Statistical Learning Research Articles

Forecasting Cryptocurrency Markets: Predictive Modelling Using Statistical and Machine Learning Approaches

The rapidly evolving landscape of cryptocurrency markets presents unique challenges and opportunities. The significant daily variations in cryptocurrency exchange rates lead to substantial risks associated with investments in crypto assets. This study aims to forecast the prices of cryptocurrencies using advanced machine learning models. Among seven models that were tested for their prediction and validation efficiency, Neutral Networks performed the best with minimum error. Thus, Long Short-Term Memory (LSTM) neural networks were used for predicting future trends. LSTM model is well-suited for analyzing complex dependencies in financial data. Starting with historical data collection, data preprocessing, feature engineering, normalization and integrative binning, a comprehensive Exploratory Data Analysis (EDA) was conducted on 50 cryptocurrencies. Top performers were identified based on criteria such as trading volume, market capitalization, and price trends. The LSTM model was implemented using Python to predict 90-day price movements data to check intricate patterns and relationships. Model performance was validated by performance metrics such as MAE and RMSE. The findings align with the Adaptive Market Hypothesis (AMH) which suggests that cryptocurrency markets exhibit dynamic efficiency influenced by evolving market conditions and investor behavior. The study shows the potential of machine learning models in financial economics and their role in enhancing risk management strategies and investment decision-making processes.

A comparison of meteorological normalization of PM2.5 by multiple linear regression, general additive model, and random forest methods

PM2.5 is still one of the major atmospheric pollutants worldwide. Extracting contributions of anthropogenic emission control from the observed PM2.5 variations (PM2.5_anth), which are also strongly affected by meteorological changes, is critical for effective pollution control. Statistical and machine learning methods are usually used for such purpose, but the effectiveness of these methods is hard to evaluate due to the lack of observed anthropogenic contributions. In this study, we use the chemical transport model GEOS-Chem standard simulation to mimic PM2.5 variability in the real atmosphere, and use the model simulation with fixed meteorological fields as the “true value” for PM2.5_anth. We evaluate the effectiveness of three methods in meteorological normalization of PM2.5 on decadal (2006–2017) and synoptic (one month) scale: multiple linear regression (MLR), general additive model (GAM), and random forest (RF) algorithm. For meteorological normalization of PM2.5 on decadal scale, 67–72% of the MLR simulations show positive biases and 56–75% of the RF simulations show negative biases. The “true value” of PM2.5_anth falls within the range of meteorological normalization results of the three methods in most cases, but consistent positive/negative biases are observed in ∼30% of the cases, when meteorological changes dominate PM2.5 variability. In addition, the biases are correlated to the contribution of meteorological changes. As such, multiple statistical or machine learning methods are recommended to quantify the uncertainties associated with method choice in cases anthropogenic emission changes dominate PM2.5 variability. On synoptic scale, RF performs better in reproducing the daily variations of the PM2.5_anth differences than MLR (GAM) in all (83% of) the cases, and is recommended for meteorological normalization of PM2.5 in short-term in eastern China.

Assessment and prediction of Water Quality Index (WQI) by seasonal key water parameters in a coastal city: application of machine learning models.

The Water Quality Index (WQI) provides comprehensive assessments in river systems; however, its calculation involves numerous water quality parameters, costly in sample collection and laboratory analysis. The study aimed to determine key water parameters and the most reliable models, considering seasonal variations in the water environment, to maximize the precision of WQI prediction by a minimal set of water parameters. Ten statistical or machine learning models were developed to predict the WQI over four seasons using water quality dataset collected in a coastal city adjacent to the Yellow Sea in China, based on which the key water parameters were identified and the variations were assessed by the Seasonal-Trend decomposition procedure based on Loess (STL). Results indicated that model performance generally improved with adding more input variables except Self-Organizing Map (SOM). Tree-based ensemble methods like Extreme Gradient Boosting (XGB) and Random Forest (RF) demonstrated the highest accuracy, particularly in winter. Nutrients (Ammonia Nitrogen (AN) and Total Phosphorus (TP)), Dissolved Oxygen (DO), and turbidity were determined as key water parameters, based on which, the prediction accuracy for Medium and Low grades was perfect while it was over 80% for the Good grade in spring and winter and dropped to around 70% in summer and autumn. Nutrient concentrations were higher at inland stations; however, it worsened at coastal stations, especially in summer. The study underscores the importance of reliable WQI prediction models in water quality assessment, especially when data is limited, which are crucial for managing water resources effectively.

Superpixel-ComBat modeling: A joint approach for harmonization and characterization of inter-scanner variability in T1-weighted images

Abstract T1-weighted imaging holds wide applications in clinical and research settings; however, the challenge of inter-scanner variability arises when combining data across scanners, which impedes multi-site research. To address this, post-acquisition harmonization methods such as statistical or deep learning approaches have been proposed to unify cross-scanner images. Nevertheless, how inter-scanner variability manifests in images and derived measures, and how to harmonize it in an interpretable manner, remains underexplored. To broaden our knowledge of inter-scanner variability and leverage it to develop a new harmonization strategy, we devised a pipeline to assess the interpretable inter-scanner variability in matched T1-weighted images across four 3T MRI scanners. The pipeline incorporates ComBat modeling with 3D superpixel parcellation algorithm (namely SP-ComBat), which estimates location and scale effects to quantify the shift and spread in relative signal distributions, respectively, concerning brain tissues in the image domain. The estimated parametric maps revealed significant contrast deviations compared to the joint signal distribution across scanners (p < 0.001), and the identified deviations in signal intensities may relate to differences in the inversion time acquisition parameter. To reduce the inter-scanner variability, we implemented a harmonization strategy involving proper image preprocessing and site effect removal by ComBat-derived parameters, achieving substantial improvement in image quality and significant reduction in variation of volumetric measures of brain tissues (p < 0.001). We also applied SP-ComBat to evaluate and characterize the performance of various image harmonization techniques, demonstrating a new way to assess image harmonization. In addition, we reported various metrics of T1-weighted images to quantify the impact of inter-scanner variation, including signal-to-noise ratio, contrast-to-noise ratio, signal inhomogeneity index, and structural similarity index. This study demonstrates a pipeline that extends the implementation of statistical ComBat method to the image domain in a practical manner for characterizing and harmonizing the inter-scanner variability in T1-weighted images, providing further insight for the studies focusing on the development of image harmonization methodologies and their applications.

A probabilistic framework for identifying anomalies in urban air quality data.

Just as the value of crude oil is unlocked through refining, the true potential of air quality data is realized through systematic processing, analysis, and application. This refined data is critical for making informed decisions that may protect health and the environment. Perhaps ground-based air quality monitoring data often face quality control issues, notably outliers. The outliers in air quality data are reported as error and event-based. The error-based outliers are due to instrument failure, self-calibration, sensor drift over time, and the event based focused on the sudden change in meteorological conditions. The event-based outliers are meaningful while error-based outliers are noise that needs to be eliminated and replaced post-detection. In this study, we address error-based outlier detection in air quality data, particularly targeting particulate pollutants (PM2.5 and PM10) across various monitoring sites in Delhi. Our research specifically examines data from sites with less than 5% missing values and identifies four distinct types of error-based outliers: extreme values due to measurement errors, consecutive constant readings and low variance due to instrument malfunction, periodic outliers from self-calibration exceptions, and anomalies in the PM2.5/PM10 ratio indicative of issues with the instruments' dryer unit. We developed a robust methodology for outlier detection by fitting a non-linear filter to the data, calculating residuals between observed and predicted values, and then assessing these residuals using a standardized Z-score to determine their probability. Outliers are flagged based on a probability threshold established through sensitivity testing. This approach helps distinguish normal data points from suspicious ones, ensuring the refined quality of data necessary for accurate air quality modeling. This method is essential for improving the reliability of statistical and machine learning models that depend on high-quality environmental data.

Improved decision-making through life event prediction: A case study in the financial services industry

Life event prediction is an important tool for customer relationship management (CRM), because life events shift customers’ preferences towards different products and services. Existing life event research mainly uses cross-sectional data, whereas in the CRM field, incorporating longitudinal data is increasingly common. Because longitudinal data can capture the dynamics of customer behavior, opportunities arise to benchmark the power of longitudinal customer data for predictions of cross-sectional versus longitudinal life events. Therefore, this study compares statistical and machine learning (SaML) classifiers, such as logistic regression, random forest, and XGBoost, with long- and short-term memory networks (LSTM), using data represented in both cross-sectional and longitudinal setups for life event prediction. Through a real-life longitudinal customer data set from a European bank, the authors represent the longitudinal data in a cross-sectional data format, using featurization in the form of aggregation. The available data cover 42 end-of-month snapshots for 760,438 unique customers. For marketing decision-making literature, this article (1) introduces three novel life events (i.e., primary, secondary, and rental residence purchases) to life event predictions; (2) offers guidance for how to leverage longitudinal customer data, according to the comparison of various featurization approaches and benchmarking SaML classifiers against LSTM; and (3) clarifies the importance of features and timing for improving marketing decision-making dynamically. The results show that aggregating features over time is preferable as a featurization approach for cross-sectional modeling using SaML classifiers. Furthermore, LSTM can capture behavioral changes over time, unlike SaML classifiers. It also performs significantly better than SaML classifiers on the area under curve and F1 metrics. Insights into the uses of integrated gradients reveal that feature importance changes over time. An integrated gradients method can assist decision-makers in their efforts to plan effective communication with customers in advance, such as by allocating more resources to customers who exhibit high probabilities of a particular life event occurrence.

Early Caregiver Predictability Shapes Neural Indices of Statistical Learning Later in Infancy.

Caregivers play an outsized role in shaping early life experiences and development, but we often lack mechanistic insight into how exactly caregiver behavior scaffolds the neurodevelopment of specific learning processes. Here, we capitalized on the fact that caregivers differ in how predictable their behavior is to ask if infants' early environmental input shapes their brains' later ability to learn about predictable information. As part of an ongoing longitudinal study in South Africa, we recorded naturalistic, dyadic interactions between 103 (46 females and 57 males) infants and their primary caregivers at 3-6 months of age, from which we calculated the predictability of caregivers' behavior, following caregiver vocalization and overall. When the same infants were 6-12-months-old they participated in an auditory statistical learning task during EEG. We found evidence of learning-related change in infants' neural responses to predictable information during the statistical learning task. The magnitude of statistical learning-related change in infants' EEG responses was associated with the predictability of their caregiver's vocalizations several months earlier, such that infants with more predictable caregiver vocalization patterns showed more evidence of statistical learning later in the first year of life. These results suggest that early experiences with caregiver predictability influence learning, providing support for the hypothesis that the neurodevelopment of core learning and memory systems is closely tied to infants' experiences during key developmental windows.

Research on English Translation Optimization Algorithm Based on Statistical Machine Learning

In the study titled Research on English Translation Optimization Algorithm Based on Statistical Machine Learning: IAAM-NN (Integrating Advanced Attention Mechanisms with Neural Networks), we explore the fusion of advanced attention mechanisms with neural networks to enhance English translation accuracy. This research delves into the intersection of statistical machine learning and language processing, presenting a novel approach termed IAAM-NN. This method capitalizes on the strengths of neural networks in learning complex patterns and the refined attention mechanisms’ ability to accurately map contextual relationships within text. The core objective is to address the challenges faced in traditional translation algorithms – primarily context misinterpretation and semantic inaccuracies. By harnessing the power of advanced attention mechanisms, the IAAM-NN algorithm effectively deciphers nuanced linguistic structures, ensuring more accurate and contextually relevant translation outputs. This study demonstrates the potential of combining neural network models with enhanced attention processes, illustrating significant improvements in translation quality compared to standard machine learning approaches. The implementation of IAAM-NN marks a step forward in the realm of machine translation, offering insights into developing more sophisticated and reliable translation tools in the future.

Developing some models to predict the uniaxial compressive strength of various sedimentary rocks (Case studies: Large dam site and mine in Southeast China)

Direct determination of uniaxial compressive strength (UCS) is time-consuming, expensive, and challenging. Therefore, this study aims to indirectly predict UCS using statistical and machine learning methods. First, laboratory measurements were conducted to determine carbonate percentage, water absorption percentage, moisture content, porosity percentage, P-wave velocity, and UCS of sandstone, dolomite, dolomitic limestone, marl limestone, and limestone samples. Subsequently, various models were established to predict UCS using multivariate linear regression (MVLR), random forest regression (RFR), Gaussian process regression (GPR) based on squared exponential kernel function, and adaptive neuro-fuzzy inference system (ANFIS). The influence of Jurassic limestone texture on physical and mechanical properties in stable and unstable slopes in the Three Gorges Dam site and reservoir (TGDSR) showed that the percentage of mudstone texture in unstable slopes is higher than in stable slopes. The UCS, density, compressional wave velocity, and percentage of carbonate in unstable slopes is less than stable slopes. The results indicated that the average measured UCS is 60.60 MPa. Moreover, the average predicted UCS based on the three intelligent methods was 60.55 MPa. The percentage difference between the measured and predicted UCS was −0.09 %, demonstrating that the average error of the three employed methods is less than one percent, highlighting the high accuracy of these methods in estimating rock UCS. Notably, based on error level, Taylor diagram, Wilmot agreement index (WAI), A10 and A20 indices, Nash-Sutcliffe efficiency (NSE), and PM (performance metric) criteria the RFR exhibited superior precision (R2=99 %, and RMSE= 0.06 MPa) compared to the other used methods. The Kruskal-Wallis test (KWT) results showed that there is no significant difference between the measured and predicted values.

Fourier transform InfraRed spectra analyzed by multivariate and machine learning methods in determination spectroscopy marker of prostate cancer in dried serum

Prostate cancer represents the second most prevalent form of cancer in males globally. In the diagnosis of prostate cancer, the most commonly utilised biomarker is prostate-specific antigen (PSA). It is unfortunate that approximately 25 % of men with elevated PSA levels do not have cancer, and that approximately 20 % of patients with prostate cancer have normal serum PSA levels. Accordingly, a more sensitive methodology must still be identified. It is imperative that new diagnostic methods be non-invasive, cost-effective, rapid, and highly sensitive. Fourier transform infrared spectroscopy (FTIR) is a technique that fulfils all of the aforementioned criteria. Consequently, the present study used FTIR to assess dried serum samples obtained from a cohort of prostate cancer patients (n = 53) and a control group of healthy individuals (n = 40). Furthermore, this study proposes FTIR markers of prostate cancer obtained from serum. For this purpose, FTIR spectra of dried serum were measured and analysed using statistical, chemometric and machine learning (ML) algorithms including decision trees C5.0, Random Forest (RF), k-Nearest Neighbours (kNN) and Support Vector Machine (SVM). The FTIR spectra of serum collected from patients suffering from prostate cancer exhibited a reduced absorbance values of peaks derived from phospholipids, amides, and lipids. However, these differences were not statistically significant. Furthermore, principal component analysis (PCA) demonstrated that it is challenging to distinguish serum samples from healthy and non-healthy patients. The ML algorithms demonstrated that FTIR was capable of differentiating serum collected from both analysed groups of patients with high accuracy (values between 0.74 and 0.93 for the range from 800 cm−1 to 1800 cm−1 and around 0.70 and 1 for the range from 2800 cm−1 to 3000 cm−1), depending on the ML algorithms used. The results demonstrated that the peaks at 1637 cm−1 and 2851 cm−1 could serve as a FTIR marker for prostate cancer in serum samples. Furthermore, the correlation test indicated a clear correlation between these two wavenumbers and four of the five clinical parameters associated with prostate cancer. However, the relatively small number of samples collected only from patients over the age of 60 indicated that the results should be further investigated using a larger number of serum samples collected from a mean age range. In conclusion, this study demonstrated the potential of FTIR for the detection of prostate cancer in serum samples, highlighting the presence of distinctive spectroscopic markers associated with the analysed cancer type.

Real-time Traffic Conflict Prediction at Signalized Intersections Using Vehicle Trajectory Data and Deep Learning

Real-time conflict prediction at signalized intersections is crucial for urban road safety management. This study developed a real-time conflict prediction framework for signalized intersections using video data real-time recognition technology and deep learning techniques, incorporating lane-level information and feature interactions. The modeling framework consists of three stages: real-time video data extraction and processing, the development of a Deep and Cross Network (DCN)-based real-time traffic conflict prediction model, and conflict-driven factor interpretability analysis through SHapley Additive exPlanations (SHAP). In the first stage, an efficient automated trajectory extraction system is designed to obtain vehicle trajectories in real time for dynamic traffic parameters and conflict frequency identification. In the second stage, a DCN model is developed to construct the relationships between dynamic traffic parameters, including their interactions, and traffic conflicts. In the third stage, SHAP explores the impact mechanisms of different dynamic traffic parameters on traffic conflicts. The model’s predictive performance and interpretability are evaluated using intersection video data from Changsha City, China. The results show that: 1) In real-time traffic conflict prediction at signalized intersections across different modified time-to-conflict thresholds (1.5s and 3.0s), the DCN model consistently outperformed statistical and machine learning models. 2) High traffic flow on main and secondary roads at signalized intersections significantly increases the complexity and frequency of conflicts, with varying sensitivity depending on the interaction of traffic flow, speed, and platoon length. 3) The proposed framework provides a safety measurement standard for data-driven road safety management methods.

How realistic are multi-decadal reconstructions of GRACE-like total water storage anomalies?

Reconstructions allow us to extend the Gravity Recovery And Climate Experiment (GRACE) data record into the past and bridge the one-year gap between GRACE and its successor, GRACE-FO (Follow on). Reconstructed total water storage anomalies (TWSA) are obtained by identifying relations between GRACE-derived TWSA and climate variables via statistical and machine learning techniques. However, a comparative analysis of the characteristics and realism of reconstructions is missing.In this contribution, we close this gap by comparing three global reconstructions by Humphrey and Gudmundsson (2019), Li et al. (2021) and Chandanpurkar et al. (2022) mutually and against output from the Water Global Analysis and Prognosis (WaterGAP) hydrological model from 1979 onwards, against large-scale mass-change derived from geodetic satellite laser ranging (SLR) from 1992 onwards, and finally against differing GRACE and GRACE-FO solutions from 2002 onwards. The reconstructions vary regarding design and trained GRACE solution.Reconstructions recover the TWSA signal for humid climate regions but disagree for arid climate regions, which is evident on the inter-annual timescales. At seasonal and sub-seasonal timescales, the reconstructions agree surprisingly well in many regions. Our comparison against independent SLR data reveals that reconstructions (only) partially succeed in representing anomalous TWSA for areas that are influenced by significant climate modes such as El Niño-Southern Oscillation (ENSO).

Constructing phylogenetic trees for microbiome data analysis: A mini-review

As next-generation sequencing technologies advance rapidly and the cost of metagenomic sequencing continues to decrease, researchers now face an unprecedented volume of microbiome data. This surge has stimulated the development of scalable microbiome data analysis methods and necessitated the incorporation of phylogenetic information into microbiome analysis for improved accuracy. Tools for constructing phylogenetic trees from 16S rRNA sequencing data are well-established, as the highly conserved regions of the 16S gene are limited, simplifying the identification of marker genes. In contrast, metagenomic and whole genome shotgun (WGS) sequencing involve sequencing from random fragments of the entire gene, making identification of consistent marker genes challenging owing to the vast diversity of genomic regions, resulting in a scarcity of robust tools for constructing phylogenetic trees. Although bacterial sequence tree construction tools exist for upstream bioinformatics, many downstream researchers—those integrating these trees into statistical models or machine learning—are either unaware of these tools or find them difficult to use due to the steep learning curve of processing raw sequences. This is compounded by the fact that public datasets often lack phylogenetic trees, providing only abundance tables and taxonomic classifications. To address this, we present a comprehensive review of phylogenetic tree construction techniques for microbiome data (16S rRNA or whole-genome shotgun sequencing). We outline the strengths and limitations of current methods, offering expert insights and step-by-step guidance to make these tools more accessible and widely applicable in quantitative microbiome data analysis.

SAE-Impute: imputation for single-cell data via subspace regression and auto-encoders

BackgroundSingle-cell RNA sequencing (scRNA-seq) technology has emerged as a crucial tool for studying cellular heterogeneity. However, dropouts are inherent to the sequencing process, known as dropout events, posing challenges in downstream analysis and interpretation. Imputing dropout data becomes a critical concern in scRNA-seq data analysis. Present imputation methods predominantly rely on statistical or machine learning approaches, often overlooking inter-sample correlations.ResultsTo address this limitation, We introduced SAE-Impute, a new computational method for imputing single-cell data by combining subspace regression and auto-encoders for enhancing the accuracy and reliability of the imputation process. Specifically, SAE-Impute assesses sample correlations via subspace regression, predicts potential dropout values, and then leverages these predictions within an autoencoder framework for interpolation. To validate the performance of SAE-Impute, we systematically conducted experiments on both simulated and real scRNA-seq datasets. These results highlight that SAE-Impute effectively reduces false negative signals in single-cell data and enhances the retrieval of dropout values, gene-gene and cell-cell correlations. Finally, We also conducted several downstream analyses on the imputed single-cell RNA sequencing (scRNA-seq) data, including the identification of differential gene expression, cell clustering and visualization, and cell trajectory construction.ConclusionsThese results once again demonstrate that SAE-Impute is able to effectively reduce the droupouts in single-cell dataset, thereby improving the functional interpretability of the data.

Ứng dụng phương pháp học máy dự báo mức độ căng thẳng tài chính của doanh nghiệp niêm yết tại Việt Nam

This study utilizes the traditional statistical method and machine learning methods to forecast the level of financial distress of listed companies in Vietnam. The data used in the study was collected from 646 listed companies on the HOSE and HNX exchanges during the period from 2012 to 2022. The study experiments with the dataset on 6 machine learning models: Multiple Regression Model (MRL), LASSO, Generalized Additive Model (GAM), Random Forests (RF), Gradient Boosting Regression Trees (GBRT), and a single layer, feed forward neural network (NN), as well as the traditional statistical method. The research results demonstrate a congruence between the outcomes of the traditional method and modern machine learning models. Among these, the model with the highest accuracy is Random Forest (RF) with an accuracy rate of 98.8%. The variables that most influence the financial distress status of companies are TANG, ROA, LTD, NPM. Based on these results, our study proposes recommendations to support informed and effective financial decisions for stakeholders (companies, regulatory agencies, shareholders, creditors, investors).

Incorporating multi-source uncertainties in fast building wall thermal resistance estimation through physics-based and multi-fidelity statistical learning models

Meta-modeling and Bayesian inversion technique are proposed for fast and accurate in-situ estimation of the total thermal resistance (RTot) of walls using non-intrusive wall instrumentation. Various sources of uncertainties are taken into account to provide an enhanced credible interval for the thermal resistance estimate. In the considered protocol, a small zone of the internal surface of the wall is excited by a prototype to get faster in situ estimation and to limit the influence of external weather conditions. To be independent of the heat transfer coefficients and of the misknown layer thicknesses, which are difficult to estimate, we use herein the measurements of internal and external surface temperatures as boundary conditions in a thermal direct problem reformulated. A meta-model of the thermal model is created based on a statistical multi-fidelity approach with two levels of fidelity, Resistance-Capacitance (RC) and 1D models, to achieve the Bayesian estimation of the total thermal resistance in a reasonable computation time. The RTot estimation method is applied to realistic internal insulated walls (IIW), from poorly to highly insulated, under different weather conditions. Several numerical tests are carried out and credible intervals are provided to study the importance of the wall initial condition, the excitation time and the instrumentation. Finally, an experimental application is conducted using real measurements on an internal insulated wall (IIW) in Nancy (France). The obtained experimental results show that, in a short excitation time (10h) with a reduced instrumentation, the proposed method accurately estimates the minimum wall thermal resistance. For a standard wall of about 4 m2.K/W, a relevant estimate of RTot with a relative deviation less than 10% can be achieved by using a polynomial initial temperature profile proposed in this study, sufficient measurements and an excitation time of 3 days. This study thus offers prospects for improved energy assessment of buildings before and after renovation.

Applying Gaussian Process Regression for Machine Learning-Assisted Reactor Simulations

Abstract This study explores the integration of machine learning, specifically Gaussian Process Regression (GPR), into traditional reactor core simulations. Building upon previous work on Boiling Water Reactors (BWR), GPR is implemented to predict and correct errors in lower-fidelity simulation outcomes. The findings demonstrate significant improvements in prediction accuracy when GPR is coupled with the diffusion-based core simulator, exhibiting remarkable reductions in both keff and nodal power errors. The comparison reveals that the GPR-enhanced core simulation model significantly outperforms both the standalone simulation and a combination of simulation with Multivariate Linear Regression. It also competes effectively with the performance of a Deep Neural Network-enhanced model. Importantly, this methodology enhances simulation accuracy while maintaining low computational costs. The research emphasizes the vast potential of machine learning, particularly GPR, in progressing nuclear reactor simulations, highlighting the immense value of combining traditional simulation methods with advanced statistical learning techniques.

Evaluation of statistical and machine learning models using satellite data to estimate aboveground biomass: A study in Vietnam Tropical Forests

The combination of machine learning models with satellite imagery is becoming a popular data-modeling tool for biomass prediction, supporting land cover management. This study aims to select the most suitable model to estimate tropical forest aboveground biomass in Vietnam, helping to manage and monitor changes in biomass at regional and local scales. The study identified the optimal model for estimating forest aboveground biomass and minimizing the number of input variables while achieving satisfactory model performance. A total of 59 input variables, including topography, texture features, and vegetation indices, from satellite data were used in four non-parametric algorithms and a conventional parametric model, Artificial Neural Networks (ANN), Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Multiple Linear Regression (MLR) to predict biomass and evaluate changes aboveground biomass over 10 years in two tropical forests in Vietnam. The results indicated that all models had good estimation performance with R2 ranging from 0.615 to 0.754. For RF, MLR, and XGBoost, vegetation indices contributed the highest model weights, occupying 77.71% – 92.48%. For ANN and SVM, textural and topographic features were the majority of the model weights (73.74 – 96.36%). The RF model performed the best using 59 variables (R2 = 0.754, MAE = 78.5 Mg·ha−1, and %RMSE = 13.57%) and ten variables (R2 = 0.745, MAE = 85.8 Mg·ha−1, and %RMSE = 16.17%). The biomass map using the RF and ten variables achieved a good degree of fitting of 0.76, so it was suitable for managing and monitoring forest biomass in Vietnam. The results indicated a sharp decrease in the areas of dense and very dense forests from 2013 to 2021 and a gradual increase in 2023.

Comparing Machine Learning Regression Models for Early-Age Compressive Strength Prediction of Recycled Aggregate Concrete

A branch of artificial intelligence called machine learning is well-positioned as a prediction method that can take into consideration several influencing factors and complex inter-factor connections. Without being specifically trained to do so, these machine learning models have the ability to generalize, predict, and learn from data. Regression theory is a key topic in statistical modelling and machine learning. The main goal of this study is to compare the performance of several popular machine learning regression models for predicting the early-age compressive strength of concretes made from recycled concrete aggregates from a structure that demolished following the Sivrice-Elazig earthquake on January 24, 2020. Early-age concrete compressive strength is even more crucial due to factors like the fact that there are thousands of newly built structures in the aftermath of the earthquake, the quick manufacturing of these structures, and the completion of the project in the lowest amount of time. Determining the early-age concrete strength with high accuracy and in a useful manner is crucial for this reason. Seven different classical machine learning algorithms were employed in this study to achieve all of these goals. Early-age concrete compressive strength values were considered for 1 and 3 days. The relationship between the experimental results and the predicted outcomes of the employed algorithms was investigated, and a thorough comparison of these intelligent regression algorithms was conducted. Within the scope of sustainable development and circular economy goals, it is thought that this article will make significant contributions to the literature in terms of utilizing these waste materials and determining the early-age compressive strengths of the concretes produced with high accuracy.

Application of multiparametric methods of data science for the classification of Russian subjects on the basis of subsidisation

The relevance of the study is justified by the importance of monitoring and forecasting the subsidisation of the Russian regions in order to identify the main criteria for classifying subjects on the basis of subsidisation. In a brief review of the literature, mathematical models used to model the subsidisation of the Russian regions are considered. They have mainly fixed socio-economic indicators that need to be given attention while applying, and also regression models are used, but mathematically sound recommendations for the withdrawal of regions from clusters of subsidisation are not provided. The paper analyses the socio-economic and demographic indicators of the Russian regions applying methods that identify patterns in a multiparametric dataset. The methods of traditional statistical analysis and machine learning, including the author’s ones, are used. Statistically significant patterns have been identified, reflecting the relationship of subsidisation with such indicators as investments in fixed capital, fixed assets, average per capita income and average size of assigned pensions, unemployment rate, etc. The performed logical and statistical analysis strongly supports the use of machine learning (Data Science) methods in identifying statistically significant relationships between various indicators characterising the development of the regions of the Russian Federation.