Data Sampling Methods Research Articles

Questioning the reliability of open-loop calibration methods: Introducing a robust data sampling for year-round high accuracy

Heliostat calibration in solar tower plants is critical for optimizing plant efficiencies through precise solar tracking. Current practices often assume heliostat precision degrades over time, leading to the development of new calibration procedures utilizing time-dependent data sets. However, contrary to this prevailing assumption, our study demonstrates the consistency of tracking accuracy over extended periods when appropriate calibration points are selected. We introduce a novel data sampling method that uses sun positions in Euler angles as relevancy scores, enabling higher accuracy with a reduced data requirement. Our thorough analysis challenges the common belief that time significantly impacts calibration accuracy. Furthermore, we unveil an overlooked relationship between prediction accuracy and solar position coverage, raising legitimate concerns about the reliability of reported accuracies in previous publications. To promote transparency, we present clear data and advocate for improved reporting practices in future publications. Applying the new data set sampling to a non optimized data set we archive a year-round stable accuracy below 1.5 mrad with as little as 27 calibration points.

Long-span multi-layer spillovers between moments of advanced equity markets: The role of climate risks

In this paper, we examine the potential spillovers between returns, volatility, skewness and kurtosis of developed stock markets under the lenses of rare disaster events, proxied by climate risks. The aforementioned moments based on model-implied distributions of stock returns are derived from the quantile autoregressive distributed lag mixed-frequency data sampling (QADL-MIDAS) method, using a long span of data. The empirical findings are as follows: firstly, spillovers are significant within- and across stock markets for each of the four moments. Secondly, based on a nonparametric causality-in-quantiles approach, changes in temperature anomalies, have the predictive power to shape the entire conditional distribution of various metrics of spillover involving single- and multiple-layers of returns and risks layers. In sum, we show that the multi-layer approach offers a comprehensive and nuanced view of how stock market-related information is transmitted across the stock markets of advanced economies, carrying implications for investors and policymakers.

Data-driven prediction of soccer outcomes using enhanced machine and deep learning techniques

This paper introduces a novel framework for soccer game prediction using advanced machine learning and deep learning techniques, initially focusing on the Dutch Eredivisie League and later expanding to include the Scottish Premiership and the Belgian Jupiler Pro League. The methodology includes data preprocessing, feature engineering, model training, and testing. Various models are evaluated, including enhanced versions of Logistic Regression, XGBoost, Random Forest, SVM, Naive Bayes, Feedforward Neural Network, and Vanilla Recurrent Neural Network. Unlike existing studies that focus on end-of-game features, this research incorporates real-time features like half-time results and goals for in-game decision-making. Advanced data normalization and sampling methods, such as SVM-SMOTE and Near-Miss, are applied to improve model performance. Models are assessed using accuracy, recall, precision, F1-score, and Area under the ROC Curve. Results indicate that the Feedforward Neural Network excels in predicting game results, while Logistic Regression is best for predicting under and over 2.5 goals. The integration of Random Forest and XGBoost in a voting model consistently achieves the highest accuracy across both prediction tasks. The combined use of data from the three leagues further validates the models’ robustness and generalizability. This study demonstrates the potential of machine and deep learning to enhance soccer game predictions through advanced techniques and comprehensive data analysis, making significant contributions to sports analytics.

The Linear Sampling Method for Data Generated by Small Random Scatterers

The Linear Sampling Method for Data Generated by Small Random Scatterers

Leveraging visible-near-infrared spectroscopy and machine learning to detect nickel contamination in soil: Addressing class imbalances for environmental management

Excessive concentrations of Ni in soil have many severe effects, negatively affecting human health and leading to disease, while also posing a threat to animals and plants. Although the dangers of high Ni concentrations have been widely recognized, rapid and large-scale tools for the identification of Ni contamination are still lacking. Visible-near-infrared (Vis-NIR) spectroscopy has been employed to rapidly identify Ni contamination; however, previous studies suffer from issues inherent to small datasets and the tendency to negate data imbalances. To address these issues, a large dataset comprising 18,675 soil samples was used to predict soil Ni contamination by combining Vis-NIR data with machine learning (ML). The data imbalance inherent to previous studies was addressed using two data sampling methods. To build a robust classification model for Ni contamination, four spectral preprocessing methods and four ML algorithms were compared. The optimal extreme gradient boosting model achieved recall, accuracy, area under the curve, and geometric mean scores of 0.8203, 0.8806, 0.9268, and 0.8508, respectively. Model predictions across the United States identified specific regions with high possibility of Ni contamination. Overall, the model developed in this study offers an improved accuracy in predicting soil Ni contamination at the continental scale, and can be used to prioritize further testing and guide policymaking.

ANALISIS TINGKAT KEKRITISAN LAHAN DI KAWASAN REHABILITASI PT. ARUTMIN INDONESIA KABUPATEN BANJAR PROVINSI KALIMANTAN SELATAN

The purpose of this research is to analyze the level of criticality of land in the Riam Kanan Sub-watershed, Banua Riam Village, Aranio District, Banjar Regency as an effort to control the level of criticality of land and reduce the level of flood vulnerability for environmentalsustainability. The data sampling method was determined using a purposive sampling technique, which means the sample points were determined dliberately. The sample points taken are based on land units originating from the land unit map (overlay). Sampling will be carried out in two ways, namely the first way using a soil drill to analyze the structure, soil solum, texture and organic material, while the second way uses a sample ring to determine the permeability at each place. At each point the biophysical parameters were observed in the form of land cover type, slope slope and soil conservation and soil samples were taken for further observations in the soil laboratory. Land Criticality Level (TKL) shows relatively varied classes, namely Somewhat Critical and Potentially Critical. Land cover of PT. Rehabilitation area. Arutmin Indonesia Benua Riam Village, Aranio District, Banjar Regency is a Plantation Forest (HT) with an area of TKL Index 2 (Somewhat Critical) of 13.93 ha (8%), Index 3 (Potentially Critical) of 162.00 ha (92%)

Sensitivity analysis of a multi-scale biofuel primary atomization simulation tool

The purpose is to produce a benchmarked commercial Volume of Fluid (VOF)-to-Discrete Phase Modeling (DPM) numerical algorithm using an experimental study of high-viscosity jet fuel blend C-3. Where the mesh resolution was too coarse to resolve sufficient gas-liquid interfacial curvature, the solver automatically converted VOF biofuel phase mass, momentum, and energy into the equivalent DPM biofuel phase at the sub-grid scale level. Particular attention herein was given to the sensitivity of the results to various numerical degrees of freedom related to the local criteria for conversion of a biofuel from VOF to DPM. The proliferation of commercial simulation tools mandates detailed parametric evaluations. It was found that, while instantaneous conversion rates were extremely sensitive to conversion criteria, atomization physics were not sensitive to the conversion rate effects. Also, this flow system exhibited an outstanding dependence on simulated azimuthal angle, rendering lower order models ineffective. Data sampling methods and durations, along with mesh resolution, were explored such that a particular set of parameters provided a validated model.

CIRA: Class imbalance resilient adaptive Gaussian process classifier

The problem of class imbalance is pervasive across various real-world applications, resulting in machine learning classifiers exhibiting bias towards majority classes. Algorithm-level balancing approaches adapt the machine learning algorithms to learn from imbalanced datasets while preserving the data’s original distribution. The Gaussian process classifier is a powerful machine learning classification algorithm, however, as with other standard classifiers, its classification performance could be exacerbated by class imbalance. In this work, we propose the Class Imbalance Resilient Adaptive Gaussian process classifier (CIRA), an algorithm-level adaptation of the binary Gaussian process classifier to alleviate the class imbalance. To the best of our knowledge, the proposed algorithm (CIRA) is the first adaptive method for the Gaussian process classifier to handle unbalanced data. The proposed CIRA algorithm consists of two balancing modifications to the original classifier. The first modification balances the posterior mean approximation to learn a more balanced decision boundary between the majority and minority classes. The second modification adopts an asymmetric conditional prediction model to give more emphasis to the minority points during the training process. We conduct extensive experiments and statistical significance tests on forty-two real-world unbalanced datasets. Through the experiments, our proposed CIRA algorithm surpasses six popular data sampling methods with an average of 2.29%, 3.25%, 3.67%, and 1.81% in terms of the Geometric mean, F1-measure, Matthew correlation coefficient, and Area under the receiver operating characteristics curve performance metrics respectively.

A machine learning potential construction based on radial distribution function sampling.

Sampling reference data is crucial in machine learning potential (MLP) construction. Inadequate coverage of local configurations in reference data may lead to unphysical behaviors in MLP-based molecular dynamics (MLP-MD) simulations. To address this problem, this study proposes a new on-the-fly reference data sampling method called radial distribution function (RDF)-based data sampling for MLP construction. This method detects and extracts anomalous structures from the trajectories of MLP-MD simulations by focusing on the shapes of RDFs. The detected structures are added to the reference data to improve the accuracy of the MLP. This method allows us to realize a reasonable MLP construction for liquid water with minimal additional data. We prepare data from an H2O molecular cluster system and verify whether the constructed MLPs are practical for bulk water systems. MLP-MD simulations without RDF-based data sampling show unphysical behaviors, such as atomic collisions. In contrast, after applying this method, we obtain MLP-MD trajectories with features, such as RDF shapes and angle distributions, that are comparable to those of ab initio MD simulations. Our simulation results demonstrate that the RDF-based data sampling approach is useful for constructing MLPs that are robust to extrapolations from molecular cluster systems to bulk systems without any specialized know-how.

Research on Hard Rock Pillar Stability Prediction Based on SABO-LSSVM Model

The increase in mining depth necessitates higher strength requirements for hard rock pillars, making mine pillar stability analysis crucial for pillar design and underground safety operations. To enhance the accuracy of predicting the stability state of mine pillars, a prediction model based on the subtraction-average-based optimizer (SABO) for hyperparameter optimization of the least-squares support vector machine (LSSVM) is proposed. First, by analyzing the redundancy of features in the mine pillar dataset and conducting feature selection, five parameter combinations were constructed to examine their effects on the performance of different models. Second, the SABO-LSSVM prediction model was compared vertically with classic models and horizontally with other optimized models to ensure comprehensive and objective evaluation. Finally, two data sampling methods and a combined sampling method were used to correct the bias of the optimized model for different categories of mine pillars. The results demonstrated that the SABO-LSSVM model exhibited good accuracy and comprehensive performance, thereby providing valuable insights for mine pillar stability prediction.

Revisiting scale effect on joint roughness coefficient and shear strength considering sampling methods and geometric characteristics

The scale effect on shear strength of rock joints is well-documented. However, whether scale effects are negative, positive, or even exist or not is still controversial. Joint roughness significantly influences the shear strength of rock joints. Compared to the shear tests, using the joint roughness coefficient (JRC) and its roughness parameters offers a more convenient method for describing the scale effect on shear strength. However, it is crucial to understand that the scale effect mechanisms of JRC are distinct from those of shear strength. Therefore, this paper aims to clarify these distinct mechanisms. By digitally extracting roughness parameters from granite samples, it's found that the scale effect of roughness parameters mainly comes from the sampling methods and the geometric characteristics of parameters. Furthermore, a full data sampling method considering heterogeneity is proposed to obtain more representative roughness parameters. To reveal the scale effect mechanisms of shear strength, Gaussian filtering is firstly used to separate the waviness and unevenness components of roughness, facilitating a deeper understanding of the geometric characteristics of roughness. It is suggested that the wavelength of the waviness component can reflect the scale effect on shear strength. Secondly, numerical simulations of ideal artificial joint models are conducted to validate that the wavelength of the waviness component serves as the dividing point between positive and negative scale effects. The mechanical mechanisms of positive and negative scale effects are also interpreted. Finally, these mechanisms successfully elucidate the occurrence patterns of the scale effect on natural joint profiles.

MERA: Meta-Learning Based Runtime Adaptation for Industrial Wireless Sensor-Actuator Networks

IEEE 802.15.4-based industrial wireless sensor-actuator networks (WSANs) have been widely deployed to connect sensors, actuators, and controllers in industrial facilities. Configuring an industrial WSAN to meet the application-specified quality of service (QoS) requirements is a complex process, which involves theoretical computation, simulation, and field testing, among other tasks. Since industrial wireless networks become increasingly hierarchical, heterogeneous, and complex, many research efforts have been made to apply wireless simulations and advanced machine learning techniques for network configuration. Unfortunately, our study shows that the network configuration model generated by the state-of-the-art method decays quickly over time. To address this issue, we develop a ME ta-learning based R untime A daptation (MERA) method that efficiently adapts network configuration models for industrial WSANs at runtime. Under MERA, the parameters of the network configuration model are explicitly trained such that a small number of optimization steps with only a few new measurements will produce good generalization performance after the network condition changes. We also develop a data sampling method to reduce the measurements required by MERA at runtime without sacrificing its performance. Experimental results show that MERA achieves higher prediction accuracy with less physical measurements, less computation time, and longer adaptation intervals compared to a state-of-the-art baseline.

FedGA: A greedy approach to enhance federated learning with Non-IID data

In the context of federated learning, smart terminal devices inherently exhibit various factors such as personalized user behaviors, regional differences, and heterogeneous hardware configurations due to their unique data capturing capabilities. Consequently, they inevitably present non-independent and identically distributed (Non-IID) data during the training process, making it challenging for traditional federated learning methods to achieve desired model performance and convergence effects when dealing with such complex data distributions. To address this challenge, researchers have explored data augmentation techniques, adaptive optimization algorithms, and improved model aggregation rules. However, these methods often fail to deliver satisfactory performance when confronted with Non-IID problems. In this paper, we propose a federated learning framework based on a greedy algorithm (FedGA). Unlike traditional approaches that rely on global parameter averaging aggregation, FedGA progressively searches for partially optimal models and aggregates them to obtain the global model. We first gather client data information and finely classify all clients, employing two strategies to optimize client data distribution: (1) for clients with imbalanced quantities, we utilize data sampling methods to balance client data; (2) for clients with imbalanced class distributions, we introduce a complementary federated meta-learning method, called FedComMeta, to improve the data distribution of client groups. Experimental results demonstrate that in scenarios involving Non-IID data, FedGA achieves significant improvements in model performance compared to existing methods such as FedAvg, FedProx, and Astraea, validating the effectiveness and superiority of our approach in handling Non-IID data distributions.

The effectiveness of data pre-processing methods on the performance of machine learning techniques using RF, SVR, Cubist and SGB: a study on undrained shear strength prediction

In the field of data engineering in machine learning (ML), a crucial component is the process of scaling, normalization, and standardization. This process involves transforming data to make it more compatible with modeling techniques. In particular, this transformation is essential to ensure the suitability of the data for subsequent analysis. Despite the application of many conventional and relatively new approaches to ML, there remains a conspicuous lack of research, particularly in the geotechnical discipline. In this study, ML-based prediction models (i.e., RF, SVR, Cubist, and SGB) were developed to estimate the undrained shear strength (UDSS) of cohesive soil from the perspective of a wide range of data-scaling and transformation methods. Therefore, this work presents a novel ML framework based on data engineering approaches and the Cubist regression method to predict the UDSS of cohesive soil. A dataset including six different features and one target variable were used for building prediction models. The performance of ML models was examined considering the impact of the data pre-processing issue. For that purpose, data scaling and transformation methods, namely Range, Z-Score, Log Transformation, Box-Cox, and Yeo-Johnson, were used to generate the models. The results were then systematically compared using different sampling ratios to understand how model performance varies as various data scaling/transformation methods and ML algorithms were combined. It was observed that data transformation or data sampling methods had considerable or limited effects on the UDSS model performance depending on the algorithm type and the sampling ratio. Compared to RF, SVR, and SGB models, Cubist models provided higher performance metrics after applying the data pre-processing steps. The Box-Cox transformed Cubist model yielded the best prediction performance among the other models with an R2 of 0.87 for the 90% training set. Also, the UDSS prediction model generally yielded the best performance metrics when it was used with the transformed-based models (i.e., Box-Cox, Log, and Yeo-Johnson) than that of scaled-based (i.e., Range and Z-Score) models. The results show that the Cubist model has a higher potential for UDSS prediction, and data pre-processing methods have impacts on the predictive capacity of the evaluated regression models.

An efficient hybrid deep learning architecture for predicting short antimicrobial peptides.

Short-length antimicrobial peptides (AMPs) have been demonstrated to have intensified antimicrobial activities against a wide spectrum of microbes. Therefore, exploration of novel and promising short AMPs is highly essential in developing various types of antimicrobial drugs or treatments. In addition to experimental approaches, computational methods have been developed to improve screening efficiency. Although existing computational methods have achieved satisfactory performance, there is still much room for model improvement. In this study, we proposed iAMP-DL, an efficient hybrid deep learning architecture, for predicting short AMPs. The model was constructed using two well-known deep learning architectures: the long short-term memory architecture and convolutional neural networks. To fairly assess the performance of the model, we compared our model with existing state-of-the-art methods using the same independent test set. Our comparative analysis shows that iAMP-DL outperformed other methods. Furthermore, to assess the robustness and stability of our model, the experiments were repeated 10 times to observe the variation in prediction efficiency. The results demonstrate that iAMP-DL is an effective, robust, and stable framework for detecting promising short AMPs. Another comparative study of different negative data sampling methods also confirms the effectiveness of our method and demonstrates that it can also be used to develop a robust model for predicting AMPs in general. The proposed framework was also deployed as an online web server with a user-friendly interface to support the research community in identifying short AMPs.

Identification of Elastoplastic Constitutive Model of GaN Thin Films Using Instrumented Nanoindentation and Machine Learning Technique

This study presents a novel inverse identification approach to determine the elastoplastic parameters of a 2 µm thick GaN semiconductor thin film deposited on a sapphire substrate. This approach combines instrumented nanoindentation with finite element (FE) simulations and an artificial neural network (ANN) model. Experimental load–depth curves were obtained using a Berkovich indenter. To generate a comprehensive database for the inverse analysis, FE models were constructed to simulate load–depth responses across a wide range of GaN thin film properties. The accuracy of both 2D and 3D simulations was compared to select the optimal model for database generation. The Box–Behnken design-based data sampling method was used to define the number of simulations and input variables for the FE models. The ANN technique was then employed to establish the complex mapping between the simulated load–depth curves (input) and the corresponding stress–strain curve (output). The generated database was used to train and test the ANN model. Then, the learned ANN model was used to achieve high accuracy in identifying the stress–strain curve of the GaN thin film from the experimental load–depth data. This work demonstrates the successful application of an inverse analysis framework, combining experimental nanoindentation tests, FE modeling, and an ANN model, for the characterization of the elastoplastic behavior of GaN thin films.

Enhancing cardiovascular risk prediction through AI-enabled calcium-omics

Whole-heart coronary calcium Agatston score is a well-established predictor of major adverse cardiovascular events (MACE), but it does not account for individual calcification features related to the pathophysiology of the disease (e.g., multiple-vessel disease, spread of the disease along the vessel, stable calcifications, numbers of lesions, and density). We used novel, hand-crafted calcification features (calcium-omics); Cox time-to-event modeling; elastic net; and up and down synthetic sampling methods for imbalanced data, to assess MACE risk. We used 2457 CT calcium score (CTCS) images enriched for MACE events from our large no-cost CLARIFY program (ClinicalTrials.gov Identifier: NCT04075162). Among calcium-omics features, numbers of calcifications, LAD mass, and diffusivity (a measure of spatial distribution) were especially important determinants of increased risk, with dense calcification (> 1000HU, stable calcifications) associated with reduced risk Our calcium-omics model with (training/testing, 80/20) gave C-index (80.5%/71.6%) and 2-year AUC (82.4%/74.8%). Although the C-index is notoriously impervious to model improvements, calcium-omics compared favorably to Agatston and gave a significant difference (P < 0.001). The calcium-omics model identified 73.5% of MACE cases in the high-risk group, a 13.2% improvement as compared to Agatston, suggesting that calcium-omics could be used to better identity candidates for intensive follow-up and therapies. The categorical net-reclassification index was NRI = 0.153. Our findings from this exploratory study suggest the utility of calcium-omics in improved risk prediction. These promising results will pave the way for more extensive, multi-institutional studies of calcium-omics.

Research on the Optimization of Multi-Class Land Cover Classification Using Deep Learning with Multispectral Images

With the advancement of artificial intelligence, deep learning has become instrumental in land cover classification. While there has been a notable emphasis on refining model structures to improve classification accuracy, it is imperative to also emphasize the pivotal role of data-driven optimization techniques. This paper presents an in-depth investigation into optimizing multi-class land cover classification using high-resolution multispectral images from Worldview3. We explore various optimization strategies, including refined sampling strategies, data band combinations, loss functions, and model enhancements. Our optimizations led to a substantial increase in the Mean Intersection over Union (mIoU) classification accuracy, improving from a baseline of 0.520 to a final accuracy of 0.709, which represents a 35.2% enhancement. Specifically, by optimizing the classic semantic segmentation network in four key aspects, we improved the mIoU by 15.5%. Further improvements through changes in data combinations, sampling methods, and loss functions led to an overall 17.2% increase in mIoU. The proposed model optimization methods enabled the OUNet to outperform the baseline model by providing more precise edge detection and feature representation, while reducing the model parameters scale. Experimental evidence shows that in the application of multi-class land surface classification, increasing the quantity and diversity of samples, avoiding data imbalance issues, is equally valuable for improving overall classification accuracy as it is for enhancing model performance.

Risk prediction model based on machine learning for predicting miscarriage among pregnant patients with immune abnormalities.

Introduction: It is known that patients with immune-abnormal co-pregnancies are at a higher risk of adverse pregnancy outcomes. Traditional pregnancy risk management systems have poor prediction abilities for adverse pregnancy outcomes in such patients, with many limitations in clinical application. In this study, we will use machine learning to screen high-risk factors for miscarriage and develop a miscarriage risk prediction model for patients with immune-abnormal pregnancies. This model aims to provide an adjunctive tool for the clinical identification of patients at high risk of miscarriage and to allow for active intervention to reduce adverse pregnancy outcomes. Methods: Patients with immune-abnormal pregnancies attending Sichuan Provincial People's Hospital were collected through electronic medical records (EMR). The data were divided into a training set and a test set in an 8:2 ratio. Comparisons were made to evaluate the performance of traditional pregnancy risk assessment tools for clinical applications. This analysis involved assessing the cost-benefit of clinical treatment, evaluating the model's performance, and determining its economic value. Data sampling methods, feature screening, and machine learning algorithms were utilized to develop predictive models. These models were internally validated using 10-fold cross-validation for the training set and externally validated using bootstrapping for the test set. Model performance was assessed by the area under the characteristic curve (AUC). Based on the best parameters, a predictive model for miscarriage risk was developed, and the SHapley additive expansion (SHAP) method was used to assess the best model feature contribution. Results: A total of 565 patients were included in this study on machine learning-based models for predicting the risk of miscarriage in patients with immune-abnormal pregnancies. Twenty-eight risk warning models were developed, and the predictive model constructed using XGBoost demonstrated the best performance with an AUC of 0.9209. The SHAP analysis of the best model highlighted the total number of medications, as well as the use of aspirin and low molecular weight heparin, as significant influencing factors. The implementation of the pregnancy risk scoring rules resulted in accuracy, precision, and F1 scores of 0.3009, 0.1663, and 0.2852, respectively. The economic evaluation showed a saving of ¥7,485,865.7 due to the model. Conclusion: The predictive model developed in this study performed well in estimating the risk of miscarriage in patients with immune-abnormal pregnancies. The findings of the model interpretation identified the total number of medications and the use of other medications during pregnancy as key factors in the early warning model for miscarriage risk. This provides an important basis for early risk assessment and intervention in immune-abnormal pregnancies. The predictive model developed in this study demonstrated better risk prediction performance than the Pregnancy Risk Management System (PRMS) and also demonstrated economic value. Therefore, miscarriage risk prediction in patients with immune-abnormal pregnancies may be the most cost-effective management method.

Using Qualitative Methods to Understand the Interconnections Between Cities and Health: A Methodological Review.

Objective: Using different perspectives and methods to investigate the links between the urban phenomenon and health is critical in an urbanizing world. This review discusses qualitative methods in the context of urban health research. Methods: We conducted a narrative review following these steps: We identified the qualitative data collection, analysis and sampling methods that could be more relevant for the problems researched in the urban health field. We conducted searches for methodological articles and other documents about those methods. We included some influential materials and examples of empirical urban health studies using those methods. Results: We included 88 studies and identified several qualitative data gathering, analysis and sampling methods relevant for urban health researchers. We present those methods, focusing their strengths and limitations, and providing examples of their use in the field of urban health. These methods are flexible and allow in-depth analysis of small samples by collecting and analyzing rich and nuanced data. Conclusion: This article should contribute to a better understanding of how, and when, qualitative methods may improve our knowledge on urban health.