and technology development. [ABSTRACT FROM AUTHOR]

Psychological problems are complex in nature and accurate identification of these problems is important. For the identification of psychological problems, one of the preliminary tools is the use of interviews/questionnaires. Questionnaires are preferred over interviews if the group under study is large. A strengths and difficulties questionnaire (SDQ) is one of the most widely used and powerful questionnaires to identify behavioral problems and distresses being faced by the respondents, affecting their day-to-day lives (responsible for social dysfunction). This study was held on college/university students in India, with the objective of examining if the extent of social dysfunction as measured by an impact score can be extracted from behavioral problems which are the components of the difficulty score of SDQ. Two surveys were conducted during the COVID-19 pandemic period, between the months of May-June 2020 and October 2020-February 2021 for the study. Only those responses were considered who felt distressed ("yes" to item 26 of SDQ). The numbers of such responses were 772/1020 and 584/743, respectively, in the two surveys. Distress levels were treated as ordered variables and three categories of distress level, viz., "Normal", "Borderline", and "Abnormal" were estimated through behavioral problems using ordinal regression (OR) methods with a negative log-log link function. The fitting of OR models was tested and accepted using Cox and Snell, Nagelkerke, and McFadden test. Hyperactivity-inattention and emotional symptoms were significant contributors to estimating levels of distress among respondents in survey 1 (p < 0.05). In addition to these components, in survey 2, peer problems were also significant. OR models were good at estimating the extreme categories; however, the "Borderline" category was not estimated well. One of the reasons was the use of qualitative and complex data with the least wide "Borderline" category, both for the "Difficulty" and the "Impact" scores. [ABSTRACT FROM AUTHOR]

Background: Availability of personal protective equipment (PPE) and its effective use may influence safety climate perceptions among health care personnel (HCP). It is unclear how health care organizations can leverage the effective use of respiratory protection to engage in continuous improvement of their safety climate, which can inform opportunities for employee education and engagement. Methods: After using an elastomeric half mask respirator (EHMR) as their primary form of respiratory protection for several months, 1,080 HCP provided feedback in an electronic survey about respiratory protection training, confidence in EHMR use, barriers during use, and perceived safety climate. Ordinal logistic regressions were used as nonlinear models to test relationships between these variables. Findings: We observed that an increase in user confidence (p <.013), training content (p <.001), training formats (p <.001), and a decrease in EHMR barriers (p <.001) were associated with a statistically significant increase in proactive safety climate. In the second model, an increase in user confidence (p <.006) and training content (p <.001), and a decrease in barriers (p <.001), was associated with a statistically significant increase in compliant safety climate. Conclusions/Application to Practice: HCP EHMR confidence was positively associated with safety climate perceptions, underscoring the value of competency building by respiratory protection leaders prior to implementation. Because fewer barriers experienced while using an EHMR were associated with a more positive perception of safety climate, it is important to first communicate with end users about potential barriers and, second, to continue research with end users and manufacturers to improve the design of EHMRs moving forward. [ABSTRACT FROM AUTHOR]

Purpose: State-owned enterprises' (SOEs) goals are perceived as two-sided blades, providing goods or services to the public on one side and escalating the government's wealth on the other side. Treating the SOEs, government encounters the problem of injection strategy or privatize them. At the same time, managers have the option to formulate the SOEs strategy to boost performance. By using Miles and Snow's typology strategy and the above factors, this paper investigates those impacts on Indonesia's SOEs' performance. This study aims to propose strategic typology as the main predictor with other variables such as the size, ownership structure, market competitiveness and capital subsidy on SOEs. Design/methodology/approach: The study uses archived SOEs' financial data from 2014 to 2018 to predict the financial performance using ordinal logistic regression analysis. The additional factors, such as firm size, ownership structure, market concentration and capital subsidy, are incorporated. Findings: The result demonstrates that SOEs strategic typology, market concentration, size, ownership structure and capital subsidy significantly affect Indonesia's SOEs' performance. Originality/value: To the best of the authors' knowledge, this paper is the first elaborating government policies for SOEs, such as capital subsidy and state ownership, on the perspective of Miles and Snow's strategy-performance relationship. Correspondingly, the paper contributes to examine the Indonesian characteristic SOE type with the performance. No single study has previously explored this relationship in the context of SOE in Indonesia. [ABSTRACT FROM AUTHOR]

The assessment of bone age is important for evaluating child development, optimizing the treatment for endocrine diseases, etc. And the well-known Tanner-Whitehouse (TW) clinical method improves the quantitative description of skeletal development based on setting up a series of distinguishable stages for each bone individually. However, the assessment is affected by rater variability, which makes the assessment result not reliable enough in clinical practice. The main goal of this work is to achieve a reliable and accurate skeletal maturity determination by proposing an automated bone age assessment method called PEARLS, which is based on the TW3-RUS system (analysis of the radius, ulna, phalanges, and metacarpal bones). The proposed method comprises the point estimation of anchor (PEA) module for accurately localizing specific bones, the ranking learning (RL) module for producing a continuous stage representation of each bone by encoding the ordinal relationship between stage labels into the learning process, and the scoring (S) module for outputting the bone age directly based on two standard transform curves. The development of each module in PEARLS is based on different datasets. Finally, corresponding results are presented to evaluate the system performance in localizing specific bones, determining the skeletal maturity stage, and assessing the bone age. The mean average precision of point estimation is 86.29%, the average stage determination precision is 97.33% overall bones, and the average bone age assessment accuracy is 96.8% within 1 year for the female and male cohorts. [ABSTRACT FROM AUTHOR]

Purpose: Socioeconomic factors are known to modulate health. Concerning sleep apnea, influences of income, education, work, and living in a partnership are established. However, results differ between national and ethnic groups. Results also differ between various clinical studies and population-based approaches. The goal of our study was to determine if such factors can be verified in the population of Pomerania, Germany. Methods: A subgroup from the participants of the population-based Study of Health in Pomerania volunteered for an overnight polysomnography. Their data were subjected to an ordinal regressions analysis with age, sex, body mass index (BMI), income, education, work, and life partner as predictors for the apnea–hypopnea index. Results: Among the subgroup (N = 1209) from the population-based study (N = 4420), significant effects were found for age, sex, and BMI. There were no significant effects for any of the socioeconomic factors. Conclusion: Significant effects for well-established factors as age, sex, and BMI show that our study design has sufficient power to verify meaningful associations with sleep apnea. The lack of significant effects for the socioeconomic factors suggests their clinical irrelevance in the tested population. [ABSTRACT FROM AUTHOR]

Within the highly complex ecosystem of industry-university collaboration in open innovation, three specific antecedents typically characterize the patterns of their interaction, i.e., motivations, barriers, and channels of knowledge transfer. However, an investigation of the extent to which these antecedents of opening up innovation impact the perceived importance of universities as an external knowledge source to the industry is still missing in the literature. Based on a research framework developed from a review of the literature, a two-stage ordinal regression, and neural network approach was performed to investigate this impact. In the first stage, the hypotheses of the proposed research framework were tested based on an ordinal regression, and those antecedents that significantly impacted the importance perception were revealed. In the second stage, an artificial neural network analysis was carried out to capture the complex relationships among the significant antecedents and the important perception of universities as an external knowledge source to the industry. On the whole, the findings of our study expand the existing open innovation literature and contribute to a more articulate view of the collaboration between industry and university in this field by providing a first perspective on which of the three antecedents has a significant impact on this perception and how such an impact can be predicted. [ABSTRACT FROM AUTHOR]

This paper presents a result of research about the student's radical intention related to their tolerance and personality type. The main research variable that is radical intention has a psychological construct that is theoretically built with a social approach and political point of view. As a big country, Indonesia has various pluralism i.e ethnic and religion, so that it requires a high tolerance attitude to live in a harmony. Students as the next generation and important elements in society are expected to avoid intolerance. The research subjects were 175 students from an Islamic university in Indonesia. The data were analyzed with Ordinal Regression which intention of radicalism (ordinal) as the dependent variable, personality type (nominal), and tolerance attitude level (ordinal) as independent variables. The majority of these students have good moral values so they can tolerate the difference. From the regression analysis, only a tolerance attitude has a significant effect on radicalism intention. [ABSTRACT FROM AUTHOR]

Objective: Menopause is associated with multiple health risks. In several studies, a higher incidence or a higher risk for obstructive sleep apnea (OSA) in post-menopausal than pre-menopausal women is reported. This study was designed to verify such a connection between menopause and OSA in a population-based sample. Methods: For a subsample (N = 1209) of the Study of Health in Pomerania (N = 4420), complete polysomnography data was available. Of these, 559 females completed a structured interview about their menstrual cycle. Splines and ordinal regression analysis were used to analyze the resulting data. Results: In the ordinal regression analysis, a significant association between the apnea–hypopnea index (AHI) and menopause indicated that post-menopausal women had a substantially higher risk of OSA. In accordance with previous studies, risk indicators such as body mass index (BMI), age, and the influence of hysterectomies or total oophorectomies were included in the model. Conclusions: Our results clearly confirmed the assumed connection between menopause and OSA. This is important because OSA is most often associated with male patients, and it warrants further research into the underlying mechanisms. [ABSTRACT FROM AUTHOR]

Public expectations of forests as high-quality restorative environments that facilitate subjective well-being and stress relief along with numerous health benefits have been rising sharply during recent decades. In addition, the COVID-19 pandemic and its accompanying restrictive measures also transformed forests into some of the few places to spend time away from home. The presented study drew on the assumption that the pandemic situation and a rise in the number of forest visits would affect the experience, recognition, and appreciation of the well-being aspects related to spending time in forests. The study goal was to elucidate the potential effects of the COVID-19 pandemic on the relationships between forest visits, well-being and stress relief, emotions, perception of nature and forest value and importance, pro-environmental behavior, and societal expectations of the role of forests and forest ecosystem services. A survey using a digital questionnaire was conducted several months after the pandemic outbreak on a representative sample of the Slovak population. The Wilcoxon test and ordinal regression analysis were used to identify significant relationships, e.g., between the recency of anger episodes and the number of forest visits. The results showed that the pandemic strengthened the perception of forests as a high-quality restorative environment and that emotions associated with forest visits played an important role in the perceived importance of forests and their possible overexploitation. The results underscore the urgent need to put demands for forest recreation on par with the forest bioeconomy and to sensitize forest visitors to management and conservation requirements. [ABSTRACT FROM AUTHOR]

Compared to the nominal scale, the ordinal scale for a categorical outcome variable has the property of making a monotonicity assumption for the covariate effects meaningful. This assumption is encoded in the commonly used proportional odds model, but there it is combined with other parametric assumptions such as linearity and additivity. Herein, the considered models are non-parametric and the only condition imposed is that the effects of the covariates on the outcome categories are stochastically monotone according to the ordinal scale. We are not aware of the existence of other comparable multivariable models that would be suitable for inference purposes. We generalize our previously proposed Bayesian monotonic multivariable regression model to ordinal outcomes, and propose an estimation procedure based on reversible jump Markov chain Monte Carlo. The model is based on a marked point process construction, which allows it to approximate arbitrary monotonic regression function shapes, and has a built-in covariate selection property. We study the performance of the proposed approach through extensive simulation studies, and demonstrate its practical application in two real data examples. [ABSTRACT FROM AUTHOR]

Raspberry (Rosales: Rosaceae) production in the U.K. has moved rapidly in the last 10 years to under polythene, combined with a reduced availability of broad-spectrum fungicides. Hence, the incidence of previously less prevalent diseases, such as Cladosporium (Capnodiales: Cladosporiaceae), has largely increased. This study aimed to identify the predominant Cladosporium species on raspberry and to understand the nature of its infection on raspberry fruit. Raspberries were collected from farms across the U.K. and Spain and incubated; fungal isolates were then isolated from typical Cladosporium lesions and identified to the species level based on the sequences of the trans elongation factor α and actin genes. Cladosporium cladosporioides (Fres) de Vries was confirmed as the predominant species responsible for infecting raspberry fruit close to harvest on fruit from the U.K. and Spain, being present on 41.5% of U.K. fruit and 84.6% of Spanish fruit. Raspberries were subsequently inoculated at different developmental stages with C. cladosporioides isolates to determine the susceptibility to Cladosporium skin lesions and stigmata infections in relation to the developmental stage. Only the ripening and ripe raspberries were susceptible to Cladosporium, resulting in skin lesions. Cladosporium can colonise the stigmata of raspberries earlier in fruit development and future research is required to determine if such stigmata infections could cause subsequent skin lesion infections. This study has provided the necessary epidemiological information to develop effective management measures against the Cladosporium species. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic raised the need for an increase in public services to counter the negative economic ramifications of the pandemic. However, this meteoric emergence of coronavirus inadvertently gave birth to inefficiencies entrenched in the delivery of government interventions to contain the disease and its economic effects. The purpose of this paper is to investigate the efficiency in delivery of government services and interventions aimed at ameliorating the COVID-19 pandemic. This study uses descriptive statistics and ordinal regression analysis to identify the drivers of inefficiency perceptions among recipients of social security interventions during the pandemic. Survey data for a sample of 855 participants was drawn from King Cetshwayo District municipality in KwaZulu Natal, South Africa. The key findings revealed that the delivery of most government interventions in South Africa was perceived as not well coordinated and poorly communicated, hence inefficient. Drivers of these perceptions included age, income level, race, and employment status. In addition, whether or not an individual had received some form of social security assistance during the pandemic also influenced their perceptions about government efficiency in providing social security support. We recommend strengthening monitoring and evaluation mechanisms across government service delivery initiatives and improving communication of government programs to improve user experience and access. [ABSTRACT FROM AUTHOR]

Ordinal regression methods are widely used to predict the ordered labels of data, among which support vector ordinal regression (SVOR) methods are popular because of their good generalization. In many realistic circumstances, data are collected by a distributed network. In order to protect privacy or due to some practical constraints, data cannot be transmitted to a center for processing. However, as far as we know, existing SVOR methods are all centralized. In the above situations, centralized methods are inapplicable, and distributed methods are more suitable choices. In this paper, we propose a distributed SVOR (dSVOR) algorithm. First, we formulate a constrained optimization problem for SVOR in distributed circumstances. Since there are some difficulties in solving the problem with classical methods, we used the random approximation method and the hinge loss function to transform the problem into a convex optimization problem with constraints. Then, we propose subgradient-based algorithm dSVOR to solve it. To illustrate the effectiveness, we theoretically analyze the consensus and convergence of the proposed method, and conduct experiments on both synthetic data and a real-world example. The experimental results show that the proposed dSVOR could achieve close performance to that of the corresponding centralized method, which needs all the data to be collected together. [ABSTRACT FROM AUTHOR]

Introduction: Suicidal ideation (SI) and attempts (SA) are prevalent in late adolescence and emerging adulthood. Prior research has identified perceived support as a correlate of SI and SA. Less is known, though, about the role of perceived support in differentiating among suicidal outcomes and between the incremental escalation of suicidal outcomes from SI to SA to serious suicide attempts (SSA). Method: Using ordinal regression, we used Wave 1 and 2 data from the National Longitudinal Study of Adolescent to Adult Health (N = 4500; 53% female; Mage = 16.6; 12% Hispanic) to examine cross‐sectional, longitudinal, and transitional models of perceived support and suicidality. Results: Cross‐sectional results indicated that youths with higher perceived support were less likely to have suicidal ideation. Longitudinal results showed that youths with higher perceived support at Wave 1 were less likely to have suicidal ideation or serious suicide attempts at Wave 2. Transitional model results revealed that higher perceived support at Wave 1 was negatively associated with escalation in suicidal outcomes from Wave 1 to 2. Conclusion: We discuss findings in the context of theories of suicide and discuss implications for suicide risk identification, intervention, and prevention efforts in late adolescence and emerging adulthood. [ABSTRACT FROM AUTHOR]

Face anti-spoofing is a crucial link to ensure the security of face recognition. This paper proposes a novel face anti-spoofing method, which performs ordinal regression with representative feature strengthening to learn generalized and discriminative representation for the live and spoof face classification. Specifically, we propose a semantic label schema, which encodes the inter-class ordinal relationships among live and various spoof faces into supervision information to supervise deep neural networks to perform ordinal regression. It enables the learned model to finely constrain the relative distances among features of different categories in the feature space according to the ordinal relationships. The representative feature strengthening network is designed to strengthen important features and meanwhile weaken redundant features for the classification decision. It leverages a dual-task architecture that takes the same single image as input and shares representations via feature fusing blocks. The network first fuses hierarchical paired convolutional features of two streams to learn the common concern of the two related tasks and then, aggregates the learned local convolutional features into a global representation by a learnable feature weighting block. The network is trained to minimize the Kullback–Leibler divergence loss in an end-to-end manner supervised by the semantic labels. Extensive intra-dataset and cross-dataset experiments demonstrate that the proposed method outperforms the state-of-the-art approaches on four widely used face anti-spoofing datasets. [ABSTRACT FROM AUTHOR]

This paper proposes a novel end-to-end pipeline that uses the ordinal information and relative relation of images for visibility estimation (VISOR-NET). By encoding ordinal information into a set of relatively ordered image pairs, VISOR-NET can learn a global ranking function effectively. Due to the lack of real scenes or continuous labels in public foggy datasets, we collect a large-scale dataset that we term Foggy Highway Visibility Images (FHVI), which are taken from real surveillance scenes, and synthesize an INDoor Foggy images dataset (INDF) with continuous annotation. This work measures the estimation effectiveness on two public datasets and our FHVI dataset as a classification task and then on the INDF dataset as a regression task. Comprehensive experiments with existing deep-learning methods demonstrate the performance of the proposed method in terms of estimation accuracy, the convergence rate, model stability, and data requirements. Moreover, this method can extend inter-level visibility estimation to intra-level visibility estimation and can realize approximate regression estimation under discrete-level labels. [ABSTRACT FROM AUTHOR]