Selected Data Sets Research Articles

Contrastive Graph Representations for Logical Formulas Embedding

Currently, the non-transparent computing process of deep learning has become a significant reason hindering its further development. The Neural-Symbolic (NS) system formed by integrating logic rules into neural networks has attracted increasing attention owing to its direct interpretability. Embedding symbolic logical formulas into a low-dimensional continuous space provides an effective way for the NS system. However, current studies are all constrained by the modeling ability for its syntactic structure and fail to preserve the intrinsic semantics in embeddings, which causes poor performance on downstream reasoning tasks. To this end, this paper proposes a novel method of <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Con</b> trastive <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</b> raph <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</b> epresentations (ConGR) for logical formulas embedding. First, to improve the modeling ability for the syntactic structure, ConGR introduces a densely connected graph convolutional network (GCN) with an attention mechanism to process syntax parsing graphs of formulas. In this way, discriminative local and global embeddings of formulas are obtained at the syntax level. Second, the contrastive instances (positive or negative) for each anchor formula are generated by the transformation under the guidance of logical properties. To preserve semantic information, two types of contrast, global-local and global-global, are carried out to refine formula embeddings. Extensive experiments demonstrate that ConGR obtains superior performance against state-of-the-art baselines on entailment checking and premise selection datasets.

Transformer for Skeleton-based action recognition: A review of recent advances

Skeleton-based action recognition has rapidly become one of the most popular and essential research topics in computer vision. The task is to analyze the characteristics of human joints and accurately classify their behaviors through deep learning technology. Skeleton provides numerous unique advantages over other data modalities, such as robustness, compactness, noise immunity, etc. In particular, the skeleton modality is extremely lightweight, which is especially beneficial for deep learning research in low-resource environments. Due to the non-European nature of skeleton data, Graph Convolution Network (GCN) has become mainstream in the past few years, leveraging the benefits of processing topological information. However, with the explosive development of transformer methods in natural language processing and computer vision, many works have applied transformer into the field of skeleton action recognition, breaking the accuracy monopoly of GCN. Therefore, we conduct a survey using transformer method for skeleton-based action recognition, forming of a taxonomy on existing works. This paper gives a comprehensive overview of the recent transformer techniques for skeleton action recognition, proposes a taxonomy of transformer-style techniques for action recognition, conducts a detailed study on benchmark datasets, compares the algorithm accuracy of standard methods, and finally discusses the future research directions and trends. To the best of our knowledge, this study is the first to describe skeleton-based action recognition techniques in the style of transformers and to suggest novel recognition taxonomies in a review. We are confident that Transformer-based action recognition technology will become mainstream in the near future, so this survey aims to help researchers systematically learn core tasks, select appropriate datasets, understand current challenges, and select promising future directions.

Imaging-based 3D particle tracking system for field characterization of particle dynamics in atmospheric flows

A particle tracking velocimetry apparatus is presented that is capable of measuring three-dimensional particle trajectories across large volumes, of the order of several meters, during natural snowfall events. Field experiments, aimed at understanding snow settling kinematics in atmospheric flows, were conducted during the 2021/2022 winter season using this apparatus, from which we show preliminary results. An overview of the methodology, wherein we use a UAV-based calibration method, is provided, and analysis is conducted of a select dataset to demonstrate the capabilities of the system for studying inertial particle dynamics in atmospheric flows. A modular camera array is used, designed specifically for handling the challenges of field deployment during snowfall. This imaging system is calibrated using synchronized imaging of a UAV-carried target to enable measurements centered 10 m above the ground within approximately a 4 m $$\times$$ 4 m $$\times$$ 6 m volume. Using the measured Lagrangian particle tracks, we present data concerning 3D trajectory curvature and acceleration statistics, as well as clustering behavior using Voronoï analysis. The limitations, as well as potential future developments, of such a system are discussed in the context of applications with other inertial particles.

Analysis of the of training and test data distribution for audio series classification

The effectiveness of machine learning algorithms for any given task largely depends on the training and test datasets. This manifests itself not only in the amount of data, but also in its content (that is, its relevance for the task at hand), as well as in its organization. Generally, the common approach is to split the dataset into training and testing sets to avoid model overfitting. In addition, to achieve better metrics for the selected criteria (accuracy, learning rate, etc.) of model performance, different ratios of training and test sets are used in the partitioning. The goal of this paper is to analyze methods of data set partitioning for use in training neural networks and statistical models. One of the reviewed methods, specifically the cross-validation method, was applied to a dataset developed from the LibriSpeach corpus, an open English speech corpus based on the LirbiVox project of voluntarily contributed audio books. The result of applying the selected data partitioning method on the selected data set is demonstrated.

Joint visualization of seasonal influenza serology and phylogeny to inform vaccine composition.

Seasonal influenza vaccines must be updated regularly to account for mutations that allow influenza viruses to escape our existing immunity. A successful vaccine should represent the genetic diversity of recently circulating viruses and induce antibodies that effectively prevent infection by those recent viruses. Thus, linking the genetic composition of circulating viruses and the serological experimental results measuring antibody efficacy is crucial to the vaccine design decision. Historically, genetic and serological data have been presented separately in the form of static visualizations of phylogenetic trees and tabular serological results to identify vaccine candidates. To simplify this decision-making process, we have created an interactive tool for visualizing serological data that has been integrated into Nextstrain's real-time phylogenetic visualization framework, Auspice. We show how the combined interactive visualizations may be used by decision makers to explore the relationships between complex data sets for both prospective vaccine virus selection and retrospectively exploring the performance of vaccine viruses.

Fully efficient, two-stage analysis of multi-environment trials with directional dominance and multi-trait genomic selection

Key messageR/StageWise enables fully efficient, two-stage analysis of multi-environment, multi-trait datasets for genomic selection, including support for dominance heterosis and polyploidy.Plant breeders interested in genomic selection often face challenges to fully utilizing multi-trait, multi-environment datasets. R package StageWise was developed to go beyond the capabilities of most specialized software for genomic prediction, without requiring the programming skills needed for more general-purpose software for mixed models. As the name suggests, one of the core features is a fully efficient, two-stage analysis for multiple environments, in which the full variance–covariance matrix of the Stage 1 genotype means is used in Stage 2. Another feature is directional dominance, including for polyploids, to account for inbreeding depression in outbred crops. StageWise enables selection with multi-trait indices, including restricted indices with one or more traits constrained to have zero response. For a potato dataset with 943 genotypes evaluated over 6 years, including the Stage 1 errors in Stage 2 reduced the Akaike Information Criterion (AIC) by 29, 67, and 104 for maturity, yield, and fry color, respectively. The proportion of variation explained by heterosis was largest for yield but still only 0.03, likely because of limited variation for the genomic inbreeding coefficient. Due to the large additive genetic correlation (0.57) between yield and maturity, naïve selection on an index combining yield and fry color led to an undesirable response for later maturity. The restricted index coefficients to maximize genetic merit without delaying maturity were identified. The software and three vignettes are available at https://github.com/jendelman/StageWise.

Influence of Skin Color and Data Pre-processing on Gender Classification

Face recognition and gender classification is one of the hot spots at present, how to get better results in the recognition process is the key. This research was based on neural networks. While some researchers have explored this issue through neural networks, this research focuses on the impact of data processing other than the model on the final results. First of all, through the manual review and screening of data sets, the training set of face images only retained deep color skin face images, and the test set did not do selection processing. The final results of the model which based on selected data set are not much different from that of the model based on the unselected training set, except for a slight decrease in the recall rate of female face recognition. Secondly, by the method of control variables, the effect of the three kinds of data pre-processing is compared. The results show that both random cropping and normalization can improve some attributes of the model to varying degrees, but only random horizontal flipping has a certain negative effect on the model. In this research, it was found that the smaller proportion of white skin face image training sets hardly affected the model performance. Data pre-processing can effectively improve the model, but the use of random horizontal flips in a data set with a great number of small tilt angle images may lead to the deterioration of the results on the training set.

Vehicle Recognition Based on Region Growth of Relative Tension and Similarity Measurement of Side Projection Profile of Vehicle Body

Current vehicle recognition methods are less concerned simultaneously with: (1) the scale difference between vehicles and other objects in urban city; and (2) the impact of physical characteristics of vehicles. Based on the region growth of relative tension, a method for measuring the similarity of side projection profile of a vehicle’s body is proposed for recognizing vehicles. First, region growth of relative tension is used to divide 3D point clouds into a series of spatial regions. Point clouds in these regions are projected to a 2D plane. Then, relevant 2D features are extracted, including side projection profile of vehicle body and sizes of vehicles. Screening by these relevant features, part of these regions, and point clouds inside them which conforms to the similarity measurement conditions of vehicles are selected. Quantitative evaluations on the selected data set show that the proposed algorithm achieves a recall, precision, and F-score of 0.837, 0.979, and 0.902, respectively, in recognizing vehicles. Comparative studies demonstrate the superior performance of the proposed algorithm.

Estimating Overhead Performance of Supervised Machine Learning Algorithms for Intrusion Detection

Estimating the energy and memory consumption of machine learning(ML) models for intrusion detection ensures efficient allocation of system resources. This study investigates the impact of supervised ML algorithms on the energy and memory consumption of intrusion detection systems. Experiments are conducted with seven ML algorithms and a proposed ensemble model, utilizing two intrusion detection datasets. Pearson correlation coefficient(PCC) and Spearman correlation coefficient are employed for the selection of optimum features. Regarding energy consumption, the findings reveal that the PCC with the UNSW-NB15 dataset uses the least amount of DRAM and CPU power. For ML methods, SVM utilizes the highest energy for both feature selection methods and datasets. Concerning memory consumption, the results show that decision tree uses the most current memory with PCC on the UNSW-NB15. The proposed ensemble model demonstrates the highest performance. These findings offer practical guidelines to ML experts when choosing the optimum model with the most efficient utilization of energy and memory.

Solving Optimization Problems Using an Extended Gradient-Based Optimizer

This paper proposes an improved method for solving diverse optimization problems called EGBO. The EGBO stands for the extended gradient-based optimizer, which improves the local search of the standard version of the gradient-based optimizer (GBO) using expanded and narrowed exploration behaviors. This improvement aims to increase the ability of the GBO to explore a wide area in the search domain for the giving problems. In this regard, the local escaping operator of the GBO is modified to apply the expanded and narrowed exploration behaviors. The effectiveness of the EGBO is evaluated using global optimization functions, namely CEC2019 and twelve benchmark feature selection datasets. The results are analyzed and compared to a set of well-known optimization methods using six performance measures, such as the fitness function’s average, minimum, maximum, and standard deviations, and the computation time. The EGBO shows promising results in terms of performance measures, solving global optimization problems, recording highlight accuracies when selecting significant features, and outperforming the compared methods and the standard version of the GBO.

Predicting rheumatoid arthritis from the biomarkers of clinical trials using improved harmony search optimization with adaptive neuro-fuzzy inference system

Rheumatoid Arthritis (RA) is a chronic autoimmune disease whose symptoms are hard to determine due to the overlapping indications of the condition with other illnesses such as dengue, malaria, etc. As the symptoms of RA disease are similar to inflammatory diseases, general physicians (GPs) find it difficult to detect the disease earlier. A computer aided framework is proposed in this study to assist and support the GPs to diagnose RA better. In this work Improved Harmony Search Optimization (IHSO) approach is proposed to select the significant feature subset of RA and Adaptive Neuro-Fuzzy Inference System (ANFIS) is used as a classification model. The performance of the proposed IHSO-ANFIS model is examined with metrics such as Balanced Accuracy (Bacc), Area under Curve (AUC), Sensitivity (Sen), Specificity (Spec), and Matthew’s Correlation Coefficient (MCC) using 10-Fold cross-validation. Additionally, the results of the IHSO-ANFIS are compared with HSO-ANFIS, ANFIS without any feature selection and standard bench mark datasets. IHSO-ANFIS attained 87.05% Bacc, 89.95% AUC and 0.6586 MCC on the RA dataset. From the results it is clear that IHSO-ANFIS could assist general physicians to diagnose RA earlier and pave the way for timely treatment.

Research on Supply Chain Financial Risk Prevention Based on Machine Learning.

Artificial intelligence (AI) proves decisive in today's rapidly developing society and is a motive force for the evolution of financial technology. As a subdivision of artificial intelligence research, machine learning (ML) algorithm is extensively used in all aspects of the daily operation and development of the supply chain. Using data mining, deductive reasoning, and other characteristics of machine learning algorithms can effectively help decision-makers of enterprises to make more scientific and reasonable decisions by using the existing financial index data. At present, globalization uncertainties such as COVID-19 are intensifying, and supply chain enterprises are facing bankruptcy risk. In the operation process, practical tools are needed to identify and opportunely respond to the threat in the supply chain operation promptly, predict the probability of business failure of enterprises, and take scientific and feasible measures to prevent a financial crisis in good season. Artificial intelligence decision-making technology can help traditional supply chains to transform into intelligent supply chains, realize smart management, and promote supply chain transformation and upgrading. By applying machine learning algorithms, the supply chain can not only identify potential risks in time and adopt scientific and feasible measures to deal with the crisis but also strengthen the connection and cooperation between different enterprises with the advantage of advanced technology to provide overall operation efficiency. On account of this, the paper puts forward an artificial intelligence-based corporate financial-risk-prevention (FRP) model, which includes four stages: data preprocessing, feature selection, feature classification, and parameter adjustment. Firstly, relevant financial index data are collected, and the quality of the selected data is raised through preprocessing; secondly, the chaotic grasshopper optimization algorithm (CGOA) is used to simulate the behavior of grasshoppers in nature to build a mathematical model, and the selected data sets are selected and optimized for features. Then, the support vector machine (SVM) performs classification processing on the quantitative data with reduced features. Empirical risk is calculated using the hinge loss function, and a regular operation is added to optimize the risk structure. Finally, slime mould algorithm (SMA) can optimize the process to improve the efficiency of SVM, making the algorithm more accurate and effective. In this study, Python is used to simulate the function of the corporate business finance risk prevention model. The experimental results show that the CGOA-SVM-SMA algorithm proposed in this paper achieves good results. After calculation, it is found that the prediction and decision-making capabilities are good and better than other comparative models, which can effectively help supply chain enterprises to prevent financial risks.

Comparative analysis of selected algorithms for qualitative data clustering

Data clustering can apply to both numeric and categorical attributes. The numerical characteristics of data are all such values that can be written as digits. This work is not directly devoted to this category of attributes. The research's primary and most crucial goal is to compare the clustering processes, the quality of the obtained clusters, and the clustering results between the selected algorithms for clustering numerical sets (using coding techniques) and qualitative data sets. Design experiments were performed on three datasets. The algorithms used to group the observations into classes were the k-means algorithm and the kmodes algorithm. Three different distance determination measures were used in the case of the k-means algorithm - the Euclidean measure, the urban measure, and the Chebyshev measure. It can be concluded that for the structures of the three selected data sets, the k-modes algorithm presents better results of the clustering quality and thus more effectively distributes observations to classes. It also does it in a much shorter time than the k-means algorithm. The keyword used here, however, is dataset structure.

Outlier Detection in Test Samples using Standard Deviation and Unsupervised Training Set Selection

Outlier detection is a technique to identify and remove significantly different data from the more correct and consistent data in a data set. Outlier data can have negative impact on classification and clustering performance; that should be identified and removed to improve the classification efficiency. Regardless of whether a classifying technique classifies an outlier correctly, the very notion of identifying a data as outlier is of great significance. In this paper, a new approach is proposed for outlier data detection within a test data set along with unsupervised training set selection. The selected training set is used for two-step classification. After unsupervised clustering the training set, the closest cluster to a test sample is selected using the Euclidean distance measure. Then, the outlier in the test sample is identified with the concepts of standard deviation and mean value. The results showed by evaluating the distance of each sample of the test set with the new selected data set. the accuracy of the classifiers is enhanced after detection and elimination of outlier data.

Development of a Predictive System Model Using Big Data in the Transport Sector

This article discusses the possibility of creating a predictive system model using smart innovative technologies to generate a request for spare parts for the automotive industry using big data analysis, which is quite relevant for many transport, logistics and repair companies. The authors seek to generalize and systematize research in this area, with the possibility of integrating practical knowledge and big data for the implementation of urgent management and logistics tasks that will allow economic growth. In addition, the relevance of timely diagnostics and rapid leveling of vehicle defects is explored in light of current market conditions. Using data from the domestic market, a hypothesis has been proposed for specific parts and assemblies that may fail for a given car model. The top-selling models on the Russian second-hand market, consisting of 9 brands and 27 models from foreign manufacturers, were selected. An algorithm for analyzing the selected data set was developed, implemented using the Python programming language in Jupiter Notebook. Following a comprehensive investigation of the car's flaws, stacked diagrams were created to show the flaws, and the relevance of the 27 most popular model's flaws and their structural makeup were determined according to the country of origin. A model for predicting used car spare parts based on the results of the analysis of the structure of defects has been developed. The model combines data from revocable companies, feedback from car owners, maintenance services and component suppliers. Also, this article establishes the direction for future research in this area.

An Improved Method for Skin Cancer Prediction Using Machine Learning Techniques

Among skin diseases the type that causes cancer are the fatal ones and pose the biggest issues. These issues arise since cancers are just much larger quantities of the same cells that are present around the body, which makes diagnosis very difficult until later stages. Now the onset of artificial intelligence and machine learning techniques, in the field of images, has allowed computers to identify sequences and patterns in images that can never be observed by the naked eye. Hence in order to battle skin cancer in its early stages a system has been proposed to identify and predict skin cancer in its earlier stages. A skin cancer prediction system has hence been created and implemented to predict three major types of skin cancer that affect humans. A dataset of the said skin cancer types and other types of skin diseases have been taken and analyzed. Apart from the model, a web application has been constructed for deployment on the web to enable the access of this model to the general masses. The current work is limited to selective dataset and model, which can be further extended.

Zinc on the edge—isotopic and geophysical evidence that cratonic edges control world-class shale-hosted zinc-lead deposits

The North Australian Zinc Belt is the largest zinc-lead province in the world, containing three of the ten largest known individual deposits (HYC, Hilton-George Fisher, and Mount Isa). The Northern Cordillera in North America is the second largest zinc-lead province, containing a further two of the world’s top ten deposits (Red Dog and Howards Pass). Despite this world-class endowment, exploration in both mineral provinces during the past 2 decades has not been particularly successful, yielding only two significant discoveries (Teena, Australia, and Boundary, Canada). One of the most important aspects of exploration is to choose mineral provinces and districts within geological belts that have the greatest potential for discovery. Here, we present results from these two zinc belts that highlight previously unused datasets for area selection and targeting. Lead isotope mapping using analyses of mineralized material has identified gradients in μ (238U/204Pb) that coincide closely with many major deposits. Locations of these deposits also coincide with a gradient in the depth of the lithosphere-asthenosphere boundary determined from calibrated surface wave tomography models converted to temperature. Furthermore, gradients in upward-continued gravity anomalies and a step in Moho depth correspond to a pre-existing major crustal boundary in both zinc belts. A spatial association of deposits with a linear mid- to lower-crustal resistivity anomaly from magnetotelluric data is also observed in the North Australian Zinc Belt. The change from thicker to thinner lithosphere is interpreted to localize prospective basins for zinc-lead mineralization and to control the gradient in lead isotope and geophysical data. These data, when combined with data indicative of paleoenvironment and changes in plate motion at the time of mineralization, provide new exploration criteria that can be used to identify prospective mineralized basins and define the most favorable parts of these basins.

Cross‐Cultural Generalisation in Three Research Practices: Historicising, Comparing, and Theorising in the Study of Religion\s*

This article argues for a re‐appreciation of explicit and self‐reflective historicising, comparing, and theorising as three research practices that offer the best answers to the main challenges that the historical study of religion\s faces today. In examining these research practices, I stress the intersection of particularising and generalising tendencies. First, the practice of historicising requires a contextualisation of the historical object(s) and the historian's own situatedness; such a dual contextualisation dovetails with the relational paradigm that characterises current studies of religion\s. Second, comparative research practices make explicit what is often concealed: the methodological back‐and‐forth between the contemporary researcher's frameworks and the selected data set. Rather than delegitimising comparison, this awareness should lead to deeper scrutiny and an ambition to carefully generalise. Third, shifting to a processual notion of theorising rather than engaging solidified theory enables cross‐disciplinary collaboration on and public engagement with large themes in history and society. By illustrating these three research practices and highlighting several of their operational steps, I hope to contribute to the dialogue between historians and social‐scientific theory.

Development and validation of a blood‐based protein predictor of 20‐year dementia risk from middle age

AbstractBackgroundIn the US the number of individuals affected by dementia is expected to double by 2040. Thus, tools enabling identification of at‐risk individuals earlier in disease progression, or before disease onset, are vital. Proteomics‐driven risk stratification for dementia may enable the initiation of life‐planning and/or elicit changes in modifiable lifestyle‐related risk factors. Moreover, test results may facilitate enrichment of clinical trial enrollment, and ultimately as an aid in precision prescribing of preventative therapeutics. Therefore, we sought to develop and validate a blood‐based protein‐only predictor of 20‐year dementia risk from middle age.MethodUsing modified‐aptamer proteomics technology, SomaScan® assay v4.0, we scanned ∼5,000 proteins in 11,277 EDTA plasma samples from individuals aged 49‐73 without known dementia at visit 3 blood draw of the Atherosclerosis Risk in Communities (ARIC) study, totaling ∼56million protein measurements. A total 1,305 incident dementia diagnoses occurred within 20 years of blood‐draw. Time to dementia diagnosis events were modeled with protein measurements using machine learning methods in 70% of ARIC V3 as a training dataset. A model was selected based on performance in a 15% holdout sample subset and validated in the remaining 15% samples. In a subset of 3,852 individuals with known ApoE status, the performance of the proteomic model was compared to that of the predictive performance of risk genotype.ResultA 25‐feature protein‐only accelerated‐failure‐time Weibull model was successfully developed to predict the probability of a dementia diagnosis within 20 years of blood draw. Model performance was measured using AUC, which was equal to 0.73, 0.73, and 0.70, in the training, model selection, and validation datasets, respectively. Based on predicted probabilities from the model, individuals were stratified into low, medium‐low, medium‐high, and high risk bins, with a 20‐year event rate of 3.79% vs 35.58% in low vs high risk bins. Model performance was significantly superior to that of ApoE genotype.ConclusionWe successfully developed a well calibrated protein‐only model with a 10‐fold dynamic range that predicts 20‐y risk of a dementia diagnosis. Performance of the protein model out‐performs leading genetic risk factors for dementia and given the exclusion of immutable factors it has the potential to monitor changing risk.

Radiomics models based on multi-sequence MRI for preoperative evaluation of MUC4 status in pancreatic ductal adenocarcinoma: a preliminary study.

Mucin 4 (MUC4) overexpression promotes tumorigenesis and increases the aggressiveness of pancreatic ductal adenocarcinoma (PDAC). To date, no study has reported the association between radiomics and MUC4 expression in PDAC. Thus, we aimed to explore the utility of radiomics based on multi-sequence magnetic resonance imaging (MRI) to predict the status of MUC4 expression in PDAC preoperatively. This retrospective study included 52 patients with PDAC who underwent MRI. The patients were divided into two groups based on MUC4 expression status. Two feature sets were extracted from the arterial and portal phases (PPs) of dynamic contrast-enhanced MRI (DCE-MRI). Univariate analysis, minimum redundancy maximum relevance (MRMR), and principal component analysis (PCA) were performed for the feature selection of each dataset, and features with a cumulative variance of 90% were selected to develop radiomics models. Clinical characteristics were gathered to develop a clinical model. The selected radiomics features and clinical characteristics were modeled by multivariable logistic regression. The combined model integrated radiomics features from different selected data sets and clinical characteristics. The classification metrics were applied to assess the discriminatory power of the models. There were 22 PDACs with a high expression of MUC4 and 30 PDACs with a low expression of MUC4. The area under the receiver operating characteristic (ROC) curve (AUC) values of the arterial phase (AP) model, the PP model, and the combined model were 0.732 (0.591-0.872), 0.709 (0.569-0.849), and 0.861 (0.760-0.961), respectively. The AUC of the clinical model was 0.666 (0.600-0.682). The combined model that was constructed outperformed the AP, the PP, and the clinical models (P<0.05, although no statistical significance was observed in the combined model vs. AP model). Radiomics models based on multi-sequence MRI have the potential to predict MUC4 expression levels in PDAC.