Statistical Learning Techniques Research Articles

Unified Machine Learning Techniques for High-Dimensional Survival Data Analysis

Survival analysis is a statistical method used to analyze time-to-event data. The existence of states where event results become invisible after a given time is one of the primary difficulties with this regulation. This is considered censorship. This kind of data may be found in a variety of applications, such as mechanical system failure rates, patient mortality rates during clinical trials, and the length of unemployment in a community. Assessing the so-called survival and hazard functions is one of the primary goals of survival analysis. Many machine-learning algorithms have also been developed to tackle censored data and other difficult problems with real-world data. Machine-learning techniques enhance survival analysis by incorporating flexible modeling approaches, handling high-dimensional data, capturing nonlinear relationships, and accounting for censorship. They provide powerful tools to extract meaningful insights and make accurate predictions in time-to-event analysis across various healthcare, finance, and engineering domains. The standard statistical approaches and machine learning techniques advanced for survival analysis are structured in this unified framework, as is the implementation of some machine learning techniques applying to the GBSG2 survival analysis dataset.

Time Series Analysis in Electrical Load Forecasting

Time series analysis in electricity load projection is a key part of the energy sector because it makes it possible to control and distribute energy more efficiently. It is important to have accurate load forecasts in order to balance supply and demand, make power systems run more efficiently, and lower operating costs. This essay covers a wide range of ways that time series analysis can be used to guess how much electricity will be used. The study looks at a number of different models, such as the autoregressive integrated moving average (ARIMA), exponential smoothing, and machine learning methods like Long Short-Term Memory (LSTM) networks. These models are judged by how well they can show the patterns and time relationships that are common in electricity load data. A lot of attention is paid to the problems that come up because of non-stationarity, timing, and outside factors like weather that cause load changes. The study talks about how feature selection, data pre-processing, and model evaluation can help make forecasts more accurate. The study shows the trade-offs between model interpretability and forecasting power by comparing how well standard statistical methods and new machine learning techniques work. The study also talks about how mixed models, which take the best parts of more than one method and combine them, might help make forecasts more accurate. The results make it clear how important time series analysis is for building accurate load predicting models, which are needed to keep modern power systems reliable and efficient.

Thermal Footprint of the Urbanization Process: Analyzing the Heat Effects of the Urbanization Index (UI) on the Local Climate Zone (LCZ) and Land Surface Temperature (LST) over Two Decades in Seville

Urbanization is a multifaceted process characterized by changes in urban areas through various means, such as sprawl, ribbon development, or infill and compact growth. This phenomenon changes the pattern of the local climate zone (LCZ) and significantly affects the climate, vegetation dynamics, energy consumption, water resources, and public health. This study aims to discern the impacts of changes in urban growth on the LCZ and land surface temperature (LST) over a two-decade period. A comprehensive methodology that integrates statistical analysis, data visualization, machine learning, and advanced techniques, such as remote sensing technology and geospatial analysis systems, is employed. ENVI, GEE, and GIS tools are utilized to collect, process, and monitor satellite data and imagery of temporal and spatial variations in intensive or diffuse urbanization processes from 2003 to 2023 to analyze and simulate land use and land cover (LULC) changes, urbanization index (UI), LCZ patterns, and LST changes over the years and to make overlapping maps of changes to recognize the relation between LULC, LCZ, and LST. This study focuses on Seville’s urban area, which has experienced rapid urbanization and a significant increase in average temperature during the last few decades. The findings of this study will provide actionable recommendations into the interplay between urban growth and climate and highlight the pivotal role of urban growth in shaping resilience and vulnerable areas based on microclimate changes. Urban planners can leverage these insights to predict alternatives for the future development of urban areas and define practical climate mitigation strategies.

Exploring statistical and machine learning methods for modeling probability distribution parameters in downtime length analysis: a paper manufacturing machine case study

Manufacturing companies focus on improving productivity, reducing costs, and aligning performance metrics with strategic objectives. In industries like paper manufacturing, minimizing equipment downtime is essential for maintaining high throughput. Leveraging the extensive data generated by these facilities offers opportunities for gaining competitive advantages through data-driven insights, revealing trends, patterns, and predicting future performance indicators like unplanned downtime length, which is essential in optimizing maintenance and minimizing potential losses. This paper explores statistical and machine learning techniques for modeling downtime length probability distributions and correlation with machine vibration measurements. We proposed a novel framework, employing advanced data-driven techniques like artificial neural networks (ANNs) to estimate parameters of probability distributions governing downtime lengths. Our approach specifically focuses on modeling parameters of these distribution, rather than directly modeling probability density function (PDF) values, as is common in other approaches. Experimental results indicate a significant performance boost, with the proposed method achieving up to 30% superior performance in modeling the distribution of downtime lengths compared to alternative methods. Moreover, this method facilitates unsupervised training, making it suitable for big data repositories of unlabelled data. The framework allows for potential expansion by incorporating additional input variables. In this study, machine vibration velocity measurements are selected for further investigation. The study underscores the potential of advanced data-driven techniques to enables companies to make better-informed decisions regarding their current maintenance practices and to direct improvement programs in industrial settings.

A Proposed Method of Automating Data Processing for Analysing Data Produced from Eye Tracking and Galvanic Skin Response

The use of eye tracking technology, together with other physiological measurements such as psychogalvanic skin response (GSR) and electroencephalographic (EEG) recordings, provides researchers with information about users’ physiological behavioural responses during their learning process in different types of tasks. These devices produce a large volume of data. However, in order to analyse these records, researchers have to process and analyse them using complex statistical and/or machine learning techniques (supervised or unsupervised) that are usually not incorporated into the devices. The objectives of this study were (1) to propose a procedure for processing the extracted data; (2) to address the potential technical challenges and difficulties in processing logs in integrated multichannel technology; and (3) to offer solutions for automating data processing and analysis. A Notebook in Jupyter is proposed with the steps for importing and processing data, as well as for using supervised and unsupervised machine learning algorithms.

Analysis of NBA player salary based on multiple linear regression model

Abstract. This study explores the use of machine learning techniques to predict NBA player salaries. Traditional salary evaluation methods often rely on subjective expert judgment, whereas data-driven approaches can provide more objective and accurate predictions. With the advancement of data analysis techniques and machine learning algorithms, it is now feasible to predict player salaries based on performance data. This study employs advanced statistical and machine learning techniques to analyze detailed player performance data, including points scored, rebounds, assists, steals, and blocks, to establish a data- and algorithm-based salary prediction model. This model can assist team management in making more scientific decisions during contract negotiations and player acquisitions, thereby avoiding the overvaluation or undervaluation of players and achieving a more balanced and fair salary distribution. Accurate salary predictions help teams allocate their limited salary cap more effectively, optimizing budget management and enhancing overall team competitiveness. This study not only demonstrates the practical value of data analysis and machine learning methods in the sports field but also promotes the further development of data science in sports management. Additionally, the results of the prediction model can provide valuable references for fans and media, enhancing their understanding of player salaries and team management strategies. This transparency enriches the overall fan experience and media coverage of the sport, facilitating more informed discussions and debates about player value and team decisions.

Spark: A Statistical Comparison and Evaluation of Classification Algorithms for Fault Prediction in Electrical Secondary Distribution Network

Managing faults in the electrical secondary distribution network is a challenging task given the nature, size, and complexity. Predicting faults early before they occur helps in increasing the safety and reliability of the power distribution system. Various statistical and machine learning techniques are being used to predict different types of faults. This study applies classification algorithms available in the big data framework Apache Spark through its python interface PySpark to predict electrical secondary distribution network faults. The study evaluates and compares nine algorithms: Decision tree, Gradient-boosted tree, Logistic regression, Naïve Bayes, Multilayer perceptron, Random forest, Linear Support Vector Machine, One-versus-rest and Factorization machines. The research uses Friedman’s test followed by the Nemenyi post hoc test to find the significance of performance differences among the algorithms. The results show significant differences among the algorithms. Gradient-boosted tree and One-versus-rest with Gradient-boosted tree had the best performance for binary and multiclass classification, respectively, while Naïve Bayes had the worst performance.

Genetic selection for lung adenocarcinoma: a statistical approach based on pathological genetic data

Lung adenocarcinoma (LUAD) is the most common subtype of non-small cell lung cancer (NSCLC), with high morbidity and mortality worldwide, posing a serious threat to human health. Due to the complex molecular mechanism of lung adenocarcinoma, which involves a variety of genetic and environmental factors, this makes early diagnosis and treatment a major challenge. This research aims to identify the key pathogenic genes of lung adenocarcinoma to solve the challenges in early diagnosis and treatment. In this paper, three differential analysis methods, limma, DESeq2 and edgeR, were used to select 3315 differential genes. Then, combined with Lasso regression and XGboost algorithm, the pathological gene data were analyzed in depth, and through these advanced statistical and machine learning techniques, the genes related to lung adenocarcinoma were screened from a large number of gene expression data, and 17 characteristic genes of the highest importance were found GO enrichment analysis and KEGG enrichment analysis were performed on these characteristic genes to clarify the biological functions of the genes. Finally, 8 significant pathogenic genes were identified by Cox survival analysis. The expression levels of these genes are closely related to the prognosis of lung adenocarcinoma patients, providing a new perspective for understanding the disease mechanism. The conclusions of this study not only improve the understanding of the molecular mechanism of lung adenocarcinoma, but also provide potential biomarkers for clinical diagnosis and treatment. The discovery of these genes is expected to promote the development of early diagnosis technology and guide the formulation of personalized treatment plans, thereby improving the treatment efficacy and quality of life of lung adenocarcinoma patients. In the future, these genes may become key targets for the development of new drugs and therapeutic strategies.

Unlocking Fungal Potential: The CRISPR-Cas System as a Strategy for Secondary Metabolite Discovery.

Natural products (NPs) are crucial for the development of novel antibiotics, anticancer agents, and immunosuppressants. To highlight the ability of fungi to produce structurally diverse NPs, this article focuses on the impact of genome mining and CRISPR-Cas9 technology in uncovering and manipulating the biosynthetic gene clusters (BGCs) responsible for NP synthesis. The CRISPR-Cas9 system, originally identified as a bacterial adaptive immune mechanism, has been adapted for precise genome editing in fungi, enabling targeted modifications, such as gene deletions, insertions, and transcription modulation, without altering the genomic sequence. This review elaborates on various CRISPR-Cas9 systems used in fungi, notably the Streptococcus pyogenes type II Cas9 system, and explores advancements in different Cas proteins for fungal genome editing. This review discusses the methodologies employed in CRISPR-Cas9 genome editing of fungi, including guide RNA design, delivery methods, and verification of edited strains. The application of CRISPR-Cas9 has led to enhanced production of secondary metabolites in filamentous fungi, showcasing the potential of this system in biotechnology, medical mycology, and plant pathology. Moreover, this article emphasizes the integration of multi-omics data (genomics, transcriptomics, proteomics, and metabolomics) to validate CRISPR-Cas9 editing effects in fungi. This comprehensive approach aids in understanding molecular changes, identifying off-target effects, and optimizing the editing protocols. Statistical and machine learning techniques are also crucial for analyzing multi-omics data, enabling the development of predictive models and identification of key molecular pathways affected by CRISPR-Cas9 editing. In conclusion, CRISPR-Cas9 technology is a powerful tool for exploring fungal NPs with the potential to accelerate the discovery of novel bioactive compounds. The integration of CRISPR-Cas9 with multi-omics approaches significantly enhances our ability to understand and manipulate fungal genomes for the production of valuable secondary metabolites and for promising new applications in medicine and industry.

Some notes on the consequences of pretreatment of multivariate data

With the advent of data technologies, we have various types of data, such as structured, unstructured and semi-structured. Performing certain statistical or machine learning techniques may require careful preprocessing or pretreatment of the data to make them suitable for analysis. For example, given a data matrix X, which represents n multivariate observations or cases on p variables or features, the columns/rows of X may be pretreated before applying statistical or machine learning techniques to the data. While centering and/or scaling the variables do not alter the correlation structure nor the graphical representation of the data, centering/scaling the observations do. We investigate various row pretreatment methods more closely and show with theoretical proofs and numerical examples that centering/scaling the rows of X changes both the graphical structure of the observations in the multi-dimensional space and the correlation structure among the variables. There may be good reasons for performing row centering/scaling on the data and we are not against it, but analysts who use such row operations should be aware of the geometrical and correlation structures one has performed on the data and should also demonstrate that the process results in a new, more appropriate structure for their questions.

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).

Incorporating driving behavior into vehicle fuel consumption prediction: methodology development and testing

This study is a significant endeavor involving the development and testing of a comprehensive methodology to incorporate driving behavior into the analysis and prediction of vehicle fuel consumption. It underscores the crucial importance of understanding how different driving behavior affect fuel efficiency. The framework we present is a theoretical construct and a practical tool. It provides a robust, multi-step process for linking driving behavior to fuel consumption, leveraging both traditional statistical methods and advanced machine learning techniques to derive actionable insights. To test the framework, we used a naturalistic data that includes about 5408 different road users in a mixed traffic environment and urban settings in Germany. We applied a microscopic fuel consumption model to calibrate the framework and an unsupervised clustering algorithm to classify the behavior of the driver interacting with each other and with vulnerable road users. The framework includes developing Linear regression model as a baseline, which yields an R-squared of 0.511 and a Mean Squared Error (MSE) of 0.031, indicating moderate predictive accuracy. The final step includes choosing Random Forest as a better model, which achieves a higher R-squared of 0.956 and a lower MSE of 0.003. We also found that conservative and aggressive driving leads to significantly higher and more discrepancy in fuel consumption than normal driving behavior. These insights can promote more efficient driving practices, leading to significant fuel savings and environmental benefits.

Deep Information Retention Network‐Enabled Data Modeling for Key Quality Indicator Prediction in the Chemical Industry

ABSTRACTDeep learning has attracted widespread attention in data modeling and key quality indicator prediction in the chemical industry. However, traditional deep learning networks usually distort the original data distribution due to the superposition effect of multiple layers of nonlinear activation functions. In this case, multivariate statistical learning techniques present an avenue to reveal the intrinsic relationship of the data by combining the linear trends between input and predictor variables. To comprehensively capture data features from multiple perspectives, this study proposes a deep learning‐based data modeling network called the information retention unit (IRU). This network combines intrinsic attributes to partial least squares (PLS) and autoencoder (AE) modalities, thus engendering an adaptive response to the complex linear and nonlinear data features. Furthermore, multiple IRUs can be stacked to construct a deep information retention network (DIRN), which enhances the robust extraction of deep data features. Finally, the effectiveness of the proposed network is validated through its prediction application on a dataset obtained from a real‐world chemical industrial process. This method combines multivariate statistical learning techniques based on deep learning, providing an innovative and practical solution for data analysis and prediction in the chemical industry.

A Survey on Data-Driven Approaches for Reliability, Robustness, and Energy Efficiency in Wireless Body Area Networks

Wireless Body Area Networks (WBANs) are pivotal in health care and wearable technologies, enabling seamless communication between miniature sensors and devices on or within the human body. These biosensors capture critical physiological parameters, ranging from body temperature and blood oxygen levels to real-time electrocardiogram readings. However, WBANs face significant challenges during and after deployment, including energy conservation, security, reliability, and failure vulnerability. Sensor nodes, which are often battery-operated, expend considerable energy during sensing and transmission due to inherent spatiotemporal patterns in biomedical data streams. This paper provides a comprehensive survey of data-driven approaches that address these challenges, focusing on device placement and routing, sampling rate calibration, and the application of machine learning (ML) and statistical learning techniques to enhance network performance. Additionally, we validate three existing models (statistical, ML, and coding-based models) using two real datasets, namely the MIMIC clinical database and biomarkers collected from six subjects with a prototype biosensing device developed by our team. Our findings offer insights into strategies for optimizing energy efficiency while ensuring security and reliability in WBANs. We conclude by outlining future directions to leverage approaches to meet the evolving demands of healthcare applications.

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.

The impact of predictive analytics on financial risk management in businesses

This paper examines the impact of predictive analytics on financial risk management in businesses. Predictive analytics involves the use of statistical algorithms, machine learning, and data mining techniques to analyze historical data and predict future outcomes. In the context of financial risk management, predictive analytics plays a critical role in identifying, assessing, and mitigating potential financial risks. This paper explores various machine learning algorithms, including neural networks, decision trees, and support vector machines, and their applications in risk management. It also discusses data sources, preprocessing techniques, and the challenges associated with data privacy, model interpretability, and prediction accuracy. The review highlights successful implementations of predictive analytics in financial risk management and provides recommendations for future research and practical applications. As predictive analytics continues to advance, its integration with emerging technologies such as artificial intelligence and blockchain promises to enhance financial risk management practices.

COVID-19 from symptoms to prediction: A statistical and machine learning approach

During the COVID-19 pandemic, the analysis of patient data has become a cornerstone for developing effective public health strategies. This study leverages a dataset comprising over 10,000 anonymized patient records from various leading medical institutions to predict COVID-19 patient age groups using a suite of statistical and machine learning techniques. Initially, extensive statistical tests including ANOVA and t-tests were utilized to assess relationships among demographic and symptomatic variables. The study then employed machine learning models such as Decision Tree, Naïve Bayes, KNN, Gradient Boosted Trees, Support Vector Machine, and Random Forest, with rigorous data preprocessing to enhance model accuracy. Further improvements were sought through ensemble methods; bagging, boosting, and stacking. Our findings indicate strong associations between key symptoms and patient age groups, with ensemble methods significantly enhancing model accuracy. Specifically, stacking applied with random forest as a meta leaner exhibited the highest accuracy (0.7054). In addition, the implementation of stacking techniques notably improved the performance of K-Nearest Neighbors (from 0.529 to 0.63) and Naïve Bayes (from 0.554 to 0.622) and demonstrated the most successful prediction method. The study aimed to understand the number of symptoms identified in COVID-19 patients and their association with different age groups. The results can assist doctors and higher authorities in improving treatment strategies. Additionally, several decision-making techniques can be applied during pandemic, tailored to specific age groups, such as resource allocation, medicine availability, vaccine development, and treatment strategies. The integration of these predictive models into clinical settings could support real-time public health responses and targeted intervention strategies.

Development, study, and comparison of models of cross-immunity to the influenza virus using statistical methods and machine learning.

The World Health Organization considers the values of antibody titers in the hemagglutination inhibition assay as one of the most important criteria for assessing successful vaccination. Mathematical modeling of cross-immunity allows for identification on a real-time basis of new antigenic variants, which is of paramount importance for human health. This study uses statistical methods and machine learning techniques from simple to complex: logistic regression model, random forest method, and gradient boosting. The calculations used the AAindex matrices in parallel to the Hamming distance. The calculations were carried out with different types and values of antigenic escape thresholds, on four data sets. The results were compared using common binary classification metrics. Significant differentiation is shown depending on the data sets used. The best results were demonstrated by all three models for the forecast autumn season of 2022, which were preliminary trained on the February season of the same year (Auroc 0.934; 0.958; 0.956, respectively). The lowest results were obtained for the entire forecast year 2023, they were set up on data from two seasons of 2022 (Aucroc 0.614; 0.658; 0.775). The dependence of the results on the types of thresholds used and their values turned out to be insignificant. The additional use of AAindex matrices did not significantly improve the results of the models without introducing significant deterioration. More complex models show better results. When developing cross-immunity models, testing on a variety of data sets is important to make strong claims about their prognostic robustness.

Predicting time to cracking of concrete composites under restrained shrinkage: A review with insights from statistical analysis and ensemble machine learning approaches

Restrained shrinkage cracking significantly undermines the performance of reinforced concrete and shortens the structures' lifespan. Standard methods have been established to examine restrained shrinkage cracking of cementitious composites, i.e., ASTM C1581, AASHTO T 334, AASHTO T 363, and RILEM TC 119-TCE. Deficiencies in testing methods for accommodating and evaluating different cementitious composites have been recognized. Nevertheless, the significance of the restrained shrinkage cracking factors and cracking vulnerability based on the degree of restraint provided by different testing methods remain unexplored. This article provides a critical review of testing methods and studies on restrained shrinkage cracking in cementitious composites, highlighting the limitations, advantages, and further capabilities. Comprehensive experimental test datasets associated with standard restrained shrinkage cracking test methods are compiled. Advanced statistical analysis and machine learning (ML) techniques are utilized to predict time-to-cracking (TTC) of cementitious composites subjected to various testing methods based on the cracking factors. Robust and precise ML's bagging and boosting algorithms such as random forest, gradient boosting machine, extreme gradient boosting, adaptive boosting, categorical gradient boosting, and stacking ensemble models are utilized to merge predictions of the various approaches on TTC. Despite the satisfactory performance of statistical modeling, stacking demonstrates the highest precision in forecasting TTC, achieving an R2 of 0.92 for the ASTM dataset and 0.65 for the AASHTO dataset. The derived statistical and ML models reveal the significance of drying shrinkage, binder content, and moist curing as the most important factors in TTC based on ASTM C1581 and AASHTO T 334 standard testing methods. Equations are derived to predict cracking vulnerability and design concrete composites that offer delayed TTC and prolonged service life.

Utilizing machine learning to forecast mechanical characteristics of NaOH-Treated jute fiber reinforced composite materials

The prediction of mechanical properties in composite materials is crucial for optimizing their performance in various engineering applications. This study focuses on NaOH treated jute fiber reinforced glass epoxy composites, aiming to predict key mechanical characteristics like flexural strength, tensile strength, and the hardness. A comprehensive dataset of 974 samples was analyzed, encompassing a range of input parameters including fiber content, fiber orientation, matrix type, and processing conditions. Advanced statistical and machine learning techniques were employed to develop predictive models, with XGBoost showing itself to be the best model in terms of predicting each of the three mechanical properties. Feature importance analysis revealed that fiber content is the most significant factor influencing the predictions.