Search

Review studies play a key role in the development of clinical practice by synthesizing data and drawing conclusions from multiple scientific sources. In recent decades, there has been a significant increase in the number of review studies conducted and published by researchers. In clinical research, different types of review studies (systematic, scoping, umbrella, and narrative reviews) are conducted with different objectives and methodologies. Despite the abundance of guidelines for conducting review studies, researchers often face challenges in selecting the most appropriate review method, mainly due to their overlapping characteristics, including the complexity of matching review types to specific research questions. The aim of this article is to compare the main features of systematic, scoping, umbrella, and narrative reviews in clinical research and to address key considerations for selecting the most appropriate review approach. It also discusses future opportunities for updating their strategies based on emerging trends in clinical research. Understanding the differences between review approaches will help researchers, practitioners, journalists, and policymakers to effectively navigate the complex and evolving field of scientific research, leading to informed decisions that ultimately enhance the overall quality of healthcare practices. [ABSTRACT FROM AUTHOR]

Time series forecasting has witnessed a rapid proliferation of novel neural network approaches in recent times. However, performances in terms of benchmarking results are generally not consistent, and it is complicated to determine in which cases one approach fits better than another. Therefore, we propose adopting a data-centric perspective for benchmarking neural network architectures on time series forecasting by generating ad hoc synthetic datasets. In particular, we combine sinusoidal functions to synthesize univariate time series data for multi-input-multi-output prediction tasks. We compare the most popular architectures for time series, namely long short-term memory (LSTM) networks, convolutional neural networks (CNNs), and transformers, and directly connect their performance with different controlled data characteristics, such as the sequence length, noise and frequency, and delay length. Our findings suggest that transformers are the best architecture for dealing with different delay lengths. In contrast, for different noise and frequency levels and different sequence lengths, LSTM is the best-performing architecture by a significant amount. Based on our insights, we derive recommendations which allow machine learning (ML) practitioners to decide which architecture to apply, given the dataset’s characteristics.

Time series forecasting has witnessed a rapid proliferation of novel neural network approaches in recent times. However, performances in terms of benchmarking results are generally not consistent, and it is complicated to determine in which cases one approach fits better than another. Therefore, we propose adopting a data-centric perspective for benchmarking neural network architectures on time series forecasting by generating ad hoc synthetic datasets. In particular, we combine sinusoidal functions to synthesize univariate time series data for multi-input-multi-output prediction tasks. We compare the most popular architectures for time series, namely long short-term memory (LSTM) networks, convolutional neural networks (CNNs), and transformers, and directly connect their performance with different controlled data characteristics, such as the sequence length, noise and frequency, and delay length. Our findings suggest that transformers are the best architecture for dealing with different delay lengths. In contrast, for different noise and frequency levels and different sequence lengths, LSTM is the best-performing architecture by a significant amount. Based on our insights, we derive recommendations which allow machine learning (ML) practitioners to decide which architecture to apply, given the dataset's characteristics. [ABSTRACT FROM AUTHOR]

Chlorophyll-a (Chl-a) is a pivotal indicator of lake eutrophication. Studies examining nutrients limiting lake eutrophication at large scales have traditionally focused on summer and autumn, potentially limiting the applicability of their findings. This study encompasses 86 state-controlled points in the Eastern China Basin, spanning data collected from January 2020 to July 2023. Furthermore, we focus on the application of three machine-learning models (i.e., eXtreme Gradient Boosting, Support Vector Machines, and Naive Bayes Classifier) to analyze the seasonal nutrient dynamics in lake ecosystems. We categorized the monitoring data by season to eliminate outliers and employed adaptive synthetic sampling to address data imbalance issues. The results reveal that the direct correlations between total nitrogen (TN), total phosphorus (TP), and TP in conjunction with turbidity and Chl-a are broadly weak, possibly because of geographic variations, nutrient lag effects on algae, and differences in algal community composition. However, probabilistic analyses revealed that as TP or TN levels transitioned from oligo-mesotrophic (O) to eutrophic (E), TP exhibited a greater influence on the variation in Chl-a status than TN during spring and winter (p

Abstract: The San Francisco Estuary, in central California, has several long-running monitoring programs that have been used to reveal human-induced changes throughout the estuary in the last century. Here, we pair synoptic records of particulate organic matter (POM) composition from 1990–1996 and 2007–2016 with more robust long-term monitoring program records of total suspended sediment (TSS) concentrations generally starting in the mid-1970s to better understand how POM and TSS sources and transport have shifted. Specifically, POM C:N ratios and stable isotope values were used as indicators of POM source and to separate the bulk POC pool into detrital and phytoplankton components. We found that TSS and POC sources have shifted significantly across the estuary in time and space from declines in terrestrial inputs. Landward freshwater and brackish water sites, in the Delta and near Suisun Bay, witnessed long-term declines in TSS (32 to 52%), while seaward sites, near San Pablo Bay, recorded recent increases in TSS (16 to 121%) that began to trend downwards at the end of the record considered. Bulk POM C:N ratios shifted coeval with the TSS concentration changes at nearly all sites, with mean declines of 12 to 27% between 1990–1996 and 2007–2016. The widespread declines in bulk POM C:N ratios and inferred changes in POC concentrations from TSS trends, along with the substantial declines in upstream TSS supply through time (56%), suggest measurable reductions in terrestrial inputs to the system. Changes in terrestrial TSS and POM inputs have implications for biotic (e.g., food web dynamics) and abiotic organic matter cycling (e.g., burial, export) along the estuarine continuum. This work demonstrates how human-generated environmental changes can propagate spatially and temporally through a large river-estuary system. More broadly, we show how underutilized monitoring program datasets can be paired with existing (and often imperfect) synoptic records to generate new system insight in lieu of new data collection.

Cardiovascular diseases remain one of the main threats to human health, significantly affecting the quality and life expectancy. Effective and prompt recognition of these diseases is crucial. This research aims to develop an effective novel hybrid method for automatically detecting dangerous arrhythmias based on cardiac patients’ short electrocardiogram (ECG) fragments. This study suggests using a continuous wavelet transform (CWT) to convert ECG signals into images (scalograms) and examining the task of categorizing short 2-s segments of ECG signals into four groups of dangerous arrhythmias that are shockable, including ventricular flutter (C1), ventricular fibrillation (C2), ventricular tachycardia torsade de pointes (C3), and high-rate ventricular tachycardia (C4). We propose developing a novel hybrid neural network with a deep learning architecture to classify dangerous arrhythmias. This work utilizes actual electrocardiogram (ECG) data obtained from the PhysioNet database, alongside artificially generated ECG data produced by the Synthetic Minority Over-sampling Technique (SMOTE) approach, to address the issue of imbalanced class distribution for obtaining an accuracy-trained model. Experimental results demonstrate that the proposed approach achieves high accuracy, sensitivity, specificity, precision, and an F1-score of 97.75%, 97.75%, 99.25%, 97.75%, and 97.75%, respectively, in classifying all the four shockable classes of arrhythmias and are superior to traditional methods. Our work possesses significant clinical value in real-life scenarios since it has the potential to significantly enhance the diagnosis and treatment of lifethreatening arrhythmias in individuals with cardiac disease. Furthermore, our model also has demonstrated adaptability and generality for two other datasets. [ABSTRACT FROM AUTHOR]

Deep learning models have been used for a variety of image processing tasks. However, most of these models are developed through supervised learning approaches, which rely heavily on the availability of large-scale annotated datasets. Developing such datasets is tedious and expensive. In the absence of an annotated dataset, synthetic data can be used for model development; however, due to the substantial differences between simulated and real data, a phenomenon referred to as domain gap, the resulting models often underperform when applied to real data. In this research, we aim to address this challenge by first computationally simulating a large-scale annotated dataset and then using a generative adversarial network (GAN) to fill the gap between simulated and real images. This approach results in a synthetic dataset that can be effectively utilized to train a deep-learning model. Using this approach, we developed a realistic annotated synthetic dataset for wheat head segmentation. This dataset was then used to develop a deep-learning model for semantic segmentation. The resulting model achieved a Dice score of 83.4% on an internal dataset and Dice scores of 79.6% and 83.6% on two external datasets from the Global Wheat Head Detection datasets. While we proposed this approach in the context of wheat head segmentation, it can be generalized to other crop types or, more broadly, to images with dense, repeated patterns such as those found in cellular imagery. [ABSTRACT FROM AUTHOR]

Heterogeneous data have been used to enhance behavior prediction performance; however, it involves issues such as missing data, which need to be addressed. This paper proposes enhanced pet behavior prediction via Sensor to Skeleton Generative Adversarial Networks (S2GAN)-based heterogeneous data synthesis. The S2GAN model synthesizes the key features of video skeletons based on collected nine-axis sensor data and replaces missing data, thereby enhancing the accuracy of behavior prediction. In this study, data collected from 10 pets in a real-life-like environment were used to conduct recognition experiments on 9 commonly occurring types of indoor behavior. Experimental results confirmed that the proposed S2GAN-based synthesis method effectively resolves possible missing data issues in real environments and significantly improves the performance of the pet behavior prediction model. Additionally, by utilizing data collected under conditions similar to the real environment, the method enables more accurate and reliable behavior prediction. This research demonstrates the importance and utility of synthesizing heterogeneous data in behavior prediction, laying the groundwork for applications in various fields such as abnormal behavior detection and monitoring. [ABSTRACT FROM AUTHOR]

Abstract Background This study examined the synthesis methods used in meta-analyses pooling data from observational studies (OSs) and randomised controlled trials (RCTs) from various medical disciplines. Methods We searched Medline via PubMed to identify reports of systematic reviews of interventions, including and pooling data from RCTs and OSs published in 110 high-impact factor general and specialised journals between 2015 and 2019. Screening and data extraction were performed in duplicate. To describe the synthesis methods used in the meta-analyses, we considered the first meta-analysis presented in each article. Results Overall, 132 reports were identified with a median number of included studies of 14 [9–26]. The median number of OSs was 6.5 [3–12] and that of RCTs was 3 [1–6]. The effect estimates recorded from OSs (i.e., adjusted or unadjusted) were not specified in 82% (n = 108) of the meta-analyses. An inverse-variance common-effect model was used in 2% (n = 3) of the meta-analyses, a random-effects model was used in 55% (n = 73), and both models were used in 40% (n = 53). A Poisson regression model was used in 1 meta-analysis, and 2 meta-analyses did not report the model they used. The mean total weight of OSs in the studied meta-analyses was 57.3% (standard deviation, ± 30.3%). Only 44 (33%) meta-analyses reported results stratified by study design. Of them, the results between OSs and RCTs had a consistent direction of effect in 70% (n = 31). Study design was explored as a potential source of heterogeneity in 79% of the meta-analyses, and confounding factors were investigated in only 10% (n = 13). Publication bias was assessed in 70% (n = 92) of the meta-analyses. Tau-square was reported in 32 meta-analyses with a median of 0.07 [0–0.30]. Conclusion The inclusion of OSs in a meta-analysis on interventions could provide useful information. However, considerations of several methodological and conceptual aspects of OSs, that are required to avoid misleading findings, were often absent or insufficiently reported in our sample.

Due to the increasing severity of network security issues, training corresponding detection models requires large datasets. In this work, we propose a novel method based on generative adversarial networks to synthesize network data traffic. We introduced a network traffic data normalization method based on Gaussian mixture models (GMM), and for the first time, incorporated a generator based on the Swin Transformer structure into the field of network traffic generation. To further enhance the robustness of the model, we mapped real data through an AE (autoencoder) module and optimized the training results in the form of evolutionary algorithms. We validated the training results on four different datasets and introduced four additional models for comparative experiments in the experimental evaluation section. Our proposed SEGAN outperformed other state-of-the-art network traffic emulation methods. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases remain one of the main threats to human health, significantly affecting the quality and life expectancy. Effective and prompt recognition of these diseases is crucial. This research aims to develop an effective novel hybrid method for automatically detecting dangerous arrhythmias based on cardiac patients’ short electrocardiogram (ECG) fragments. This study suggests using a continuous wavelet transform (CWT) to convert ECG signals into images (scalograms) and examining the task of categorizing short 2-s segments of ECG signals into four groups of dangerous arrhythmias that are shockable, including ventricular flutter (C1), ventricular fibrillation (C2), ventricular tachycardia torsade de pointes (C3), and high-rate ventricular tachycardia (C4). We propose developing a novel hybrid neural network with a deep learning architecture to classify dangerous arrhythmias. This work utilizes actual electrocardiogram (ECG) data obtained from the PhysioNet database, alongside artificially generated ECG data produced by the Synthetic Minority Over-sampling Technique (SMOTE) approach, to address the issue of imbalanced class distribution for obtaining an accuracy-trained model. Experimental results demonstrate that the proposed approach achieves high accuracy, sensitivity, specificity, precision, and an F1-score of 97.75%, 97.75%, 99.25%, 97.75%, and 97.75%, respectively, in classifying all the four shockable classes of arrhythmias and are superior to traditional methods. Our work possesses significant clinical value in real-life scenarios since it has the potential to significantly enhance the diagnosis and treatment of life-threatening arrhythmias in individuals with cardiac disease. Furthermore, our model also has demonstrated adaptability and generality for two other datasets.

Data augmentation involves artificially expanding a dataset by applying various transformations to the existing data. Recent developments in deep learning have advanced data augmentation, enabling more complex transformations. Especially vital in the medical domain, deep learning-based data augmentation improves model robustness by generating realistic variations in medical images, enhancing diagnostic and predictive task performance. Therefore, to assist researchers and experts in their pursuits, there is a need for an extensive and informative study that covers the latest advancements in the growing domain of deep learning-based data augmentation in medical imaging. There is a gap in the literature regarding recent advancements in deep learning-based data augmentation. This study explores the diverse applications of data augmentation in medical imaging and analyzes recent research in these areas to address this gap. The study also explores popular datasets and evaluation metrics to improve understanding. Subsequently, the study provides a short discussion of conventional data augmentation techniques along with a detailed discussion on applying deep learning algorithms in data augmentation. The study further analyzes the results and experimental details from recent state-of-the-art research to understand the advancements and progress of deep learning-based data augmentation in medical imaging. Finally, the study discusses various challenges and proposes future research directions to address these concerns. This systematic review offers a thorough overview of deep learning-based data augmentation in medical imaging, covering application domains, models, results analysis, challenges, and research directions. It provides a valuable resource for multidisciplinary studies and researchers making decisions based on recent analytics.

With the vigorously developed services of cloud computing, it is relatively easier and more convenient for organizations or enterprises to open data on clouds. However, as personal information in electronic data becomes more massive and detailed, how to balance data opening and personal privacy has become a critical issue. In this paper, we propose the Theseus Data Synthesis Approach (TDSA), which generates synthetic data by replacing partial records until no record from the original dataset remains. Unlike other data anonymization works such as k-anonymity and differential privacy, which encountered limitations and challenges when applying to real-world scenarios. In our work, Since there are no real data, personal privacy is definitely preserved. We also analyze the quality and utility of the synthetic dataset and make comparisons with related works. We conclude that with our scheme, opening useful data on clouds and preserving personal privacy can be simultaneously achieved.

Classification models using deep or machine learning algorithms require a sufficient and balanced training dataset to improve performance. Still, they suffer from data collection due to data privacy issues. In medical research, where most data variables are sensitive information, collecting enough training data for model performance improvement is more challenging. This study presents a new medical data augmentation algorithm consisting of four steps to solve the data shortage and class imbalance issues. The main idea of the proposed algorithm is to reflect the core characteristic of the original data’s class label. The algorithm receives an original dataset as an input value to extract the feature vector and trains the individual autoencoder model. Then it verifies the augmented feature vector through a distributional equality check, and each feature vector is concatenated into one feature vector. The deep learning model inference is applied on a concatenated vector for the second verification, to finalize the augmented training dataset. Our team performed mood disorder classification using patient data to prove the presented data augmentation algorithm. With the method, the classification performance improved by 0.059 in the severity classification of major depressive disorder, 0.041 in the severity classification of anxiety disorder, and 0.073 in the subtype classification of bipolar disorder. Through this study, we proved that our algorithm can be applied to minimize model bias and improve classification performance on the medical data that are unbalanced or insufficient in number by class.

Abstract As the number one building material, concrete is of fundamental importance in civil engineering. Understanding its failure mechanisms is essential for designing sustainable buildings and infrastructure. Micro-computed tomography (μCT) is a well-established tool for virtually assessing crack initiation and propagation in concrete. The reconstructed 3d images can be examined via techniques from the fields of classical image processing and machine learning. Ground truths are a prerequisite for an objective evaluation of crack segmentation methods. Furthermore, they are necessary for training machine learning models. However, manual annotation of large 3d concrete images is not feasible. To tackle the problem of data scarcity, the image pairs of cracked concrete and corresponding ground truth can be synthesized. In this work we propose a novel approach to stochastically model crack structures via Voronoi diagrams. The method is based on minimum-weight surfaces, an extension of shortest paths to 3d. Within a dedicated image processing pipeline, the surfaces are then discretized and embedded into real μCT images of concrete. The method is flexible and fast, such that a variety of different crack structures can be generated in a short amount of time.

Supervised Neural Networks are used for segmentation in many biological and biomedical applications. To omit the time-consuming and tiring process of manual labeling, unsupervised Generative Adversarial Networks (GANs) can be used to synthesize labeled data. However, the training of GANs requires extensive computation and is often unstable. Due to the lack of established stopping criteria, GANs are usually trained multiple times for a heuristically fixed number of epochs. Early stopping and epoch selection can lead to better synthetic datasets resulting in higher downstream segmentation quality on biological or medical data. This article examines whether the Frechet Inception Distance (FID), the Kernel Inception Distance (KID), or the WeightWatcher tool can be used for early stopping or epoch selection of unsupervised GANs. The experiments show that the last trained GAN epoch is not necessarily the best one to synthesize downstream segmentation data. On complex datasets, FID and KID correlate with the downstream segmentation quality, and both can be used for epoch selection.

Classification of sheep behaviour from a sequence of tri-axial accelerometer data has the potential to enhance sheep management. Sheep behaviour is inherently imbalanced (e.g., more ruminating than walking) resulting in underperforming classification for the minority activities which hold importance. Existing works have not addressed class imbalance and use traditional machine learning techniques, e.g., Random Forest (RF). We investigated Deep Learning (DL) models, namely, Long Short Term Memory (LSTM) and Bidirectional LSTM (BLSTM), appropriate for sequential data, from imbalanced data. Two data sets were collected in normal grazing conditions using jaw-mounted and ear-mounted sensors. Novel to this study, alongside typical single classes, e.g., walking, depending on the behaviours, data samples were labelled with compound classes, e.g., walking_grazing. The number of steps a sheep performed in the observed 10 s time window was also recorded and incorporated in the models. We designed several multi-class classification studies with imbalance being addressed using synthetic data. DL models achieved superior performance to traditional ML models, especially with augmented data (e.g., 4-Class + Steps: LSTM 88.0%, RF 82.5%). DL methods showed superior generalisability on unseen sheep (i.e., F1-score: BLSTM 0.84, LSTM 0.83, RF 0.65). LSTM, BLSTM and RF achieved sub-millisecond average inference time, making them suitable for real-time applications. The results demonstrate the effectiveness of DL models for sheep behaviour classification in grazing conditions. The results also demonstrate the DL techniques can generalise across different sheep. The study presents a strong foundation of the development of such models for real-time animal monitoring.

When classifiers face imbalanced class distributions, they often misclassify minority class samples, consequently diminishing the predictive performance of machine learning models. Existing oversampling techniques predominantly rely on the selection of neighboring data via interpolation, with less emphasis on uncovering the intrinsic patterns and relationships within the data. In this research, we present the usefulness of an algorithm named RuLer to deal with the problem of classification with imbalanced data. RuLer is a learning algorithm initially designed to recognize new sound patterns within the context of the performative artistic practice known as live coding. This paper demonstrates that this algorithm, once adapted (Ad-RuLer), has great potential to address the problem of oversampling imbalanced data. An extensive comparison with other mainstream oversampling algorithms (SMOTE, ADASYN, Tomek-links, Borderline-SMOTE, and KmeansSMOTE), using different classifiers (logistic regression, random forest, and XGBoost) is performed on several real-world datasets with different degrees of data imbalance. The experiment results indicate that Ad-RuLer serves as an effective oversampling technique with extensive applicability. [ABSTRACT FROM AUTHOR]

As the number one building material, concrete is of fundamental importance in civil engineering. Understanding its failure mechanisms is essential for designing sustainable buildings and infrastructure. Micro-computed tomography (μCT) is a well-established tool for virtually assessing crack initiation and propagation in concrete. The reconstructed 3d images can be examined via techniques from the fields of classical image processing and machine learning. Ground truths are a prerequisite for an objective evaluation of crack segmentation methods. Furthermore, they are necessary for training machine learning models. However, manual annotation of large 3d concrete images is not feasible. To tackle the problem of data scarcity, the image pairs of cracked concrete and corresponding ground truth can be synthesized. In this work we propose a novel approach to stochastically model crack structures via Voronoi diagrams. The method is based on minimum-weight surfaces, an extension of shortest paths to 3d. Within a dedicated image processing pipeline, the surfaces are then discretized and embedded into real μCT images of concrete. The method is flexible and fast, such that a variety of different crack structures can be generated in a short amount of time. [ABSTRACT FROM AUTHOR]

Recently, deep learning (DL) models have been increasingly adopted for automatic analyses of medical data, including electrocardiograms (ECGs). Large, available ECG datasets, generally of high quality, often lack specific distortions, which could be helpful for enhancing DL-based algorithms. Synthetic ECG datasets could overcome this limitation. A generative adversarial network (GAN) was used to synthesize realistic 3D magnetohydrodynamic (MHD) distortion templates, as observed during magnetic resonance imaging (MRI), and then added to available ECG recordings to produce an augmented dataset. Similarity metrics, as well as the accuracy of a DL-based R-peak detector trained with and without data augmentation, were used to evaluate the effectiveness of the synthesized data. Three-dimensional MHD distortions produced by the proposed GAN were similar to the measured ones used as input. The precision of a DL-based R-peak detector, tested on actual unseen data, was significantly enhanced by data augmentation; its recall was higher when trained with augmented data. Using synthesized MHD-distorted ECGs significantly improves the accuracy of a DL-based R-peak detector, with a good generalization capacity. This provides a simple and effective alternative to collecting new patient data. DL-based algorithms for ECG analyses can suffer from bias or gaps in training datasets. Using a GAN to synthesize new data, as well as metrics to evaluate its performance, can overcome the scarcity issue of data availability. [ABSTRACT FROM AUTHOR]

Deep learning models have been used for a variety of image processing tasks. However, most of these models are developed through supervised learning approaches, which rely heavily on the availability of large-scale annotated datasets. Developing such datasets is tedious and expensive. In the absence of an annotated dataset, synthetic data can be used for model development; however, due to the substantial differences between simulated and real data, a phenomenon referred to as domain gap, the resulting models often underperform when applied to real data. In this research, we aim to address this challenge by first computationally simulating a large-scale annotated dataset and then using a generative adversarial network (GAN) to fill the gap between simulated and real images. This approach results in a synthetic dataset that can be effectively utilized to train a deep-learning model. Using this approach, we developed a realistic annotated synthetic dataset for wheat head segmentation. This dataset was then used to develop a deep-learning model for semantic segmentation. The resulting model achieved a Dice score of 83.4% on an internal dataset and Dice scores of 79.6% and 83.6% on two external datasets from the Global Wheat Head Detection datasets. While we proposed this approach in the context of wheat head segmentation, it can be generalized to other crop types or, more broadly, to images with dense, repeated patterns such as those found in cellular imagery.

Heterogeneous data have been used to enhance behavior prediction performance; however, it involves issues such as missing data, which need to be addressed. This paper proposes enhanced pet behavior prediction via Sensor to Skeleton Generative Adversarial Networks (S2GAN)-based heterogeneous data synthesis. The S2GAN model synthesizes the key features of video skeletons based on collected nine-axis sensor data and replaces missing data, thereby enhancing the accuracy of behavior prediction. In this study, data collected from 10 pets in a real-life-like environment were used to conduct recognition experiments on 9 commonly occurring types of indoor behavior. Experimental results confirmed that the proposed S2GAN-based synthesis method effectively resolves possible missing data issues in real environments and significantly improves the performance of the pet behavior prediction model. Additionally, by utilizing data collected under conditions similar to the real environment, the method enables more accurate and reliable behavior prediction. This research demonstrates the importance and utility of synthesizing heterogeneous data in behavior prediction, laying the groundwork for applications in various fields such as abnormal behavior detection and monitoring.

The usage of synthetic data is gaining momentum in part due to the unavailability of original data due to privacy and legal considerations and in part due to its utility as an augmentation to the authentic data. Generative adversarial networks (GANs), a paragon of generative models, initially for images and subsequently for tabular data, has contributed many of the state-of-the-art synthesizers. As GANs improve, the synthesized data increasingly resemble the real data risking to leak privacy. Differential privacy (DP) provides theoretical guarantees on privacy loss but degrades data utility. Striking the best trade-off remains yet a challenging research question. In this study, we propose CTAB-GAN+ a novel conditional tabular GAN. CTAB-GAN+ improves upon state-of-the-art by (i) adding downstream losses to conditional GAN for higher utility synthetic data in both classification and regression domains; (ii) using Wasserstein loss with gradient penalty for better training convergence; (iii) introducing novel encoders targeting mixed continuous-categorical variables and variables with unbalanced or skewed data; and (iv) training with DP stochastic gradient descent to impose strict privacy guarantees. We extensively evaluate CTAB-GAN+ on statistical similarity and machine learning utility against state-of-the-art tabular GANs. The results show that CTAB-GAN+ synthesizes privacy-preserving data with at least 21.9% higher machine learning utility (i.e., F1-Score) across multiple datasets and learning tasks under given privacy budget.

Used as a communicative tool for risk management, risk maps provide a service to the public, conveying information that can raise risk awareness and encourage mitigation. Several studies have utilized risk maps to determine risks associated with the distribution of Borrelia burgdorferi, the causal agent of Lyme disease in North America and Europe, as this zoonotic disease can lead to severe symptoms. This literature review focused on the use of risk maps to model distributions of B. burgdorferi and its vector, the blacklegged tick (Ixodes scapularis), in North America to compare variables used to predict these spatial models. Data were compiled from the existing literature to determine which ecological, environmental, and anthropic (i.e., human focused) variables past research has considered influential to the risk level for Lyme disease. The frequency of these variables was examined and analyzed via a non-metric multidimensional scaling analysis to compare different map elements that may categorize the risk models performed. Environmental variables were found to be the most frequently used in risk spatial models, particularly temperature. It was found that there was a significantly dissimilar distribution of variables used within map elements across studies: Map Type, Map Distributions, and Map Scale. Within these map elements, few anthropic variables were considered, particularly in studies that modeled future risk, despite the objective of these models directly or indirectly focusing on public health intervention. Without including human-related factors considering these variables within risk map models, it is difficult to determine how reliable these risk maps truly are. Future researchers may be persuaded to improve disease risk models by taking this into consideration.

Keywords: data synthesis; database; germination; open science; plant reproduction; repository; seed; trait EN data synthesis database germination open science plant reproduction repository seed trait 466 470 5 09/25/23 20231015 NES 231015 Data availability The data and code used to produce this article are available at https://github.com/efernandezpascual/seedarcms. The need for a global archive of primary seed germination data The seed ecology community has recently recognized the need to synthesize knowledge, setting the research agenda for functional seed ecology (Saatkamp I et al i ., [34]). I SeedArc i compiles primary seed germination data to synthesize the seed germination spectrum at a global scale. The theory underlying the seed germination spectrum has been laid out by decades of work on seed ecology (Baskin & Baskin, [1]), but empirical studies testing major ecological hypotheses at both global and local scales remain elusive without a standardized seed germination database. [Extracted from the article]

Ecological status assessment under the European Water Framework Directive (WFD) often integrates the impact of multiple stressors into a single index value. This hampers the identification of individual stressors being responsible for status deterioration. As a consequence, management measures are often disentangled from assessment results. To close this gap and to support river basin managers in the diagnosis of stressors, we linked numerous macroinvertebrate assessment metrics and one diatom index with potential causes of ecological deterioration through Bayesian belief networks (BBNs). The BBNs were informed by WFD monitoring data as well as regular consultation with experts and allow to estimate the probabilities of individual degradation causes based upon a selection of biological metrics. Macroinvertebrate metrics were shown to be stronger linked to hydromorphological conditions and land use than to water quality-related parameters (e.g., thermal and nutrient pollution). The modeled probabilities also allow to order the potential causes of degradation hierarchically. The comparison of assessment metrics showed that compositional and trait-based community metrics performed equally well in the diagnosis. The testing of the BBNs by experts resulted in an agreement between model output and expert opinion of 17–92% for individual stressors. Overall, the expert-based validation confirmed a good diagnostic potential of the BBNs; on average 80% of the diagnosed causes were in agreement with expert judgement. We conclude that diagnostic BBNs can assist the identification of causes of stream and river degradation and thereby inform the derivation of appropriate management decisions. [ABSTRACT FROM AUTHOR]

Most existing data synthesis methods are designed to tackle problems with dataset imbalance, data anonymization, and an insufficient sample size. There is a lack of effective synthesis methods in cases where the actual datasets have a limited number of data points but a large number of features and unknown noise. Thus, in this paper we propose a data synthesis method named Adaptive Subspace Interpolation for Data Synthesis (ASIDS). The idea is to divide the original data feature space into several subspaces with an equal number of data points, and then perform interpolation on the data points in the adjacent subspaces. This method can adaptively adjust the sample size of the synthetic dataset that contains unknown noise, and the generated sample data typically contain minimal errors. Moreover, it adjusts the feature composition of the data points, which can significantly reduce the proportion of the data points with large fitting errors. Furthermore, the hyperparameters of this method have an intuitive interpretation and usually require little calibration. Analysis results obtained using simulated original data and benchmark original datasets demonstrate that ASIDS is a robust and stable method for data synthesis. [ABSTRACT FROM AUTHOR]

Facial expression recognition (FER) is an important method to study and distinguish human emotions. In the virtual reality (VR) context, people's emotions are instantly and naturally triggered and mobilized due to the high immersion and realism of VR. However, when people are wearing head mounted display (HMD) VR equipment, the eye regions will be covered. The FER accuracy will be reduced if the eye region information is discarded. Therefore, it is necessary to obtain the information of eye regions using other methods. The main difficulty in FER in an immersive VR context is that the conventional FER methods depend on public databases. The image facial information in the public databases is complete, so these methods are difficult to directly apply to the VR context. To solve this problem, this paper designs and implements a solution for FER in the VR context as follows. A real facial expression database collection scheme in the VR context is implemented by adding an infrared camera and infrared light source to the HMD. A virtual database construction method is presented for FER in the VR context, which can improve the generalization of models. A deep network named the multi-region facial expression recognition model is designed for FER in the VR context. [ABSTRACT FROM AUTHOR]

Data trust in IoT is crucial for safeguarding privacy, security, reliable decision-making, user acceptance, and complying with regulations. Various approaches based on supervised or unsupervised machine learning (ML) have recently been proposed for evaluating IoT data trust. However, assessing their real-world efficacy is hard mainly due to the lack of related publicly available datasets that can be used for benchmarking. Since obtaining such datasets is challenging, we propose a data synthesis method, called random walk infilling (RWI), to augment IoT time-series datasets by synthesizing untrustworthy data from existing trustworthy data. Thus, RWI enables us to create labeled datasets that can be used to develop and validate ML models for IoT data trust evaluation. We also extract new features from IoT time-series sensor data that effectively capture its autocorrelation as well as its cross-correlation with the data of the neighboring (peer) sensors. These features can be used to learn ML models for recognizing the trustworthiness of IoT sensor data. Equipped with our synthesized ground-truth-labeled datasets and informative correlation-based features, we conduct extensive experiments to critically examine various approaches to evaluating IoT data trust via ML. The results reveal that commonly used ML-based approaches to IoT data trust evaluation, which rely on unsupervised cluster analysis to assign trust labels to unlabeled data, perform poorly. This poor performance is due to the underlying assumption that clustering provides reliable labels for data trust, which is found to be untenable. The results also indicate that ML models, when trained on datasets augmented via RWI and using the proposed features, generalize well to unseen data and surpass existing related approaches. Moreover, we observe that a semi-supervised ML approach that requires only about 10% of the data labeled offers competitive performance while being practically more appealing compared to the fully supervised approaches. The related Python code and data are available online. [ABSTRACT FROM AUTHOR]

The International Union for Conservation of Nature (IUCN) Red List is an important and widely used tool for conservation assessment. The IUCN uses information about a species' range, population size, habitat quality and fragmentation levels, and trends in abundance to assess extinction risk. Genetic diversity is not considered, although it affects extinction risk. Declining populations are more strongly affected by genetic drift and higher rates of inbreeding, which can reduce the efficiency of selection, lead to fitness declines, and hinder species' capacities to adapt to environmental change. Given the importance of conserving genetic diversity, attempts have been made to find relationships between red‐list status and genetic diversity. Yet, there is still no consensus on whether genetic diversity is captured by the current IUCN Red List categories in a way that is informative for conservation. To assess the predictive power of correlations between genetic diversity and IUCN Red List status in vertebrates, we synthesized previous work and reanalyzed data sets based on 3 types of genetic data: mitochondrial DNA, microsatellites, and whole genomes. Consistent with previous work, species with higher extinction risk status tended to have lower genetic diversity for all marker types, but these relationships were weak and varied across taxa. Regardless of marker type, genetic diversity did not accurately identify threatened species for any taxonomic group. Our results indicate that red‐list status is not a useful metric for informing species‐specific decisions about the protection of genetic diversity and that genetic data cannot be used to identify threat status in the absence of demographic data. Thus, there is a need to develop and assess metrics specifically designed to assess genetic diversity and inform conservation policy, including policies recently adopted by the UN's Convention on Biological Diversity Kunming‐Montreal Global Biodiversity Framework. [ABSTRACT FROM AUTHOR]

Alfalfa is critical to global food security, and its data is abundant in the U.S. nationally, but often scarce locally, limiting the potential performance of machine learning (ML) models in predicting alfalfa biomass yields. Training ML models on local-only data results in very low estimation accuracy when the datasets are very small. Therefore, we explore synthesizing non-local data to estimate biomass yields labeled as high, medium, or low. One option to remedy scarce local data is to train models using non-local data; however, this only works about as well as using local data. Therefore, we propose a novel pipeline that trains models using data synthesized from non-local data to estimate local crop yields. Our pipeline, synthesized non-local training (SNLT pronounced like sunlight), achieves a gain of 42.9% accuracy over the best results from regular non-local and local training on our very small target dataset. This pipeline produced the highest accuracy of 85.7% with a decision tree classifier. From these results, we conclude that SNLT can be a useful tool in helping to estimate crop yields with ML. Furthermore, we propose a software application called Predict Your CropS (PYCS pronounced like Pisces) designed to help farmers and researchers estimate and predict crop yields based on pretrained models.

Abstract Background Community-based exercise is a continuation and complement to inpatient rehabilitation for Parkinson's disease and does not require a professional physical therapist or equipment. The effects, parameters, and forms of each exercise are diverse, and the effect is affected by many factors. A meta-analysis was conducted to determine the effect and the best parameters for improving motor symptoms and to explore the possible factors affecting the effect of community-based exercise. Methods We conducted a comprehensive search of six databases: PEDro, PubMed/Medline, CENTRAL, Scopus, Embase, and WOS. Studies that compared community-based exercise with usual care were included. The intervention mainly included dance, Chinese martial arts, Nordic walking, and home-based exercise. The primary outcome measure was the Unified Parkinson’s Disease Rating Scale part III (UPDRS-III) score. The mean difference (95% CI) was used to calculate the treatment outcomes of continuous outcome variables, and the I2 statistic was used to estimate the heterogeneity of the statistical analysis. We conducted subgroup analysis and meta-regression analysis to determine the optimal parameters and the most important influencing factors of the exercise effect. Results Twenty-two studies that enrolled a total of 809 subjects were included in the analysis. Exercise had a positive effect on the UPDRS-III (MD = -5.83; 95% CI, -8.29 to -3.37), Timed Up and Go test (MD = -2.22; 95% CI -3.02 to -1.42), UPDRS ((MD = -7.80; 95% CI -10.98 to -6.42), 6-Minute Walk Test (MD = 68.81; 95% CI, 32.14 to 105.48), and Berg Balance Scale (MD = 4.52; 95% CI, 2.72 to 5.78) scores. However, the heterogeneity of each included study was obvious. Weekly frequency, age, and duration of treatment were all factors that potentially influenced the effect. Conclusions This meta-analysis suggests that community-based exercise may benefit motor function in patients with PD. The most commonly used modalities of exercise were tango and tai chi, and the most common prescription was 60 min twice a week. Future studies should consider the influence of age, duration of treatment, and weekly frequency on the effect of exercise. PROSPERO trial registration number CRD42022327162.

Polycystic Ovary Syndrome (PCOS) is among the most prevalent endocrinological abnormalities seen in reproductive female bodies posing serious health hazards. The correctness of interpreting this condition depends heavily on the wide spectrum of associated symptoms and the doctor's expertise, making real-time clinical detection quite challenging. Thus, investigations on computer-aided PCOS detection systems have recently been explored by several researchers worldwide as a potential replacement for manual assessment. This review study's objective is to analyze the relevant research works on computer-assisted methods for automatically identifying PCOS through a systematic literature review (SLR) methodology as well as investigate the research limitations and explore potential future research scopes in this domain. 28 articles have been selected using the PRISMA approach based on a set of inclusion-exclusion criteria for conducting the review. The data synthesis of the selected articles has been conducted using six data exploration themes. As outcomes, the SLR explored the topical association between the studies; their research profiles; objectives; data size, type, and sources; methodologies applied for the detection of PCOS; and lastly the research outcomes along with their evaluation measures and performances. The study also highlights areas for future research directions examining the study gaps to enhance the current efforts for autonomous PCOS identification; such as integrating advanced techniques with the current methods; developing interactive software systems; exploring deep learning and unsupervised machine learning techniques; enhancing datasets and country context; and investigating more unknown factors behind PCOS. Thus, this SLR provides a state-of-the-art paradigm of autonomous PCOS detection which will support significantly efficient clinical assessment, diagnosis and treatment of PCOS.

Introduction: Transversus abdominis plane block (TAPB) is now commonly administered for postoperative pain control and reduced opioid consumption in patients undergoing major colorectal surgeries, such as colorectal cancer, diverticular disease, and inflammatory bowel disease resection. However, there remain several controversies about the effectiveness and safety of laparoscopic TAPB compared to ultrasound-guided TAPB. Therefore, the aim of this study is to integrate both direct and indirect comparisons to identify a more effective and safer TAPB approach. Materials and methods: Systematic electronic literature surveillance will be performed in the PubMed, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), and ClinicalTrials.gov databases for eligible studies through July 31, 2023. The Cochrane Risk of Bias version 2 (RoB 2) and Risk of Bias in Non-randomized Studies of Interventions (ROBINS-I) tools will be applied to scrutinize the methodological quality of the selected studies. The primary outcomes will include (1) opioid consumption at 24 hours postoperatively and (2) pain scores at 24 hours postoperatively both at rest and at coughing and movement according to the numerical rating scale (NRS). Additionally, the probability of TAPB-related adverse events, overall postoperative 30-day complications, postoperative 30-day ileus, postoperative 30-day surgical site infection, postoperative 7-day nausea and vomiting, and length of stay will be analyzed as secondary outcome measures. The findings will be assessed for robustness through subgroup analyses and sensitivity analyses. Data analyses will be performed using RevMan 5.4.1 and Stata 17.0. P value of less than 0.05 will be defined as statistically significant. The certainty of evidence will be examined via the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) working group approach. Ethics and dissemination: Owing to the nature of the secondary analysis of existing data, no ethical approval will be required. Our meta-analysis will summarize all the available evidence for the effectiveness and safety of TAPB approaches for minimally invasive colorectal surgery. High-quality peerreviewed publications and presentations at international conferences will facilitate disseminating the results of this study, which are expected to inform future clinical trials and help anesthesiologists and surgeons determine the optimal tailored clinical practice for perioperative pain management. [ABSTRACT FROM AUTHOR]

Due to the increasing severity of network security issues, training corresponding detection models requires large datasets. In this work, we propose a novel method based on generative adversarial networks to synthesize network data traffic. We introduced a network traffic data normalization method based on Gaussian mixture models (GMM), and for the first time, incorporated a generator based on the Swin Transformer structure into the field of network traffic generation. To further enhance the robustness of the model, we mapped real data through an AE (autoencoder) module and optimized the training results in the form of evolutionary algorithms. We validated the training results on four different datasets and introduced four additional models for comparative experiments in the experimental evaluation section. Our proposed SEGAN outperformed other state-of-the-art network traffic emulation methods.

Estimating the number of people in hidden populations is needed for public health research, yet available methods produce highly variable and uncertain results. The Anchored Multiplier calculator uses a Bayesian framework to synthesize multiple population size estimates to generate a consensus estimate. Users submit point estimates and lower/upper bounds which are converted to beta probability distributions and combined to form a single posterior probability distribution. The Anchored Multiplier calculator is available as a web browser-based application. The software allows for unlimited empirical population size estimates to be submitted and combined according to Bayes Theorem to form a single estimate. The software returns output as a forest plot (to visually compare data inputs and the final Anchored Multiplier estimate) and a table that displays results as population percentages and counts. The web application 'Anchored Multiplier Calculator' is free software and is available at [http://globalhealthsciences.ucsf.edu/resources/tools] or directly at [http://anchoredmultiplier.ucsf.edu/].

The use of CMOS sensors for rotational spectroscopy is a promising, but challenging avenue for low-cost gas sensing and molecular identification. A main challenge in this approach is that practical CMOS spectroscopy samples contain various different noise sources that reduce the effectiveness of matching techniques for molecular identification with rotational spectroscopy. To help solve this challenge, we develop a software application tool that can demonstrate the feasibility and reliability of detection with CMOS sensor samples. Specifically, the tool characterizes the types of noise in CMOS sample collection and synthesizes spectroscopy files based upon existing databases of rotational spectroscopy samples gathered from other sensors. We use the software to create a large database of plausible CMOS-generated sample files of gases. This dataset is used to help evaluate spectral matching algorithms used in gas sensing and molecular identification applications. We evaluate these traditional methods on the synthesized dataset and discuss how peak finding and spectral matching algorithms can be altered to accommodate the noise sources present in CMOS sample collection.

IntroductionTransversus abdominis plane block (TAPB) is now commonly administered for postoperative pain control and reduced opioid consumption in patients undergoing major colorectal surgeries, such as colorectal cancer, diverticular disease, and inflammatory bowel disease resection. However, there remain several controversies about the effectiveness and safety of laparoscopic TAPB compared to ultrasound-guided TAPB. Therefore, the aim of this study is to integrate both direct and indirect comparisons to identify a more effective and safer TAPB approach.Materials and methodsSystematic electronic literature surveillance will be performed in the PubMed, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), and ClinicalTrials.gov databases for eligible studies through July 31, 2023. The Cochrane Risk of Bias version 2 (RoB 2) and Risk of Bias in Non-randomized Studies of Interventions (ROBINS-I) tools will be applied to scrutinize the methodological quality of the selected studies. The primary outcomes will include (1) opioid consumption at 24 hours postoperatively and (2) pain scores at 24 hours postoperatively both at rest and at coughing and movement according to the numerical rating scale (NRS). Additionally, the probability of TAPB-related adverse events, overall postoperative 30-day complications, postoperative 30-day ileus, postoperative 30-day surgical site infection, postoperative 7-day nausea and vomiting, and length of stay will be analyzed as secondary outcome measures. The findings will be assessed for robustness through subgroup analyses and sensitivity analyses. Data analyses will be performed using RevMan 5.4.1 and Stata 17.0. P value of less than 0.05 will be defined as statistically significant. The certainty of evidence will be examined via the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) working group approach.Ethics and disseminationOwing to the nature of the secondary analysis of existing data, no ethical approval will be required. Our meta-analysis will summarize all the available evidence for the effectiveness and safety of TAPB approaches for minimally invasive colorectal surgery. High-quality peer-reviewed publications and presentations at international conferences will facilitate disseminating the results of this study, which are expected to inform future clinical trials and help anesthesiologists and surgeons determine the optimal tailored clinical practice for perioperative pain management.Systematic review registrationhttps://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=281720, identifier (CRD42021281720).

The global loss of biodiversity has inspired actions to restore nature across the planet. Translocation and social attraction actions deliberately move or lure a target species to a restoration site to reintroduce or augment populations and enhance biodiversity and ecosystem resilience. Given limited conservation funding and rapidly accelerating extinction trajectories, tracking progress of these interventions can inform best practices and advance management outcomes. Seabirds are globally threatened and commonly targeted for translocation and social attraction (“active seabird restoration”), yet no framework exists for tracking these efforts nor informing best practices. This study addresses this gap for conservation decision makers responsible for seabirds and coastal management. We systematically reviewed active seabird restoration projects worldwide and collated results into a publicly accessible Seabird Restoration Database. We describe global restoration trends, apply a systematic process to measure success rates and response times since implementation, and examine global factors influencing outcomes. The database contains 851 active restoration events in 551 locations targeting 138 seabird species; 16% of events targeted globally threatened taxa. Visitation occurred in 80% of events and breeding occurred in 76%, on average 2 y after implementation began (SD = 3.2 y). Outcomes varied by taxonomy, with the highest and quickest breeding response rates for Charadriiformes (terns, gulls, and auks), primarily with social attraction. Given delayed and variable response times to active restoration, 5 y is appropriate before evaluating outcomes. The database and results serve as a model for tracking and evaluating restoration outcomes, and is applicable to measuring conservation interventions for additional threatened taxa. [ABSTRACT FROM AUTHOR]

Alfalfa is critical to global food security, and its data is abundant in the U.S. nationally, but often scarce locally, limiting the potential performance of machine learning (ML) models in predicting alfalfa biomass yields. Training ML models on local-only data results in very low estimation accuracy when the datasets are very small. Therefore, we explore synthesizing non-local data to estimate biomass yields labeled as high, medium, or low. One option to remedy scarce local data is to train models using non-local data; however, this only works about as well as using local data. Therefore, we propose a novel pipeline that trains models using data synthesized from non-local data to estimate local crop yields. Our pipeline, synthesized non-local training (SNLT pronounced like sunlight), achieves a gain of 42.9% accuracy over the best results from regular non-local and local training on our very small target dataset. This pipeline produced the highest accuracy of 85.7% with a decision tree classifier. From these results, we conclude that SNLT can be a useful tool in helping to estimate crop yields with ML. Furthermore, we propose a software application called Predict Your CropS (PYCS pronounced like Pisces) designed to help farmers and researchers estimate and predict crop yields based on pretrained models. [ABSTRACT FROM AUTHOR]

This study addresses the challenges of privacy, utility, and efficiency in releasing privacy-preserving operational data for AC Optimal Power Flow (AC-OPF) research. Traditional methods, injecting noise into operational data (i.e. , demand data and dispatch profiles) within the Differential Privacy (DP) framework, often violate physical constraints within the data, leading to unrealistic and infeasible outcomes that diminish data utility. While AC-OPF-solver-based bi-level post-processing optimizations can enforce physical feasibility, the objective divergence between post-processing and AC-OPF leads to discrepancies, compromising data utility. Additionally, their non-convex and adversarial nature makes computation prohibitively expensive, further preventing efficient data release. To overcome these challenges, our research introduces a DP approach that combines strategic noise injection for demand data with the computation of corresponding dispatch profiles, ensuring the privacy-preserving data satisfy AC-OPF's physical constraints. To accelerate data release, we employ Physics-Informed Neural Networks (PINNs). This ensures solutions' physical feasibility while enhancing computational efficiency. Furthermore, we incorporate active learning to target the most informative data samples, enhancing PINN training and optimizing efficiency while maintaining solution accuracy. Comprehensive experiments on IEEE test systems reveal our approach's improved performance and accelerated computation speed over traditional methods, highlighting its efficiency in maintaining data privacy and utility and decreasing computational burden amidst diverse privacy considerations. • Realistic, feasible, and fast data synthesis via AC-OPF-tailored PINNs. • Quantifying trade-off between demand privacy and dispatch profile accuracy. • Sampling efficient PINN training set via active learning. [ABSTRACT FROM AUTHOR]

When classifiers face imbalanced class distributions, they often misclassify minority class samples, consequently diminishing the predictive performance of machine learning models. Existing oversampling techniques predominantly rely on the selection of neighboring data via interpolation, with less emphasis on uncovering the intrinsic patterns and relationships within the data. In this research, we present the usefulness of an algorithm named RuLer to deal with the problem of classification with imbalanced data. RuLer is a learning algorithm initially designed to recognize new sound patterns within the context of the performative artistic practice known as live coding. This paper demonstrates that this algorithm, once adapted (Ad-RuLer), has great potential to address the problem of oversampling imbalanced data. An extensive comparison with other mainstream oversampling algorithms (SMOTE, ADASYN, Tomek-links, Borderline-SMOTE, and KmeansSMOTE), using different classifiers (logistic regression, random forest, and XGBoost) is performed on several real-world datasets with different degrees of data imbalance. The experiment results indicate that Ad-RuLer serves as an effective oversampling technique with extensive applicability.