Vector Regression Research Articles

Factors Inducing Cutaneous Adverse Reactions in Cancer Patients Treated with PD-1 and PD-L1 Inhibitors: A Machine-Learning Algorithm Approach

Immune checkpoint inhibitors (ICIs) show promise in cancer treatment but can lead to immune-related adverse events (irAEs), notably affecting the skin. Understanding the factors behind these skin reactions is crucial for effective management during treatment. Hence, the aim of this study was to uncover associations between patient characteristics and cutaneous adverse reactions among cancer patients undergoing ICI treatment. The study involved 209 cancer patients receiving ICIs. Statistical methods, including the chi-square test, Fisher's exact test, and multivariable logistic regression, were employed to analyze variables such as hypertension, antihistamine use, cancer metastasis, diabetes, and opioid usage. Additionally, machine learning techniques, including logistic regression, elastic net, random forest, and support vector machines (SVM), were utilized to develop predictive models anticipating skin-related adverse events. Results highlighted significant associations between specific patient attributes and the incidence of skin reactions post-ICI treatment. Notably, patients using antihistamines or with cancer metastasis exhibited higher rates of skin adverse reactions, while those with diabetes or using opioids displayed lower incidence rates. Robust performance in forecasting these adverse events was observed, particularly in the predictive models employing logistic regression and elastic net. This pioneering study contributes crucial insights into predictive modeling for ICI-induced skin reactions, emphasizing the importance of personalized treatment strategies. By identifying risk factors and utilizing tailored predictive models, healthcare providers can proactively manage adverse events, optimizing the benefits of ICIs while mitigating potential side effects.

AI-Powered Geotechnics: Enhancing Rock Mass Classification for Safer Engineering Practices

AbstractRock mass classification is fundamental for evaluating rock mass quality, essential for stability analysis and geotechnical design. Traditional classification methods are limited by joint observation technology, which typically gathers joint information from one-dimensional or two-dimensional perspectives, failing to comprehensively capture three-dimensional joint occurrences. This often necessitates empirical formulas for joint distribution, resulting in less precise joint parameter calculations. This paper reviews 44 seminal articles on rock engineering classification in construction and subterranean projects, tracing the evolution from foundational methods like Rock Quality Designation, Rock Mass Rating, Q-system, Basic Quality, and Hydropower Classification to contemporary techniques. It highlights the transformative impact of data science, particularly artificial intelligence, on rock engineering. The analysis reveals 73 distinct algorithms used 162 times in literature, with Support Vector Machines Support, Vector Regression, K-means clustering, K-Nearest Neighbors, Artificial Neural Networks and Random Forest being the most successful. This paper examines each method's advantage and limitations, discussing the challenges of algorithm deployment in the scientific community. The findings underscore the integration of machine learning and meta-heuristic optimization methods in rock engineering classification, offering valuable insights for future research and applications.

Novel statistically equivalent signature-based hybrid feature selection and ensemble deep learning LSTM and GRU for chronic kidney disease classification

Chronic kidney disease (CKD) involves numerous variables, but only a few significantly impact the classification task. The statistically equivalent signature (SES) method, inspired by constraint-based learning of Bayesian networks, is employed to identify essential features in CKD. Unlike conventional feature selection methods, which typically focus on a single set of features with the highest predictive potential, the SES method can identify multiple predictive feature subsets with similar performance. However, most feature selection (FS) classifiers perform suboptimally with strongly correlated data. The FS approach faces challenges in identifying crucial features and selecting the most effective classifier, particularly in high-dimensional data. This study proposes using the Least Absolute Shrinkage and Selection Operator (LASSO) in conjunction with the SES method for feature selection in CKD identification. Following this, an ensemble deep-learning model combining long short-term memory (LSTM) and gated recurrent unit (GRU) networks is proposed for CKD classification. The features selected by the hybrid feature selection method are fed into the ensemble deep-learning model. The model’s performance is evaluated using accuracy, precision, recall, and F1 score metrics. The experimental results are compared with individual classifiers, including decision tree (DT), Random Forest (RF), logistic regression (LR), and support vector machine (SVM). The findings indicate a 2% improvement in classification accuracy when using the proposed hybrid feature selection method combined with the LSTM and GRU ensemble deep-learning model. Further analysis reveals that certain features, such as HEMO, POT, bacteria, and coronary artery disease, contribute minimally to the classification task. Future research could explore additional feature selection methods, including dynamic feature selection that adapts to evolving datasets and incorporates clinical knowledge to enhance CKD classification accuracy further.

NIMG-02. DEVELOPING A RADIOMIC HIERARCHICAL GAUSSIAN PROCESS BOOSTING MODEL TO PREDICT PRIMARY TUMOR ORIGIN FROM MULTICENTRIC LONGITUDINAL MRI DATA OF BRAIN METASTASES

Abstract Focal neurologic deficits due to brain metastases might be the initial presentation in patients with cancer. Common approaches to investigate the occult primary malignancy include a whole-body PET-CT, whole-body MRI, studying tumor markers, or histopathological examination. Most of these modalities are expensive, time-consuming, invasive, and delay treatment. The field of radiomics leverages quantitative features extracted from images to improve the decision-making process in clinical practices. Although not easily understandable, these features are proxies for the tumor’s shape, contour, texture, and intensity patterns. They can help understand tumor heterogeneity, predict tumor behavior, and assess treatment response. We propose a robust radiomic workflow using longitudinal MRI data from 914 high-resolution imaging studies from 12 different centers (Ocaña-Tienda et al. (2023), Ramakrishnan et al. (2023), Wang et al. (2023)) to predict the origin of brain metastases from brain MRI scans. After using ensemble feature selection methods, we trained three fixed-effects and one mixed-effects multiclass classification model to account for longitudinal data. Fixed-effects logistic regression and support vector kernel models performed the worst (AUC 0.74 and 0.75, respectively), while the random forest performed better (AUC 0.97). The mixed-effects hierarchical Gaussian process boosting (GPBoost) model performed the best with an accuracy of 85.8%, precision of 85.4%, sensitivity of 85.8%, specificity of 95.7%, and an AUC of 0.98. In one-versus-rest classification, the GPBoost model identified the primary tumor as melanoma with the highest accuracy (96.1%) and non-small cell lung cancer with the lowest accuracy (89.0%). Developing such models holds great promise in reducing patient and institutional costs, improving time to effective treatment, and enhancing overall survival rates through personalized therapy approaches. In the future, we hope that incorporating newer patient data and refining the model to improve external validity would enable more accurate and generalizable predictions, leading to better clinical outcomes across diverse populations.

QLTI-07. COLLABORATIVE RESEARCH SUITE FOR GENOMIC ANALYSIS, DATA REPORTING AND WORKFLOW CUSTOMISATION

Abstract The genomic analysis pipeline involves multiple stages, including data extraction, transformation, and loading (ETL), exploratory data analysis (EDA), machine learning (ML) modeling, and reporting. The ETL stage involves data profiling and quality control measures to ensure data integrity and consistency. The EDA stage employs statistical and visualization methods to understand data distribution, identify patterns, and detect anomalies. Machine learning modelling involves supervised classification techniques, such as logistic regression and support vector machines (SVMs), to predict tumour classification and develop gene signatures. Unsupervised classification techniques, such as K-means clustering and Hierarchical clustering, identify patterns and relationships in genomic data. Quality metrics evaluate data completeness, accuracy, and consistency, ensuring data reliability and validity. The integration of data science techniques into a comprehensive framework can be achieved with the development of Application Dashboards that provide real-time insights into genomic data across every stage of the analysis pipeline. This enables clinical researchers and bioinformaticians to make informed decisions quickly, improving turn-around time and accelerating the discovery of new insights. In contrast to conventional methods of using stand-alone scripts, these dashboards offer a reusable and scalable solution, allowing for easy modification and adaptation to new datasets and analysis pipelines, thereby reducing development effort and increasing productivity. The dashboards constitute a centralized platform for data visualization, exploration, and analysis, facilitating collaboration and communication among research team members. With customizable and interactive visualizations, users can explore genomic data from multiple dimensions and the integration of multiple sources, including genomic and transcriptomic data. The technologies used to power this Research suite include Streamlit for Web App development, Python for data analysis, Opensearch for data storage and other utility libraries for reporting.

Improving Rainfall Prediction Accuracy in the USA Using Advanced Machine Learning Techniques

The key aim of this research project is to design and evaluate advanced machine learning models for increasing accuracy in rainfall forecasting over the USA. We intended to investigate nonlinear relationships typical of the atmospheric variables using state-of-the-art ML methods for more accurate rainfall predictions. For this research project on rainfall forecasting in the USA, we utilized an extensive dataset that comprises historical rainfall data collected from the National Oceanic and Atmospheric Administration (NOAA) and other meteorological agencies. The main dataset we use in this paper consists of daily rainfall measurements across various geographical locations of the USA, thus capturing the wide-ranging historical data necessary for both training and validation of the model. Besides measuring rainfall, we included meteorological data from sources such as NOAA's Global Historical Climatology Network and NASA's Modern-Era Retrospective Analysis for Research and Applications. These datasets further provided key variables that are known to affect rain, including temperature, humidity, wind speed, and atmospheric pressure. The performance metrics used in this research work for the models considered include accuracy, precision, recall, and F1 score. The above table shows that the Random Forest Classifier outperformed the other models, achieving perfect accuracy. That indicated that it rightly classified all the instances in the test set. The Logistic Regression and Support Vector Machine models gave a quite good performance by giving above average accuracy but had lower precision and recall for the rainfall prediction. Accurate rainfall forecasting has direct consequences on agriculture, greatly empowering farmers and agricultural planners to make more effective decisions regarding planting, harvesting, and crop management. The forecasts of rainfall are also of critical importance in disaster management regarding planning for flood emergencies. Moreover, precise forecasting of rainfall, particularly in sustainable water resources management, presents the most important data in planning for and conserving these resources.

Machine learning-based rational design for efficient discovery of allatostatin analogs as promising lead candidates for novel IGRs.

Insect neuropeptide allatostatins (ASTs) play a vital role in regulating insect growth, development, and reproduction, making them potential candidates for new insect growth regulators (IGRs). However, the practical use of natural ASTs in pest management is constrained by their long sequences and high production costs, thus the development of AST analogs with shorter sequences and reduced cost is essential. Traditional methods for designing AST analogs are often time-consuming and resource-intensive. This study aims to employ new computational methodologies to understand the structure-activity relationship and efficiently discover potent AST analogs. Two machine learning models, utilizing multiple linear regression and support vector machine, were constructed to reveal the key structural factors that influence the juvenile hormone-inhibiting activity of AST analogs. These models suggested that a potent AST analog should contain styrene, hydrophilic, and aromatic groups, and rotatable bonds at positions 1, 2, 3, and 4, respectively. Six analogs (A52-A57) were designed and synthesized, and they exhibited potent juvenile hormone-inhibiting activity (IC50 < 16 nM). Notably, analog A53 showed the best activity (IC50 = 2.07 nM), surpassing that of most natural Dippu-ASTs, making it a potential lead candidate for IGRs. These models promote the efficient design, screening, and prioritization of new or untested AST analogs. The study clarifies how a machine learning-based strategy facilitates the development of AST analogs as novel IGR lead candidates, offering a useful reference for pest management. © 2024 Society of Chemical Industry.

Exploiting EEG to identify confused students in online learning: A machine learning model comparison

Abstract. The COVID-19 pandemic has forced most schools, including universities, to adopt online courses for teaching. Due to the breaking of the constraints of time and space, online courses still occupy a large proportion in education until now, and large-scale open online education courses will become a major trend in the future. Of course, problems also arise in this process. As teachers cannot receive feedback from students anytime and anywhere in online courses, such as micro expressions, body movements, etc., they cannot know whether students are confused. Therefore, how to effectively detect students' learning status has grown in popularity. In the last few years, machine learning has developed rapidly, and a large number of artificial intelligence have emerged, making it possible to detect whether students are confused by combining electroencephalography with machine learning. In order to determine whether students were confused, this study used a wireless single channel Mindset device to collect Electroencephalography (EEG) signals. Six machine learning modelsrandom forests, eXtreme Gradient boosting, K-nearest neighbors, gradient boosting machines, logistic regression, and support vector machineswere then chosen. The findings indicate that other machine learning models have a high accuracy rate in classifying students' bewilderment, with the exception of the logistic regression model. With a 99.69% accuracy rate, the eXtreme gradient boosting model performs better than a number of other models.

Experimental and modelling analysis of waste material-based geopolymer concrete incorporated with crumb rubber particles

Rubberized geopolymer concrete (RuGPC) emerges as an eco-friendly alternative to conventional concrete, significantly reducing greenhouse gas emissions. This study investigates the use of steel slag (SS) in varying proportions (30 %, 35 %, and 40 %) as a replacement for ground granulated blast furnace slag (GGBS) in geopolymer concrete, with crumb rubber (CR) replacing crusher dust (CD) as fine aggregate due to its increasing demand. The research focuses on understanding the impact of aluminosilicate materials on the mechanical, thermal, and microstructural properties of geopolymer concrete cured at 60°C. Advanced characterization techniques, including Scanning Electron Microscopy (SEM), Energy-Dispersive X-ray Spectroscopy (EDX), X-ray Diffraction (XRD), and Fourier Transform Infrared Spectroscopy (FTIR), were employed. SEM and EDX analyses revealed that the microstructural properties of GGBS and SS materials, mainly Na/Si, Si/Al, H₂O/Na₂O, and Na/Al ratios, significantly influence RuGPC performance through gel formation. FTIR analysis indicates a shift in the stretching vibrations of GGBS and SS to lower wavenumbers due to geopolymerization changes. XRD results show the formation of C-S-H gel at around 27–30° 2theta, attributed to increased GGBS and SS content. Despite efforts to incorporate CR into geopolymer matrices, challenges in mitigating strength degradation persist. To address this, a predictive model was developed to understand the key factors affecting RuGPC performance. Six machine learning techniques—M5P (pruned and unpruned), random forest, random tree, linear regression, and support vector machine with various kernels (PUK, RBF, PK, and NPK), and artificial neural network (ANN)—were employed to predict the physical and thermal behavior of RuGPC. The analysis identified ANN-based models as the most effective. Sensitivity analysis highlighted the grade of rubber and the CR replacement percentage by volume of CD as the most influential parameters determining RuGPC compressive strength, density, and thermal conductivity. Moreover, The economic analysis revealed that RuGPC mixtures were 1.2–11.61 % more cost-effective than OPC concrete. These findings underscore the importance of predictive model development in optimizing RuGPC properties for practical applications, offering valuable insights for decision-making processes.

Characteristics of Machine Learning-based Univariate Time Series Imputation Method

Handling missing values in univariate time series analysis poses a challenge, potentially leading to inaccurate conclusions, especially with frequently occurring consecutive missing values. Machine Learning-based Univariate Time Series Imputation (MLBUI) methods, utilizing Random Forest Regression (RFR) and Support Vector Regression (SVR), aim to address this challenge. Considering factors such as time series patterns, missing data patterns, and volume, this study explores the performance of MLBUI in simulated Autoregressive Integrated Moving Average (ARIMA) datasets. Various missing data scenarios (6%, 10%, and 14%) and model scenarios (Autoregressive (AR) models: AR(1) and AR(2); Moving Average (MA) models: MA(1) and MA(2); Autoregressive Moving Average (ARMA) models: ARMA(1,1) and ARMA(2,2); and Autoregressive Integrated Moving Average (ARIMA) models: ARIMA(1,1,1) and ARIMA(1,2,1)) with different standard deviations (0.5, 1, and 2) were examined. Five comparative methods were also used in this research, including Kalman StructTS, Kalman Auto-ARIMA, Spline Interpolation, Stine Interpolation, and Moving Average. The research findings indicate that MLBUI performs exceptionally well in imputing successive missing values. The results of this study indicate that the performance of MLBUI in imputing consecutive missing values, based on MAPE, yielded values of less than 10% across all scenarios used.

Assessing groundwater quality in the northwestern coastal area of Sri Lanka using multivariate statistical techniques

The objective of the present study was to assess groundwater quality in the northwestern coastal region of Sri Lanka by analyzing hydrogeochemical data using multivariate techniques. The study examined the relationship between water quality and sources influencing groundwater quality and proposed useful statistical tools for water resource management. Descriptive, comparative, correlation, factor analysis (FA), and discriminant analysis (DA) were among the techniques used. The water quality in terms of electrical conductivity (EC), total dissolved solids (TDS), and dissolved nitrate and phosphate concentrations of the northwestern coastal area, where different aquifer conditions prevailed, were compared, and differences in the mean concentrations of the above parameters were identified. The study also employed ridge regression and support vector machines (SVM) to predict nitrate levels and validate the results using a 70:30 train/test split. The analysis found that the mean concentrations of EC, TDS, and HCO3- are higher in the sandy aquifer area, while Fe2+ and PO43- are higher in the regolith aquifer area. EC, TDS, PO43-, and HCO3- in the hard-rock aquifer area exceed permissible limits. Factor analysis identified four factors contributing to pollution, and a linear discriminant model classified all observations with 99.9% accuracy. The water quality index for Kalpitiya, Vanathavillu, and Katana-Negombo areas was 68.1, 99.2, and 287.9, respectively, while the World Health Organization (WHO) cutoff was 50. The use of multivariate statistical techniques demonstrated the value of analyzing hydrogeochemical data to gain valuable insights into the complex interplay of factors affecting groundwater quality. The SVM model, using a linear kernel, was identified as the best model to predict nitrate levels. A combination of statistical analyses reveals that, with the exclusion of a few wells, the groundwater in the study area is polluted and inappropriate for human consumption or culinary purposes. Nonetheless, the inhabitants persist in utilizing it as their primary source of drinking water. This study reveals the combination of statistical analyses is useful for the management of groundwater resources.

How Can Machine Learning Contribute to the Credit Scoring Process in SME Lending?

This research investigates the potential of machine learning to enhance the credit scoring process in small and medium-sized enterprise (SME) lending. SMEs are vital to global economies, accounting for over 90\% of businesses and more than half of total employment worldwide, according to The World Bank (2023). In emerging economies, SME lending is particularly crucial, providing access to capital that supports economic growth and development. However, assessing the credit risk of SMEs poses unique challenges due to limited financial histories and variable cash flows, making accurate credit scoring essential for lenders. Machine learning offers promising solutions for the risk assessment process in SME lending, leveraging algorithms and large datasets to identify patterns and improve decision-making. By applying techniques such as artificial neural networks, decision tree learning, gradient boosting, logistic regression, random forest, and support vector machines, machine learning can enhance the accuracy and efficiency of credit scoring models. This research explores how these machine learning methods can reduce biases, improve risk prediction, and ultimately support sustainable lending practices by enabling lenders to make more informed credit decisions. The findings aim to illustrate the transformative potential of machine learning in SME credit scoring, offering a framework for financial institutions seeking to integrate advanced data-driven technologies in the credit assessment process.

Comparing Feature and Trajectory-Based Remaining Useful Life Modeling of Electrical Resistance Heating Wires

Industrial heating significantly contributes to global greenhouse gas emissions, accounting for a substantial portion of annual emissions. The transition to fossil-free operations in the heating industry is closely linked to advancements in industrial electrical heating systems, especially those using resistance heating wires. In this context, Prognostics and Health Management is crucial for enhancing system reliability and sustainability through predictive maintenance strategies. The integration of machine learning technologies into Prognostics and Health Management has significantly improved the precision and applicability of Remaining Useful Life modeling. This improvement enables more accurate predictions of component lifespans, optimizes maintenance schedules, and enhances operational efficiency in industrial heating applications. These developments are essential for reducing greenhouse gas emissions in the sector. This paper serves as a guide for conducting Remaining Useful Life modeling for industrial batch processes. It evaluates and compares two methodologies: deep learning-based approaches using full time-series data, such as recurrent neural networks and their variants, and feature-engineering-based methods, including random forest regression and support vector machines. Our results show that the feature-oriented approach performs better overall in terms of predictive accuracy and computational efficiency. The study includes a detailed sensitivity analysis and hyperparameter estimation for each method, providing valuable insights into developing robust and transparent Prognostics and Health Management systems. These systems are crucial in supporting the heating industry’s move towards more sustainable and emission-free operations. The findings reveal that feature-oriented methods are both performant and robust, particularly excelling in handling outliers. The random forest regression model, in particular, demonstrated the highest performance on the test dataset according to the chosen evaluation metrics. Conversely, trajectory-oriented methods exhibited less bias across varying levels of degradation, a helpful characteristic for Prognostics and Health Management systems. While feature-oriented methods tend to systematically underestimate Remaining Useful Life at high true values and overestimate it at low actual values, this issue is less pronounced in trajectory-oriented models. Overall, these insights highlight the strengths and limitations of each approach, guiding the development of more effective and reliable predictive maintenance strategies.

Electroencephalogram Emotion Recognition via AUC Maximization

Imbalanced datasets pose significant challenges in areas including neuroscience, cognitive science, and medical diagnostics, where accurately detecting minority classes is essential for robust model performance. This study addressed the issue of class imbalance, using the ‘liking’ label in the DEAP dataset as an example. Such imbalances were often overlooked by prior research, which typically focused on the more balanced arousal and valence labels and predominantly used accuracy metrics to measure model performance. To tackle this issue, we adopted numerical optimization techniques aimed at maximizing the area under the curve (AUC), thus enhancing the detection of underrepresented classes. Our approach, which began with a linear classifier, was compared against traditional linear classifiers, including logistic regression and support vector machines (SVMs). Our method significantly outperformed these models, increasing recall from 41.6% to 79.7% and improving the F1-score from 0.506 to 0.632. These results underscore the effectiveness of AUC maximization methods in neuroscience research by offering a robust solution for managing imbalanced datasets, developing more precise diagnostic tools and interventions for detecting critical minority classes in real-world scenarios.

Factors affected housing prices: taking Boston as an example

Abstract. Real estate price prediction plays a vital role in urban planning, investment decision-making, and risk management. However, existing prediction models often show problems such as insufficient generalization ability and susceptibility to outliers when faced with complex nonlinear relationships, multidimensional features, and noisy data. Therefore, choosing a model that can accurately capture complex patterns and has strong robustness has become the focus of research. This paper introduces the random forest model and compares it with multivariate linear regression, XGBoost, and support vector machine (SVM). Compared with the traditional regression model, the random forest model combines the flexibility of decision trees and the multi-level feature extraction ability of deep learning, and can better handle the complex nonlinear relationships in the Boston housing price dataset. The experimental results show that the random forest model has achieved excellent performance in all evaluation indicators, and the model accuracy indicators are distributed as MSE=8.2502, RMSE=2.8723, MAE=2.0668, and R^2=0.8875. These results show that the random forest model not only outperforms other models in prediction accuracy but also shows significant advantages in dealing with data complexity and improving generalization ability. Therefore, the random forest model provides an efficient and reliable tool for future real estate price prediction research and applications.

Prediction of Postoperative Mechanical Complications in ASD Patients Based on Total Sequence and Proportional Score of Spinal Sagittal Plane

This article aimed to predict the occurrence of postoperative mechanical complications in adult spinal deformity (ASD) patients through the total sequence and proportional score of the spinal sagittal plane, to improve the quality of life of patients after surgery. The study adopted a comprehensive evaluation and data analysis method, including data collection and preprocessing, feature selection, model construction and training, and constructed a prediction model based on the Random Forest (RF) algorithm. The experimental results showed that the model significantly reduced the risk of complications in randomized controlled trials. The incidence of mechanical complications in the experimental group was 10%, while that in the control group was 25%, with statistical significance (P<0.05). In addition, in retrospective data analysis, the accuracy of the article's model on five datasets ranged from 89% to 93%, outperforming logistic regression and support vector machine models, and performing well on other performance data. In prospective studies, the model's predictions showed good consistency with the actual occurrence of complications. Sensitivity analysis shows that the model has low sensitivity to changes in key parameters and exhibits stability, indicating that the model proposed in this article is suitable for uncertain medical environments. The expert rating further confirmed the effectiveness and practicality of the model in predicting postoperative mechanical complications in ASD patients, with the highest score reaching 4.9. These data demonstrate the high accuracy and clinical potential of the model in predicting postoperative complications of ASD.

Deep learning for prediction and classifying the dynamical behaviour of piecewise-smooth maps

This paper explores novel ways of predicting and classifying the dynamics of piecewise smooth maps using various deep learning models. Moreover, we have used machine learning models such as Decision Tree Classifier, Logistic Regression, K-Nearest Neighbor, Random Forest, and Support Vector Machine for predicting the border collision bifurcation in the 1D normal form map and the 1D tent map. The decision tree classifier best predicts the border collision bifurcation for the 1D normal form map, the random forest, and the 1D tent map. This study introduces a novel application of deep learning models to cobweb diagrams and phase portraits, which provides a new perspective for classifying regular and chaotic behaviour. Further, we classified the regular and chaotic behaviour of the 1D tent map and the 2D Lozi map using deep learning models like Convolutional Neural Network (CNN), ResNet50, and ConvLSTM via cobweb diagram and phase portraits, where CNN exhibits better performance than other models. We also classified the chaotic and hyperchaotic behaviour of the 3D piecewise smooth map using deep learning models such as the Feed Forward Neural Network (FNN), Long Short-Term Memory (LSTM), and Recurrent Neural Network (RNN). We have shown that LSTM performs best for classifying chaotic and hyperchaotic behaviour. Additionally, LSTM outperforms other models in accuracy and computational efficiency, making it highly effective for real-time analysis. Finally, deep learning models such as Long Short Term Memory (LSTM) and Recurrent Neural Network (RNN) are used for reconstructing the two-parameter bifurcation charts of 2D normal form map, in which LSTM is more precise than RNN in reconstructing the two-parametric charts.

Bayesian additive regression trees for predicting childhood asthma in the CHILD cohort study

BackgroundAsthma is a heterogeneous disease that affects millions of children and adults. There is a lack of objective gold standard diagnosis that spans the ages; instead, diagnoses are made by clinician assessment based on a cluster of signs, symptoms and objective tests dependent on age. Yet, there is a clear morbidity associated with chronic asthma symptoms. Machine learning has become a popular tool to improve asthma diagnosis and classification. There is a paucity of literature on the use of Bayesian machine learning algorithms to predict asthma diagnosis in children. This paper develops a prediction model using the Bayesian additive regression trees (BART) and compares its performance to various machine learning algorithms in predicting the diagnosis of childhood asthma.MethodsClinically relevant variables collected at or before 3 years of age from 2794 participants in the CHILD Cohort Study were used to predict physician-diagnosed asthma at age 5. BART and six other commonly used machine learning algorithms, namely adaptive boosting, logistic regression, decision tree, neural network, random forest, and support vector machine were trained. Measures of performance including sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve were calculated. The confidence intervals were calculated using Bootstrapping samples. Important predictors and interaction effects associated with asthma were also identified using BART.ResultsBART, logistic regression and random forest showed the highest area under the ROC curve compared to other machine learning algorithms. Based on BART, recurrent wheeze, respiratory infection and food sensitization at 3 years of age were the most important predictors. The three most important interaction effects were found to be interaction terms of respiratory infection at 3 years and recurrent wheezing at 3 years, maternal asthma and paternal asthma, and maternal wheezing and inhalant sensitization of child at 3 years.ConclusionsBART demonstrated promising prediction performance when compared to other machine learning algorithms. Future research could validate the BART in an external cohort to evaluate its reliability and generalizability.

주식시장 수익률과 개인 투자자의 매매 성향

This study examines the relationship between individual investors and the KOSPI stock market using long-term data spanning 25 years from 1999 to 2023. However, this study analyzes the relationship between individual investors' net buys and KOSPI returns by dividing the entire period into five sun-periods of five years and applying two-sided regression and structural vector autoregressive (SVAR) models. The main findings are as follows: First, compared to foreign investors, both institutional and individual investors exhibit relatively higher turnover ratios. Second, cross-sectional analysis shows that KOSPI returns decrease monotonically with the individuals' net buys. Third, the results of the two-sided regressions indicate a Granger causality, where past returns negatively influence individual investors' net buys. In addition, today's individual net buys negatively Granger cause future returns. Fourth, the SVAR analysis also shows that KOSPI returns have a strong negative effect on individual net buys. Finally, according to the results of SVAR impulse response function, net buys response negatively to KOSPI shocks, and this response dissipates almost entirely by the third day. In summary, individual investors tend to engage in net selling in response to positive news in the KOSPI market, and this tendency may be a key reason for their lower performance.

Non-Linear Saturated Multi-Objective Pseudo-Screening Using Support Vector Machine Learning, Pareto Front, and Belief Functions: Improving Wastewater Recycling Quality

Increasing wastewater treatment efficiency is a primary aim in the circular economy. Wastewater physicochemical and biochemical processes are quite complex, often requiring a combination of statistical and machine learning tools to empirically model them. Since wastewater treatment plants are large-scale operations, the limited opportunities for extensive experimentation may be offset by miniaturizing experimental schemes through the use of fractional factorial designs (FFDs). A recycling quality improvement study that relies on non-linear multi-objective multi-parameter FFD (NMMFFD) datasets was reanalyzed. A published NMMFFD ultrafiltration screening/optimization case study was re-examined regarding how four controlling factors affected three paper mill recycling characteristic responses using a combination of statistical and machine learning methods. Comparative machine learning screening predictions were provided by (1) quadratic support vector regression and (2) optimizable support vector regression, in contrast to quadratic linear regression. NMMFFD optimization was performed by employing Pareto fronts. Pseudo-screening was applied by decomposing the replicated NMMFFD dataset to single replicates and then testing their replicate repeatability by introducing belief functions that sought to maximize credibility and plausibility estimates. Various versions of belief functions were considered, since the novel role of the three process characteristics, as independent sources, created a high level of conflict during the information fusion phase, due to the inherent divergent belief structures. Correlations between two characteristics, but with opposite goals, may also have contributed to the source conflict. The active effects for the NMMFFD dataset were found to be the transmembrane pressure and the molecular weight cut-off. The modified adjustment was pinpointed to the molecular weight cut-off at 50 kDa, while the optimal transmembrane pressure setting persisted at 2.0 bar. This mixed-methods approach may provide additional confidence in determining improved recycling process adjustments. It would be interesting to implement this approach in polyfactorial wastewater screenings with a greater number of process characteristics.