Search

This paper reviews the role of ANOVA correction model in the homogenization of climatic time series. In the present context ANOVA has only weak connection to its original meaning (analysis of variance), so we propose the new name "Benova" to replace the confusing old name. In the linear model of Benova corrections (hereafter Benova) the information of statistically detected inhomogeneities and metadata are jointly considered for all time series of a given climatic region. Benova has indisputable advantages on the accuracy of homogenization results, and this has both theoretical and practical evidence. The study presents two principal versions of Benova: in simple Benova the climate signal is presumed to be spatially invariant, while in weighted Benova the spatial variation of climate is considered. In Benova models usually only breaks (i.e., sudden shifts of section mean) are considered, but this restriction has practical reasons, rather than theoretical limits, and the study shows an extended version of the method with which trend‐like inhomogeneity biases can also be removed. Benova can be used for a group of time series covering varied time periods, the operations can be performed in any time resolution, and statistical characteristics others than climatic means can also be homogenized by the method. Benova can be used together with any break detection method. The study discusses the likely reasons of the relatively slow spread in practical application. PRODIGE was the first homogenization method which used Benova corrections. Until now, all homogenization methods including Benova corrections include also the same kind break detection method, i.e., penalized maximum likelihood method with step function fitting. The brief descriptions of two modern methods of this method family, that is, ACMANT and Bart methods, are also provided. [ABSTRACT FROM AUTHOR]

Error correction has proven to be an effective means for refining mistakes produced by Automatic Speech Recognition (ASR) models, thereby contributing to a notable reduction in the Word Error Rate (WER) at the ASR post-edit stage. Existing ASR error correction methods built upon sequence-to-sequence architecture may be suffered from the over-correction issue, resulting in the introduction of new mistakes or alterations to correct portions. In this paper, we propose a Pronunciation Guided Copy and Correction (PGCC) model for ASR error correction. Leveraging the fact that ASR hypotheses share a big overlap with the correct text and are frequently characterized by homophone errors, our approach incorporates a copy module into the BART pre-trained model's encoder-decoder structure, this module optimally decides whether to retain a token from the source input (via copying) or generate a modified one through the decoder. Furthermore, a hierarchical phonetic feature encoder is designed to provide guidance to the copy module and BART decoder, implicitly identifying the positions of homophone errors and generating precise corrections. Experiments on two public datasets demonstrate the effectiveness of our proposed method, showcasing remarkable reductions of 18.18% and 44.84% in character error rate and outperforming solid baseline models. [ABSTRACT FROM AUTHOR]

Estimating pasture biomass has emerged as a promising avenue to assist farmers in identifying the best cutting times for maximizing biomass yield using satellite data. This study aims to develop an innovative framework integrating field and satellite data to estimate aboveground biomass in alfalfa (Medicago sativa L.) at farm scale. For this purpose, samples were collected throughout the 2022 growing season on different mowing dates at three fields in Kansas, USA. The satellite data employed comprised four sources: Sentinel-2, PlanetScope, Planet Fusion, and Biomass Proxy. A grid of hyperparameters was created to establish different combinations and select the best coefficients. The permutation feature importance technique revealed that the Planet's PlanetScope near-infrared (NIR) band and the Biomass Proxy product were the predictive features with the highest contribution to the biomass prediction model's. A Bayesian Additive Regression Tree (BART) was applied to explore its ability to build a predictive model. Its performance was assessed via statistical metrics (r2: 0.61; RMSE: 0.29 kg.m−2). Additionally, uncertainty quantifications were proposed with this framework to assess the range of error in the predictions. In conclusion, this integration in a nonparametric approach achieved a useful predicting tool with the potential to optimize farmers' management decisions. [ABSTRACT FROM AUTHOR]

Anorexia nervosa (AN) is a severe psychiatric disorder marked by extreme weight control behaviors and significant impacts on physical and psychosocial health. This study explores the relationship between vitamin D (Vit-D) levels and impulsivity in women with AN. Forty-six cisgender White women participants were assessed upon admission and before discharge from a specialized eating disorder treatment center, with an average duration of 2.5 ± 0.10 months. Methods included self-reported questionnaires and behavioral tasks to measure impulsivity, alongside serum Vit-D levels. Our results showed significant improvements in Vit-D levels and certain impulsivity measures, such as faster reaction times and fewer errors on the go/no-go task, correlating with higher Vit-D levels. However, no significant correlations were found between Vit-D levels and self-reported impulsivity. These findings suggest that adequate Vit-D levels may enhance cognitive functions related to impulse control in AN. Given this study's limitations, including its exclusive focus on women and small sample size, future research should involve larger, more diverse populations and randomized clinical trials to better understand the causal relationships and therapeutic potential of Vit-D in managing AN-related impulsivity. [ABSTRACT FROM AUTHOR]

Censoring occurs when an outcome is unobserved beyond some threshold value. Methods that do not account for censoring produce biased predictions of the unobserved outcome. This paper introduces Type I Tobit Bayesian Additive Regression Tree (TOBART-1) models for censored outcomes. Simulation results and real data applications demonstrate that TOBART-1 produces accurate predictions of censored outcomes. TOBART-1 provides posterior intervals for the conditional expectation and other quantities of interest. The error term distribution can have a large impact on the expectation of the censored outcome. Therefore, the error is flexibly modeled as a Dirichlet process mixture of normal distributions. An R package is available at . [ABSTRACT FROM AUTHOR]

Real-time stance detection can be used in a wide range of applications like debate analysis, sentiment analysis, system feedback, etc. This study focuses on stance detection in political speeches, discerning whether the speaker is in favor, against, neutral, or lacking any stance on a given topic. The problem with this type of speeches dwells in the modification of the existing methods of stance detection to allow for the fine distinctions of Hinglish, a language mixture blending Hindi and English, as conveyed in human-edited texts. The proposed method utilizes the Bidirectional Auto-Regressive Transformers Multi-Genre Natural Language Inference (BART-large-MNLI) model with zero-Shot, few-Shot and N-Shot learning approaches. The proposed model is compared with the existing models of stance detection on Hinglish texts. For the pre-trained BART-based models, a limited number of labeled examples are utilized to determine the labels of test instances. For the other models, the train-test split method is adopted to get accurate results. The results indicate that the model surpasses the previous models. [ABSTRACT FROM AUTHOR]

Bayesian additive regression trees (BART) is a nonparametric model that is known for its flexibility and strong statistical foundation. To address a robust and flexible approach to analyse ordinal data, we extend BART into an ordered probit regression framework (OPBART). Further, we propose a semiparametric setting for OPBART (semi‐OPBART) to model covariates of interest parametrically and confounding variables nonparametrically. We also provide Gibbs sampling procedures to implement the proposed models. In both simulations and real data studies, the proposed models demonstrate superior performance over other competing ordinal models. We also highlight enhanced interpretability of semi‐OPBART in terms of inference through marginal effects. [ABSTRACT FROM AUTHOR]

Previous research has revealed that daily variations in human neurobehavioral functions are driven in part by the endogenous circadian system. The objective of this study was to explore whether there exists a circadian influence on performance regarding a risky decision-making task and to determine whether the performance changes with sleep deprivation (SD). Thirteen participants underwent a 39 h constant routine (CR) protocol, during which they remained awake in constant conditions and performed the BART (balloon analogue risk task) every two hours. The mean pumps (gains) (p < 0.001) and balloons popped (losses) (p = 0.003) exhibited variation during the CR. The reaction time (RT) also showed significant variation across the CR (p < 0.001), with slower mean RTs in the morning hours following SD. A greater risk propensity was observed around midday before SD and a lower risk propensity after 29.5 h of being awake. The sensitivity to punishment varied during the CR, but did not follow a predictable trend. Further research using real monetary incentives and neurophysiological measures is warranted to elucidate these findings.

Previous research has revealed that daily variations in human neurobehavioral functions are driven in part by the endogenous circadian system. The objective of this study was to explore whether there exists a circadian influence on performance regarding a risky decision-making task and to determine whether the performance changes with sleep deprivation (SD). Thirteen participants underwent a 39 h constant routine (CR) protocol, during which they remained awake in constant conditions and performed the BART (balloon analogue risk task) every two hours. The mean pumps (gains) (p < 0.001) and balloons popped (losses) (p = 0.003) exhibited variation during the CR. The reaction time (RT) also showed significant variation across the CR (p < 0.001), with slower mean RTs in the morning hours following SD. A greater risk propensity was observed around midday before SD and a lower risk propensity after 29.5 h of being awake. The sensitivity to punishment varied during the CR, but did not follow a predictable trend. Further research using real monetary incentives and neurophysiological measures is warranted to elucidate these findings. [ABSTRACT FROM AUTHOR]

Text continues to remain a relevant form of representation for information. Text documents are created either in digital native platforms or through the conversion of other media files such as images and speech. While the digital native text is invariably obtained through physical or virtual keyboards, technologies such as OCR and speech recognition are utilised to transform the images and speech signals into text content. All these variety of mechanisms of text generation also introduce errors into the captured text. This project aims at analysing different kinds of errors that occur in text documents. The work employs two of the advanced deep neural network-based language models, namely, BART and MarianMT, to rectify the anomalies present in the text. Transfer learning of these models with available dataset is performed to finetune their capacity for error correction. A comparative study is conducted to investigate the effectiveness of these models in handling each of the defined error categories. It is observed that while both models can bring down the erroneous sentences by 20+%, BART can handle spelling errors far better (24.6%) than grammatical errors (8.8%). [ABSTRACT FROM AUTHOR]

Automatic text summarization is a lucrative field in natural language processing (NLP). The amount of data flow has multiplied with the switch to digital. The massive datasets hold a wealth of knowledge and information must be extracted to be useful. This article focusses on creating an unmanned text summarizing structure that accepts text as data feeded into the system to outputs a summary using a cutting-edge machine learning model. Advancements in NLP led to the introduction of transformers in the field and their outstanding performance pulled a lot of attention towards them. The two transformer-based language models namely, Bidirectional and Auto-regressive Transformer (BART) and Text-To-Text Transfer Transformer (T5) were implemented on the CNN_dailymail dataset. BART outperforms T5 by 3.02% in ROUGE-1 Score. The model provides a worthier performance in comparison to the other models introduced in the existing literature for performing the same task. [ABSTRACT FROM AUTHOR]

Nowadays, deep learning models are used to summarize the large volume of text data to understand its intent effectively. Processing huge amounts of data can lead to an Information overload, where the models may generate text summaries that miss out on the important information of actual text content. Such problems in business document summaries can impact progressive business growth. This study employs a dataset comprising business articles sourced from BBC News to conduct an extensive comparative analysis of three prominent text summarization algorithms: Bidirectional and Auto-Regressive Transformers, Text-to-Text Transfer Transformer, and Pre-training with Extracted Gap-sentences for Abstractive Summarization, within the domain of business news summarization. The primary objective is to assess the accuracy of these models in generating concise and coherent summaries, utilizing ROUGE and METEOR scores as the benchmark for evaluation. Each model's proficiency in distilling business narratives while retaining crucial insights is carefully examined. This study analyzes the summaries generated and compares them with the already existing summaries. From the result analysis it observed that BART and PEGASUS show ROUGE-I score of 0.308 and 0.245, and METEOR score 0.28 and 0.25 respectively. The outcomes of this study show that the T5 excelled in the ROUGE-1 and METEOR scores which were 0.354 and 0.35 respectively. outcomes of this research offer significant implications for both researchers and practitioners, equipping them with advanced summarization techniques for extracting information effectively from business-related content. In an age where information overload is prevalent, the findings from this study can guide the selection and deployment of text summarization models to enhance information extraction processes, ultimately facilitating more efficient decision-making and information dissemination in the business domain. [ABSTRACT FROM AUTHOR]

To address the problem of poor entity recognition performance caused by the lack of Chinese annotation in clinical electronic medical records, this paper proposes a multi-medical entity recognition method F-MNER using a fusion technique combining BART, Bi-LSTM, and CRF. First, after cleaning, encoding, and segmenting the electronic medical records, the obtained semantic representations are dynamically fused using a bidirectional autoregressive transformer (BART) model. Then, sequential information is captured using a bidirectional long short-term memory (Bi-LSTM) network. Finally, the conditional random field (CRF) is used to decode and output multi-task entity recognition. Experiments are performed on the CCKS2019 dataset, with micro avg Precision, macro avg Recall, weighted avg Precision reaching 0.880, 0.887, and 0.883, and micro avg F1-score, macro avg F1-score, weighted avg F1-score reaching 0.875, 0.876, and 0.876 respectively. Compared with existing models, our method outperforms the existing literature in three evaluation metrics (micro average, macro average, weighted average) under the same dataset conditions. In the case of weighted average, the Precision, Recall, and F1-score are 19.64%, 15.67%, and 17.58% higher than the existing BERT-BiLSTM-CRF model respectively. Experiments are performed on the actual clinical dataset with our MF-MNER, the Precision, Recall, and F1-score are 0.638, 0.825, and 0.719 under the micro-avg evaluation mechanism. The Precision, Recall, and F1-score are 0.685, 0.800, and 0.733 under the macro-avg evaluation mechanism. The Precision, Recall, and F1-score are 0.647, 0.825, and 0.722 under the weighted avg evaluation mechanism. The above results show that our method MF-MNER can integrate the advantages of BART, Bi-LSTM, and CRF layers, significantly improving the performance of downstream named entity recognition tasks with a small amount of annotation, and achieving excellent performance in terms of recall score, which has certain practical significance. Source code and datasets to reproduce the results in this paper are available at https://github.com/xfwang1969/MF-MNER. Illustration of the proposed MF-MNER. The method mainly includes four steps: (1) medical electronic medical records need to be cleared, coded, and segmented. (2) The semantic representation obtained by dynamic fusion of the bidirectional autoregressive converter (BART) model. (3) The sequence information is captured by a bi-directional short-term memory (Bi-LSTM) network. (4) the multi-task entity recognition is decoded and output by conditional random field (CRF). [ABSTRACT FROM AUTHOR]

Abstract Hepatitis B and C viruses (HBV and HCV) are significant causes of chronic liver diseases, with approximately 350 million infections globally. To accelerate the finding of effective treatment options, we introduce HBCVTr, a novel ligand-based drug design (LBDD) method for predicting the inhibitory activity of small molecules against HBV and HCV. HBCVTr employs a hybrid model consisting of double encoders of transformers and a deep neural network to learn the relationship between small molecules’ simplified molecular-input line-entry system (SMILES) and their antiviral activity against HBV or HCV. The prediction accuracy of HBCVTr has surpassed baseline machine learning models and existing methods, with R-squared values of 0.641 and 0.721 for the HBV and HCV test sets, respectively. The trained models were successfully applied to virtual screening against 10 million compounds within 240 h, leading to the discovery of the top novel inhibitor candidates, including IJN04 for HBV and IJN12 and IJN19 for HCV. Molecular docking and dynamics simulations identified IJN04, IJN12, and IJN19 target proteins as the HBV core antigen, HCV NS5B RNA-dependent RNA polymerase, and HCV NS3/4A serine protease, respectively. Overall, HBCVTr offers a new and rapid drug discovery and development screening method targeting HBV and HCV.

Hepatitis B and C viruses (HBV and HCV) are significant causes of chronic liver diseases, with approximately 350 million infections globally. To accelerate the finding of effective treatment options, we introduce HBCVTr, a novel ligand-based drug design (LBDD) method for predicting the inhibitory activity of small molecules against HBV and HCV. HBCVTr employs a hybrid model consisting of double encoders of transformers and a deep neural network to learn the relationship between small molecules’ simplified molecular-input line-entry system (SMILES) and their antiviral activity against HBV or HCV. The prediction accuracy of HBCVTr has surpassed baseline machine learning models and existing methods, with R-squared values of 0.641 and 0.721 for the HBV and HCV test sets, respectively. The trained models were successfully applied to virtual screening against 10 million compounds within 240 h, leading to the discovery of the top novel inhibitor candidates, including IJN04 for HBV and IJN12 and IJN19 for HCV. Molecular docking and dynamics simulations identified IJN04, IJN12, and IJN19 target proteins as the HBV core antigen, HCV NS5B RNA-dependent RNA polymerase, and HCV NS3/4A serine protease, respectively. Overall, HBCVTr offers a new and rapid drug discovery and development screening method targeting HBV and HCV. [ABSTRACT FROM AUTHOR]

Conjoint experiments are fast becoming one of the dominant experimental methods within the social sciences. Despite recent efforts to model heterogeneity within this type of experiment, the relationship between the conjoint design and lower-level causal estimands is underdeveloped. In this article, we clarify how conjoint heterogeneity can be construed as a set of nested, causal parameters that correspond to the levels of the conjoint design. We then use this framework to propose a new estimation strategy, using machine learning, that better allows researchers to evaluate treatment effect heterogeneity. We also provide novel tools for classifying and analyzing heterogeneity postestimation using partitioning algorithms. Replicating two conjoint experiments, we demonstrate our theoretical argument and show how this method helps estimate and detect substantive patterns of heterogeneity. To accompany this article, we provide new a R package, cjbart, that allows researchers to model heterogeneity in their experimental conjoint data. [ABSTRACT FROM AUTHOR]

In the emerging field of materials informatics, a fundamental task is to identify physicochemically meaningful descriptors, or materials genes, which are engineered from primary features and a set of elementary algebraic operators through compositions. Standard practice directly analyzes the high-dimensional candidate predictor space in a linear model; statistical analyses are then substantially hampered by the daunting challenge posed by the astronomically large number of correlated predictors with limited sample size. We formulate this problem as variable selection with operator-induced structure (OIS) and propose a new method to achieve unconventional dimension reduction by using the geometry embedded in OIS. Although the model remains linear, we iterate nonparametric variable selection for effective dimension reduction. This enables variable selection based on ab initio primary features, leading to a method that is orders of magnitude faster than existing methods, with improved accuracy. To select the nonparametric module, we discuss a desired performance criterion that is uniquely induced by variable selection with OIS; in particular, we propose to employ a Bayesian Additive Regression Trees (BART)-based variable selection method. Numerical studies show superiority of the proposed method, which continues to exhibit robust performance when the input dimension is out of reach of existing methods. Our analysis of single-atom catalysis identifies physical descriptors that explain the binding energy of metal-support pairs with high explanatory power, leading to interpretable insights to guide the prevention of a notorious problem called sintering and aid catalysis design. for this article are available online. [ABSTRACT FROM AUTHOR]

In contrast to earlier ABSA studies primarily concentrating on individual sentiment components, recent research has ventured into more complex ABSA tasks encompassing multiple elements, including pair, triplet, and quadruple sentiment analysis. Quadruple sentiment analysis, also called aspect-category-opinion-sentiment quadruple Extraction (ACOSQE), aims to dissect aspect terms, aspect categories, opinion terms, and sentiment polarities while considering implicit sentiment within sentences. Nonetheless, a comprehensive overview of ACOSQE and its corresponding solutions is currently lacking. This is the precise gap that our survey seeks to address. To be more precise, we systematically reclassify all subtasks of ABSA, reorganizing existing research from the perspective of the involved sentiment elements, with a primary focus on the latest advancements in the ACOSQE task. Regarding solutions, our survey offers a comprehensive summary of the state-of-the-art utilization of language models within the ACOSQE task. Additionally, we explore the application of ChatGPT in sentiment analysis. Finally, we review emerging trends and discuss the challenges, providing insights into potential future directions for ACOSQE within the broader context of ABSA. [ABSTRACT FROM AUTHOR]

The task of abstractive text summarization aims to automatically generate a short and concise summary of a given source article. In recent years, automatic abstractive text summarization has attracted the attention of researchers because large volumes of digital text are readily available in multiple languages on a wide range of topics. Automatically generating precise summaries from large text has potential application in the generation of news headlines, a summary of research articles, the moral of the stories, media marketing, search engine optimization, financial research, social media marketing, question-answering systems, and chatbots. In literature, the problem of abstractive text summarization has been mainly investigated for English and some other languages. However, it has not been thoroughly explored for the Urdu language despite having a huge amount of data available in digital format. To fulfill this gap, this paper presents a large benchmark corpus of 2,067,784 Urdu news articles for the Urdu abstractive text summarization task. As a secondary contribution, we applied a range of deep learning (LSTM, Bi-LSTM, LSTM with attention, GRU, Bi-GRU, and GRU with attention), and large language models (BART and GPT-3.5) on our proposed corpus. Our extensive evaluation on 20,000 test instances showed that GRU with attention model outperforms the other models with ROUGE- $1=46.7$ , ROUGE- $2=24.1$ , and ROUGE-L =48.7. To foster research in Urdu, our proposed corpus is publically and freely available for research purposes under the Creative Common Licence.

A major challenge in deep learning (DL) model training is data scarcity. Data scarcity is commonly found in specific domains, such as clinical or low-resource languages, that are not vastly explored in AI research. In this paper, we investigate the generation capability of large language models such as Text-To-Text Transfer Transformer (T5) and Bidirectional and Auto-Regressive Transformers (BART) for Clinical Health-Aware Reasoning across Dimensions (CHARDAT) dataset by applying the ChatGPT augmentation technique. We employed ChatGPT to rephrase each instance of the training set into conceptually similar but semantically different samples and augmented them to the dataset. This study aims to investigate the utilization of large language models, ChatGPT in particular, for data augmentation to overcome the limited availability in the clinical domain. In addition to the ChatGPT augmentation, we applied other augmentation techniques, such as easy data augmentation (EDA) and an easier data augmentation (AEDA), to clinical data. ChatGPT comprehended the contextual significance of sentences within the dataset and successfully modified English terms but not clinical terms. The original CHARDAT datasets represent 52 health conditions across three clinical dimensions, i.e., Treatments, Risk Factors, and Preventions. We compared the outputs for different augmentation techniques and evaluated their relative performance. Additionally, we examined how these techniques perform with different pre-trained language models, assessing their sensitivity in various contexts. Despite the relatively small size of the CHARDAT dataset, our results demonstrated that augmentation methods like ChatGPT augmentation surpassed the efficiency of the previously employed back-translation augmentation. Specifically, our findings revealed that the BART model resulted in superior performance, achieving a rouge score of 52.35 for ROUGE-1, 41.59 for ROUGE-2, and 50.71 for ROUGE-L.

Estimating pasture biomass has emerged as a promising avenue to assist farmers in identifying the best cutting times for maximizing biomass yield using satellite data. This study aims to develop an innovative framework integrating field and satellite data to estimate aboveground biomass in alfalfa (Medicago sativa L.) at farm scale. For this purpose, samples were collected throughout the 2022 growing season on different mowing dates at three fields in Kansas, USA. The satellite data employed comprised four sources: Sentinel-2, PlanetScope, Planet Fusion, and Biomass Proxy. A grid of hyperparameters was created to establish different combinations and select the best coefficients. The permutation feature importance technique revealed that the Planet’s PlanetScope near-infrared (NIR) band and the Biomass Proxy product were the predictive features with the highest contribution to the biomass prediction model’s. A Bayesian Additive Regression Tree (BART) was applied to explore its ability to build a predictive model. Its performance was assessed via statistical metrics (r2: 0.61; RMSE: 0.29 kg.m−2). Additionally, uncertainty quantifications were proposed with this framework to assess the range of error in the predictions. In conclusion, this integration in a nonparametric approach achieved a useful predicting tool with the potential to optimize farmers’ management decisions.

Anorexia nervosa (AN) is a severe psychiatric disorder marked by extreme weight control behaviors and significant impacts on physical and psychosocial health. This study explores the relationship between vitamin D (Vit-D) levels and impulsivity in women with AN. Forty-six cisgender White women participants were assessed upon admission and before discharge from a specialized eating disorder treatment center, with an average duration of 2.5 ± 0.10 months. Methods included self-reported questionnaires and behavioral tasks to measure impulsivity, alongside serum Vit-D levels. Our results showed significant improvements in Vit-D levels and certain impulsivity measures, such as faster reaction times and fewer errors on the go/no-go task, correlating with higher Vit-D levels. However, no significant correlations were found between Vit-D levels and self-reported impulsivity. These findings suggest that adequate Vit-D levels may enhance cognitive functions related to impulse control in AN. Given this study’s limitations, including its exclusive focus on women and small sample size, future research should involve larger, more diverse populations and randomized clinical trials to better understand the causal relationships and therapeutic potential of Vit-D in managing AN-related impulsivity.

Alobster eye (LE) is a wide-field type of X-ray optics, which provides a large field of view at the expense of angular resolution. The optics presented in this paper are the LE optics in Schmidt arrangement made from glass sheets with golden reflective coatings. Itwas used as a scientific payload on theWRXR rocket experiment. Before the mission itself, the optics was tested on ground to obtain more information about its behavior. Part of these tests were several nights of observation at the Ondrejov observatory. We used the optics in combination with a CMOS camera to acquire images in visible light of various bright sources in the sky. In order to enable long-time exposures, the robotic mount of the BART telescopewas used. The goal of this experimentwas to confirm the focal length of the optics using a source at infinity, and to show how the optics, designed for X-ray observations, performs in visible light. This brief article describes the methods used for evaluation and presents and discusses the results obtained within the night observation experiment. [ABSTRACT FROM AUTHOR]

Many popular survival models rely on restrictive parametric, or semiparametric, assumptions that could provide erroneous predictions when the effects of covariates are complex. Modern advances in computational hardware have led to an increasing interest in flexible Bayesian nonparametric methods for time‐to‐event data such as Bayesian additive regression trees (BART). We propose a novel approach that we call nonparametric failure time (NFT) BART in order to increase the flexibility beyond accelerated failure time (AFT) and proportional hazard models. NFT BART has three key features: (1) a BART prior for the mean function of the event time logarithm; (2) a heteroskedastic BART prior to deduce a covariate‐dependent variance function; and (3) a flexible nonparametric error distribution using Dirichlet process mixtures (DPM). Our proposed approach widens the scope of hazard shapes including nonproportional hazards, can be scaled up to large sample sizes, naturally provides estimates of uncertainty via the posterior and can be seamlessly employed for variable selection. We provide convenient, user‐friendly, computer software that is freely available as a reference implementation. Simulations demonstrate that NFT BART maintains excellent performance for survival prediction especially when AFT assumptions are violated by heteroskedasticity. We illustrate the proposed approach on a study examining predictors for mortality risk in patients undergoing hematopoietic stem cell transplant (HSCT) for blood‐borne cancer, where heteroskedasticity and nonproportional hazards are likely present. [ABSTRACT FROM AUTHOR]

Analysis of observational studies increasingly confronts the challenge of determining which of a possibly high‐dimensional set of available covariates are required to satisfy the assumption of ignorable treatment assignment for estimation of causal effects. We propose a Bayesian nonparametric approach that simultaneously (1) prioritizes inclusion of adjustment variables in accordance with existing principles of confounder selection; (2) estimates causal effects in a manner that permits complex relationships among confounders, exposures, and outcomes; and (3) provides causal estimates that account for uncertainty in the nature of confounding. The proposal relies on specification of multiple Bayesian additive regression trees models, linked together with a common prior distribution that accrues posterior selection probability to covariates on the basis of association with both the exposure and the outcome of interest. A set of extensive simulation studies demonstrates that the proposed method performs well relative to similarly‐motivated methodologies in a variety of scenarios. We deploy the method to investigate the causal effect of emissions from coal‐fired power plants on ambient air pollution concentrations, where the prospect of confounding due to local and regional meteorological factors introduces uncertainty around the confounding role of a high‐dimensional set of measured variables. Ultimately, we show that the proposed method produces more efficient and more consistent results across adjacent years than alternative methods, lending strength to the evidence of the causal relationship between SO2 emissions and ambient particulate pollution. [ABSTRACT FROM AUTHOR]

Decision making under acute stress is frequent in daily life. While evidence suggests for a modulatory role of neuroticism on risky decision-making behaviors, the neural correlates underlying the association between neuroticism and risky decision-making under acute stress remain to be elucidated. Based on a modified Balloon Analogue Risk Task (BART) with concurrent functional magnetic resonance imaging, we evaluated the effect of acute stress on risk-taking behavior in 27 healthy male adults, and further assessed stress-induced changes in brain activation according to the individual differences in neuroticism. Higher trait neuroticism levels positively correlated with increased stress-modulated activation of the right dorsal anterior cingulate cortex during risk-taking, and negatively correlated with decreased stress-modulated activation of the right dorsolateral prefrontal cortex during cash-outs. Only male participants were recruited. We found a positive correlation between neuroticism and greater risk-taking behavior under acute stress. These results extend our understanding of the increased risk-taking propensity in high neurotic individuals under acute stress. • Neuroticism correlates positively with risk-taking behavior under acute stress. • Neuroticism correlates positively with right dACC activation during risk-taking. • Neuroticism correlates negatively with right dlPFC activation during cash-outs. [ABSTRACT FROM AUTHOR]

[Display omitted] • Determining drought vulnerability assessment considering AD, HD, MD and S-ED groups. • AHP, RF and BART models were used to assess drought vulnerability. • Relevant risk factors and weighting criteria were taken into account. • Highest areal extent of severe and high drought vulnerability is found in AD group. Drought is a complicated and diverse natural calamity that causes huge global economic losses. Drought, particularly in dominant agricultural areas, is becoming more severe, posing a threat to global food security. Drought stress has a wide range of effects on a region, and it is largely dependent upon climate variability, groundwater availability and soil moisture condition. Droughts are influenced by a wide range of factors, including climatic factors like rainfall and temperature and economic factors like population density, irrigated land, and so on. In India, the recurrence of drought is largely owed to sole physical and climatic susceptibilities. As a result, this research study makes an intensive effort to assess drought vulnerability assessment in India considering "meteorological, hydrological, agricultural and socio-economic drought" groups. The statistical method of "analytical hierarchy process (AHP)" and machine learning algorithms of "random forest (RF)" and "Bayesian additive regression trees (BART)" were used for respective modelling purposes. The modelling outcomes were assessed using "receiver operating characteristics area under the curve (ROC-AUC)", "mean square error (MSE)", "root mean square error (RMSE)", and the Taylor diagram. The evaluation measure indicates that BART is the most optimal (AUC = 0.901, r = 0.931) followed by RF (AUC = 0.872, r = 0.901). The findings suggest that the method used to determine drought vulnerability in the region is successful, which will aid planners in developing drought mitigation measures. [ABSTRACT FROM AUTHOR]

A major challenge for the future wireless network is to design the self-organizing architecture. The reactive self-organizing model of traditional networks needs to be transformed into an active self-organizing network. Due to the user mobility and the coverage of small cells, the network load often becomes unbalanced, resulting in poor network performance. Mobility management has become an important issue to ensure seamless communication when users move between cells, and proactive mobility management is one of the important functions of the active Self-Organizing Network (SON). This paper proposes a proactive mobility management framework for active SON, which transforms the original reactive load balancing into a forward-aware and proactive load balancing. The proposed framework firstly uses the BART model to predict the users’ temporal and spatial mobility based on a weekly cycle and then formulate the MLB optimization problem based on the soft load. Two solutions are proposed to solve the above MLB problem. The simulation results show that the proposed method can better optimize the network performance and realize intelligent mobile management for the future network.

BackgroundRisky decision-making is an important facet of addiction. Individuals with alcohol dependence show abnormalities in gambling and other risk-taking tasks. In one such measure, the Balloon Analogue Risk Task (BART), participants sequentially choose to pump a virtual balloon to increase potential reward while the risk of explosion increases, or to cash-out and take earnings. In a prior study, alcohol-dependent participants differed from controls in brain activation during decision-making on the BART, but the relationship between risk/reward magnitude and brain activation was not studied, nor were participants compared to controls. Here we compared the degree to which risk and magnitude of reward influenced brain activation in alcohol-dependent participants vs. controls during decision-making on the BART.MethodsThirty-two participants (16 alcohol-dependent, 16 control; 5 females/group) performed the BART during fMRI. A parametric analysis tested for a relationship between risk/reward magnitude and activation in rDLPFC and bilateral striatum regions of interest when participants chose to take risk or to cash out. An exploratory whole-brain voxel-wise analysis of mean activation during pumping, cash-out, and explosion events was also conducted.ResultsCompared with controls, alcohol-dependent participants displayed less modulation of activation in the rDLPFC when taking risk. Exploratory analyses found that alcohol-dependent participants showed less activation than controls during explosions in a cluster including the insula. No differences were seen in striatal activation.ConclusionsInsensitivity of the rDLPFC to risk and of the insula to loss may contribute to decision-making deficits in alcohol dependence.

IntroductionMethods and tools evaluating treatment effect have been primarily developed for binary type of treatment. Yet, treatment is rarely binary outside the experimental setting, varies by dosage, frequency and time. Treatment is routinely adjusted, initiated or stopped when being administered over a period of time.MethodsBoth Gaussian Process (GP) regression and Bayesian additive regression tree (BART) have been used successfully for handling complex setting involving time-varying treatments that is either adaptive or non-adaptive. Here, we introduce an application programming interface (API) that implements both BART and GP for estimating averaged treatment effect (ATE) and conditional averaged treatment (CATE) for the two-stage time-varying treatment strategies.ResultsWe provide two real applications for evaluating comparative effectiveness of time-varying treatment strategies. The first example evaluates an early aggressive treatment strategies for caring children with newly diagnosed Juvenile Idiopathic Arthritis (JIA). The second evaluates the persistent per-protocol treatment effectiveness in a large randomized pragmatic trial. The examples demonstrate the use of the API calling from R and Python, for handling both non-adaptive or adaptive treatments, with presences of partially observed or missing data issues. Summary tables and interactive figures of the results are downloadable.

The rational design of chemical entities with desired properties for a specific target is a long-standing challenge in drug design. Generative neural networks have emerged as a powerful approach to sample novel molecules with specific properties, termed as inverse drug design. However, generating molecules with biological activity against certain targets and predefined drug properties still remains challenging. Here, we propose a conditional molecular generation net (CMGN), the backbone of which is a bidirectional and autoregressive transformer. CMGN applies large-scale pretraining for molecular understanding and navigates the chemical space for specified targets by fine-tuning with corresponding datasets. Additionally, fragments and properties were trained to recover molecules to learn the structure–properties relationships. Our model crisscrosses the chemical space for specific targets and properties that control fragment-growth processes. Case studies demonstrated the advantages and utility of our model in fragment-to-lead processes and multi-objective lead optimization. The results presented in this paper illustrate that CMGN has the potential to accelerate the drug discovery process. [ABSTRACT FROM AUTHOR]

The application of Natural Language Processing (NLP) to medical data has revolutionized different aspects of health care. The benefits obtained from the implementation of this technique spill over into several areas, including in the implementation of chatbots, which can provide medical assistance remotely. Every possible application of NLP depends on one first main step: the pre-processing of the corpus retrieved. The raw data must be prepared with the aim to be used efficiently for further analysis. Considerable progress has been made in this direction for the English language but for other languages, such as Italian, the state of the art is not equivalently advanced, especially for texts containing technical medical terms. The aim of this work is to identify and develop a preprocessing pipeline suitable for medical data written in Italian. The pipeline has been developed in Python environment, employing Enchant, ntlk modules and Hugging Face's BERT and BART-based models. Then, it has been tested on real conversations typed between patients and physicians regarding medical questions. The algorithm has been developed within the MULTI-SITA project of the Italian Society of Anti-Infective Therapy (SITA), but shows a flexible structure that can adapt to a large variety of data. [ABSTRACT FROM AUTHOR]

Humans globally are reaping the benefits of longer lives. Yet, longer life spans also require engaging with consequential but often uncertain decisions well into old age. Previous research has yielded mixed findings with regards to life span differences in how individuals make decisions under uncertainty. One factor contributing to the heterogeneity of findings is the diversity of paradigms that cover different aspects of uncertainty and tap into different cognitive and affective mechanisms. In this study, 175 participants (53.14% females, mean age = 44.9 years, SD = 19.0, age range = 16 to 81) completed functional neuroimaging versions of two prominent paradigms in this area, the Balloon Analogue Risk Task and the Delay Discounting Task. Guided by neurobiological accounts of age-related changes in decision-making under uncertainty, we examined age effects on neural activation differences in decision-relevant brain structures, and compared these across multiple contrasts for the two paradigms using specification curve analysis. In line with theoretical predictions, we find age differences in nucleus accumbens, anterior insula, and medial prefrontal cortex, but the results vary across paradigm and contrasts. Our results are in line with existing theories of age differences in decision making and their neural substrates, yet also suggest the need for a broader research agenda that considers how both individual and task characteristics determine the way humans deal with uncertainty. [ABSTRACT FROM AUTHOR]

Realistic simulations of complex systems are fundamental for climate and environmental studies. Large computer systems are often not sufficient to run sophisticated computational models for large numbers of different input settings. Statistical surrogate models, or emulators, are key tools enabling fast exploration of the simulator input space. Gaussian processes have become standard for computer simulator emulation. However, they require careful implementation to scale appropriately, motivating alternative methods more recently introduced. We present a comparison study of surrogates of the Sea, Lake, and Overland Surges from Hurricanes (SLOSH) simulator—the simulator of choice for government agencies—using four emulation approaches: BASS; BART; SEPIA; and RobustGaSP. SEPIA and RobustGaSP use Gaussian processes, BASS implements adaptive splines, and BART is based on ensembles of regression trees. We describe the four models and compare them in terms of computation time and predictive metrics. These surrogates use proven and distinct methodologies, are available through accessible software, and quantify prediction uncertainty. Our data cover millions of response values. We find that SEPIA and RobustGaSP provide exceptional predictive power, but cannot scale to emulate experiments as large as the one considered in this paper as effectively as BASS and BART. [ABSTRACT FROM AUTHOR]

Previous research on boredom suggest it function as animportant self-regulatory signal, indicating that the currentstate of the environment carries opportunity-costs andtherefore driving the need to explore alternative activities. Traitboredom proneness is associated with negative consequencesincluding increased risk-taking and impulsivity. Thesefindings often rely on self-reports and not much is known aboutthe role of state and trait boredom in controlled laboratorytasks, or their neural correlates. Sixty-two participantscompleted the Balloon Analogue Risk Task and a go/no-gotask while electrical brain activity was recorded using EEG.Results showed that state boredom leads to impulsivity andpoor performance monitoring, as evident by behavioral,subjective and ERP metrics. Trait boredom was associatedwith increased risk-taking, and modulated the correlationbetween errors and state boredom: high boredom pronenessincreased the sensitivity of trait boredom to errors. Overall,these findings emphasize the involvement of executivefunctions in the interaction between state and trait boredom.

Nowadays, pre-trained sequence-to-sequence models such as PEGASUS and BART have shown state-of-the-art results in abstractive summarization. In these models, during fine-tuning, the encoder transforms sentences to context vectors in the latent space and the decoder learns the summary generation task based on the context vectors. In our approach, we consider two clusters of salient and non-salient context vectors, using which the decoder can attend more over salient context vectors for summary generation. For this, we propose a novel cluster generator layer between the encoder and the decoder, which first generates two clusters of salient and non-salient vectors, and then normalizes and shrinks the clusters to make them apart in the latent space. Our experimental results show that the proposed model outperforms the state-of-the-art models such as BART and PEGASUS by learning these distinct cluster patterns, improving up to 2~30% in ROUGE and 0.1~0.8% in BERTScore in CNN/DailyMail and XSUM data sets.