Search

The inverter is considered the core of the PV power plant. The inverter's failure leads to generation loss and decreases plant availability. So, it is required to investigate a clear Root Cause Analysis (RCA) to deduce the failure causes and implement the required corrective action in addition to the preventive action to avoid more inverter failure, hereby maintaining the plant available to a certain value. This paper discusses real-time mode operation data analysis of the PV grid-connected inverter due to real central inverter incidents in Benban solar park located in Egypt.The central inverter plays an important role in the Mega-Scale PV power plant. The main function of this inverter is to convert the DC power produced by the PV modules to AC power to be injected into the utility grid by considering specific characteristics based on the grid code. The availability of any PV power plant directly depends on the healthy inverter's operation. The more increases for the installed inverters, the less availability loss in the case of inverter partial or catastrophic failures. So, it is required to focus on the failure causes of the central inverter by implementing a technical analysis using the available operational data. The monitored data of the central inverter in the PV power plant is classified into two types. The first type is the continuous time data stored in the memory. It represents the waveforms of inverter outputs like voltage, current, frequency, .... etc. Unfortunately, in case of a catastrophic failure, the central inverter is completely charred, and the continuous time data is lost due to storage memory damage. The second type is the operation data that is recorded by the SCADA system (per one-minute interval). Hereby, the operation data is the sole data in the case of the completely charred inverter. The representation of the operational data in curves indicates symptoms that can be used for the RCA processes. The investigation outcomes include three results. The first result is detecting the signature of the IGBT thermal stress on the voltage balance of the DC link capacitor. The second result is verifying a scenario for the cause of the IGBT failure by implementing a technical mathematical model based on the detected symptoms that denote the fault signature which is considered the thread-tip for detecting the failure cause. The third result is the simulating scenario for the interpretation of a DC link capacitors explosion due to the short circuit fault that occurred due to IGBT failure. The investigation in this paper is performed based on operation data analysis of the PV grid-connected inverter (central type) due to a real incident. The analysis methodology is based on mathematical calculation for the IGBT junction temperature using the measured heatsink temperature. The study concludes that after the IGBT failure occurred, it was a short circuit for a while and closed the terminals of the DC link capacitors. So, the DC link capacitors exploded and produced heavy sparks that led to enough fire to burn the inverter container completely. [ABSTRACT FROM AUTHOR]

Spectroscopic techniques generate one-dimensional spectra with distinct peaks and specific widths in the frequency domain. These features act as unique identities for material characteristics. Deep neural networks (DNNs) has recently been considered a powerful tool for automatically categorizing experimental spectra data by supervised classification to evaluate material characteristics. However, most existing work assumes balanced spectral data among various classes in the training data, contrary to actual experiments, where the spectral data is usually imbalanced. The imbalanced training data deteriorates the supervised classification performance, hindering understanding of the phase behavior, specifically, sol-gel transition (gelation) of soft materials and glycomaterials. To address this issue, this paper applies a novel data augmentation method based on a generative adversarial network (GAN) proposed by the authors in their prior work. To demonstrate the effectiveness of the proposed method, the actual imbalanced spectral data from Pluronic F-127 hydrogel and Alpha-Cyclodextrin hydrogel are used to classify the phases of data. Specifically, our approach improves 8.8%, 6.4%, and 6.2% of the performance of the existing data augmentation methods regarding the classifier's F-score, Precision, and Recall on average, respectively. Specifically, our method consists of three DNNs: the generator, discriminator, and classifier. The method generates samples that are not only authentic but emphasize the differentiation between material characteristics to provide balanced training data, improving the classification results. Based on these validated results, we expect the method's broader applications in addressing imbalanced measurement data across diverse domains in materials science and chemical engineering. [ABSTRACT FROM AUTHOR]

Tabular data analysis is a critical task in various domains, enabling us to uncover valuable insights from structured datasets. While traditional machine learning methods can be used for feature engineering and dimensionality reduction, they often struggle to capture the intricate relationships and dependencies within real-world datasets. In this paper, we present Multi-representation DeepInsight (MRep-DeepInsight), a novel extension of the DeepInsight method designed to enhance the analysis of tabular data. By generating multiple representations of samples using diverse feature extraction techniques, our approach is able to capture a broader range of features and reveal deeper insights. We demonstrate the effectiveness of MRep-DeepInsight on single-cell datasets, Alzheimer's data, and artificial data, showcasing an improved accuracy over the original DeepInsight approach and machine learning methods like random forest, XGBoost, LightGBM, FT-Transformer and L2-regularized logistic regression. Our results highlight the value of incorporating multiple representations for robust and accurate tabular data analysis. By leveraging the power of diverse representations, MRep-DeepInsight offers a promising new avenue for advancing decision-making and scientific discovery across a wide range of fields. [ABSTRACT FROM AUTHOR]

In this paper, we explore the mutual effect of prior background expectations and visibility afforded by the 3D configuration of the physical environment on wayfinding efficiency and strategy in multilevel buildings. We perform new analyses on data from 149 participants who performed six unaided and directed wayfinding tasks in virtual buildings with varying degrees of visibility. Our findings reveal that the interaction between visibility and prior background expectations significantly affects wayfinding efficiency and strategy during between-floor wayfinding tasks. We termed this interaction effect strategic visibility, which emphasizes the importance of the strategic allocation of visibility towards actionable building elements in promoting efficient wayfinding and shaping wayfinding strategy. Our study highlights the significance of strategic visibility in promoting inclusive and accessible built environments for neurodiversity. Finally, we provide an open-source dataset that can be used to develop and test new wayfinding theories and models to advance research in the emerging field of human-building interaction. [ABSTRACT FROM AUTHOR]

The paper presents a novel statistical approach for analyzing the daily coronavirus case and fatality statistics. The survival discretization method was used to generate a two-parameter discrete distribution. The resulting distribution is referred to as the "Discrete Marshall–Olkin Length Biased Exponential (DMOLBE) distribution". Because of the varied forms of its probability mass and failure rate functions, the DMOLBE distribution is adaptable. We calculated the mean and variance, skewness, kurtosis, dispersion index, hazard and survival functions, and second failure rate function for the suggested distribution. The DI index demonstrates that the proposed model can represent both over-dispersed and under-dispersed data sets. We estimated the parameters of the DMOLBE distribution. The behavior of ML estimates is checked via a comprehensive simulation study. The behavior of Bayesian estimates is checked by generating 10,000 iterations of Markov chain Monte Carlo techniques, plotting the trace, and checking the proposed distribution. From simulation studies, it was observed that the bias and mean square error decreased with an increase in sample size. To show the importance and flexibility of DMOLBE distribution using two data sets about deaths due to coronavirus in China and Pakistan are analyzed. The DMOLBE distribution provides a better fit than some important discrete models namely the discrete Burr-XII, discrete Bilal, discrete Burr-Hatke, discrete Rayleigh distribution, and Poisson distributions. We conclude that the new proposed distribution works well in analyzing these data sets. The data sets used in the paper was collected from 2020 year. [ABSTRACT FROM AUTHOR]

Mass spectrometry technology can realize dynamic detection of many complex matrix samples in a simple, rapid, compassionate, precise, and high-throughput manner and has become an indispensable tool in accurate diagnosis. The mass spectrometry data analysis is mainly to analyze all metabolites in the organism quantitatively and to find the relative relationship between metabolites and physiological and pathological changes. A feature construction of mass spectrometry data (MSFS) method is proposed to construct the features of the original mass spectrometry data, so as to reduce the noise in the mass spectrometry data, reduce the redundancy of the original data and improve the information content of the data. Chi-square test is used to select the optimal non-redundant feature subset from high-dimensional features. And the optimal feature subset is visually analyzed and corresponds to the original mass spectrum interval. Training in 10 kinds of supervised learning models, and evaluating the classification effect of the models through various evaluation indexes. Taking two public mass spectrometry datasets as examples, the feasibility of the method proposed in this paper is verified. In the coronary heart disease dataset, during the identification process of mixed batch samples, the classification accuracy on the test set reached 1.000; During the recognition process, the classification accuracy on the test set advanced to 0.979. On the colorectal liver metastases data set, the classification accuracy on the test set reached 1.000. This paper attempts to use a new raw mass spectrometry data preprocessing method to realize the alignment operation of the raw mass spectrometry data, which significantly improves the classification accuracy and provides another new idea for mass spectrometry data analysis. Compared with MetaboAnalyst software and existing experimental results, the method proposed in this paper has obtained better classification results., (© 2023. Springer Nature Limited.)

For most bioinformatics statistical methods, particularly for gene expression data classification, prognosis, and prediction, a complete dataset is required. The gene sample value can be missing due to hardware failure, software failure, or manual mistakes. The missing data in gene expression research dramatically affects the analysis of the collected data. Consequently, this has become a critical problem that requires an efficient imputation algorithm to resolve the issue. This paper proposed a technique considering the local similarity structure that predicts the missing data using clustering and top K nearest neighbor approaches for imputing the missing value. A similarity-based spectral clustering approach is used that is combined with the K-means. The spectral clustering parameters, cluster size, and weighting factors are optimized, and after that, missing values are predicted. For imputing each cluster's missing value, the top K nearest neighbor approach utilizes the concept of weighted distance. The evaluation is carried out on numerous datasets from a variety of biological areas, with experimentally inserted missing values varying from 5 to 25%. Experimental results prove that the proposed imputation technique makes accurate predictions as compared to other imputation procedures. In this paper, for performing the imputation experiments, microarray gene expression datasets consisting of information of different cancers and tumors are considered. The main contribution of this research states that local similarity-based techniques can be used for imputation even when the dataset has varying dimensionality and characteristics. [ABSTRACT FROM AUTHOR]

Rapid and accurate judgment of the rock mass condition is the key to guaranteeing the safety and efficiency of tunnel boring machine (TBM) tunneling. This paper proposes a method for evaluating rock mass parameters based on K-means clustering, grouping tunneling areas according to the values of TBM tunneling parameters. A dataset including rock mass and TBM tunneling data is treated by logistic normalization and principal component analysis (PCA), and large volumes of tunneling data with different features are transformed into appropriate volumes of dimensionless data. K-means clustering is used, samples are grouped according to the values of tunneling data, and the specific ranges as defined by clustering are regarded as the unified evaluated results of each group. Based on the C1 part of the Pearl Delta water resources allocation project, 100 training samples and 30 testing samples were field-collected, and the proposed method was realized by the training samples and verified by the testing samples. The evaluation accuracies of uniaxial compressive strength (UCS), and joint frequency (Jf) were 90%, and 86.7% respectively, demonstrating that the evaluation had acceptable values, and the proposed method was greatly helpful for judging rock conditions. [ABSTRACT FROM AUTHOR]

The analysis of data over space and time is a core part of descriptive epidemiology, but the complexity of spatiotemporal data makes this challenging. There is a need for methods that simplify the exploration of such data for tasks such as surveillance and hypothesis generation. In this paper, we use combined clustering and dimensionality reduction methods (hereafter referred to as 'cluster embedding' methods) to spatially visualize patterns in epidemiological time-series data. We compare several cluster embedding techniques to see which performs best along a variety of internal cluster validation metrics. We find that methods based on k-means clustering generally perform better than self-organizing maps on real world epidemiological data, with some minor exceptions. We also introduce EpiVECS, a tool which allows the user to perform cluster embedding and explore the results using interactive visualization. EpiVECS is available as a privacy preserving, in-browser open source web application at https://episphere.github.io/epivecs. [ABSTRACT FROM AUTHOR]

Pump sizing is the process of dimensional matching of an impeller and stator to provide a satisfactory performance test result and good service life during the operation of progressive cavity pumps. In this process, historical data analysis and dimensional monitoring are done manually, consuming a large number of man-hours and requiring a deep knowledge of progressive cavity pump behavior. This paper proposes the use of graph neural networks in the construction of a prototype to recommend interference during the pump sizing process in a progressive cavity pump. For this, data from different applications is used in addition to individual control spreadsheets to build the database used in the prototype. From the pre-processed data, complex network techniques and the betweenness centrality metric are used to calculate the degree of importance of each order confirmation, as well as to calculate the dimensionality of the rotors. Using the proposed method a mean squared error of 0.28 is obtained for the cases where there are recommendations for order confirmations. Based on the results achieved, it is noticeable that there is a similarity of the dimensions defined by the project engineers during the pump sizing process, and this outcome can be used to validate the new design definitions. [ABSTRACT FROM AUTHOR]

Nowadays, several companies prefer storing their data on multiple data centers with replication for many reasons. The data that spans various data centers ensures the fastest possible response time for customers and workforces who are geographically separated. It also provides protecting the information from the loss in case a single data center experiences a disaster. However, the amount of data is increasing at a rapid pace, which leads to challenges in storage, analysis, and various processing tasks. In this paper, we propose and design a geographically distributed data management framework to manage the massive data stored and distributed among geo-distributed data centers. The goal of the proposed framework is to enable efficient use of the distributed data blocks for various data analysis tasks. The architecture of the proposed framework is composed of a grid of geo-distributed data centers connected to a data controller (DCtrl). The DCtrl is responsible for organizing and managing the block replicas across the geo-distributed data centers. We use the BDMS system as the installed system on the distributed data centers. BDMS stores the big data file as a set of random sample data blocks, each being a random sample of the whole data file. Then, DCtrl distributes these data blocks into multiple data centers with replication. In analyzing a big data file distributed based on the proposed framework, we randomly select a sample of data blocks replicated from other data centers on any data center. We use simulation results to demonstrate the performance of the proposed framework in big data analysis across geo-distributed data centers. [ABSTRACT FROM AUTHOR]

Applications such as disaster management enormously benefit from rapid availability of satellite observations. Traditionally, data analysis is performed on the ground after being transferred—downlinked—to a ground station. Constraints on the downlink capabilities, both in terms of data volume and timing, therefore heavily affect the response delay of any downstream application. In this paper, we introduce RaVÆn, a lightweight, unsupervised approach for change detection in satellite data based on Variational Auto-Encoders (VAEs), with the specific purpose of on-board deployment. RaVÆn pre-processes the sampled data directly on the satellite and flags changed areas to prioritise for downlink, shortening the response time. We verified the efficacy of our system on a dataset—which we release alongside this publication—composed of time series containing a catastrophic event, demonstrating that RaVÆn outperforms pixel-wise baselines. Finally, we tested our approach on resource-limited hardware for assessing computational and memory limitations, simulating deployment on real hardware. [ABSTRACT FROM AUTHOR]

Time series classification is a basic task in the field of streaming data event analysis and data mining. The existing time series classification methods have the problems of low classification accuracy and low efficiency. To solve these problems, this paper proposes a T-CNN time series classification method based on a Gram matrix. Specifically, we perform wavelet threshold denoising on time series to filter normal curve noise, and propose a lossless transformation method based on the Gram matrix, which converts the time series to the time domain image and retains all the information of events. Then, we propose an improved CNN time series classification method, which introduces the Toeplitz convolution kernel matrix into convolution layer calculation. Finally, we introduce a Triplet network to calculate the similarity between similar events and different classes of events, and optimize the squared loss function of CNN. The proposed T-CNN model can accelerate the convergence rate of gradient descent and improve classification accuracy. Experimental results show that, compared with the existing methods, our T-CNN time series classification method has great advantages in efficiency and accuracy. [ABSTRACT FROM AUTHOR]

Anomaly detection is a highly important task in the field of data analysis. Traditional anomaly detection approaches often strongly depend on data size, structure and features, while introducing the idea of ensemble into anomaly detection can greatly improve the generalization ability. Ensemble-based anomaly detection methods still face some challenges, however, such as data imbalance, time and space demand and the selection of base detectors. To this end, we propose a selective ensemble method for anomaly detection based on parallel learning (SEAD-PL). First, a differentiated stratified sampling method is designed to alleviate the problem of data imbalance. Then, a distributed parallel training frame is built to address the problem of excessive time and space consumption for base detector training. Finally, a clustering-based ensemble selection strategy is introduced to balance the accuracy and diversity of base detectors. Experiments are performed on six datasets, which demonstrate that the proposed method has obvious advantages over four selected methods. [ABSTRACT FROM AUTHOR]

This paper proposes a KC Score to measure feature importance in clustering analysis of high-dimensional data. The KC Score evaluates the contribution of features based on the correlation between the original features and the reconstructed features in the low dimensional latent space. A KC Score-based feature selection strategy is further developed for clustering analysis. We investigate the performance of the proposed strategy by conducting a study of four single-cell RNA sequencing (scRNA-seq) datasets. The results show that our strategy effectively selects important features for clustering. In particular, in three datasets, our proposed strategy selected less than 5% of the features and achieved the same or better clustering performance than when using all of the features. [ABSTRACT FROM AUTHOR]

Multi- and hyperspectral endoscopy are possibilities to improve the endoscopic detection of neoplastic lesions in the colon and rectum during colonoscopy. However, most studies in this context are performed on histological samples/biopsies or ex vivo. This leads to the question if previous results can be transferred to an in vivo setting. Therefore, the current study evaluated the usefulness of multispectral endoscopy in identifying neoplastic lesions in the colon. The data set consists of 25 mice with colonic neoplastic lesions and the data analysis is performed by machine learning. Another question addressed was whether adding additional spatial features based on Gauss–Laguerre polynomials leads to an improved detection rate. As a result, detection of neoplastic lesions was achieved with an MCC of 0.47. Therefore, the classification accuracy of multispectral colonoscopy is comparable with hyperspectral colonoscopy in the same spectral range when additional spatial features are used. Moreover, this paper strongly supports the current path towards the application of multi/hyperspectral endoscopy in clinical settings and shows that the challenges from transferring results from ex vivo to in vivo endoscopy can be solved. [ABSTRACT FROM AUTHOR]

Vaccines save millions of lives every year. They are recommended by experts, trusted by the majority of people, and promoted by expensive health campaigns. Even so, people with neutral attitudes are more persuaded by people holding anti-vaccine than pro-vaccine attitudes. Our analysis of vaccine-related attitudes in more than 140 countries makes sense of this paradox by including approaches from social influence. Specifically, we show that neutral people are positioned closer to anti- than to pro-vaccine people in the opinion space, and therefore more persuadable by them. We use dynamic social simulations seeded with vaccine survey data, to show how this effect results in a drift towards anti-vaccine opinions. Linking this analysis to data from two other multi-country datasets, we found that countries in which the pro-vaccine people are less associated to the neutrals (and so less able to influence them) exhibit lower vaccination rates and stronger increase in distrust. We conclude our paper by showing how taking social influence into account in vaccine-related policy-making can possibly reduce waves of distrust towards vaccination. [ABSTRACT FROM AUTHOR]

The 2018–2020 Ebola virus disease epidemic in Democratic Republic of the Congo (DRC) resulted in 3481 cases (probable and confirmed) and 2299 deaths. In this paper, we use a novel statistical method to analyze the individual-level incidence and hospitalization data on DRC Ebola victims. Our analysis suggests that an increase in the rate of quarantine and isolation that has shortened the infectiousness period by approximately one day during the epidemic's third and final wave was likely responsible for the eventual containment of the outbreak. The analysis further reveals that the total effective population size or the average number of individuals at risk for the disease exposure in three epidemic waves over the period of 24 months was around 16,000–a much smaller number than previously estimated and likely an evidence of at least partial protection of the population at risk through ring vaccination and contact tracing as well as adherence to strict quarantine and isolation policies. [ABSTRACT FROM AUTHOR]

Several parameters affect our brain's neuronal system and can be identified by analyzing electroencephalogram (EEG) signals. One of the parameters is alcoholism, which affects the pattern of our EEG signals. By analyzing these EEG signals, one can derive information regarding the alcoholic or normal stage of an individual. Many road accident cases around the world, including drinking and driving scenarios, which result in loss of life, have been reported. Another reason for such incidents is that riders avoid wearing helmets while driving two-wheelers. Many road accident cases involving two-wheelers, including drinking, driving, overspeeding, and nonwearing helmets, have been reported. Therefore, to solve such issues, the present work highlights the features of an intelligent model that can predict the alcoholism level of the subject, wearing of a helmet, vehicle speed, location, etc. The system is designed with the latest technologies and is smart enough to make decisions. The system is based on multilayer perceptron, histogram of oriented gradients (HoG) feature extraction, and random forest to make decisions in real time. The accuracy of the proposed method is approximately 95%, which will reduce the fatality rate due to road accidents. The system is tested under different working environments, i.e., indoor and outdoor, and satisfactory outcomes are observed. [ABSTRACT FROM AUTHOR]

Partial accelerated life tests (PALTs) are employed when the results of accelerated life testing cannot be extended to usage circumstances. This work discusses the challenge of different estimating strategies in constant PALT with complete data. The lifetime distribution of the test item is assumed to follow the power half-logistic distribution. Several classical and Bayesian estimation techniques are presented to estimate the distribution parameters and the acceleration factor of the power half-logistic distribution. These techniques include Anderson–Darling, maximum likelihood, Cramér von-Mises, ordinary least squares, weighted least squares, maximum product of spacing and Bayesian. Additionally, the Bayesian credible intervals and approximate confidence intervals are constructed. A simulation study is provided to compare the outcomes of various estimation methods that have been provided based on mean squared error, absolute average bias, length of intervals, and coverage probabilities. This study shows that the maximum product of spacing estimation is the most effective strategy among the options in most circumstances when adopting the minimum values for MSE and average bias. In the majority of situations, Bayesian method outperforms other methods when taking into account both MSE and average bias values. When comparing approximation confidence intervals to Bayesian credible intervals, the latter have a higher coverage probability and smaller average length. Two authentic data sets are examined for illustrative purposes. Examining the two real data sets shows that the value methods are workable and applicable to certain engineering-related problems. [ABSTRACT FROM AUTHOR]

This study examines the spatiotemporal variability of drought and associated physical processes over the Arabian Peninsula (AP). For this purpose, we computed the standardized precipitation evapotranspiration index (SPEI) for the period 1951–2020 using the Climate Research Unit and fifth generation ECMWF atmospheric reanalysis datasets. By applying rotated empirical orthogonal function analysis on the SPEI data, we identified four homogeneous and coherent drought regions. The droughts in the northern regions follow a relatively similar temporal evolution as compared to those in the southern region. All four sub-regions of the AP exhibit a significant drying trend (p < 0.01) with an abrupt acceleration in drought frequency and intensity over the last two decades. The increase in droughts is associated with the reduction of synoptic activity and an increase in the high pressure over the AP. Seasonally, potential evapotranspiration is the dominant driver of summer droughts in the AP, whereas both precipitation and temperature are important for driving winter droughts. The summer droughts, mainly over the northern AP, are due to the occurrence of an anomalous equivalent barotropic high associated with anomalous dry and hot conditions. However, anomalous dry conditions in winter are a result of an anomalous paucity of winter storms caused by the weakening of the sub-tropical jets. [ABSTRACT FROM AUTHOR]

With the development of wireless communication technology, Ultra-Wideband (UWB) has become an important solution for indoor positioning. In complex indoor environments, the influence of non-line-of-sight (NLOS) factors leads to increased positioning errors. To improve the positioning accuracy, fuzzy iterative self-organizing data analysis clustering algorithm (ISODATA) is introduced to process a large amount of UWB data to reduce the influence of NLOS factors, and to stabilize positioning error within 2 cm, enhances the accuracy of the positioning system. To further improve the running efficiency of the algorithm, FPGA is used to accelerate the key computational part of the algorithm, compared with running on the MATLAB platform, which improves the speed about 100 times, enhances the algorithm's computational speed dramatically. [ABSTRACT FROM AUTHOR]

The primary aim of this investigation was to leverage radiomics features derived from contrast-enhanced abdominal computed tomography (CT) scans to devise a predictive model to discern the benign and malignant nature of intraductal papillary mucinous neoplasms (IPMNs). Radiomic signatures were meticulously crafted to delineate benign from malignant IPMNs by extracting pertinent features from contrast-enhanced CT images within a designated training cohort (n = 84). Subsequent validation was conducted with data from an independent test cohort (n = 37). The discriminative ability of the model was quantitatively evaluated through receiver operating characteristic (ROC) curve analysis, with the integration of carefully selected clinical features to improve the comparative analysis. Arterial-phase images were utilized to construct a model comprising 8 features for distinguishing between benign and malignant cases. The model achieved an accuracy of 0.891 [95% confidence interval (95% CI), 0.816–0.996] in the cross-validation set and 0.553 (95% CI 0.360–0.745) in the test set. Conversely, employing 9 features from the venous-phase resulted in a model with a cross-validation accuracy of 0.862 (95%CI 0.777–0.946) and a test set accuracy of 0.801 (95% CI 0.653–0.950).Integrating the identified clinical features with imaging features yielded a model with a cross-validation accuracy of 0.934 (95% CI 0.879–0.990) and a test set accuracy of 0.904 (95% CI 0.808–0.999), thereby further improving its discriminatory ability. Our findings distinctly illustrate that venous-phase radiomics features eclipse arterial-phase radiomic features in terms of predictive accuracy regarding the nature of IPMNs. Furthermore, the synthesis and meticulous screening of clinical features with radiomic data significantly increased the diagnostic efficacy of our model, underscoring the pivotal importance of a comprehensive and integrated approach for accurate risk stratification in IPMN management. [ABSTRACT FROM AUTHOR]

Access to individual-level health data is essential for gaining new insights and advancing science. In particular, modern methods based on artificial intelligence rely on the availability of and access to large datasets. In the health sector, access to individual-level data is often challenging due to privacy concerns. A promising alternative is the generation of fully synthetic data, i.e., data generated through a randomised process that have similar statistical properties as the original data, but do not have a one-to-one correspondence with the original individual-level records. In this study, we use a state-of-the-art synthetic data generation method and perform in-depth quality analyses of the generated data for a specific use case in the field of nutrition. We demonstrate the need for careful analyses of synthetic data that go beyond descriptive statistics and provide valuable insights into how to realise the full potential of synthetic datasets. By extending the methods, but also by thoroughly analysing the effects of sampling from a trained model, we are able to largely reproduce significant real-world analysis results in the chosen use case. [ABSTRACT FROM AUTHOR]

People living with HIV (PLHIV) report lower health-related quality-of-life (HRQoL) than HIV-negative people. HIV stigma may contribute to this. We explored the association between HIV stigma and HRQoL among PLHIV. We used cross-sectional data from 3991 randomly selected PLHIV who were surveyed in 2017–2018 for HPTN 071 (PopART), a cluster randomised trial in Zambia and South Africa. Participants were 18–44 years, had laboratory-confirmed HIV infection, and knew their status. HRQoL was measured using the EuroQol-5-dimensions-5-levels (EQ-5D-5L) questionnaire. Stigma outcomes included: internalised stigma, stigma experienced in the community, and stigma experienced in healthcare settings. Associations were examined using logistic regression. Participants who had experienced community stigma (n = 693/3991) had higher odds of reporting problems in at least one HRQoL domain, compared to those who had not (adjusted odds ratio, aOR: 1.51, 95% confidence interval, 95% Cl: 1.16–1.98, p = 0.002). Having experienced internalised stigma was also associated with reporting problems in at least one HRQoL domain (n = 552/3991, aOR: 1.98, 95% CI: 1.54–2.54, p < 0.001). However, having experienced stigma in a healthcare setting was less common (n = 158/3991) and not associated with HRQoL (aOR: 1.04, 95% CI: 0.68–1.58, p = 0.850). A stronger focus on interventions for internalised stigma and stigma experienced in the community is required. [ABSTRACT FROM AUTHOR]

Metal–organic frameworks (MOFs), self-assembled porous materials synthesized from metal ions and organic ligands, are promising candidates for the direct capture of CO2 from the atmosphere. In this work, we developed a regression model to predict the optimal component of the MOF that governs the amount of CO2 adsorption per volume based on experimentally observed adsorption and structure data combined with MOF adsorption sites. The structural descriptors were generated by topological data analysis with persistence diagrams, an advanced mathematical method for quantifying the rings and cavities within the MOF. This enables us to analyze direct effects and significance of the geometric structure of the MOF on the efficiency of CO2 adsorption in a novel way. The proposed approach is proved to be highly correlated with experimental data and thus offers an effective screening tool for MOFs with optimized structures. [ABSTRACT FROM AUTHOR]

In the modern day, multimedia and digital resources play a crucial role in demystifying complex topics and improving communication. Additionally, images, videos, and documents speed data administration, fostering both individual and organizational efficiency. Healthcare providers use tools like X-rays, MRIs, and CT scans to improve diagnostic and therapeutic capacities, highlighting the importance of these tools in contemporary communication, data processing, and healthcare. Protecting medical data becomes essential for maintaining patient confidentiality and service dependability in a time when digital assets are crucial to the healthcare industry. In order to overcome this issue, this study analyses the DWT-HD-SVD algorithm-based invisible watermarking in medical data. The main goal is to verify medical data by looking at a DWT-based hybrid technique used on X-ray images with various watermark sizes (256*256, 128*128, 64*64). The algorithm's imperceptibility and robustness are examined using metrics like Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) and are analyzed using Normalized Connection (NC), Bit Error Rate (BER), and Bit Error Rate (BCR) in order to evaluate its resistance to various attacks. The results show that the method works better with smaller watermark sizes than it does with larger ones. [ABSTRACT FROM AUTHOR]

The watershed system has a complex game relationship between the benign operation and coordinated development of various elements of flood-sediment transportation, eco-environment, and socio-economy (FES). With the increasing breadth, depth, and intensity of human activities in watersheds, it is urgent to coordinate the FES. The relationship of water–sediment in the Yellow River Basin (YRB) is complex, with a prominent contradiction in water supply and a fragile ecosystem. This research tries to build a comprehensive evaluation model for FES and explore the complex interaction between FES in the YRB from 2000 to 2020. The results demonstrated that (1) the comprehensive flood-sediment transportation index (CFTI) and comprehensive eco-environment index (CEI) presented fluctuating growth. In contrast, the comprehensive socio-economy index (CSI) revealed a linear growth trend. The CFTI of Sanmenxia, CEI of Toudaokuan, and CSI of Ningxia had the highest growth rates, with 36.03%, 6.48%, and 107.5%, respectively. (2) FES's positive and negative effects were alternating, with heterogeneity in both time and space. (3) The coupling coordination degree (CCD) in the YRB indicated an increasing trend, ranging from 0.53 to 0.87, from reluctantly coordinated development to good coordinated development. The lagging subsystem was CFTI (2000–2001 and 2008–2020) and CSI (2002–2007), and the CEI was not lagging. (4) Exploratory Spatial Data Analysis (ESDA) demonstrated significant differences in the CCD of the YRB, and areas with similar CCD within the basin tend to be centrally distributed in space. At the same time, there was negative spatial autocorrelation in coordination. The results provide a scientific theoretical and methodological framework for strategic research on the YRB system's governance, protection, and management. [ABSTRACT FROM AUTHOR]

We analyzed parentage data collected over a ten-year period in a Zimbabwean DNA testing laboratory. Parentage case types, prevalence, exclusion data, mutations rates and observed genotyping irregularities were analyzed. We report analysis results from 1303 cases. DNA extraction and STR typing was conducted using standard commercial kits. Paternity was the most requested test (87.37%) followed by the indirect biological kinship tests (7.01%). Duo paternity (motherless) was the most common paternity test for both regular and court cases. We observed 367 paternity exclusions from 1135 cases, giving an overall paternity exclusion rate of 32.33%. Maternity had the lowest exclusion rate (8.33%), with criminal cases having the highest paternity (61.11%) and maternity (33.33%) exclusion rates. The number of mismatched STR loci ranged from 2–12 for duo cases and 4–18 for the trio cases. FGA, D2S1338, D18S51 and D2S441 were the most informative markers for exclusion. We detected 30 mutations out of 837 cases with an estimated paternal and maternal mutation rate of 0.0021 and 0.0011 respectively. Triallelic patterns were only observed at the TPOX locus with allele 10 and 11 being the extra alleles transmitted. Our report provides forensic parameters which can improve parentage and forensic analysis in Zimbabwe. [ABSTRACT FROM AUTHOR]

The tongue surface houses a range of papillae that are integral to the mechanics and chemistry of taste and textural sensation. Although gustatory function of papillae is well investigated, the uniqueness of papillae within and across individuals remains elusive. Here, we present the first machine learning framework on 3D microscopic scans of human papillae ( n = 2092 ), uncovering the uniqueness of geometric and topological features of papillae. The finer differences in shapes of papillae are investigated computationally based on a number of features derived from discrete differential geometry and computational topology. Interpretable machine learning techniques show that persistent homology features of the papillae shape are the most effective in predicting the biological variables. Models trained on these features with small volumes of data samples predict the type of papillae with an accuracy of 85%. The papillae type classification models can map the spatial arrangement of filiform and fungiform papillae on a surface. Remarkably, the papillae are found to be distinctive across individuals and an individual can be identified with an accuracy of 48% among the 15 participants from a single papillae. Collectively, this is the first evidence demonstrating that tongue papillae can serve as a unique identifier, and inspires a new research direction for food preferences and oral diagnostics. [ABSTRACT FROM AUTHOR]

Apple cankers are extremely destructive diseases threatening the global apple industry through direct and indirect losses. The population structure of the pathogens is of paramount significance for the development of efficient management strategies. Therefore, phenotypic, pathogenic, and genetic diversity of Diplodia seriata causing black rot canker of apple was investigated in this study. All the isolates were included for investigating the in vitro mycelial growth, conidial dimensions, and pathogenic variability on two-year-old potted apple seedlings. The ISSR approach was used to investigate the molecular diversity of D. seriata. Mycelial growth rates were found to vary significantly amongst the isolates; however, there were no major variations seen between the different geographical groupings of isolates. Pathogenicity tests revealed variations in the size of cankers among the isolates indicating the presence of virulence variability. The isolates were segregated into three virulence groups based on canker length. The Bayesian analyses of ISSR data divided the isolates into two genetic clusters. The genetic clustering of the isolates revealed no relationship with geographical origin of the isolates. Furthermore, no direct relationship of genetic clustering was observed with morphological or pathogenic variability. The ISSR primers revealed very high level of variability in D. seriata; however, no distinct populations of the pathogen existed which is an indication of high level of gene flow between the diverse geographical populations. According to our knowledge, this is the first thorough investigation on the diversity of D. seriata associated with apple black rot canker in India. [ABSTRACT FROM AUTHOR]

An ever-growing portion of the economy is dedicated to the field of education, intensifying the urgency of identifying strategies to secure the sector's enduring prosperity and elevate educational standards universally. This study introduces a model for enhancing games and optimizing data analysis within the context of early childhood education (ECE) majors, hinging on deep learning (DL). This approach aims to enhance the quality of instruction provided to ECE majors and refine the effectiveness of their professional pursuits. This study commences by examining the incorporation of DL technologies within the domain of ECE and delving into their fundamental underpinnings. Subsequently, it expounds upon the design philosophy underpinning ECE games operating within the framework of DL. Finally, it outlines the game improvement and data analysis (GIADA) model tailored to ECE majors. This model is constructed upon DL technology and further refined through the integration of convolutional neural networks (CNN). Empirical findings corroborate that the DL-CNN GIADA model achieves data analysis accuracy ranging from 83 to 93% across four datasets, underscoring the pronounced optimization prowess bestowed by CNN within the DL-based GIADA model. This study stands as an invaluable reference for the application and evolution of artificial intelligence technology within the realm of education, thereby contributing substantively to the broader landscape of educational advancement. [ABSTRACT FROM AUTHOR]

The evaluation index system is constructed based on the connotation and characteristics of health tourism. Using the entropy method, Thiel index, exploratory spatial data analysis method, spatial Markov chain and spatial econometric model, research is carried out around the development index, difference status, spatial-temporal pattern, dynamic evolution and influencing factors of health tourism. The following results were drawn: (1) The development index of health tourism in China is low, but the development speed is fast. The inter-regional development index shows an eastern China > central China > western China pattern, and the development speed exhibits a western China > central China > eastern China situation. (2) In the overall difference in China's health tourism development, the intra-regional difference is consistently higher than the inter-regional difference. Among the three major regions, the overall difference between eastern China and western China is always higher than that of central China. (3) The development of health tourism in China is positively correlated in the global space, with some local spatial clustering. (4) The dynamic evolution of health tourism development in China shows part of the "Matthew effect" characteristics, with an obvious spatial spillover effect. (5) Various influencing factors produced widely varying direct, indirect and total effects on health tourism development in China, eastern China, central China and western China. Finally, based on the results of the above empirical analysis, policy recommendations to promote the development of health tourism in China are proposed. [ABSTRACT FROM AUTHOR]

Continuous glucose monitoring systems (CGM) are a very useful tool to understand the behaviour of glucose in different situations and populations. Despite the widespread use of CGM systems in both clinical practice and research, our understanding of the reproducibility of CGM data remains limited. The present work examines the reproducibility of the results provided by a CGM system in a random sample of a free-living adult population, from a functional data analysis approach. Functional intraclass correlation coefficients (ICCs) and their 95% confidence intervals (CI) were calculated to assess the reproducibility of CGM results in 581 individuals. 62% were females 581 participants (62% women) mean age 48 years (range 18–87) were included, 12% had previously been diagnosed with diabetes. The inter-day reproducibility of the CGM results was greater for subjects with diabetes (ICC 0.46 [CI 0.39–0.55]) than for normoglycaemic subjects (ICC 0.30 [CI 0.27–0.33]); the value for prediabetic subjects was intermediate (ICC 0.37 [CI 0.31–0.42]). For normoglycaemic subjects, inter-day reproducibility was poorer among the younger (ICC 0.26 [CI 0.21–0.30]) than the older subjects (ICC 0.39 [CI 0.32–0.45]). Inter-day reproducibility was poorest among normoglycaemic subjects, especially younger normoglycaemic subjects, suggesting the need to monitor some patient groups more often than others. [ABSTRACT FROM AUTHOR]

We propose a general method for combining multiple models to predict tissue microstructure, with an exemplar using in vivo diffusion-relaxation MRI data. The proposed method obviates the need to select a single 'optimum' structure model for data analysis in heterogeneous tissues where the best model varies according to local environment. We break signal interpretation into a three-stage sequence: (1) application of multiple semi-phenomenological models to predict the physical properties of tissue water pools contributing to the observed signal; (2) from each Stage-1 semi-phenomenological model, application of a tissue microstructure model to predict the relative volumes of tissue structure components that make up each water pool; and (3) aggregation of the predictions of tissue structure, with weightings based on model likelihood and fractional volumes of the water pools from Stage-1. The multiple model approach is expected to reduce prediction variance in tissue regions where a complex model is overparameterised, and bias where a model is underparameterised. The separation of signal characterisation (Stage-1) from biological assignment (Stage-2) enables alternative biological interpretations of the observed physical properties of the system, by application of different tissue structure models. The proposed method is exemplified with human prostate diffusion-relaxation MRI data, but has potential application to a wide range of analyses where a single model may not be optimal throughout the sampled domain. [ABSTRACT FROM AUTHOR]

One of the most elusive challenges within the area of topological data analysis is understanding the distribution of persistence diagrams arising from data. Despite much effort and its many successful applications, this is largely an open problem. We present a surprising discovery: normalized properly, persistence diagrams arising from random point-clouds obey a universal probability law. Our statements are based on extensive experimentation on both simulated and real data, covering point-clouds with vastly different geometry, topology, and probability distributions. Our results also include an explicit well-known distribution as a candidate for the universal law. We demonstrate the power of these new discoveries by proposing a new hypothesis testing framework for computing significance values for individual topological features within persistence diagrams, providing a new quantitative way to assess the significance of structure in data. [ABSTRACT FROM AUTHOR]

With the growing complexity of single-cell and spatial genomics data, there is an increasing importance of unbiased and efficient exploratory data analysis tools. One common exploratory data analysis step is the prediction of genes with different levels of activity in a subset of cells or locations inside a tissue. We previously developed singleCellHaystack, a method for predicting differentially expressed genes from single-cell transcriptome data, without relying on comparisons between clusters of cells. Here we present an update to singleCellHaystack, which is now a universally applicable method for predicting differentially active features: (1) singleCellHaystack now accepts continuous features that can be RNA or protein expression, chromatin accessibility or module scores from single-cell, spatial and even bulk genomics data, and (2) it can handle 1D trajectories, 2-3D spatial coordinates, as well as higher-dimensional latent spaces as input coordinates. Performance has been drastically improved, with up to ten times reduction in computational time and scalability to millions of cells, making singleCellHaystack a suitable tool for exploratory analysis of atlas level datasets. singleCellHaystack is available as packages in both R and Python. [ABSTRACT FROM AUTHOR]

The polycystic ovarian syndrome (PCOS) is closely associated with enhanced apoptosis of granulosa cells, which have a vital role in maturation of oocytes. p53 plays a critical role in the regulation of apoptosis and cell cycle arrest, metabolism and insulin resistance. The aim of this study was to investigate the impact of p53 pathway in enhancing apoptosis and abnormal function of granulosa cells. In this study, microarray analysis and RNA sequencing were downloaded from the GEO and used as datasets. Principal Component Analysis (PCA) and online SSizer tool were applied to evaluate the experiment quality control and sample sufficiency, respectively. Bioinformatics' analyses were performed on the selected datasets, and validated by qRT-PCR and western blot analyses. Three datasets out of five ones were chosen for re-analyzing based on the PCA outcomes. 21 deregulated genes were identified via filters including p < 0.05 and |log2FC|≥ 1. Functional enrichment analysis confirmed the relevance of cell cycle regulation and apoptosis as common biological hallmarks in PCOS. Results have shown differentially expressed p53 target genes involved in apoptosis (BAX, FAS, PMAIP1, and CASP8), cell cycle (Cyclins, Cyclin dependent kinases), glucose metabolism and insulin resistance (THBS1), and p53 regulation (MDM2). Subsequently, the relative mRNA expression of FAS, PMAIP1 and MDM2 genes, and protein levels of p53 and MDM2 were confirmed using granulosa cells collected from 20 PCOS women and 18 control individuals by qRT-PCR and western blot, respectively. Results of this study represent the possible role of p53 pathway in pathogenesis of PCOS particularly, through the enhancement of apoptosis in granulosa cells. [ABSTRACT FROM AUTHOR]

Diabetes is a heterogenous, multimorbid disorder with a large variation in manifestations, trajectories, and outcomes. The aim of this study is to validate a novel machine learning method for the phenotyping of diabetes in the context of comorbidities. Data from 9967 multimorbid patients with a new diagnosis of diabetes were extracted from Clinical Practice Research Datalink. First, using BEHRT (a transformer-based deep learning architecture), the embeddings corresponding to diabetes were learned. Next, topological data analysis (TDA) was carried out to test how different areas in high-dimensional manifold correspond to different risk profiles. The following endpoints were considered when profiling risk trajectories: major adverse cardiovascular events (MACE), coronary artery disease (CAD), stroke (CVA), heart failure (HF), renal failure (RF), diabetic neuropathy, peripheral arterial disease, reduced visual acuity and all-cause mortality. Kaplan Meier curves were plotted for each derived phenotype. Finally, we tested the performance of an established risk prediction model (QRISK) by adding TDA-derived features. We identified four subgroups of patients with diabetes and divergent comorbidity patterns differing in their risk of future cardiovascular, renal, and other microvascular outcomes. Phenotype 1 (young with chronic inflammatory conditions) and phenotype 2 (young with CAD) included relatively younger patients with diabetes compared to phenotypes 3 (older with hypertension and renal disease) and 4 (older with previous CVA), and those subgroups had a higher frequency of pre-existing cardio-renal diseases. Within ten years of follow-up, 2592 patients (26%) experienced MACE, 2515 patients (25%) died, and 2020 patients (20%) suffered RF. QRISK3 model's AUC was augmented from 67.26% (CI 67.25–67.28%) to 67.67% (CI 67.66–67.69%) by adding specific TDA-derived phenotype and the distances to both extremities of the TDA graph improving its performance in the prediction of CV outcomes. We confirmed the importance of accounting for multimorbidity when risk stratifying heterogenous cohort of patients with new diagnosis of diabetes. Our unsupervised machine learning method improved the prediction of clinical outcomes. [ABSTRACT FROM AUTHOR]

We consider the analysis of temporal data arising from online interactive social experiments, which is complicated by the fact that classical independence assumptions about the observations are not satisfied. Therefore, we propose an approach that compares the output of a fitted (linear) model from the observed interaction data to that generated by an assumed agent-based null model. This allows us to discover, for example, the extent to which the structure of social interactions differs from that of random interactions. Moreover, we provide network visualisations that identify the extent of ingroup favouritism and reciprocity as well as particular individuals whose behaviour differs markedly from the norm. We specifically consider experimental data collected via the novel Virtual Interaction APPLication (VIAPPL). We find that ingroup favouritism and reciprocity are present in social interactions observed on this platform, and that these behaviours strengthen over time. Note that, while our proposed methodology was developed with VIAPPL in mind, its potential usage extends to any type of social interaction data. [ABSTRACT FROM AUTHOR]

The DAMA/LIBRA collaboration has reported the observation of an annual modulation in the event rate that has been attributed to dark matter interactions over the last two decades. However, even though tremendous efforts to detect similar dark matter interactions were pursued, no definitive evidence has been observed to corroborate the DAMA/LIBRA signal. Many studies assuming various dark matter models have attempted to reconcile DAMA/LIBRA's modulation signals and null results from other experiments, however no clear conclusion can be drawn. Apart from the dark matter hypothesis, several studies have examined the possibility that the modulation is induced by variations in detector's environment or their specific analysis methods. In particular, a recent study presents a possible cause of the annual modulation from an analysis method adopted by the DAMA/LIBRA experiment in which the observed annual modulation could be reproduced by a slowly varying time-dependent background. Here, we study the COSINE-100 data using an analysis method similar to the one adopted by the DAMA/LIBRA experiment and observe a significant annual modulation, however the modulation phase is almost opposite to that of the DAMA/LIBRA data. Assuming the same background composition for COSINE-100 and DAMA/LIBRA, simulated experiments for the DAMA/LIBRA without dark matter signals also provide significant annual modulation with an amplitude similar to DAMA/LIBRA with opposite phase. Even though this observation does not directly explain the DAMA/LIBRA results directly, this interesting phenomenon motivates more profound studies of the time-dependent DAMA/LIBRA background data. [ABSTRACT FROM AUTHOR]

Overly restrictive eligibility criteria for clinical trials may limit the generalizability of the trial results to their target real-world patient populations. We developed a novel machine learning approach using large collections of real-world data (RWD) to better inform clinical trial eligibility criteria design. We extracted patients' clinical events from electronic health records (EHRs), which include demographics, diagnoses, and drugs, and assumed certain compositions of these clinical events within an individual's EHRs can determine the subphenotypes—homogeneous clusters of patients, where patients within each subgroup share similar clinical characteristics. We introduced an outcome-guided probabilistic model to identify those subphenotypes, such that the patients within the same subgroup not only share similar clinical characteristics but also at similar risk levels of encountering severe adverse events (SAEs). We evaluated our algorithm on two previously conducted clinical trials with EHRs from the OneFlorida+ Clinical Research Consortium. Our model can clearly identify the patient subgroups who are more likely to suffer or not suffer from SAEs as subphenotypes in a transparent and interpretable way. Our approach identified a set of clinical topics and derived novel patient representations based on them. Each clinical topic represents a certain clinical event composition pattern learned from the patient EHRs. Tested on both trials, patient subgroup (#SAE=0) and patient subgroup (#SAE>0) can be well-separated by k-means clustering using the inferred topics. The inferred topics characterized as likely to align with the patient subgroup (#SAE>0) revealed meaningful combinations of clinical features and can provide data-driven recommendations for refining the exclusion criteria of clinical trials. The proposed supervised topic modeling approach can infer the clinical topics from the subphenotypes with or without SAEs. The potential rules for describing the patient subgroups with SAEs can be further derived to inform the design of clinical trial eligibility criteria. [ABSTRACT FROM AUTHOR]

The current article reports data from three Polish samples to examine the Relationship Assessment Scale (RAS) with respect to its unidimensionality, invariance across countries, gender, formal and informal relationships, degree of precision (or information) across latent levels of relationship satisfaction, and the functioning of individual items. The analyses of the data from the reference sample (n = 733) confirmed a clear 1-factor structure of the RAS-PL and good internal consistency. Configural, metric, and scalar invariance for countries (Poland, Hungary, USA), gender (women and men) and relationship types (formal and informal relationships) were achieved. Item Response Theory Analysis (IRT) suggested that the RAS-PL assesses relationship satisfaction most reliably at low to average levels. Analyses of the data from validation samples (n = 203 and n = 209) confirmed the convergent and divergent validity by weak, medium, and large correlations of the RAS-PL with measures of other theoretically related constructs. Concurrent criterion validity was demonstrated by a strong positive correlation between the RAS-PL and the intent to continue the current relationship. This investigation provides considerable psychometric information about the items and scale of the RAS-PL. [ABSTRACT FROM AUTHOR]

Over time, artworks often sustain paint layer separation and air gaps within their internal structure due to storage conditions and past restoration efforts. Because of this, paint layer consolidation interventions are an essential activity for art conservators. However, it is difficult to determine the exact location and the extent of layer separation on a piece of art in a non-invasive way, and even more difficult to evaluate the success of a consolidation intervention. In this work, a fifteenth-century wood panel painting was analyzed using terahertz time-domain imaging before and after it was consolidated. Using the terahertz data, it was possible to determine the areas on the artwork in need of consolidation and aid the intervention. The analysis of the after data allowed for the control and determination of the success of the consolidation effort in a non-destructive manner. [ABSTRACT FROM AUTHOR]

Machine Learning has become more important for materials engineering in the last decade. Globally, automated machine learning (AutoML) is growing in popularity with the increasing demand for data analysis solutions. Yet, it is not frequently used for small tabular data. Comparisons and benchmarks already exist to assess the qualities of AutoML tools in general, but none of them elaborates on the surrounding conditions of materials engineers working with experimental data: small datasets with less than 1000 samples. This benchmark addresses these conditions and draws special attention to the overall competitiveness with manual data analysis. Four representative AutoML frameworks are used to evaluate twelve domain-specific datasets to provide orientation on the promises of AutoML in the field of materials engineering. Performance, robustness and usability are discussed in particular. The results lead to two main conclusions: First, AutoML is highly competitive with manual model optimization, even with little training time. Second, the data sampling for train and test data is of crucial importance for reliable results. [ABSTRACT FROM AUTHOR]

Ongoing resurgence affects Campi Flegrei caldera (Italy) via bradyseism, i.e. a series of ground deformation episodes accompanied by increases in shallow seismicity. In this study, we perform a mathematical analysis of the GPS and seismic data in the instrumental catalogs from 2000 to 2020, and a comparison of them to the preceding data from 1983 to 1999. We clearly identify and characterize two overlying trends, i.e. a decennial-like acceleration and cyclic oscillations with various periods. In particular, we show that all the signals have been accelerating since 2005, and 90–97% of their increase has occurred since 2011, 40–80% since 2018. Nevertheless, the seismic and ground deformation signals evolved differently—the seismic count increased faster than the GPS data since 2011, and even more so since 2015, growing faster than an exponential function The ground deformation has a linearized rate slope, i.e. acceleration, of 0.6 cm/yr2 and 0.3 cm/yr2 from 2000 to 2020, respectively for the vertical (RITE GPS) and the horizontal (ACAE GPS) components. In addition, all annual rates show alternating speed-ups and slow-downs, consistent between the signals. We find seven major rate maxima since 2000, one every 2.8–3.5 years, with secondary maxima at fractions of the intervals. A cycle with longer period of 6.5–9 years is also identified. Finally, we apply the probabilistic failure forecast method, a nonlinear regression that calculates the theoretical time limit of the signals going to infinity (interpreted here as a critical state potentially reached by the volcano), conditional on the continuation of the observed nonlinear accelerations. Since 2000, we perform a retrospective analysis of the temporal evolution of these forecasts which highlight the periods of more intense acceleration. The failure forecast method applied on the seismic count from 2001 to 2020 produces upper time limits of [0, 3, 11] years (corresponding to the 5th, 50th and 95th percentiles, respectively), significantly shorter than those based on the GPS data, e.g. [0, 6, 21] years. Such estimates, only valid under the model assumption of continuation of the ongoing decennial-like acceleration, warn to keep the guard up on the future evolution of Campi Flegrei caldera. [ABSTRACT FROM AUTHOR]

The Red Sea is a modern analogue for studying continental break-up. Particularly, the Red Sea shows along-strike variability in the architecture, magmatism and associated style of rifting. In order to study these variabilities, continuous geophysical data that cover the entire length of the basin is desired. Our study aims to produce a continuous, reliable and robust magnetic anomaly map for the Red Sea. We present a new magnetic anomaly map for the Red Sea, derived from re-processing of shipborne data, merged and conformed to a recent satellite model, LCS-1. The new magnetic map reveals prominent patterns of magnetic anomalies in sub-perpendicular directions to the Red Sea, with a northward increase in obliquity. We provide further analysis for the magnetic data and associate sets of magnetic trends with transtensional basement structures. Directional analysis suggests a gradual increase in shear component along the Red Sea. The magnetic trends are coaxial with independent indicators of finite and instantaneous strains, and thus implies that these structures and their variability are related to the kinematic framework of the rift. We discuss the consequences of rifting close to the Euler pole, i.e. rotational rifting, and argue that both passive and active forces can explain an increased along-strike transtension, and accordingly the associated variability along the Red Sea. [ABSTRACT FROM AUTHOR]

Data analysis has increasingly relied on machine learning in recent years. Since machines implement mathematical algorithms without knowing the physical nature of the problem, they may be accurate but lack the flexibility to move across different domains. This manuscript presents a machine-educating approach where a machine is equipped with a physical model, universal building blocks, and an unlabeled dataset from which it derives its decision criteria. Here, the concept of machine education is deployed to identify thin layers of organic materials using hyperspectral imaging (HSI). The measured spectra formed a nonlinear mixture of the unknown background materials and the target material spectra. The machine was educated to resolve this nonlinear mixing and identify the spectral signature of the target materials. The inputs for educating and testing the machine were a nonlinear mixing model, the spectra of the pure target materials (which are problem invariant), and the unlabeled HSI data. The educated machine is accurate, and its generalization capabilities outperform classical machines. When using the educated machine, the number of falsely identified samples is ~ 100 times lower than the classical machine. The probability for detection with the educated machine is 96% compared to 90% with the classical machine. [ABSTRACT FROM AUTHOR]

Human temporal bone specimens are used in experiments measuring the sound transfer of the middle ear, which is the standard method used in the development of active and passive middle ear implants. Statistical analyses of these experiments usually require that the TB samples are representative of the population of non-pathological middle ears. Specifically, this means that the specimens must be mechanically well-characterized. We present an in-depth statistical analysis of 478 data sets of middle ear transfer functions (METFs) from different laboratories. The data sets are preprocessed and various contributions to the variance of the data are evaluated. We then derive a statistical range as a reference against which individual METF measurements may be validated. The range is calculated as the two-sided 95% tolerance interval at audiological frequencies. In addition, the mean and 95% confidence interval of the mean are given as references for assessing the validity of a sample group. Finally, we provide a suggested procedure for measuring METFs using the methods described herein. [ABSTRACT FROM AUTHOR]

To improve the performance of data-driven reaction prediction models, we propose an intelligent strategy for predicting reaction products using available data and increasing the sample size using fake data augmentation. In this research, fake data sets were created and augmented with raw data for constructing virtual training models. Fake reaction datasets were created by replacing some functional groups, i.e., in the data analysis strategy, the fake data as compounds with modified functional groups to increase the amount of data for reaction prediction. This approach was tested on five different reactions, and the results show improvements over other relevant techniques with increased model predictivity. Furthermore, we evaluated this method in different models, confirming the generality of virtual data augmentation. In summary, virtual data augmentation can be used as an effective measure to solve the problem of insufficient data and significantly improve the performance of reaction prediction. [ABSTRACT FROM AUTHOR]