Cross-validation Technique Research Articles

Evaluation of the Changes in the Strength of Clay Reinforced with Basalt Fiber Using Artificial Neural Network Model

In this research, the impact of basalt fiber reinforcement on the unconfined compressive strength of clay soils was experimentally analyzed, and the collected data were utilized in an artificial neural network (ANN) to predict the unconfined compressive strength based on the basalt fiber reinforcement ratio and length. For this purpose, two different lengths of basalt fiber (6 mm and 12 mm) were added to unreinforced bentonite clay at ratios of 0%, 1%, 2%, 3%, 4%, and 5%, and unconfined compressive tests were performed on the prepared reinforced clay samples to determine the unconfined compressive strength (qu) values. The evaluation of the obtained experimental results was carried out by creating ANN models. To validate the prediction capabilities of the ANN, a comparative analysis was performed using linear regression, support vector machines, and Gaussian process regression models. Ultimately, a five-fold cross-validation technique was employed to objectively evaluate the overall performance of the model. The evaluations revealed that the ANN model predictions using data obtained from experimental studies showed the highest accuracy and were in close agreement with the experimental results.

Water quality estimates using machine learning techniques in an experimental watershed

ABSTRACT Estimation of the water quality parameters is important to enhance time and cost-effectiveness to that of the conventional approach. This study is aimed to identify the best machine learning (ML) approach to predict concentrations of biochemical oxygen demand (BOD), nitrate, and phosphate. Four ML techniques including decision tree, random forest, gradient boosting, and XGBoost were compared to estimate the water quality parameters based on biophysical (i.e., population, basin area, river slope, water level, and stream flow) and physicochemical properties (i.e., conductivity, turbidity, pH, temperature, and dissolved oxygen) as input parameters. The data were split into training and test sets, and the model performances were evaluated using coefficient of determination (R2), Nash–Sutcliffe efficiency coefficient (NSE), and root mean squared error (RMSE). The mean squared error (MSE) was used as the optimization target. The robust fivefold cross-validation, along with hyperparameter tuning, achieved R2 values of 0.76, 0.67, and 0.71 for phosphate, nitrate, and BOD, and NSE values of 0.73, 0.67, and 0.66, respectively. XGBoost yielded the lowest RMSE across all parameters, showcasing superior performance when considering all metrics performed. In conclusion, ML techniques, particularly with a robust cross-validation technique and hyperparameter optimization, showed good results in water quality parameter prediction.

Exploring nonlinear correlations among transition metal nanocluster properties using deep learning: a comparative analysis with LOO-CV method and cosine similarity

A novel approach is introduced for the rapid and accurate correlation analysis of nonlinear properties in Transition Metal (TM) clusters utilizing the Deep Leave-One-Out Cross-Validation technique. This investigation demonstrates that the Deep Neural Network (DNN)-based approach offers a more efficient predictive method for various properties of fourth-row TM nanoclusters compared to conventional Density Functional Theory methods, which are computationally intensive and time-consuming. The feature space, also known as descriptors, is established based on a broad spectrum of electronic and physical characteristics. Leveraging the similarities among these clusters, the DNN-based model is employed to explore the correlations among TM cluster properties. The proposed method, in conjunction with cosine similarity, achieves remarkable accuracy up to 10-9 for predicting total energy, lowest vibrational mode, binding energy, and HOMO-LUMO energy gap of TM2, TM3, and TM4nanoclusters. By analyzing correlation errors, the most closely coupled TM clusters are identified. Notably, Mn and Ni clusters exhibit the highest and lowest levels of energy coupling with other TMs, respectively. Generally, energy prediction for TM2, TM3, and TM4clusters exhibit similar trends, while an alternating behavior is observed for vibrational modes and binding energies. Furthermore, Ti, V, and Co demonstrate the highest binding energy correlations with TM2, TM3, and TM4sets, respectively. Regarding energy gap predictions, Ni exhibits the strongest correlation in the smallest TM2clusters, while Cr shows the highest dependence in TM3and TM4sets. Lastly, Zn displays the largest error in HOMO-LUMO energy gap across all sets, indicating distinctive independent energy gap characteristics.

Application of Splitting (Cross Validation) Technique and Herzberg Equation in Feed Pellet Quality Prediction Models

Application of Splitting (Cross Validation) Technique and Herzberg Equation in Feed Pellet Quality Prediction Models

Research on match fluctuation prediction and strategy based on OFS algorithm

The aim of this paper is to construct a model for predicting on-field fluctuations in matches by using OFS algorithm, combined with random forest and lattice point search algorithms, and to analyse the key factors in order to improve the coach's decision-making ability in matches. Cross-validation and hyper-parameter tuning techniques were used during the model building process to find the best hyper-parameter combinations through lattice point search to optimise the model performance and generalisation ability. The study provides a detailed description of the model implementation process, including data processing, feature selection, parameter setting, model building, training and evaluation. Meanwhile, a series of targeted recommendations are proposed to address the variability of match fluctuations, including the analysis of past matches, the focus on recent performance, the assessment of psychological quality, the study of opponent's weaknesses, the flexible response to changes in matches and the maintenance of focus, with a view to helping athletes and coaches to formulate a more effective match strategy and to achieve better match results.

Incorporating crumb rubber in slag-based geopolymer: Experimental work and predictive modelling

Crumb rubber (CR), a prevalent hazardous waste material, poses significant environmental challenges that necessitate innovative management strategies. Recent studies have focused on incorporating CR and ground granulated blast furnace slag (GGBS) into geopolymer concrete (GC) to address this challenge. This research presents a novel approach that combines experimental analysis with machine learning (ML) techniques to investigate the chemical effects of these materials on GC. Initially, compressive strength (CS) tests are conducted on rubberized geopolymer (RG) concrete, and the resulting data are further analyzed through ML algorithms to enhance the understanding of material behavior. Despite numerous attempts by researchers to integrate CR into geopolymer-based materials, the challenge of mitigating strength degradation persists. Therefore, it becomes imperative to construct a predictive model that relies on new variables influencing the strength characteristics. This research develops a predictive model to assess concrete compressive strength (CS). Key variables such as CR grade (particle size), incorporation percentage, and oxide ratio were analyzed for their impact on geopolymer strength. Employing ensemble techniques, namely Bagging (BA) and Gradient boosting (GB) with five learners (M5P, random forest (RF), random tree (RT), reduced error pruning tree (REPT), and support vector machine (SVM), the study found that M5P-GB models offered the most accurate CS predictions with the highest accuracy and lowest errors. Moreover, the dataset was checked via the k-fold cross-validation technique and confirmed the developed models' robustness, reliability, and effectiveness. Furthermore, uncertainty analysis revealed that GB-M5P-unpruned models-maintained uncertainty percentages of 14.769 % at 7 days and 11.277 % at 28 days, which was under the 35 % threshold. Additionally, the sensitivity analysis identified the CR grade and replacement percentage by volume of crusher dust (CD) as the most critical factors affecting CS. These findings underscore the importance of considering predictive model development in decision-making processes related to RG concrete properties, providing valuable insights into optimizing the model's robustness and reliability for practical applications. However, the study's reliance on specific input parameters and controlled laboratory conditions may limit the generalizability of the predictive models, necessitating further validation under diverse real-world conditions and variations in CR source and environmental factors.

Prediction of hepatocellular carcinoma response to radiation segmentectomy using an MRI-based machine learning approach.

To evaluate the value of pre-treatment MRI-based radiomics in patients with hepatocellular carcinoma (HCC) for the prediction of response to Yttrium 90 radiation segmentectomy. This retrospective study included 154 patients (38 female; mean age 66.8years) who underwent contrast-enhanced MRI prior to radiation segmentectomy. Radiomics features were manually extracted on volumes of interest on post-contrast T1-weighted images at the portal venous phase (PVP). Tumor-based response assessment was evaluated 6months post-treatment using mRECIST. A logistic regression model was used to predict binary response outcome [complete response at 6months with no-re-treatment (response group) against the rest (non-response group, including partial response, progressive disease, stable disease and complete response after re-treatment within 6months after radiation segmentectomy) using baseline clinical parameters and radiomics features. We accessed the value of different sets of predictors using cross-validation technique. AUCs were compared using DeLong tests. A total 168 HCCs (mean size 2.9 ± 1.7cm) were analyzed in 154 patients. The response group consisted of 113 HCCs and the non-response group of 55 HCCs. Baseline clinical parameters (AUC 0.531; sensitivity, 0.781; specificity, 0.279; positive predictive value (PPV), 0.345; negative predictive value (NPV), 0.724) and AFP (AUC 0.632; sensitivity, 0.833; specificity, 0.466; PPV, 0.432; NPV, 0.851) showed poor performance for response prediction. The model using a combination of radiomics features and clinical parameters/AFP showed the best performance (AUC 0.736; sensitivity, 0.706; specificity, 0.662; PPV 0.504; NPV, 0.822), significantly better than the clinical model (p < 0.001) or AFP alone (p < 0.001). The combination of radiomics features from pre-treatment MRI with clinical parameters and AFP showed fair performance for predicting HCC response to radiation segmentectomy, better than that of AFP. These results need further validation.

Innovative Sentiment Analysis and Prediction of Stock Price Using FinBERT, GPT-4 and Logistic Regression: A Data-Driven Approach

This study explores the comparative performance of cutting-edge AI models, i.e., Finaance Bidirectional Encoder representations from Transsformers (FinBERT), Generatice Pre-trained Transformer GPT-4, and Logistic Regression, for sentiment analysis and stock index prediction using financial news and the NGX All-Share Index data label. By leveraging advanced natural language processing models like GPT-4 and FinBERT, alongside a traditional machine learning model, Logistic Regression, we aim to classify market sentiment, generate sentiment scores, and predict market price movements. This research highlights global AI advancements in stock markets, showcasing how state-of-the-art language models can contribute to understanding complex financial data. The models were assessed using metrics such as accuracy, precision, recall, F1 score, and ROC AUC. Results indicate that Logistic Regression outperformed the more computationally intensive FinBERT and predefined approach of versatile GPT-4, with an accuracy of 81.83% and a ROC AUC of 89.76%. The GPT-4 predefined approach exhibited a lower accuracy of 54.19% but demonstrated strong potential in handling complex data. FinBERT, while offering more sophisticated analysis, was resource-demanding and yielded a moderate performance. Hyperparameter optimization using Optuna and cross-validation techniques ensured the robustness of the models. This study highlights the strengths and limitations of the practical applications of AI approaches in stock market prediction and presents Logistic Regression as the most efficient model for this task, with FinBERT and GPT-4 representing emerging tools with potential for future exploration and innovation in AI-driven financial analytics.

Predictive Modeling of the Hydrate Formation Temperature in Highly Pressurized Natural Gas Pipelines

In this study, we aim to develop advanced machine learning regression models for the prediction of hydrate temperature based on the chemical composition of sweet gas mixtures. Data were collected in accordance with the BOTAS Gas Network Code specifications, approved by the Turkish Energy Market Regulatory Authority (EMRA), and generated using DNV GasVLe v3.10 software, which predicts the phase behavior and properties of hydrocarbon-based mixtures under various pressure and temperature conditions. We employed linear regression, decision tree regression, random forest regression, generalized additive models, and artificial neural networks to create prediction models for hydrate formation temperature (HFT). The performance of these models was evaluated using the hold-out cross-validation technique to ensure unbiased results. This study demonstrates the efficacy of ensemble learning methods, particularly random forest with an R2 and Adj. R2 of 0.998, for predicting hydrate formation conditions, thereby enhancing the safety and efficiency of gas transport and processing. This research illustrates the potential of machine learning techniques in advancing the predictive accuracy for hydrate formations in natural gas pipelines and suggests avenues for future optimizations through hybrid modeling approaches.

Identification of risk factors and establishment of prediction models for mortality risk in patients with acute kidney injury: A retrospective cohort study.

This study investigated factors influencing death in patients with Acute Kidney Injury (AKI) and developed models to predict their mortality risk. We analyzed data from 1079 AKI patients admitted to Changsha First Hospital using a retrospective design. Patient information including demographics, medical history, lab results, and treatments were collected. Logistic regression models were built to identify risk factors and predict 90-day and 1-year mortality. The 90-day mortality rate among 1079 AKI patients was 13.8% (149/1079) and the one-year mortality rate was 14.8% (160/1079). For both 90-day and 1-year mortality in patients with AKI, age over 60, anemia, hypotension, organ failure, and an admission Scr level above 682.3 μmol/L were identified as independent risk factors through multivariate logistic regression analysis. Additionally, mechanical ventilation was associated with an increased risk of death at one year. To ensure the generalizability of the models, we employed a robust 5-fold cross-validation technique. Both the 90-day and 1-year mortality models achieved good performance, with area under the curve (AUC) values exceeding 0.8 in the training set. Importantly, the AUC values in the validation set (0.828 for 90-day and 0.796 for 1-year) confirmed that the models' accuracy holds true for unseen data. Additionally, calibration plots and decision curves supported the models' usefulness in predicting patient outcomes. The logistic regression models built using these factors effectively predicted 90-day and 1-year mortality risk. These findings can provide valuable insights for clinical risk management in AKI patients.

Data-centric automated approach to predict autism spectrum disorder based on selective features and explainable artificial intelligence.

Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by notable challenges in cognitive function, understanding language, recognizing objects, interacting with others, and communicating effectively. Its origins are mainly genetic, and identifying it early and intervening promptly can reduce the necessity for extensive medical treatments and lengthy diagnostic procedures for those impacted by ASD. This research is designed with two types of experimentation for ASD analysis. In the first set of experiments, authors utilized three feature engineering techniques (Chi-square, backward feature elimination, and PCA) with multiple machine learning models for autism presence prediction in toddlers. The proposed XGBoost 2.0 obtained 99% accuracy, F1 score, and recall with 98% precision with chi-square significant features. In the second scenario, main focus shifts to identifying tailored educational methods for children with ASD through the assessment of their behavioral, verbal, and physical responses. Again, the proposed approach performs well with 99% accuracy, F1 score, recall, and precision. In this research, cross-validation technique is also implemented to check the stability of the proposed model along with the comparison of previously published research works to show the significance of the proposed model. This study aims to develop personalized educational strategies for individuals with ASD using machine learning techniques to meet their specific needs better.

Developing a logistic regression model to predict spontaneous preterm birth from maternal socio-demographic and obstetric history at initial pregnancy registration

BackgroundCurrent predictive machine learning techniques for spontaneous preterm birth heavily rely on a history of previous preterm birth and/or costly techniques such as fetal fibronectin and ultrasound measurement of cervical length to the disadvantage of those considered at low risk and/or those who have no access to more expensive screening tools.Aims and objectivesWe aimed to develop a predictive model for spontaneous preterm delivery < 37 weeks using socio-demographic and clinical data readily available at booking -an approach which could be suitable for all women regardless of their previous obstetric history.MethodsWe developed a logistic regression model using seven feature variables derived from maternal socio-demographic and obstetric history from a preterm birth (n = 917) and a matched full-term (n = 100) cohort in 2018 and 2020 at a tertiary obstetric unit in the UK. A three-fold cross-validation technique was applied with subsets for data training and testing in Python® (version 3.8) using the most predictive factors. The model performance was then compared to the previously published predictive algorithms.ResultsThe retrospective model showed good predictive accuracy with an AUC of 0.76 (95% CI: 0.71–0.83) for spontaneous preterm birth, with a sensitivity and specificity of 0.71 (95% CI: 0.66–0.76) and 0.78 (95% CI: 0.63–0.88) respectively based on seven variables: maternal age, BMI, ethnicity, smoking, gestational type, substance misuse and parity/obstetric history.ConclusionPending further validation, our observations suggest that key maternal demographic features, incorporated into a traditional mathematical model, have promising predictive utility for spontaneous preterm birth in pregnant women in our region without the need for cervical length and/or fetal fibronectin.

Analyzing Unimproved Drinking Water Sources and Their Determinants Using Supervised Machine Learning: Evidence from the Somaliland Demographic Health Survey 2020

Access to clean and safe drinking water is a fundamental human right. Despite global efforts, including the UN’s “Water for Life” program, a significant portion of the population in developing countries, including Somaliland, continues to rely on unimproved water sources. These unimproved sources contribute to poor health outcomes, particularly for children. This study aimed to investigate the factors associated with the use of unimproved drinking water sources in Somaliland by employing supervised machine learning models to predict patterns and determinants based on data from the 2020 Somaliland Demographic and Health Survey (SHDS). Secondary data from SHDS 2020 were used, encompassing 8384 households across Somaliland. A multilevel logistic regression model was applied to analyze the individual- and community-level factors influencing the use of unimproved water sources. In addition, machine learning models, including logistic regression, decision tree, random forest, support vector machine (SVM), and K-nearest neighbor (KNN), were compared in terms of accuracy, sensitivity, specificity, and other metrics using cross-validation techniques. This study uses supervised machine learning models to analyze unimproved drinking water sources in Somaliland, providing data-driven insights into the complex determinants of water access. This enhances predictive accuracy and informs targeted interventions, offering a robust framework for addressing water-related public health issues in Somaliland. The analysis identified key determinants of unimproved water source usage, including socioeconomic status, education, region, and household characteristics. The random forest model performed the best with an accuracy of 93.57% and an area under the curve (AUC) score of 98%. Decision tree and KNN also exhibited strong performance, while SVM had the lowest predictive accuracy. This study highlights the role of socioeconomic and community factors in determining access to clean drinking water in Somali Land. Factors such as age, education, gender, household wealth, media access, urban or rural residence, poverty level, and literacy level significantly influenced access. Local policies and resource availability also contribute to variations in access. These findings suggest that targeted interventions aimed at improving education, infrastructure, and community water management practices can significantly reduce reliance on unimproved water sources and improve the overall public health.

SVOH: Rigorous Selection Approach for Optimal Hyperparameter Values

The problem we address in this paper is a model selection problem. We consider the k-fold cross-validation (KCV) technique, applied to the Gaussian support vector machine (SVM) classification algorithm. In the cross-vali- dation process, the value of k for the number of subsets is generally chosen and set aprioristically (without any ex- periment). However, the value of k affects the choice of the best compromise between the estimation error and the ap- proximation error of the model. In this way, the k value of the number of subsets can severely influence the optimal values of the SVM classifier's hyperparameters and conse- quently affect the performance of the selected model and its ability to generalize. In this work, we propose a rigorous approach for finding the values of the hyperparameters of the Gaussian SVM known as SVOH (Selection of Optimal Hyperparam- eter Values) in a context of protein-protein interaction (PPI) prediction, where it is necessary to classify the pairs of pro- teins that interact together and those that do not interact together. The proposed approach considers the k value of the number of subsets as an influential parameter of the model and therefore performs learning to find an optimal value of k.

Deep learning based automatic detection and dipole estimation of epileptic discharges in MEG: a multi-center study.

Magnetoencephalography (MEG) provides crucial information in diagnosing focal epilepsy. However, dipole estimation, a commonly used analysis method for MEG, can be time-consuming since it necessitates neurophysiologists to manually identify epileptic spikes. To reduce this burden, we developed the automatic detection of spikes using deep learning in single center. In this study, we performed a multi-center study using six MEG centers to improve the performance of the automated detection of neuromagnetically recorded epileptic spikes, which we previously developed using deep learning. Data from four centers were used for training and evaluation (internal data), and the remaining two centers were used for evaluation only (external data). We used a five-fold subject-wise cross-validation technique to train and evaluate the models. A comparison showed that the multi-center model outperformed the single-center model in terms of performance. The multi-center model achieved an average ROC-AUC of 0.9929 and 0.9426 for the internal and external data, respectively. The median distance between the neurophysiologist-analyzed and automatically analyzed dipoles was 4.36 and 7.23mm for the multi-center model for internal and external data, respectively, indicating accurate detection of epileptic spikes. By training data from multiple centers, automated analysis can improve spike detection and reduce the analysis workload for neurophysiologists. This study suggests that the multi-center model has the potential to detect spikes within 1cm of a neurophysiologist's analysis. This multi-center model can significantly reduce the number of hours required by neurophysiologists to detect spikes.

Enhanced Classification of Video-Evoked Stress Response Using Power Spectral Density Features

The analysis of stress in response to videos using electroencephalography (EEG) has emerged as a significant field of research. In this study, we propose a methodology for classifying stress responses to videos using the Database for Emotion Analysis using Physiological Signals (DEAP). EEG signals are preprocessed with resampling and a median filter. We extracted Power Spectral Density (PSD) features from the alpha, beta, delta, and theta bands of the preprocessed EEG. Instances were labeled based on the valence and arousal values provided in the DEAP dataset in response to the presented videos. Four machine learning algorithms, namely Naïve Bayes (NB), Multilayer Perceptron (MLP), Logistic Regression (LR), and Sequential Minimal Optimization (SMO) classifiers, were employed to differentiate between stressed and relaxed states using a 10-fold cross-validation technique. The SMO classifier achieved the highest accuracy of 95.65%. Additionally, statistically significant variations in the alpha band using t-tests suggest that the DEAP dataset video clips can effectively induce stress and relaxation conditions in participants.

Comparative Analysis of Cross-Validation Techniques: LOOCV, K-folds Cross-Validation, and Repeated K-folds Cross-Validation in Machine Learning Models

Effective model evaluation is crucial for robust machine learning, and cross-validation techniques play a significant role. This study compares Repeated k-folds Cross Validation, k-folds Cross Validation, and Leave-One-Out Cross Validation (LOOCV) on imbalanced and balanced datasets across four models: Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), Random Forest (RF), and Bagging, both with and without parameter tuning. On imbalanced data without parameter tuning, Repeated k-folds cross-validation demonstrated strong performance for SVM with a sensitivity of 0.541 and balanced accuracy of 0.764. K-folds Cross Validation showed a higher sensitivity of 0.784 for RF and a balanced accuracy of 0.884. In contrast, LOOCV achieved notable sensitivity for RF and Bagging at 0.787 and 0.784, respectively, but at the cost of lower precision and higher variance, as detailed in Table 1. When parameter tuning was applied to balanced data, the performance metrics improved. Sensitivity for SVM reached 0.893 with LOOCV and balanced accuracy for Bagging increased to 0.895. Stratified k-folds provided enhanced precision and F1-Score for SVM and RF. Notably, processing times varied significantly, with k-folds being the most efficient with SVM taking 21.480 seconds and Repeated k-folds showing higher computational demands where RF took approximately 1986.570 seconds in model processing, as shown in Table 4. This analysis underscores that while k-folds and repeated k-folds are generally efficient, LOOCV and balanced approaches offer enhanced accuracy for specific models but require greater computational resources. The choice of cross-validation technique should thus be tailored to the dataset characteristics and computational constraints to ensure optimal model evaluation.

Exploring predictors of interaction among low-birth-weight infants and their caregivers: a machine learning–based random forest approach

BackgroundQuality caregiver-infant interaction is crucial for infant growth, health, and development. Traditional methods for evaluating the quality of caregiver-infant interaction have predominantly relied on rating scales or observational techniques. However, rating scales are prone to inaccuracies, while observational techniques are resource-intensive. The utilization of easily collected medical records in conjunction with machine learning techniques offers a promising and viable strategy for accurate and efficient assessment of caregiver-infant interaction quality.MethodsThis study was conducted at a follow-up outpatient clinic at two tertiary maternal and infant health centers located in Shanghai, China. 68 caregivers and their 3-15-month-old infants were videotaped for 3–5 min during playing interactions in non-threatening environment. Two trained experts utilized the Infant CARE-Index (ICI) procedure to assess whether the caregivers were sensitive or not in a dyadic context. This served as the gold standard. Predictors were collected through Health Information Systems (HIS) and questionnaires, which included accessible features such as demographic information, parental coping ability, infant neuropsychological development, maternal depression, parent-infant interaction, and infant temperament. Four classification models with fivefold cross-validation and grid search hyperparameter tuning techniques were employed to yield prediction metrics. Interpretable analyses were conducted to explain the results.ResultsThe score of sensitive caregiver-infant interaction was 6.34 ± 2.62. The Random Forest model gave the best accuracy (83.85%±6.93%). Convergent findings identified infant age, care skills of infants, mother age, infant temperament-regulatory capacity, birth weight, positive coping, health-care-knowledge-of-infants, type of caregiver, MABIS-bonding issues, ASQ-Fine Motor as the strongest predictors of interaction sensitivity between infants and their caregiver.ConclusionsThe proposed method presents a promising and efficient approach that synergistically combines rating scales and artificial technology to detect important features of caregiver-infant interactions. This novel approach holds several implications for the development of automatic computational assessment tools in the field of nursing studies.

Radiomics-based machine learning role in differential diagnosis between small renal oncocytoma and clear cells carcinoma on contrast-enhanced CT: A pilot study

PurposeTo investigate the potential role of radiomics-based machine learning in differentiating small renal oncocytoma (RO) from clear cells carcinoma (ccRCC) on contrast-enhanced CT (CECT). Material and methodsFifty-two patients with small renal masses who underwent CECT before surgery between January 2016 and December 2020 were retrospectively included in the study. At pathology examination 39 ccRCC and 13 RO were identified. All lesions were manually delineated unenhanced (B), arterial (A) and venous (V) phases. Radiomics features were extracted using three different fixed bin widths (bw) of 25 HU, 10 HU, and 5 HU from each phase (B, A, V), and with different combinations (B+A, B+V, B+A+V, A+V), leading to 21 different datasets. Montecarlo Cross Validation technique was used to quantify the estimator performance. The final model built using the hyperparameter selected with Optuna was trained again on the training set and the final performance evaluation was made on the test set. ResultsThe A+V bw 10 achieved the greater median (IQR) balanced accuracy considering all the models of 0.70 (0.64–0.75), while A bw 10 considering only the monophasic ones. The A bw 10 model achieved a median (IQR) sensitivity of 0.60 (0.40–0.60), specificity of 0.80 (0.73–0.87), AUC-ROC of 0.77 (0.66–0.84), accuracy of 0.75 (0.70–0.80), and a Phi Coefficient of 0.38 (0.20–0.47). None of the nine models with the lowest mean balanced accuracy values implemented features from A. ConclusionThe A bw 10 model was identified as the most efficient mono-phasic model in differentiating small RO from ccRCC.

The Estimating Parameter and Number of Knots for Nonparametric Regression Methods in Modelling Time Series Data

This research aims to explore and compare several nonparametric regression techniques, including smoothing splines, natural cubic splines, B-splines, and penalized spline methods. The focus is on estimating parameters and determining the optimal number of knots to forecast cyclic and nonlinear patterns, applying these methods to simulated and real-world datasets, such as Thailand’s coal import data. Cross-validation techniques are used to control and specify the number of knots, ensuring the curve fits the data points accurately. The study applies nonparametric regression to forecast time series data with cyclic patterns and nonlinear forms in the dependent variable, treating the independent variable as sequential data. Simulated data featuring cyclical patterns resembling economic cycles and nonlinear data with complex equations to capture variable interactions are used for experimentation. These simulations include variations in standard deviations and sample sizes. The evaluation criterion for the simulated data is the minimum average mean square error (MSE), which indicates the most efficient parameter estimation. For the real data, monthly coal import data from Thailand is used to estimate the parameters of the nonparametric regression model, with the MSE as the evaluation metric. The performance of these techniques is also assessed in forecasting future values, where the mean absolute percentage error (MAPE) is calculated. Among the methods, the natural cubic spline consistently yields the lowest average mean square error across all standard deviations and sample sizes in the simulated data. While the natural cubic spline excels in parameter estimation, B-splines show strong performance in forecasting future values.