Search

Paired organs like eyes, ears, and lungs in humans exhibit similarities, and data from these organs often display remarkable correlations. Accounting for these correlations could enhance classification models used in predicting disease phenotypes. To our knowledge, there is limited, if any, literature addressing this topic, and existing methods do not exploit such correlations. For example, the conventional approach treats each ear as an independent observation when predicting audiometric phenotypes and is agnostic about the correlation of data from the two ears of the same person. This approach may lead to information loss and reduce the model performance. In response to this gap, particularly in the context of audiometric phenotype prediction, this paper proposes new quadratic discriminant analysis (QDA) algorithms that appropriately deal with the dependence between ears. We propose two‐stage analysis strategies: (1) conducting data transformations to reduce data dimensionality before applying QDA; and (2) developing new QDA algorithms to partially utilize the dependence between phenotypes of two ears. We conducted simulation studies to compare different transformation methods and to assess the performance of different QDA algorithms. The empirical results suggested that the transformation may only be beneficial when the sample size is relatively small. Moreover, our proposed new QDA algorithms performed better than the conventional approach in both person‐level and ear‐level accuracy. As an illustration, we applied them to audiometric data from the Medical University of South Carolina Longitudinal Cohort Study of Age‐related Hearing Loss. In addition, we developed an R package, PairQDA, to implement the proposed algorithms. [ABSTRACT FROM AUTHOR]

Traditional variance-based control performance assessment (CPA) and controller parameter tuning (CPT) methods tend to ignore non-Gaussian external disturbances. To address this limitation, this study proposes a novel class of CPA and CPT methods for non-Gaussian single-input single-output systems, denoted as data Gaussianization (inverse) transformation methods. The idea of quantile transformation is used to transform the non-Gaussian data with the goal of maximizing mutual information into virtual Gaussian data. In addition, optimal system data for the virtual loop are mapped back to the actual non-Gaussian system using quantile inverse transformation. Furthermore, a CARMA model-based recursive extended least square algorithm and a CARMA model-based least absolute deviation iterative algorithm are used to identify virtual Gaussian and non-Gaussian system process models, respectively, while implementing the CPT. Finally, a unified framework is proposed for the CPA and CPT of a non-Gaussian control system. The simulation results demonstrate that the proposed strategy can provide a consistent benchmark judgment criterion (threshold) for different non-Gaussian noises, and the tuned controller parameters have good performance. • The limitations of MVC and MEC are analyzed. • Quantile transformation formula is derived and used for non-Gaussian system CPA. • Gaussian/non-Gaussian noise is considered in proposed method. • A unified framework is designed for CPA and PID tuning of a non-Gaussian system. [ABSTRACT FROM AUTHOR]

Background: Systematic review with meta-analysis integrates findings from multiple studies, offering robust conclusions on treatment effects and guiding evidence-based medicine. However, the process is often hampered by challenges such as inconsistent data reporting, complex calculations, and time constraints. Researchers must convert various statistical measures into a common format, which can be error-prone and labor-intensive without the right tools. Implementation: Meta-Analysis Accelerator was developed to address these challenges. The tool offers 21 different statistical conversions, including median & interquartile range (IQR) to mean & standard deviation (SD), standard error of the mean (SEM) to SD, and confidence interval (CI) to SD for one and two groups, among others. It is designed with an intuitive interface, ensuring that users can navigate the tool easily and perform conversions accurately and efficiently. The website structure includes a home page, conversion page, request a conversion feature, about page, articles page, and privacy policy page. This comprehensive design supports the tool's primary goal of simplifying the meta-analysis process. Results: Since its initial release in October 2023 as Meta Converter and subsequent renaming to Meta-Analysis Accelerator, the tool has gained widespread use globally. From March 2024 to May 2024, it received 12,236 visits from countries such as Egypt, France, Indonesia, and the USA, indicating its international appeal and utility. Approximately 46% of the visits were direct, reflecting its popularity and trust among users. Conclusions: Meta-Analysis Accelerator significantly enhances the efficiency and accuracy of meta-analysis of systematic reviews by providing a reliable platform for statistical data conversion. Its comprehensive variety of conversions, user-friendly interface, and continuous improvements make it an indispensable resource for researchers. The tool's ability to streamline data transformation ensures that researchers can focus more on data interpretation and less on manual calculations, thus advancing the quality and ease of conducting systematic reviews and meta-analyses. [ABSTRACT FROM AUTHOR]

ImageGP is an extensively utilized, open‐access platform for online data visualization and analysis. Over the past 7 years, it has catered to more than 700,000 usages globally, garnering substantial user feedback. The updated version, ImageGP 2 (available at https://www.bic.ac.cn/BIC), introduces a redesigned interface leveraging cutting‐edge web technologies to enhance functionality and user interaction. Key enhancements include the following: (i) Addition of modules for data format transformation, facilitating operations such as matrix merging, subsetting, and transformation between long and wide formats. (ii) Streamlined workflows with features like preparameter selection data validation and grouping of parameters with similar attributes. (iii) Expanded repertoire of visualization functions and analysis tools, including Weighted Gene Co‐Expression Network Analysis, differential gene expression analysis, and FASTA sequence processing. (iv) Personalized user space for uploading large data sets, tracking analysis history, and sharing reproducible analysis data, scripts, and results. (v) Enhanced user support through a simplified error debugging feature accessible with a single click. (vi) Introduction of an R package, ImageGP, enabling local data visualization and analysis. These updates position ImageGP 2 as a versatile tool serving both wet‐lab and dry‐lab researchers with expanded capabilities. Highlights: Advanced user interface, expanded analytical capabilities, and seamless data handling.New modules for data transformation and preparameter selection data validation.Personalized user center, reproducible scripts, seamless error debugging, the introduction of local analysis capabilities. [ABSTRACT FROM AUTHOR]

Abstract Background Systematic review with meta-analysis integrates findings from multiple studies, offering robust conclusions on treatment effects and guiding evidence-based medicine. However, the process is often hampered by challenges such as inconsistent data reporting, complex calculations, and time constraints. Researchers must convert various statistical measures into a common format, which can be error-prone and labor-intensive without the right tools. Implementation Meta-Analysis Accelerator was developed to address these challenges. The tool offers 21 different statistical conversions, including median & interquartile range (IQR) to mean & standard deviation (SD), standard error of the mean (SEM) to SD, and confidence interval (CI) to SD for one and two groups, among others. It is designed with an intuitive interface, ensuring that users can navigate the tool easily and perform conversions accurately and efficiently. The website structure includes a home page, conversion page, request a conversion feature, about page, articles page, and privacy policy page. This comprehensive design supports the tool’s primary goal of simplifying the meta-analysis process. Results Since its initial release in October 2023 as Meta Converter and subsequent renaming to Meta-Analysis Accelerator, the tool has gained widespread use globally. From March 2024 to May 2024, it received 12,236 visits from countries such as Egypt, France, Indonesia, and the USA, indicating its international appeal and utility. Approximately 46% of the visits were direct, reflecting its popularity and trust among users. Conclusions Meta-Analysis Accelerator significantly enhances the efficiency and accuracy of meta-analysis of systematic reviews by providing a reliable platform for statistical data conversion. Its comprehensive variety of conversions, user-friendly interface, and continuous improvements make it an indispensable resource for researchers. The tool’s ability to streamline data transformation ensures that researchers can focus more on data interpretation and less on manual calculations, thus advancing the quality and ease of conducting systematic reviews and meta-analyses.

Data mining is vital in analyzing large volumes of data to extract functional patterns and knowledge hidden within the data. Data mining has practical applications in various scientific areas, such as social networks, healthcare, and finance. It is important to note that data mining also raises ethical concerns and privacy considerations. Organizations must handle data responsibly, ensuring compliance with legal and ethical guidelines. Privacy-Preserving Data Mining (PPDM) refers to conducting data mining tasks while protecting the privacy of sensitive data. PPDM techniques aim to strike a balance between privacy protection and data utility. By employing PPDM techniques, organizations can perform safe and private data analysis, protecting sensitive information while deriving valuable insights from the data. The current paper uses geometric transformation-based projection techniques such as perspective projection, isometric projection, cabinet projection, and cavalier projection to protect data privacy and improve data utility. The suggested technique's performance was assessed with the K-means clustering technique. The UCI repository's Bank Marketing dataset was used to verify the error rate of the proposed projection techniques. [ABSTRACT FROM AUTHOR]

IntroductionRequirements classification is an essential task for development of a successful software by incorporating all relevant aspects of users' needs. Additionally, it aids in the identification of project failure risks and facilitates to achieve project milestones in more comprehensive way. Several machine learning predictors are developed for binary or multi-class requirements classification. However, a few predictors are designed for multi-label classification and they are not practically useful due to less predictive performance.MethodMLR-Predictor makes use of innovative OkapiBM25 model to transforms requirements text into statistical vectors by computing words informative patterns. Moreover, predictor transforms multi-label requirements classification data into multi-class classification problem and utilize logistic regression classifier for categorization of requirements. The performance of the proposed predictor is evaluated and compared with 123 machine learning and 9 deep learning-based predictive pipelines across three public benchmark requirements classification datasets using eight different evaluation measures.ResultsThe large-scale experimental results demonstrate that proposed MLR-Predictor outperforms 123 adopted machine learning and 9 deep learning predictive pipelines, as well as the state-of-the-art requirements classification predictor. Specifically, in comparison to state-of-the-art predictor, it achieves a 13% improvement in macro F1-measure on the PROMISE dataset, a 1% improvement on the EHR-binary dataset, and a 2.5% improvement on the EHR-multiclass dataset.DiscussionAs a case study, the generalizability of proposed predictor is evaluated on softwares customer reviews classification data. In this context, the proposed predictor outperformed the state-of-the-art BERT language model by F-1 score of 1.4%. These findings underscore the robustness and effectiveness of the proposed MLR-Predictor in various contexts, establishing its utility as a promising solution for requirements classification task.

Abstract ImageGP is an extensively utilized, open‐access platform for online data visualization and analysis. Over the past 7 years, it has catered to more than 700,000 usages globally, garnering substantial user feedback. The updated version, ImageGP 2 (available at https://www.bic.ac.cn/BIC), introduces a redesigned interface leveraging cutting‐edge web technologies to enhance functionality and user interaction. Key enhancements include the following: (i) Addition of modules for data format transformation, facilitating operations such as matrix merging, subsetting, and transformation between long and wide formats. (ii) Streamlined workflows with features like preparameter selection data validation and grouping of parameters with similar attributes. (iii) Expanded repertoire of visualization functions and analysis tools, including Weighted Gene Co‐Expression Network Analysis, differential gene expression analysis, and FASTA sequence processing. (iv) Personalized user space for uploading large data sets, tracking analysis history, and sharing reproducible analysis data, scripts, and results. (v) Enhanced user support through a simplified error debugging feature accessible with a single click. (vi) Introduction of an R package, ImageGP, enabling local data visualization and analysis. These updates position ImageGP 2 as a versatile tool serving both wet‐lab and dry‐lab researchers with expanded capabilities.

Industry benchmarking involves comparing and analyzing a company’s performance with other top-performing enterprises. PDF documents contain valuable corporate information, but their non-editable nature makes data extraction complex. This study focuses on converting unstructured data from PDF documents, including tables, images, and text, to a structured format that is suitable for analysis and decision-making. The methods that are currently used for PDF document conversion primarily involve manual extraction, PDF converters, and artificial intelligence algorithms. However, they are often restricted to processing a single modality, have limitations in dealing with complex structured tables, or cannot achieve the required accuracy in practice. This study focuses on converting the periodic reports documents of listed companies from PDF format to structured data. We propose a unified framework for extracting tables, images, and text by parsing PDF documents into constituent objects. We introduce three bespoke algorithms to process complex structured tables and to develop a prototype system of visual analysis that combines AI for automated data extraction with the domain knowledge of human experts for auditing. Quantitative and qualitative experiments are conducted to validate the methodology’s superiority, including its efficiency, quality, and user-friendliness. [ABSTRACT FROM AUTHOR]

Transformational Artificial Intelligence (TRAI), a subset of Transformative AI (TAI), empowers individuals to design and implement sophisticated data transformation workflows. TRAI systems enable new ways of working and learning by progressively manipulating data through a series of operations. This article explores TRAI’s potential to revolutionise workflows, information consumption, and decision-making, offering practical guidance on leveraging existing tools to implement TRAI today. It also discusses the democratisation of workflows, the power of AI triggers, and the skills needed to excel in the TRAI landscape, emphasising that TRAI is not just for tech experts but anyone willing to learn and experiment. This article provides practical guidance on leveraging existing tools to implement TRAI today. It discusses the democratisation of workflows, the power of AI triggers, and the essential skills needed to excel in the TRAI landscape. Ultimately, TRAI is not just for tech experts but for anyone willing to learn and experiment, paving the way for more inclusive and effective AI solutions. [ABSTRACT FROM AUTHOR]

Research on chatbots aimed at facilitating more natural and engaging conversations is actively underway. With the growing recognition of the significance of personas in this context, persona-based conversational research is gaining prominence. Despite the abundance of publicly available chit-chat datasets, persona-based chat datasets remain scarce, primarily due to the higher associated costs. Consequently, we propose a methodology for transforming extensive chit-chat datasets into persona-based chat datasets. Simultaneously, we propose a model adept at effectively incorporating personas into responses, even with a constrained number of parameters. This model can discern the most relevant information from persona memory without resorting to a retrieval model. Furthermore, it makes decisions regarding whether to reference the memory, thereby enhancing the interpretability of the model's judgments. Our CC2PC framework demonstrates superior performance in both automatic and LLM evaluations when compared to high-cost persona-based chat dataset. Additionally, experimental results on the proposed model indicate the improved persona-based response capabilities. [ABSTRACT FROM AUTHOR]

In this study, we delve into a novel approach by employing a sensor-based pattern recognition model to address the automation of construction equipment activity analysis. The model integrates time of flight (ToF) sensors with deep convolutional neural networks (DCNNs) to accurately classify the operational activities of construction equipment, focusing on piston movements. The research utilized a one-twelfth-scale excavator model, processing the displacement ratios of its pistons into a unified dataset for analysis. Methodologically, the study outlines the setup of the sensor modules and their integration with a controller, emphasizing the precision in capturing equipment dynamics. The DCNN model, characterized by its four-layered convolutional blocks, was meticulously tuned within the MATLAB environment, demonstrating the model's learning capabilities through hyperparameter optimization. An analysis of 2070 samples representing six distinct excavator activities yielded an impressive average precision of 95.51% and a recall of 95.31%, with an overall model accuracy of 95.19%. When compared against other vision-based and accelerometer-based methods, the proposed model showcases enhanced performance and reliability under controlled experimental conditions. This substantiates its potential for practical application in real-world construction scenarios, marking a significant advancement in the field of construction equipment monitoring. [ABSTRACT FROM AUTHOR]

In a study published in Global Change Biology, Dickie et al. examined the effects of climate and habitat alteration on white-tailed deer density. They found that both factors contribute to deer densities, but climate plays a particularly strong role. A critique by Barnas et al. raised concerns about data transformations and model overfitting, but Dickie et al. argue that these criticisms are unfounded or align with their original conclusions. They emphasize that management decisions must consider the impact of climate change, which is predicted to increase in the future, in order to address the decline of woodland caribou populations. [Extracted from the article]

Multiple responses are often generated in agricultural and forestry research. For example, the moisture content, fatty acids, carbohydrates, size, diameter, length, shape, and hardness, among other characteristics, are measured in cottonseeds. Multivariate analysis of variance (MANOVA) can be useful for multiple response analysis when differences in treatment effects are to be determined. However, the performance of current post hoc tests in this context is not satisfactory due to the limitations of the available methods or because they are difficult to use for non-statistician researchers. Furthermore, this methodology requires the assumptions of multivariate normality and homogeneity of variance and covariance matrices, assumptions that are difficult to verify if the sample size is small. This research proposes an alternative analysis to test the hypothesis of equality of effects between treatments and post hoc tests in the case of multiple responses. An asymptotic result is demonstrated for the random variable generated in the proposal for the case of uncorrelated normal variables, and the case for correlated normal random variables is left open. A simulation study shows that the performance of the proposal with small samples is satisfactory in terms of power and that it has advantages compared to MANOVA. Furthermore, the methodological approach allows for post hoc testing in the case of multiple responses in the completely randomized experimental design. [ABSTRACT FROM AUTHOR]

Data processing plays a significant role in improving the performance of machine learning models. In an IoT network, data generated by sensor nodes will be multivariate and consist of complex patterns and correlations. Such data must be carefully preprocessed before applying ML algorithms for classification. In this paper, we propose a study that improving anomaly classification accuracy on various IoT sensor datasets. In this context, we propose a system that deals with various data distributions and detects anomalies more efficiently. The proposed study uses multiple data transformation methods to prepare the data for further analysis. The data transformation facilitates data conversion, making it more suitable for machine learning models. We demonstrate the efficacy of the proposed method on widely used IoT sensor datasets. We also demonstrate the results of the proposed system with the various machine learning models using performance metrics such as accuracy, AUC Score, F1 score, and Mean Square Error (MSE). It is observed that the proposed system is more effective on various IoT datasets. [ABSTRACT FROM AUTHOR]

Time-series data provide important information in many fields, and their processing and analysis have been the focus of much research. However, detecting anomalies is very difficult due to data imbalance, temporal dependence, and noise. Therefore, methodologies for data augmentation and conversion of time series data into images for analysis have been studied. This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance, temporal dependence, and robustness to noise. The method of data augmentation is set as the addition of noise. It involves adding Gaussian noise, with the noise level set to 0.002, to maximize the generalization performance of the model. In addition, we use the Markov Transition Field (MTF) method to effectively visualize the dynamic transitions of the data while converting the time series data into images. It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data. For anomaly detection, the PatchCore model is applied to show excellent performance, and the detected anomaly areas are represented as heat maps. It allows for the detection of anomalies, and by applying an anomaly map to the original image, it is possible to capture the areas where anomalies occur. The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images. Additionally, when processed as images rather than as time series data, there was a significant reduction in both the size of the data and the training time. The proposed method can provide an important springboard for research in the field of anomaly detection using time series data. Besides, it helps solve problems such as analyzing complex patterns in data lightweight. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have been widely used in image classification tasks and have achieved remarkable results compared with traditional methods. Their main advantage is the ability to extract hidden features automatically using local connectivity and spatial locality. However, CNN cannot be applied to tabular data, mainly due to the unsuitability of the tabular data structure to the CNN input. In this paper, we propose a new generic method for the representation of multidimensional tabular data as color-encoded images that can be used both for data visualization and classification with CNN. Our approach, named FC-Viz (Feature Clustering-Visualization), is based on user-oriented data visualization ideas, such as pixel-oriented techniques, feature clustering, and feature interactions. The proposed approach includes a transformation of each instance of the tabular data into a 2D pixel-based representation, where pixels representing features with strong correlation and interaction are adjacent to each other. We applied FC-Viz to ten multidimensional tabular datasets with dozens to thousands of features and compared its classification and visualization performance with a state-of-the-art tabular data transformation method. The evaluation experiments show that our approach is as accurate as the state-of-the-art, but with much smaller images resulting in much more compact and faster CNN models. [ABSTRACT FROM AUTHOR]

Feature selection is an important preprocessing step in many data science and machine learning applications. Although there exist several sophisticated feature selection algorithms, their benefits are sometimes overshadowed by their complexity and slow execution. Therefore, in many cases, a more simple algorithm may be better suited. In this paper, we demonstrate that a rudimentary forward selection algorithm can achieve optimal performance with a low time complexity. Our study is based on an extensive empirical evaluation of the forward feature selection algorithm in the context of linear regression. Concretely, we compare the forward selection algorithm against the gold standard exhaustive search algorithm based on several datasets. The results show that the forward selection algorithm achieves high performance with relatively fast execution. Given the simplicity, accuracy, and speed of the forward feature selection algorithm, we recommend it as a primary feature selection method for most regression applications. Our results are particularly pertinent in the case of big data and real-time analysis. [ABSTRACT FROM AUTHOR]

Metabolomics as a research field and a set of techniques is to study the entire small molecules in biological samples. Metabolomics is emerging as a powerful tool generally for precision medicine. Particularly, integration of microbiome and metabolome has revealed the mechanism and functionality of microbiome in human health and disease. However, metabolomics data are very complicated. Preprocessing/pretreating and normalizing procedures on metabolomics data are usually required before statistical analysis. In this review article, we comprehensively review various methods that are used to preprocess and pretreat metabolomics data, including MS-based data and NMR -based data preprocessing, dealing with zero and/or missing values and detecting outliers, data normalization, data centering and scaling, data transformation. We discuss the advantages and limitations of each method. The choice for a suitable preprocessing method is determined by the biological hypothesis, the characteristics of the data set, and the selected statistical data analysis method. We then provide the perspective of their applications in the microbiome and metabolome research.

ABSTRACT In this study, some transformation methods that are applied when the assumptions of analysis of variance are not met are evaluated in terms of type I error rate and the test power, under circumstances with different distributions, number of groups, number of observations, variance ratios, and different standard deviation differences. The data set used in the study consisted of random numbers generated from N (0,1), and χ2(3) distributions using the random function of the Numpy library in the Python programming language. The logarithmic, square root and root transformations were evaluated on ANOVA based on simulation combinations. It was observed that the transformation techniques of taking the square root after adding 0.5 and 0.375 to the data were relatively more reliable compared to other transformations in terms of type I error rate. However, in every case, type I error rate determined at the beginning of the experiment increased both before and after the transformation was applied. In particular, interestingly, the third and fourth degree root transformations gave better results of test power in the right skewed distribution. In addition, we compared the transformation techniques in question to determine the normality of the data and the homogeneity of variances by a real data.

High-throughput, multiplexed-amplicon sequencing has become a core tool for understanding environmental microbiomes. As researchers have widely adopted sequencing, many open-source analysis pipelines have been developed to compare microbiomes using compositional analysis frameworks. However, there is increasing evidence that compositional analyses do not provide the information necessary to accurately interpret many community assembly processes. This is especially true when there are large gradients that drive distinct community assembly processes. Recently, sequencing has been combined with Q-PCR (among other sources of total quantitation) to generate "Quantitative Sequencing" (QSeq) data. QSeq more accurately estimates the true abundance of taxa, is a more reliable basis for inferring correlation, and, ultimately, can be more reliably related to environmental data to infer community assembly processes. In this paper, we use a combination of published data sets, synthesis, and empirical modeling to offer guidance for which contexts QSeq is advantageous. As little as 5% variation in total abundance among experimental groups resulted in more accurate inference by QSeq than compositional methods. Compositional methods for differential abundance and correlation unreliably detected patterns in abundance and covariance when there was greater than 20% variation in total abundance among experimental groups. Whether QSeq performs better for beta diversity analysis depends on the question being asked, and the analytic strategy (e.g., what distance metric is being used); for many questions and methods, QSeq and compositional analysis are equivalent for beta diversity analysis. QSeq is especially useful for taxon-specific analysis; QSeq transformation and analysis should be the default for answering taxon-specific questions of amplicon sequence data. Publicly available bioinformatics pipelines should incorporate support for QSeq transformation and analysis. [ABSTRACT FROM AUTHOR]

This research paper develops an efficient model, named Taylor-Tunicate Swarm Algorithm-based Generative Adversarial Networks (Taylor-TSA-based GANs) for cancer prediction. The developed Taylor-TSA incorporates the Taylor series with Tunicate Swarm Algorithm (TSA) algorithm. The Yeo–Johnson (YJ) transformation is employed for the data transformation. The feature fusion is evaluated by Deep Stacked Autoencoder (Deep SAE). The fused feature is given as input to the cancer prediction done by GAN trained by Taylor-TSA. The developed model is an effective and efficient use of information with clinical data. The Taylor-TSA-based GAN is analyzed in terms of accuracy, False Positive Rate (FPR), and True Positive Rate (TPR) with the values of 0.9184, 0.1782, and 0.9246. [ABSTRACT FROM AUTHOR]

This work intends to discover diversified association rules efficiently using a cluster computing model. At first, the input data is pre-processed for data transformation. Then, the pre-processed data is given to k-means clustering to cluster the data. Since the initialization of the centroid is the key feature of k-means clustering, it is taken as the major challenge here. The randomly assigned centroid is optimally tuned by the new Fitness based Probability for Cuckoo Search (FP-CS) model. By exploiting adopted FP-CS, the best k-means centroid is determined. Thus, the optimal centroids are further processed for k-means clustering, and the optimal clustered data is attained. The clustered data is then given as input to the apriori algorithm, and rule mining data is attained in a proficient manner. Moreover, the adopted FP-CS model is evaluated with conservative methods, and the relevant outcomes are verified. [ABSTRACT FROM AUTHOR]

Decision making under uncertainty is pivotal in real-world scenarios, such as selecting the shortest transportation route amidst variable traffic conditions or choosing the best investment portfolio during market fluctuations. In today's big data age, while the predict-then-optimize framework has become a standard method for tackling uncertain optimization challenges using machine learning tools, many prediction models overlook data intricacies such as outliers and heteroskedasticity. These oversights can degrade decision-making quality. To enhance predictive accuracy and consequent decision-making quality, we introduce a data transformation technique into the predict-then-optimize framework. Our approach transforms target values in linear regression, decision tree, and random forest models using a power function, aiming to boost their predictive prowess and, in turn, drive better decisions. Empirical validation on several datasets reveals marked improvements in decision tree and random forest models. In contrast, the benefits of linear regression are nuanced. Thus, while data transformation can bolster the predict-then-optimize framework, its efficacy is model-dependent. This research underscores the potential of tailoring transformation techniques for specific models to foster reliable and robust decision-making under uncertainty. [ABSTRACT FROM AUTHOR]

Ensemble climatological forecasts play a critical part in benchmarking the predictive performance of hydroclimatic forecasts. Accounting for the skewness and censoring characteristics of hydroclimatic variables, ensemble climatological forecasts can be generated by the log, Box‐Cox and log‐sinh transformations, by the combinations of the Bernoulli distribution with the Gaussian, Gamma, log‐normal, generalized extreme value, generalized logistic and Pearson type III distributions and by the non‐parametric resampling, empirical cumulative distribution function and kernel density estimation methods. This paper is concentrated on the reliability of the 12 types of ensemble climatological forecasts. Specifically, mathematical formulations are presented and large‐sample tests are devised to verify the forecast reliability for the Multi‐Source Weighted‐Ensemble Precipitation version 2 across the globe. Climatological forecasts of monthly precipitation over 18,425 grid cells are generated for 30 years under leave‐one‐year‐out cross validation, leading to 6,633,000 (12 × 18425 × 30) sets of ensemble climatological forecasts. The results point out that the reliability of climatological forecasts considerably varies across the 12 methods, particularly in regions with high hydroclimatic variability. One observation is that climatological forecasts tend to deviate from the distributions of observations when there is inadequate flexibility to fit precipitation data. Another observation is that ensemble spreads can be overly wide when there exist overfits of sample‐specific noises in cross validation. Through the tests of global precipitation, the robustness of the log‐sinh transformation and the Bernoulli‐Gamma distribution is highlighted. Overall, the investigations can serve as a guidance on the uses of transformations, distributions and non‐parametric methods in generating climatological forecasts. Plain Language Summary: Ensemble climatological forecasts have been extensively used as the benchmark to evaluate forecast skill. That is, forecasts generated by a certain forecasting model are skillful when they outperform climatological forecasts and otherwise they are not. In practice, ensemble climatological forecasts are generated by different methods, including the log, Box‐Cox and log‐sinh transformations, the combinations of the Bernoulli distribution with the Gaussian, Gamma, log‐normal, generalized extreme value, generalized logistic and Pearson type III distributions and the non‐parametric resampling, empirical cumulative distribution function and kernel density estimation methods. It is important to investigate pros and cons of different types of climatological forecasts. Focusing on the reliability, that is, statistical consistency between forecasts and observations, this paper has devised large‐sample tests of global monthly precipitation. The results show that owing to hydroclimatic variability, different types of climatological forecasts exhibit varying characteristics of reliability. On the one hand, climatological forecasts can deviate from observations when there is inadequate flexibility to fit precipitation data, especially for the Bernoulli‐Gaussian distribution. On the other hand, ensemble spreads can be too wide when there exist overfits of sample‐specific noises in cross validation. Among the 12 methods, the robustness of the log‐sinh transformation and the Bernoulli‐Gamma distribution is highlighted. Key Points: Climatological forecasts can be generated by using data transformations, statistical distributions and non‐parametric methodsThe reliability of climatological forecasts generated by different methods is shown to vary considerably in large‐sample testsThe robustness of log‐sinh transformation and Bernoulli‐Gamma distribution is illustrated through the tests of global precipitation [ABSTRACT FROM AUTHOR]

Copyright of Frontiers of Information Technology & Electronic Engineering is the property of Springer Nature 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.)

In recent years, the FAIR guiding principles and the broader concept of open science has grown in importance in academic research, especially as funding entities have aggressively promoted public sharing of research products. Key to public research sharing is deposition of datasets into online data repositories, but it can be a chore to transform messy unstructured data into the forms required by these repositories. To help generate Metabolomics Workbench depositions, we have developed the MESSES (Metadata from Experimental SpreadSheets Extraction System) software package, implemented in the Python 3 programming language and supported on Linux, Windows, and Mac operating systems. MESSES helps transform tabular data from multiple sources into a Metabolomics Workbench specific deposition format. The package provides three commands, extract, validate, and convert, that implement a natural data transformation workflow. Moreover, MESSES facilitates richer metadata capture than is typically attempted by manual efforts. The source code and extensive documentation is hosted on GitHub and is also available on the Python Package Index for easy installation. [ABSTRACT FROM AUTHOR]

Sleep stage classification is a fundamental task in diagnosing and monitoring sleep diseases. There are 2 challenges that remain open: (1) Since most methods only rely on input from a single channel, the spatial-temporal relationship of sleep signals has not been fully explored. (2) Lack of sleep data makes models hard to train from scratch. Here, we propose a vision Transformer-based architecture to process multi-channel polysomnogram signals. The method is an end-to-end framework that consists of a spatial encoder, a temporal encoder, and an MLP head classifier. The spatial encoder using a pre-trained Vision Transformer captures spatial information from multiple PSG channels. The temporal encoder utilizing the self-attention mechanism understands transitions between nearby epochs. In addition, we introduce a tailored image generation method to extract features within multi-channel and reshape them for transfer learning. We validate our method on 3 datasets and outperform the state-of-the-art algorithms. Our method fully explores the spatial-temporal relationship among different brain regions and addresses the problem of data insufficiency in clinical environments. Benefiting from reformulating the problem as image classification, the method could be applied to other 1D-signal problems in the future.