Ability Of Machine Learning Models Research Articles

Improving Time Series Regression Model Accuracy via Systematic Training Dataset Augmentation and Sampling

This study addresses a significant gap in the field of time series regression modeling by highlighting the central role of data augmentation in improving model accuracy. The primary objective is to present a detailed methodology for systematic sampling of training datasets through data augmentation to improve the accuracy of time series regression models. Therefore, different augmentation techniques are compared to evaluate their impact on model accuracy across different datasets and model architectures. In addition, this research highlights the need for a standardized approach to creating training datasets using multiple augmentation methods. The lack of a clear framework hinders the easy integration of data augmentation into time series regression pipelines. Our systematic methodology promotes model accuracy while providing a robust foundation for practitioners to seamlessly integrate data augmentation into their modeling practices. The effectiveness of our approach is demonstrated using process data from two milling machines. Experiments show that the optimized training dataset improves the generalization ability of machine learning models in 86.67% of the evaluated scenarios. However, the prediction accuracy of models trained on a sufficient dataset remains largely unaffected. Based on these results, sophisticated sampling strategies such as Quadratic Weighting of multiple augmentation approaches may be beneficial.

A Review of Machine Learning Approaches for Rumour Detection: Techniques, Challenges, and Future Directions (Machine Learning for Rumour Detection)

Rumours and misinformation propagate rapidly across online social networks, posing significant challenges to maintaining the integrity of information dissemination. In recent years, machine learning (ML) techniques have emerged as promising tools for automating the detection and mitigation of rumours. This review paper provides a comprehensive examination of the advancements in rumour detection using ML approaches. The paper begins by outlining the landscape of rumour dissemination in online social networks, highlighting the characteristics and challenges associated with rumour detection. Subsequently, it systematically categorizes and analyzes various ML methods employed for rumour detection, including supervised, unsupervised, and semi-supervised learning approaches. Furthermore, the review delves into the diverse features and representations utilized in ML models for rumour detection, such as textual content, user engagement patterns, network structures, and temporal dynamics. It discusses the strengths and limitations of different feature sets and their impact on the effectiveness of rumour detection systems. Moreover, the paper explores the intricacies of dataset construction and evaluation methodologies for training and testing rumour detection models. It examines commonly used benchmark datasets and evaluation metrics, emphasizing the importance of robust evaluation frameworks for assessing the performance of ML-based rumour detection systems accurately. Additionally, the review identifies key challenges and open research questions in the field of rumour detection using ML, including handling evolving rumour patterns, addressing adversarial attacks, and enhancing the interpretability and explain ability of ML models. It also discusses potential directions for future research aimed at advancing the state-of-the-art in rumour detection and mitigation.

Machine learning models for the prediction of turbulent combustion speed for hydrogen-natural gas spark ignition engines

The work carried out in this paper focused on “Machine learning models for the prediction of turbulent combustion speed for hydrogen-natural gas spark ignition engines”. The aim of this work is to develop and verify the ability of machine learning models to solve the problem of estimating the turbulent flame speed for a spark-ignition internal combustion engine operating with a hydrogen-natural gas mixture, then evaluate the relevance of these models in relation to the usual approaches. The novelty of this work is the possibility of a direct calculation of turbulent combustion speed with a good precision, using only machine learning model. The obtained models are also compared to each other by considering in turn as a comparison criterion: the precision of the result, calculation time, and the ability to assimilate original data (which has not undergone preprocessing). An important particularity of this work is that the input variables of the machine learning models were chosen among the variables directly measurable experimentally, based on the opinion of experts in combustion in internal combustion engines and not on the usual approaches to dimensionality reduction on a dataset. The data used for this work was taken from a MINSEL 380, a 380-cc single-cylinder engine. The results show that all the machine learning models obtained are significantly faster than the usual approach and Random Forest (R2: R-squared = 0.9939 and RMSE: Root Mean Square Error = 0.4274) gives the best results. With a forecasting accuracy of over 90 %, both approaches can make reasonable predictions for most industrial applications such as designing engine monitoring and control systems, firefighting systems, simulation, and prototyping tools.

Prediction of 30-Day Mortality Following Revision Total Hip and Knee Arthroplasty: Machine Learning Algorithms Outperform CARDE-B, 5-Item, and 6-Item Modified Frailty Index Risk Scores

BackgroundAlthough risk calculators are used to prognosticate postoperative outcomes following revision total hip and knee arthroplasty (TJA), machine learning (ML) based predictive tools have emerged as a promising alternative for improved risk stratification. This study aimed to compare the predictive ability of ML models for 30-day mortality following revision TJA to that of traditional risk-assessment indices such as the CARDE-B score (congestive heart failure, albumin (<3.5 mg/dL), renal failure on dialysis, dependence for daily living, elderly (>65 years of age), and body mass index of <25 kg/m2), 5-item (5MFI), and 6-item modified frailty index (6MFI). MethodsAdult patients undergoing revision TJA between 2013 and 2020 were selected from the ACS-NSQIP database and randomly split 80:20 to compose the training and validation cohorts. There were three ML models - extreme gradient boosting (XGB), random forest (RF), and elastic-net penalized logistic regression (NEPLR) - that were developed and evaluated using discrimination, calibration metrics, and accuracy. The discrimination of CARDE-B, 5MFI, and 6MFI scores was assessed individually and compared to that of ML models. ResultsAll models were equally accurate (Brier score = 0.005) and demonstrated outstanding discrimination with similar areas (AUC) under the receiver operating characteristic curve (XGB = 0.94, RF = NEPLR = 0.93). The NEPLR was the best-calibrated model overall (slope = 0.54, intercept = -0.004). The CARDE-B had the highest discrimination among the scores (AUC = 0.89), followed by 6MFI (AUC = 0.80), and 5MFI (AUC = 0.68). Albumin < 3.5 mg/dL and BMI (< 30.15) were the most important predictors of 30-day mortality following revision TJA. ConclusionsThe ML models outperform traditional risk-assessment indices in predicting postoperative 30-day mortality after revision TJA. Our findings highlight the utility of ML for risk stratification in a clinical setting. The identification of hypoalbuminemia and BMI as prognostic markers may allow patient-specific perioperative optimization strategies to improve outcomes following revision TJA.

Evaluating machine learning models and identifying key factors influencing spatial maize yield predictions in data intensive farm management

Understanding the relationships between crop yields, soil properties, weather patterns and input applications is important for optimizing agricultural production. Data variation analysis using statistical and machine learning (ML) approaches can help identify and understand the practices that optimize yield. The objectives of this study were (i) to evaluate the predictive accuracy of selected ML models for estimating grain yields in on-farm maize (Zea mays L.) trials with different combinations of seeding and fertilizer rates in a commercial field, and (ii) to investigate the ability of ML models to assist in identifying yield-limiting factors in the same field. Multiple linear regression, multilayer perceptron, decision tree, and random forest (RF) ML models were trained and tested using crop management and soil from a data-intensive farm management (DIFM) trial and remotely sensed data. The dataset consisted of multiple subplot treatment observations of crop management, soil properties and normalized difference vegetation index (NDVI), linked to final grain yield for the 2019/2020 and 2020/2021 seasons. The RF had the best combination of high correlation (R2 = 0.69 and 0.80) and low error (MAPE = 5.4 and 8.4% and RMSE = 0.69 and 0.95 t ha−1) when compared to other models for both seasons. Feature importance analysis revealed that urea application was consistently the most critical variable and explained yield variations to the greatest extent, whereas soil phosphorus (P), plant population, and sodium in 2020, and soil P, soil pH, clay content, and plant population in 2021 emerged as the most influential factors for explaining yields. This study concluded that the RF model was the best for spatial yield predictions using DIFM trial datasets. There was also variability between seasons in yield limiting factors resulting from temporal variations in growing conditions. To effectively apply insights from yield prediction models, it is crucial that the variables incorporated into these models have a significant connection to yield and the findings can be translated into actionable management decisions. The DIFM trials combined with ML can play an important role in advancing the field of precision agriculture by providing valuable insights into the complex interactions between crops, soils, and management practices, and identifying new opportunities for improving crop yields and environmental sustainability.

Towards quantifying biomarkers for respiratory distress in preterm infants: Machine learning on mid infrared spectroscopy of lipid mixtures

Neonatal respiratory distress syndrome (nRDS) is a challenging condition to diagnose which can lead to delays in receiving appropriate treatment. Mid infrared (IR) spectroscopy is capable of measuring the concentrations of two diagnostic nRDS biomarkers, lecithin (L) and sphingomyelin (S) with the potential for point of care (POC) diagnosis and monitoring. The effects of varying other lipid species present in lung surfactant on the mid IR spectra used to train machine learning models are explored. This study presents a lung lipid model of five lipids present in lung surfactant and varies each in a systematic approach to evaluate the ability of machine learning models to predict the lipid concentrations, the L/S ratio and to quantify the uncertainty in the predictions using the jackknife + -after-bootstrap and variant bootstrap methods. We establish the L/S ratio can be determined with an uncertainty of approximately ±0.3 mol/mol and we further identify the 5 most prominent wavenumbers associated with each machine learning model.

Machine Learning in Petrology: State-of-the-Art and Future Perspectives

Abstract This article reports on the state-of-the-art and future perspectives of machine learning (ML) in petrology. To achieve this goal, it first introduces the basics of ML, including definitions, core concepts, and applications. Then, it starts reviewing the state-of-the-art of ML in petrology. Established applications mainly concern the so-called data-driven discovery and involve specific tasks like clustering, dimensionality reduction, classification, and regression. Among them, clustering and dimensionality reduction have been demonstrated to be valuable for decoding the chemical record stored in igneous and metamorphic phases and to enhance data visualization, respectively. Classification and regression tasks find applications, for example, in petrotectonic discrimination and geo-thermobarometry, respectively. The main core of the manuscript consists of depicting emerging trends and the future directions of ML in petrological investigations. I propose a future scenario where ML methods will progressively integrate and support established petrological methods in automating time-consuming and repetitive tasks, improving current models, and boosting discovery. In this framework, promising applications include (1) the acquisition of new multimodal petrologic data; (2) the development of data fusion techniques, physics-informed ML models, and ML-supported numerical simulations; and (3) the continuous exploration of the ML potential in petrology. To boost the contribution of ML in petrology, our main challenges are: (1) to improve the ability of ML models to capture the complexity of petrologic processes, (2) progressively link ML algorithms with the physical and thermodynamic nature of the investigated problems, and (3) to start a collaborative effort among researchers coming from different disciplines, both in research and teaching.

Machine Learning Prediction of Fetal Health Status from Cardiotocography Examination in Developing Healthcare Contexts

Reducing neonatal mortality is a critical global health objective, especially in resource-constrained developing countries. This study employs machine learning (ML) techniques to predict fetal health status based on cardiotocography (CTG) examination findings, utilizing a dataset from the Kaggle repository due to the limited comprehensive healthcare data available in developing nations. Features such as baseline fetal heart rate, uterine contractions, and waveform characteristics were extracted using the RFE wrapper feature engineering technique and scaled with a standard scaler. Six ML models—Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), Categorical Boosting (CB), and Extended Gradient Boosting (XGB)—are trained via cross-validation and evaluated using performance metrics. The developed models were trained via cross-validation and evaluated using ML performance metrics. Eight out of the 21 features selected by GB returned their maximum Matthews Correlation Coefficient (MCC) score of 0.6255, while CB, with 20 of the 21 features, returned the maximum and highest MCC score of 0.6321. The study demonstrated the ability of ML models to predict fetal health conditions from CTG exam results, facilitating early identification of high-risk pregnancies and enabling prompt treatment to prevent severe neonatal outcomes.

Abstract 4912: Unsupervised detection of stromal phenotypes with distinct fibrogenic and inflamed properties in NSCLC

Abstract Background: Understanding the composition of cancer-associated stroma (CAS) is vital, as the number and location of immune cells and fibroblasts, as well as the degree of extracellular matrix deposition, have implications for cancer progression and response to treatment, including in non-small cell lung cancer (NSCLC). Manual analysis of CAS does not fully describe the stromal milieu, especially from a spatial perspective, and is highly subjective. To this end, we have developed an unsupervised machine learning (ML) model to characterize the CAS in NSCLC from hematoxylin and eosin (H&amp;E) stained whole slide images (WSI) at scale. Methods: PathExploreTM models were deployed to predict stromal tissue and cell types, while another ML model was used to detect collagen fibers from H&amp;E stained WSIs from the TCGA LUAD (N=536) and LUSC (N=464) datasets. Stroma was divided into small regions (median = 0.02 mm2), and 88 features characterizing cell distribution, tissue composition and fiber density were extracted from each region. Graphs were generated connecting neighboring regions (nodes), and an unsupervised variational graph auto-encoder (VGAE) model was trained to learn 8 latent features through dimensionality reduction. Stromal phenotypes were then derived from the latent features using k-means clustering. The fraction of each phenotype in the stroma was correlated against immune- and stroma-related gene expression signatures (GES) and overall survival (OS). Results: Deployment of VGAE on LUAD and LUSC WSIs revealed three distinct stromal phenotypes - P0, P1 and P2. Fibroblast density was elevated in P0 and P1 regions (p&amp;lt;0.001), immune cell density was elevated in P2 regions (p&amp;lt;0.001), and collagen fiber intensity was highest in P1 regions (p&amp;lt;0.001). P2 enrichment was correlated with elevated expression of the T cell-inflamed gene expression profile (TGEP; Spearman ρ = 0.43 in LUAD; ρ = 0.27 in LUSC) and with improved OS (HR = 0.696; 95% CIs: 0.571-0.847 in LUSC). Conversely, P1 enrichment was positively associated with a transforming growth factor-β-induced cancer associated fibroblast GES (TGFβ-CAF: ρ = 0.19 in LUAD and ρ = 0.12 in LUSC) and poor OS (HR = 1.358; 95% CIs: 1.149-1.603 in LUSC). These phenotypes are consistent with fibroblast-enriched, collagen-depleted stroma (P0), collagen-rich, fibroblast-enriched tumor-promoting stroma (P1), and immune cell-enriched, tumor-suppressive stroma (P2). Conclusions: We describe an unsupervised, data-driven method of predicting stromal regions with discrete patterns of cell composition and collagen deposition in NSCLC. This approach identified three phenotypes of NSCLC stroma. These results highlight the ability of ML models to characterize and find meaningful patterns within the cell, tissue, and matrix components of a tumor. This work provides further evidence of the potential of ML to discover novel precision medicine biomarkers in NSCLC. Citation Format: Neel Patel, Nhat Le, Tan Nguyen, Fedaa Najdawi, Sandhya Srinivasan, Adam Stanford-Moore, Deeksha Kartik, Jun Zhang, Jacqueline Brosnan-Cashman, Robert Egger, Justin Lee, Matthew Bronnimann. Unsupervised detection of stromal phenotypes with distinct fibrogenic and inflamed properties in NSCLC [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4912.

GIS-based non-grain cultivated land susceptibility prediction using data mining methods

The purpose of the present study is to predict and draw up non-grain cultivated land (NCL) susceptibility map based on optimized Extreme Gradient Boosting (XGBoost) model using the Particle Swarm Optimization (PSO) metaheuristic algorithm. In order to, a total of 184 NCL areas were identified based on historical records, and a total of 16 NCL susceptibility conditioning factors (NCLSCFs) were considered, based on both a systematic literature survey and local environmental conditions. The results showed that the XGBoost model optimized by PSO performed well in comparison to other machine learning algorithms; the values of sensitivity, specificity, PPV, NPV, and AUC are 0.93, 0.89, 0.88, 0.93, and 0.96, respectively. Slope, rainfall, fault density, distance from fault and drainage density are most important variables. According to the results of this study, the use of meta-innovative algorithms such as PSO can greatly enhance the ability of machine learning models.

Prediction Of Chlorophyll-a As an Index of Harmful Algal Blooms Using Machine Learning Models

Highlights The monitoring of HABs can be improved using ML models for chlorophyll-a prediction. ML model selection for HABs monitoring depends on target objectives. Random forest model predicts chlorophyll-a better when the temporal dimension is not considered. The LSTM model is essential for making time-dependent chlorophyll-a predictions for HABs monitoring. Abstract. The complex dynamics of freshwater harmful algal blooms (HABs) necessitate proactive monitoring approaches to mitigate their impacts. The rapid breakthrough in computing prowess and statistical advances is triggering the development of data-driven techniques such as machine learning (ML) models, which have been shown in different fields to be instrumental in finding patterns for explaining relationships in observed data. This study assesses the ability of ML models for HABs monitoring in a lake using chlorophyll-a concentration as the index. The selected models for this study were regression tree, random forest (RF), multilayer perceptron (MLP), support vector regression (SVR), long short-term memory (LSTM), and gated recurrent unit (GRU) models, with the last two models able to consider the temporal sequence of obtained water quality datasets. The results showed that the RF model with R2, mean absolute error (MAE), and root mean square error (RMSE) of 0.87 µgL-1, 0.97 µgL-1, and 3.53 µgL-1, respectively, outperformed the SVR, MLP, and regression tree models. LSTM model with MAE and RMSE of 2.39 µgL-1 and 3.29 µgL-1, respectively, predicted temporal dynamics of chlorophyll-a better than GRU, although with more runtime, and showed the potential for developing real-time HAB monitoring and early warning systems. The findings reveal the robustness of the chosen ML models, thereby shedding light on crucial factors that necessitate careful deliberation by researchers and policymakers in determining the most suitable approaches for monitoring HABs. Keywords: Cyanobacteria, Early warning systems, Freshwater, HABs, Machine learning models.

Prediction of vascular complications in free flap reconstruction with machine learning.

This study aims to explore the risk factors of vascular complications following free flap reconstruction and to develop a clinical auxiliary assessment tool for predicting vascular complications in patients undergoing free flap reconstruction leveraging machine learning methods. We reviewed the medical data of patients who underwent free flap reconstruction at the Affiliated Hospital of Zunyi Medical University retrospectively from January 1, 2019, to December 31, 2021. Statistical analysis was used to screen risk factors. A training data set was generated and augmented using the synthetic minority oversampling technique. Logistic regression, random forest and neural network, models were trained, using this dataset. The performance of these three predictive models was then evaluated and compared using a test set, with four metrics, area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. A total of 570 patients who underwent free flap reconstruction were included in this study, 46 of whom developed postoperative vascular complications. Among the models tested, the neural network model exhibited superior performance on the test set, achieving an AUC of 0.828. Multivariate logistic regression analysis identified that preoperative hemoglobin levels, preoperative fibrinogen levels, operation duration, smoking history, the number of anastomoses, and peripheral vascular injury as statistically significant independent risk factors for vascular complications post-free flap reconstruction. The top five predictive factors in the neural network were fibrinogen content, operation duration, donor site, body mass index (BMI), and platelet count. Hemoglobin levels, fibrinogen levels, operation duration, smoking history, and anastomotic veins are independent risk factors for vascular complications following free flap reconstruction. These risk factors enhance the ability of machine learning models to predict the occurrence of vascular complications and identify high-risk patients. The neural network model outperformed the logistic regression and random forest models, suggesting its potential to aid clinicians in early identification of high-risk patients thereby mitigating patient suffering and improving prognosis.

Machine learning for predicting intrahospital mortality in ST-elevation myocardial infarction patients with type 2 diabetes mellitus

In an era of increasing need for precision medicine, machine learning has shown promise in making accurate acute myocardial infarction outcome predictions. The accurate assessment of high-risk patients is a crucial component of clinical practice. Type 2 diabetes mellitus (T2DM) complicates ST-segment elevation myocardial infarction (STEMI), and currently, there is no practical method for predicting or monitoring patient prognosis. The objective of the study was to compare the ability of machine learning models to predict in-hospital mortality among STEMI patients with T2DM. We compared six machine learning models, including random forest (RF), CatBoost classifier (CatBoost), naive Bayes (NB), extreme gradient boosting (XGBoost), gradient boosting classifier (GBC), and logistic regression (LR), with the Global Registry of Acute Coronary Events (GRACE) risk score. From January 2016 to January 2020, we enrolled patients aged > 18 years with STEMI and T2DM at the Affiliated Hospital of Zunyi Medical University. Overall, 438 patients were enrolled in the study [median age, 62 years; male, 312 (71%); death, 42 (9.5%]). All patients underwent emergency percutaneous coronary intervention (PCI), and 306 patients with STEMI who underwent PCI were enrolled as the training cohort. Six machine learning algorithms were used to establish the best-fit risk model. An additional 132 patients were recruited as a test cohort to validate the model. The ability of the GRACE score and six algorithm models to predict in-hospital mortality was evaluated. Seven models, including the GRACE risk model, showed an area under the curve (AUC) between 0.73 and 0.91. Among all models, with an accuracy of 0.93, AUC of 0.92, precision of 0.79, and F1 value of 0.57, the CatBoost model demonstrated the best predictive performance. A machine learning algorithm, such as the CatBoost model, may prove clinically beneficial and assist clinicians in tailoring precise management of STEMI patients and predicting in-hospital mortality complicated by T2DM.

Value of radiomics-based two-dimensional ultrasound for diagnosing early diabetic nephropathy

Despite efforts to diagnose diabetic nephropathy (DN) using biochemical data or ultrasound imaging separately, a significant gap exists regarding the development of integrated models combining both modalities for enhanced early DN diagnosis. Therefore, we aimed to assess the ability of machine learning models containing two-dimensional ultrasound imaging and biochemical data to diagnose early DN in patients with type 2 diabetes mellitus (T2DM). This retrospective study included 219 patients, divided into a training or test group at an 8:2 ratio. Features were selected using minimum redundancy maximum relevance and random forest-recursive feature elimination. The predictive performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC) for sensitivity, specificity, Matthews Correlation Coefficient, F1 score, and accuracy. K-nearest neighbor, support vector machine, and logistic regression models could diagnose early DN, with AUC values of 0.94, 0.85, and 0.85 in the training cohort and 0.91, 0.84, and 0.84 in the test cohort, respectively. Early DN diagnosing using two-dimensional ultrasound-based radiomics models can potentially revolutionize T2DM patient care by enabling proactive interventions, ultimately improving patient outcomes. Our integrated approach showcases the power of artificial intelligence in medical imaging, enhancing early disease detection strategies with far-reaching applications across medical disciplines.

Machine learning models to predict success of endoscopic sleeve gastroplasty using total and excess weight loss percent achievement: a multicentre study

BackgroundThe large amount of heterogeneous data collected in surgical/endoscopic practice calls for data-driven approaches as machine learning (ML) models. The aim of this study was to develop ML models to predict endoscopic sleeve gastroplasty (ESG) efficacy at 12 months defined by total weight loss (TWL) % and excess weight loss (EWL) % achievement. Multicentre data were used to enhance generalizability: evaluate consistency among different center of ESG practice and assess reproducibility of the models and possible clinical application. Models were designed to be dynamic and integrate follow-up clinical data into more accurate predictions, possibly assisting management and decision-making.MethodsML models were developed using data of 404 ESG procedures performed at 12 centers across Europe. Collected data included clinical and demographic variables at the time of ESG and at follow-up. Multicentre/external and single center/internal and temporal validation were performed. Training and evaluation of the models were performed on Python’s scikit-learn library. Performance of models was quantified as receiver operator curve (ROC-AUC), sensitivity, specificity, and calibration plots.ResultsMulticenter external validation: ML models using preoperative data show poor performance. Best performances were reached by linear regression (LR) and support vector machine models for TWL% and EWL%, respectively, (ROC-AUC: TWL% 0.87, EWL% 0.86) with the addition of 6-month follow-up data.Single-center internal validation: Preoperative data only ML models show suboptimal performance. Early, i.e., 3-month follow-up data addition lead to ROC-AUC of 0.79 (random forest classifiers model) and 0.81 (LR models) for TWL% and EWL% achievement prediction, respectively. Single-center temporal validation shows similar results.ConclusionsAlthough preoperative data only may not be sufficient for accurate postoperative predictions, the ability of ML models to adapt and evolve with the patients changes could assist in providing an effective and personalized postoperative care. ML models predictive capacity improvement with follow-up data is encouraging and may become a valuable support in patient management and decision-making.

Application of machine learning algorithms to model soil thermal diffusivity

Soil thermal diffusivity (k) is an important thermal property that significantly affects ground energy storage and heat transfer. Direct measurements of soil thermal diffusivity are challenging due to sensor limitations and variable soil physical properties, such as water content, bulk density, mineralogy and texture. Therefore, indirect estimations of k are commonly used. In this study, the abilities of six machine learning (ML) models, including k-nearest neighbours (KNN), multilayer perceptron (MLP), support vector regression (SVR), decision tree (DT), random forest (RF) and gradient boosting decision tree (GBDT), to estimate k values are evaluated based on a compiled database consisting of 999 samples. The ML model performances are evaluated by three model performance indicators (i.e., coefficient of determination-R2, mean absolute error-MAE and root mean square error-RMSE). The GDBT model best estimates soil thermal diffusivity, showing the highest fitness (R2 = 0.99). Model estimation accuracies are determined for varying numbers of available model inputs, and recommended minimum numbers of model inputs needed to accurately estimate thermal diffusivity are tabulated. This study demonstrates the ability of ML models to estimate values of soil thermal diffusivity, and it provides reference information for future thermo-related soil science and soil engineering applications.

Deep Learning to Estimate Left Ventricular Ejection Fraction From Routine Coronary Angiographic Images

BackgroundCine images during coronary angiography contain a wealth of information besides the assessment of coronary stenosis. We hypothesized that deep learning (DL) can discern moderate-severe left ventricular dysfunction among patients undergoing coronary angiography. ObjectivesThe purpose of this study was to assess the ability of machine learning models in estimating left ventricular ejection fraction (LVEF) from routine coronary angiographic images. MethodsWe developed a combined 3D-convolutional neural network (CNN) and transformer to estimate LVEF for diagnostic coronary angiograms of the left coronary artery (LCA). Two angiograms, left anterior oblique (LAO)-caudal and right anterior oblique (RAO)-cranial projections, were fed into the model simultaneously. The model classified LVEF as significantly reduced (LVEF ≤40%) vs normal or mildly reduced (LVEF>40%). Echocardiogram performed within 30 days served as the gold standard for LVEF. ResultsA collection of 18,809 angiograms from 17,346 patients from Mayo Clinic were included (mean age 67.29; 35% women). Each patient appeared only in the training (70%), validation (10%), or testing set (20%). The model exhibited excellent performance (area under the receiver operator curve [AUC] 0.87; sensitivity 0.77; specificity 0.80) in the training set. The model’s performance exceeded human expert assessment (AUC, sensitivity, and specificity of 0.86, 0.76, and 0.77, respectively) vs (AUC, sensitivity, and specificity of 0.76-0.77, 0.50-0.44, and 0.90-0.93, respectively). In additional sensitivity analyses, combining the LAO and RAO views yielded a higher AUC, sensitivity, and specificity than utilizing either LAO or RAO individually. The original model combining CNN and transformer was superior to DL models using either 3D-CNN or transformers. ConclusionsA novel DL algorithm demonstrated rapid and accurate assessment of LVEF from routine coronary angiography. The algorithm can be used to support clinical decision-making and form the foundation for future models that could extract meaningful data from routine angiography studies.

Ensemble learning models for the prediction of the weekly peak of PM2.5 concentration in Algiers, Algeria

Introduction: This paper focuses on the prediction of weekly peak levels of Particulate Matter with an aerodynamic diameter of less than 2.5 µm (PM2.5 ), using various Machine Learning (ML) models. The study compares ML models to deep learning models and emphasizes the explain ability of ML models for PM2.5 prediction.&#x0D; Materials and methods: We examine different combinations of features and time window dimensions to evaluate the performance of ML models. It utilizes Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Decision Tree (DT), and five Ensemble Models (EL) including AdaBoost, XGBoost, LightGBM, CatBoost, and Random Forest (RF). The dataset includes three years of daily measurements of weather parameters and PM2.5.&#x0D; Results: Lagged values of PM2.5 improves prediction performance, particularly when the lagged value window size spans seven days or multiples thereof. This confirms that road traffic, which exhibits a weekly seasonality, is the primary source of PM2.5 in Algiers. Interestingly, including lagged values of weather parameters decreases prediction performance, even when chosen based on their correlation with PM2.5. The AdaBoost model performs the best, achieving a Root Mean Squared Error (RMSE) of 2.899 µg/m³ and an R2 value of 0.96.&#x0D; Conclusion: EL models, specifically AdaBoost, exhibit strong performance in predicting PM 2.5 levels. They not only provide accurate predictions but also allow analysis of feature importance. Lagged values of PM2.5 have a greater impact on predictions compared to weather parameters. Surprisingly, including weather parameters hampers prediction performance. Therefore, the utilization of ensemble learning models offers valuable insights into feature significance.

A survey on dataset quality in machine learning

With the rise of big data, the quality of datasets has become a crucial factor affecting the performance of machine learning models. High-quality datasets are essential for the realization of data value. This survey article summarizes the research direction of dataset quality in machine learning, including the definition of related concepts, analysis of quality issues and risks, and a review of dataset quality dimensions and metrics throughout the dataset lifecycle and a review of dataset quality metrics analyzed from a dataset lifecycle perspective and summarized in literatures. Furthermore, this article introduces a comprehensive quality evaluation process, which includes a framework for dataset quality evaluation with dimensions and metrics, computation methods for quality metrics, and assessment models. These studies provide valuable guidance for evaluating dataset quality in the field of machine learning, which can help improve the accuracy, efficiency, and generalization ability of machine learning models, and promote the development and application of artificial intelligence technology.

Assessment of machine learning models and conventional correlations for predicting heat transfer coefficient of liquid hydrogen during flow boiling

Liquid hydrogen has attracted widespread attention due to industrial decarbonization as an excellent carrier of renewable energy accommodation. Accurate prediction of the heat transfer coefficient during flow boiling has become a fundamental prerequisite for enhancing the design rationality and safety of hydrogen devices since a slight heat leak will trigger flow boiling. A novel selection standard of the dataset for liquid hydrogen flow boiling is proposed, and an experimental database of liquid hydrogen is compiled, including 923 data points from 5 sources. The prediction performance of eight conventional empirical correlations and six machine learning models for liquid hydrogen flow boiling is compared and evaluated. Results show that the prediction ability of machine learning models for the heat transfer coefficient of liquid hydrogen flow boiling is much higher than that of traditional correlations. Fang correlation is recommended to use as the calculation benchmark due to simplicity and reliability if the inlet condition is obscure. The Extra tree model shows the most excellent evaluating performance among the six machine learning models with a mean absolute deviation of 11.44% and a fairly superior R2 of 0.9543. The Froude number Fr exhibits an essential impact according to the feature importance analysis, which may need to be taken into account when developing new empirical correlations. An improved correlation for the flow boiling of liquid hydrogen is provided based on the Fang correlation, achieving a mean absolute deviation of 18.61% and a mean relative deviation of 16.49%. The results of this paper can offer some theoretical guidance for the design of a liquid hydrogen apparatus.