Optimal Machine Learning Algorithm Research Articles

Development and comparison of machine learning-based models for predicting heart failure after acute myocardial infarction

AimsHeart failure (HF) is one of the common adverse cardiovascular events after acute myocardial infarction (AMI), but the predictive efficacy of numerous machine learning (ML) built models is unclear. This study aimed to build an optimal model to predict the occurrence of HF in AMI patients by comparing seven ML algorithms.MethodsCohort 1 included AMI patients from 2018 to 2019 divided into HF and control groups. All first routine test data of the study subjects were collected as the features to be selected for the model, and seven ML algorithms with screenable features were evaluated. Cohort 2 contains AMI patients from 2020 to 2021 to establish an early warning model with external validation. ROC curve and DCA curve to analyze the diagnostic efficacy and clinical benefit of the model respectively.ResultsThe best performer among the seven ML algorithms was XgBoost, and the features of XgBoost algorithm for troponin I, triglycerides, urine red blood cell count, γ-glutamyl transpeptidase, glucose, urine specific gravity, prothrombin time, prealbumin, and urea were ranked high in importance. The AUC of the HF-Lab9 prediction model built by the XgBoost algorithm was 0.966 and had good clinical benefits.ConclusionsThis study screened the optimal ML algorithm as XgBoost and developed the model HF-Lab9 will improve the accuracy of clinicians in assessing the occurrence of HF after AMI and provide a reference for the selection of subsequent model-building algorithms.

Machine learning approach for predicting electrical features of Schottky structures with graphene and ZnTiO3 nanostructures doped in PVP interfacial layer

In this research, for some different Schottky type structures with and without a nanocomposite interfacial layer, the current–voltage (I–V) characteristics have been investigated by using different Machine Learning (ML) algorithms to predict and analyze the structures’ principal electric parameters such as leakage current (I0), barrier height ({varphi }_{B0}), ideality factor (n), series resistance (Rs), shunt resistance (Rsh), rectifying ratio (RR), and interface states density (Nss). The interfacial nanocomposite layer is made by composing polyvinyl-pyrrolidone (PVP), zinc titanate (ZnTiO3), and graphene (Gr) nanostructures. The Gaussian Process Regression (GPR), Kernel Ridge Regression (KRR), Support Vector Regression (SVR), and Artificial Neural Network (ANN) are used as ML algorithms. The ML techniques training data are obtained using the thermionic emission method. Finally, by comparing the experimental and predicted results, the performance of the different ML algorithms in predicting the electrical parameters of Schottky diodes (SDs) has been compared to find the optimized ML algorithm. The ML predictions of basic electrical parameters by almost all algorithms are in good agreement with the actual values, while the SVR model has predicted closer values to the corresponding actual ones. The obtained results show that the quantity of the leakage current and Nss for MS type SD decreases, and φB0 increases with the interfacial layer usage, especially with graphene dopant.

Machine learning-based cognitive load prediction model for AR-HUD to improve OSH of professional drivers.

Augmented reality head-up display (AR-HUD) interface design takes on critical significance in enhancing driving safety and user experience among professional drivers. However, optimizing the above-mentioned interfaces poses challenges, innovative methods are urgently required to enhance performance and reduce cognitive load. A novel method was proposed, combining the IVPM method with a GA to optimize AR-HUD interfaces. Leveraging machine learning, the IVPM-GA method was adopted to predict cognitive load and iteratively optimize the interface design. Experimental results confirmed the superiority of IVPM-GA over the conventional BP-GA method. Optimized AR-HUD interfaces using IVPM-GA significantly enhanced the driving performance, and user experience was enhanced since 80% of participants rated the IVPM-GA interface as visually comfortable and less distracting. In this study, an innovative method was presented to optimize AR-HUD interfaces by integrating IVPM with a GA. IVPM-GA effectively reduced cognitive load, enhanced driving performance, and improved user experience for professional drivers. The above-described findings stress the significance of using machine learning and optimization techniques in AR-HUD interface design, with the aim of enhancing driver safety and occupational health. The study confirmed the practical implications of machine learning optimization algorithms for designing AR-HUD interfaces with reduced cognitive load and improved occupational safety and health (OSH) for professional drivers.

A Prescriptive Framework for Selecting Optimal Machine Learning Algorithms for Enterprise-level Problems

We are living in a world where data is touted to be the new oil and analytics is the combustion engine. Analytics or data science comprises a number of tools and techniques from the fields of statistics, machine learning and broader AI. While there is no dearth of such tools and techniques ranging from random forests to neural networks, problems most enterprises face is that of identify the most suitable tool (s) for a business problem at hand. This paper aims to address this problem by developing a novel, comprehensive framework that identifies the optimal data science tools given the nature and type of the business problem and the constraints on the underlying data used. This framework can be an effective device for enterprises to select the suitable data science tools and techniques to apply to their problems. The intention is to empirically test this framework in future research and develop a Natural language Processing (NLP) implementation of this prescriptive framework.

Analysis and prediction of rockburst intensity using improved D-S evidence theory based on multiple machine learning algorithms

Accurate prediction of rockburst hazards is an effective means to improve the development and utilization of underground space. When using a single machine learning algorithm for rockburst prediction, the reliability of the classification results can hardly be guaranteed. In this paper, a fusion model for rockburst prediction based on multiple machine learning algorithms is proposed in combination with D-S evidence theory. Six characteristic parameters (σθ, σc, σt, SR, BR and Wet) were statistically analyzed for 304 sets of rockburst cases, and the data had outliers and class imbalances. The box plot method was used to detect replacement of a small number of outliers, and the Adasyn oversampling method eliminated the effect of data class imbalance. The visualization of the data by using the t-SNE method showed improved classifiability. SVM, BP, RBF, RF and ELM rockburst prediction models were developed with the six characteristic parameters as model inputs. In addition, the global optimization algorithms were used to find the optimal hyperparameters of the five machine learning algorithms. The accuracy of the optimized models was improved by 2.63%, 5.27%, 2.63%, 6.58% and 7.5% compared to the unoptimized models. Based on the prediction results, the precision was proposed as the fusion index. Additionally, based on improved D-S evidence theory, a fusion model for rockburst prediction was developed with five optimized machine learning algorithm models as base classifiers. Finally, the fusion model was applied to the rockburst prediction of Jiangbian Hydropower Station and Sanshan Island Gold Mine in China with the accuracy of 92.86%, and the prediction was outperformed by a single base classifier. The fusion model compensated for the uncertainty and poor robustness of the prediction results of the single-base classifier, and improved the accuracy and reliability of rockburst prediction.

Early detection of squamous cell carcinoma of the oral tongue using multidimensional plasma protein analysis and interpretable machine learning

AbstractBackgroundInterpretable machine learning (ML) for early detection of cancer has the potential to improve risk assessment and early intervention.MethodsData from 261 proteins related to inflammation and/or tumor processes in 123 blood samples collected from healthy persons, but of whom a sub‐group later developed squamous cell carcinoma of the oral tongue (SCCOT), were analyzed. Samples from people who developed SCCOT within less than 5 years were classified as tumor‐to‐be and all other samples as tumor‐free. The optimal ML algorithm for feature selection was identified and feature importance computed by the SHapley Additive exPlanations (SHAP) method. Five popular ML algorithms (AdaBoost, Artificial neural networks [ANNs], Decision Tree [DT], eXtreme Gradient Boosting [XGBoost], and Support Vector Machine [SVM]) were applied to establish prediction models, and decisions of the optimal models were interpreted by SHAP.ResultsUsing the 22 selected features, the SVM prediction model showed the best performance (sensitivity = 0.867, specificity = 0.859, balanced accuracy = 0.863, area under the receiver operating characteristic curve [ROC‐AUC] = 0.924). SHAP analysis revealed that the 22 features rendered varying person‐specific impacts on model decision and the top three contributors to prediction were Interleukin 10 (IL10), TNF Receptor Associated Factor 2 (TRAF2), and Kallikrein Related Peptidase 12 (KLK12).ConclusionUsing multidimensional plasma protein analysis and interpretable ML, we outline a systematic approach for early detection of SCCOT before the appearance of clinical signs.

Alkali–silica reaction expansion prediction in concrete using hybrid metaheuristic optimized machine learning algorithms

Alkali–silica reaction expansion prediction in concrete using hybrid metaheuristic optimized machine learning algorithms

Machine Learning Algorithm for Toxic Comments Analysis

Abstract: Online comments that are toxic tend to drive other users away from a discussion because they are nasty, abusive, or irrational. The risk of online bullying and harassment limits people from expressing opposing views, which has an impact on the free exchange of ideas. Sites fail to properly promote discussions, which forces many communities to restrict or disable user comments. In order to analyze the toxicity as accurately as possible, this paper will carefully evaluate the prevalence of online harassment. In order to solve the text classification problem and determine the optimal machine learning algorithm based on our assessment metrics for the categorization of harmful comments, we will employ six machine learning algorithms and apply them to our data. We will work to accurately assess the toxicity to reduce its negative consequences, which will encourage organizations to take the necessary action.

Prediction of chloride ion concentration distribution in basalt-polypropylene fiber reinforced concrete based on optimized machine learning algorithm

The distribution characteristics of chloride ion concentration in basalt-polypropylene fiber reinforced concrete (BPFRC-CC) are important for assessing the durability of concrete structures under marine environment. This study collected the distribution data of BPFRC-CC in three different environments: tidal, submersible, and salt spray. Several optimized machine learning models were developed to predict the distribution of BPFRC-CC. The performance of these models was evaluated based on a comparison between actual and predicted values, residual distribution histograms, and performance indicators. The research results of this article showed that the particle swarm optimization support vector regression (PSO-SVR) model exhibits significant accuracy and generalization ability, with closer proximity to the actual values in both the training and testing sets. The residual distribution histogram of the PSO-SVR model approximated a normal distribution with a smaller mean and standard deviation. Evaluation indicators, including R2, MSE, RMSE, MAE, and MAPE, for the PSO-SVR model were 0.994, 6.92e-5, 0.0083, 0.0062, and 0.0453, respectively. The SHAP values revealed that depth and age were the most critical influencing factors. The decrease in age, water-cement ratio, and water-binder ratio, the addition of basalt fibers and polypropylene fibers, and the increase in depth reduced the BPFRC-CC. In addition, BPFRC-CC in tidal, salt spray, and submersible areas decreased in that order. Finally, a graphical user interface for BPFRC-CC was developed, providing researchers and production personnel with an intuitive, efficient, and visual production experience. This study has important implications for the optimization of BPFRC formulations and the prediction and assessment of the life of BPFRC structures.

Proposing a Novel Data-Driven Optimization Methodology to Calculate the Insurance Premium in the Iranian Health Insurance Industry

ABSTRACT This study aims to manage the two most common and critical disruptions of Iranian health insurance (declining market share and errors in predicting the indemnities) by proposing a novel data-driven methodology for calculating its insurance premium. Here, using the optimal machine learning algorithm selected using a Bayesian best-worst method, insurers are classified based on their preparedness for causing disruptions. Then, the indemnity of each group of insureds is predicted. Finally, the appropriate premium for each group of insureds is calculated separately using a new mathematical optimization model. The results of our real-life case study guarantee the insurer’s profitability and reduction of its bankruptcy risk even by announcing lower premiums.

An Approach for the Classification of Rock Types Using Machine Learning of Core and Log Data

Classifying rocks based on core data is the most common method used by geologists. However, due to factors such as drilling costs, it is impossible to obtain core samples from all wells, which poses challenges for the accurate identification of rocks. In this study, the authors demonstrated the application of an explainable machine-learning workflow using core and log data to identify rock types. The rock type is determined utilizing the flow zone index (FZI) method using core data first, and then based on the collection, collation, and cleaning of well log data, four supervised learning techniques were used to correlate well log data with rock types, and learning and prediction models were constructed. The optimal machine learning algorithm for the classification of rocks is selected based on a 10-fold cross-test and a comparison of AUC (area under curve) values. The accuracy rate of the results indicates that the proposed method can greatly improve the accuracy of the classification of rocks. SHapley Additive exPlanations (SHAP) was used to rank the importance of the various well logs used as input variables for the prediction of rock types and provides both local and global sensitivities, enabling the interpretation of prediction models and solving the “black box” problem with associated machine learning algorithms. The results of this study demonstrated that the proposed method can reliably predict rock types based on well log data and can solve hard problems in geological research. Furthermore, the method can provide consistent well log interpretation arising from the lack of core data while providing a powerful tool for well trajectory optimization. Finally, the system can aid with the selection of intervals to be completed and/or perforated.

A Prediction Model for Spot LNG Prices Based on Machine Learning Algorithms to Reduce Fluctuation Risks in Purchasing Prices

The ongoing Russia–Ukraine conflict has exacerbated the global crisis of natural gas supply, particularly in Europe. During the winter season, major importers of liquefied natural gas (LNG), such as South Korea and Japan, were directly affected by fluctuating spot LNG prices. This study aimed to use machine learning (ML) to predict the Japan Korea Marker (JKM), a spot LNG price index, to reduce price fluctuation risks for LNG importers such as the Korean Gas Corporation (KOGAS). Hence, price prediction models were developed based on long short-term memory (LSTM), artificial neural network (ANN), and support vector machine (SVM) algorithms, which were used for time series data prediction. Eighty-seven variables were collected for JKM prediction, of which eight were selected for modeling. Four scenarios (scenarios A, B, C, and D) were devised and tested to analyze the effect of each variable on the performance of the models. Among the eight variables, JKM, national balancing point (NBP), and Brent price indexes demonstrated the largest effects on the performance of the ML models. In contrast, the variable of LNG import volume in China had the least effect. The LSTM model showed a mean absolute error (MAE) of 0.195, making it the best-performing algorithm. However, the LSTM model demonstrated a decreased in performance of at least 57% during the COVID-19 period, which raises concerns regarding the reliability of the test results obtained during that time. The study compared the ML models’ prediction performances with those of the traditional statistical model, autoregressive integrated moving averages (ARIMA), to verify their effectiveness. The comparison results showed that the LSTM model’s performance deviated by an MAE of 15–22%, which can be attributed to the constraints of the small dataset size and conceptual structural differences between the ML and ARIMA models. However, if a sufficiently large dataset can be secured for training, the ML model is expected to perform better than the ARIMA. Additionally, separate tests were conducted to predict the trends of JKM fluctuations and comprehensively validate the practicality of the ML models. Based on the test results, LSTM model, identified as the optimal ML algorithm, achieved a performance of 53% during the regular period and 57% d during the abnormal period (i.e., COVID-19). Subject matter experts agreed that the performance of the ML models could be improved through additional studies, ultimately reducing the risk of price fluctuations when purchasing spot LNG.

Optimizing the input feature sets and machine learning algorithms for reliable and accurate estimation of continuous, cuffless blood pressure

The advent of mobile devices, wearables and digital healthcare has unleashed a demand for accurate, reliable, and non-interventional ways to measure continuous blood pressure (BP). Many consumer products claim to measure BP with a cuffless device, but their lack of accuracy and reliability limit clinical adoption. Here, we demonstrate how multimodal feature datasets, comprising: (i) pulse arrival time (PAT); (ii) pulse wave morphology (PWM), and (iii) demographic data, can be combined with optimized Machine Learning (ML) algorithms to estimate Systolic BP (SBP), Diastolic BP (DBP) and Mean Arterial Pressure (MAP) within a 5 mmHg bias of the gold standard Intra-Arterial BP, well within the acceptable limits of the IEC/ANSI 80601-2-30 (2018) standard. Furthermore, DBP’s calculated using 126 datasets collected from 31 hemodynamically compromised patients had a standard deviation within 8 mmHg, while SBP’s and MAP’s exceeded these limits. Using ANOVA and Levene’s test for error means and standard deviations, we found significant differences in the various ML algorithms but found no significant differences amongst the multimodal feature datasets. Optimized ML algorithms and key multimodal features obtained from larger real-world data (RWD) sets could enable more reliable and accurate estimation of continuous BP in cuffless devices, accelerating wider clinical adoption.

A comprehensive GEP and MEP analysis of a cement-based concrete containing metakaolin

Due to the detrimental environmental consequence of cement formation, studies has concentrated on decreasing the environmental influence and expense of cement containing products. It is crucial to conduct research on the mechanical characteristics of cement additive/replacement products such as metakaolin (MK). To serve the said purpose, the importance of developing predictive machine learning (ML) models is growing as ecological concerns intensify. Since there are few ML approaches for them, it is imperative to develop techniques to improve the mechanical properties of such products. In order to overcome these issues, this research examines ML methods for forecasting the compressive strength (fc') of concrete containing MK. Gene expression programming (GEP) and multigene expression programming (MEP), two distinct ML predictive models, are provided in detail along with the most useful variables, enabling effective analysis and forecasting of the fc' of concrete containing MK. An important component of any prediction or simulation endeavor is model generalization, and the researchers of this study used a data set of MK concrete mechanical properties for this purpose. The database has 405 data points with pertinent model parameters to calculate the fc' of concrete containing MK. Cement, percentage of metakaolin by binder, coarse and fine aggregate by binder, water by binder, coarse aggregates by fine aggregates, percentage of superplasticizer by binder, and age are among the factors in the database that influence concrete's fc' yet still previously infrequently regarded as crucial input attributes. The effectiveness of the models is then examined in order to choose and implement the best predicted model for the mechanical properties of MK-based concrete. According to the findings of this research, the optimal ML algorithms for forecasting MK-based concrete fc' is MEP with R2 value of 0.96. Additionally, the sensitivity analysis shows that water-by-binder, percentage of superplasticizer-by-binder and age have the significant effect on the development of compressive strength of metakaolin based concrete. GEP and MEP models develop empirical expression for the outcome to forecast future databases' features to promote the usage of sustainable MK concrete. Moreover, detrimental effects caused by intensive and costly labor work can be overcome by utilizing these environmental-friendly techniques.

Hollow Core-Shell Metal Oxide Heterojunctions for the Urinary Metabolic Fingerprint-Based Noninvasive Diagnostic Strategy.

Urine is a preferred object for noninvasive diagnostic strategies. Urinary metabolic analysis is speculatively regarded as an ideal tool for screening diseases closely related to the genitourinary system in view of the intimate relationship between metabolomics and phenotype. Herein, we propose a urinary metabolic fingerprint-based noninvasive diagnostic strategy by designing hollow core-shell metal oxide heterojunctions (denoted as MOHs). With outstanding light absorption and electron-hole separation ability, MOHs aid in the extraction of high-performance urine metabolic fingerprints. Coupled with optimized machine learning algorithms, we establish a metabolic marker panel for accurate diagnosis of prostate cancer (PCa), which is the most common malignant tumor of the male genitourinary system, achieving accuracies of 84.72 and 83.33% in the discovery and validation sets, respectively. Furthermore, metabolite variations and related pathway analyses confirm the credibility and change correlation of key metabolic features in PCa. This work tends to advance the noninvasive diagnostic strategy toward clinical realities.

Transcriptome analysis based on machine learning reveals a role for autoinflammatory genes of chronic nonbacterial osteomyelitis (CNO)

Chronic nonbacterial osteomyelitis (CNO) is an autoinflammatory bone disorder. The origin and development of CNO involve many complex immune processes, resulting in delayed diagnosis and a lack of effective treatment. Although bioinformatics analysis has been utilized to seek key genes and pathways in CNO, only a few bioinformatics studies that focus on CNO pathogenesis and mechanisms have been reported. This study aimed to identify key biomarkers that could serve as early diagnostic or therapeutic markers for CNO. Two RNA-seq datasets (GSE133378 and GSE187429) were obtained from the Gene Expression Omnibus (GEO). Weighted gene coexpression network analysis (WGCNA) and differentially expressed gene (DEG) analysis were conducted to identify the genes associated with CNO. Then, the autoinflammatory genes most associated with CNO were identified based on the GeneCards database and a CNO prediction model, which was created by the LASSO machine learning algorithm. The accuracy of the model and effects of the autoinflammatory genes according to receiver operating characteristic (ROC) curves were verified in external datasets (GSE7014). Finally, we performed clustering analysis with ConsensusClusterPlus. In total, eighty CNO-related genes were identified and were significantly enriched in the biological processes regulation of actin filament organization, cell–cell junction organization and gamma-catenin binding. The main enriched pathways were adherens junctions, viral carcinogenesis and systemic lupus erythematosus. Two autoinflammatory genes with high expression in CNO samples were identified by combining an optimal machine learning algorithm (LASSO) with the GeneCards database. An external validation dataset (GSE187429) was utilized for ROC analysis of the prediction model and two genes, and the results indicated good efficiency. Then, based on consensus clustering analysis, we found that the expression of UTS2 and MPO differed between clusters. Finally, the ceRNA network of lncRNAs and the small molecule compounds targeting the two autoinflammatory genes were predicted. The identification of two autoinflammatory genes, the HCG18/has-mir-147a/UTS2/MPO axis and signalling pathways in this study can help us understand the molecular mechanism of CNO formation and provides candidate targets for the diagnosis and treatment of CNO.

Predicting liposome formulations by the integrated machine learning and molecular modeling approaches

Liposome is one of the most widely used carriers for drug delivery because of the great biocompatibility and biodegradability. Due to the complex formulation components and preparation process, formulation screening mostly relies on trial-and-error process with low efficiency. Here liposome formulation prediction models have been built by machine learning (ML) approaches. The important parameters of liposomes, including size, polydispersity index (PDI), zeta potential and encapsulation, are predicted individually by optimal ML algorithm, while the formulation features are also ranked to provide important guidance for formulation design. The analysis of key parameter reveals that drug molecules with logS [-3, -6], molecular complexity [500, 1000] and XLogP3 (≥2) are priority for preparing liposome with higher encapsulation. In addition, naproxen (NAP) and palmatine HCl (PAL) represented the insoluble and water-soluble molecules are prepared as liposome formulations to validate prediction ability. The consistency between predicted and experimental value verifies the satisfied accuracy of ML models. As the drug properties are critical for liposome particles, the molecular interactions and dynamics of NAP and PAL liposome are further investigated by coarse-grained molecular dynamics simulations. The modeling structure reveals that NAP molecules could distribute into lipid layer, while most PAL molecules aggregate in the inner aqueous phase of liposome. The completely different physical state of NAP and PAL confirms the importance of drug properties for liposome formulations. In summary, the general prediction models are built to predict liposome formulations, and the impacts of key factors are analyzed by combing ML with molecular modeling. The availability and rationality of these intelligent prediction systems have been proved in this study, which could be applied for liposome formulation development in the future.

Understanding geometrical size effect on fatigue life of A588 steel using a machine learning approach

In this paper, both experimental and machine learning results show that the fatigue life of A588 steel specimens with different gauge lengths and widths varies more greatly compared with that of the specimens with different thicknesses as the gauge dimensions are reduced from 15 mm to 1.5 mm. The optimal machine learning algorithm is derived to predict the fatigue life of specimens with a thickness of 1 mm, and the predicted results are verified by the fatigue experiments.

An interpretable machine-learned model for international oil trade network

Energy security and energy trade are the cornerstones of global economic and social development. The structural robustness of the international oil trade network (iOTN) plays an important role in the global economy. We integrate the machine learning optimization algorithm, game theory, and utility theory for learning an oil trade decision-making model that contains the benefit endowment and cost endowment of economies in international oil trades. We have reconstructed the network degree, clustering coefficient, and closeness of the iOTN well to verify the effectiveness of the model. In the end, policy simulations based on game theory and agent-based model are carried out in a more realistic environment. We find that export-oriented economies are more vulnerable to being affected than import-oriented economies after receiving external shocks. Moreover, the impact of the increase and decrease of trade friction costs on the international oil trade is asymmetrical, and there are significant differences between international organizations.

An in-process tool wear assessment using Bayesian optimized machine learning algorithm

An in-process tool wear assessment using Bayesian optimized machine learning algorithm