Machine Learning Models For Prediction Research Articles

The data mining and high-performance network model of tourism electronic word of mouth for analysis of factors influencing tourists’ purchasing behavior

This study establishes a deep learning model for personalized travel recommendations based on factors that affect tourists’ purchases to provide users with more accurate and personalized travel recommendations. Firstly, Natural Language Processing (NLP) technology is used to process and emotionally analyze tourism review information, dividing it into positive, negative, or neutral to understand tourists’ attitudes towards purchasing products and services. Secondly, a High-Performance Network (HPN) model is constructed based on factors that affect tourists’ purchases. The relationship among tourists, products, and word of mouth (WOM) is represented as a complex network to analyze and predict event occurrence patterns and influencing factors in tourism electronic word-of-mouth (EWOM) data. The construction of the model considers various factors, such as the spread of WOM, the impact of price, etc., to reveal the complex relationships among tourists, WOM, products, etc. Finally, the Recurrent Neural Network (RNN) model is combined with the Backpropagation (BP) model, the time series data is processed with the help of the gated recurrent unit, and the HPN model is trained and evaluated. The Yelp dataset is employed to verify the accuracy and feasibility of the model, which contains the score and review data of many tourist destinations. The results reveal that price, WOM, and destination are one of the main factors influencing tourists’ purchasing behavior, with WOM being the most significant. Positive WOM reviews remarkably increase product sales, while negative WOM has the opposite effect. The minimum expectation for age, occupation, education, personal monthly income, and tourists’ willingness to purchase is 0.00, and the minimum expectation for gender factors is 0.31. The RNN-BP hybrid model has higher accuracy and predictive ability, which is 1.73% and 2.30% more accurate than single models and traditional machine learning predictive models. In short, this study contributes to a better understanding travelers’ needs and preferences to optimize products and services and improve market competitiveness. In addition, the methods and models of this study can also be applied in EWOM data mining in other fields.

Flexural capacity prediction of reinforced UHPC beams using an interpretable machine learning model

Addressing the issues of inconsistency and limited accuracy in the current prediction models for the flexural capacity of reinforced ultrahigh-performance concrete (UHPC) beams, this paper proposes a machine-learning prediction model for the flexural capacity of reinforced UHPC beams based on interpretable Extreme Gradient Boosting (XGBoost) model. Firstly, a database containing 221 sets of experimental UHPC beam data is established, and the database quality is evaluated by Pearson correlation coefficient and Mahalanobis distance. Then, ten-fold cross-validation and the whale optimization algorithm (WOA) are employed to find the optimal hyperparameter combination for XGBoost. Different indices are used to evaluate the prediction accuracy of the XGBoost model with four typical machine learning models and other computational methods. The Shapley additive explanations (SHAP) method is used to provide interpretations of the prediction results. The results indicate that the XGBoost model outperforms the four other machine learning models and related standards. Compared with the existing formulas, the proposed prediction model demonstrates higher accuracy in predicting the flexural capacity of UHPC beams. The SHAP method effectively explains the prediction results of the XGBoost model, providing insights into accurately assessing the factors influencing the flexural capacity of UHPC beams. SHAP analysis reveals that the most significant factors affecting the flexural capacity of UHPC beams are the cross-sectional height and reinforcement ratio, while the least significant factors are the aspect ratio of steel fibers and volume fraction of steel fibers.

A machine learning-based method for predicting the shear behaviors of rock joints

In this study, machine learning prediction models (MLPMs), including artificial neural network (ANN), support vector regression (SVR), K-nearest neighbors (KNN), and random forest (RF) algorithms, were developed to predict the peak shear stress values and shear stress-displacement curves of rock joints. The database used contained 693 records of peak shear stress and 162 original shear stress-displacement curves derived from direct shear tests. The results demonstrated that the MLPMs provided reliable predictions for shear stress, with the mean squared errors (MSEs) between their predicted and measured shear stress varying from 0.003 to 0.069 and the coefficients of determination (R2 values) varying from 0.964 to 0.998. The feature importance values indicate that the joint surface roughness coefficient (JRC) is the most important influential factor in determining the peak shear stress, followed by the joint wall compressive strength (JCS), basic friction angle (φb), and shear surface area (As). Similarly, for the shear stress-displacement curve, the JRC is the dominant factor, followed by As, φb, and JCS. Additional direct shear tests were conducted for model validation. The validation shows that the MLPM predictions demonstrate improved consistency with the experimental results in relation to both the peak shear stress and peak shear displacement.

Performance prediction of 304 L stainless steel based on machine learning

With the development of testing technology and data mining methodologies, machine learning (ML) has been widely applied for predicting the performance of materials in various systems including stainless steel with improved performance. To address the limitations of traditional experimental and statistical methods in predicting the thermal deformation of materials, a predictive machine learning model was developed based on the data obtained from thermal simulation compression tests. Specifically, the Arrhenius and the Modified Johnson-Cook (J-C) Constitutive Model were developed utilizing experimental data to initially predict the rheological behavior of 1.52% Cu-304L stainless steel. Then, a physical metallurgy (PM)-guided Back Propagation (BP) model was developed, and Genetic Algorithm (GA), Whale Optimization Algorithm (WOA), and Mind Evolutionary Algorithm (MEA) were incorporated into the model for optimization purposes, respectively. Finally, the results indicate that the PM-MEA-BP model exhibits superior predictive performance, accurately forecasting the texture evolution of 304L stainless steel with random crystal orientation under rolling deformation conditions. Additionally, the present work also clearly demonstrated that the model not only satisfies precision requirement but also has certain guiding significance for optimizing process parameters and forecasting the microstructure and properties of stainless steel.

A Data-Driven Seismic Fragility Model for Post-Earthquake Repairable Performance of Highway Curved Bridge Portfolios

The rapid assessment of seismic fragility for highway curved bridges is crucial for enhancing the seismic resilience of transportation infrastructure. However, commonly used performance limit states fail to fully capture post-earthquake rehabilitation requirements. To address this, this paper proposes a data-driven, system-level seismic fragility assessment method for post-earthquake repairable performance of highway curved bridge portfolios. A sample database of curved bridge portfolios is generated using uniform design (UD) and a parametric finite element program, which then drives machine learning (ML) algorithms to develop a seismic fragility prediction model for post-earthquake repairable performance. The model is used to analyze the influence of various structural attributes on the median values of fragility curves (mR) for curved bridges. Additionally, a simplified fragility estimation method is developed based on the analysis results, and its reliability is validated through typical case studies. The results show that the central discrepancy of the UD sampling method is 0.0649, providing reliable and comprehensive data support for the ML prediction model. The fragility prediction model based on an artificial neural network (ANN) exhibits favorable fidelity and robustness. Curved bridges with central angles (α) in the range of 00.5rad show significant variations in mR, with a coupling effect observed between α and column height (H). The median absolute percentage error (MAPE) of the simplified fragility parameter calculation formula is below 11%, offering a preliminary reference for assessing the post-earthquake repairable performance of curved bridges.

A novel hybrid deep learning model for real-time monitoring of water pollution using sensor data

This study developed a hybrid model for predicting dissolved oxygen (DO) using real-time sensor data for thirteen parameters. This novel hybrid model integrated one-dimensional convolutional neural networks (CNN) and long short-term memory (LSTM) to improve the accuracy of prediction for DO in water. The hybrid CNN-LSTM model predicted DO concentration in water using soft sensor data. The primary input parameters to the model were temperature, pH, specific conductivity, salinity, density, chlorophyll, and blue-green algae. The model used 38,681 water quality data for training and testing the hybrid deep learning network. The training procedure for the model was successful. The training and test losses were both nearly zero and within a similar range. With a coefficient of determination (R2) of 0.94 and a mean squared error (MSE) of 0.12, the hybrid model indicated higher performance compared to the classical models. The normal distribution of residual errors confirmed the reliability of the DO predictions by the hybrid CNN-LSTM model. Feature importance analysis indicated pH as the most significant predictor and temperature as the second important predictor. The feature importance scores based on extreme gradient boosting (XGBoost) for the pH and temperature were 0.76 and 0.12, respectively. This study indicated that the hybrid model can outperform the classical machine learning models in the real-time prediction of DO concentration.

Machine learning predictive model to estimate the photo-degradation performance of stannates and hydroxystannates photocatalysts on a variety of waterborne contaminants

In this work, a comprehensive machine learning (ML) methodology was used to predict the degradation efficiency of different stannate and hydroxystannate photocatalysts on a wide range of waterborne pollutants. The structural, atomic features along with molecular fingerprints (MF) were used as descriptors of the crystalline phase of the photocatalysts and the organic compounds, respectively. The encoded features of the photocatalysts and contaminants along with the experimental variables of the degradation process are input to two ML models, named as RF (random forest) and KNN (K nearest neighbor). The RF model has achieved a very good prediction of the photocatalytic degradation efficiency (%) by different photocatalysts over a wide range of organic contaminants. The RF model performance was investigated by applying two different training strategies. The effects of different factors on photocatalytic degradation performance are further evaluated by feature importance analyses. Two illustrative applications on the use of the ML model for optimal photocatalyst selection and for assessing other types of photocatalysts for different environmental applications were provided.

Machine Learning Prediction of Quality of Life: Insight from Property Crime and Tropical Climate Analysis

<p align="center">This study delves into predicting the quality of life, a widely researched concept spanning various domains, employing mixed methodologies and indicators. Common predictors of overall quality of life encompass health status, socioeconomic factors, subjective well-being, and environmental conditions. Consequently, this research investigates the potential of utilizing machine learning prediction models for quality-of-life prediction, focusing on two key indicators.Five machine learning algorithms—Generalized Linear Model, Random Forest, Decision Tree, Gradient Boosted Tree, and Support Vector Machine—are empirically compared. Their performance in predicting quality of life is assessed based on property crime and tropical climate (temperature) attributes. Despite an initially low correlation value, temperature yields valuable insights for specific algorithms, enhancing predictive accuracy. This underscores the intricate and nuanced impact of seemingly unrelated factors in machine learning. The Support Vector Machine emerges as the top-performing algorithm, followed by Random Forest and Decision Tree. This paper offers a foundational research framework to aid educators and researchers in exploring quality of life prediction in-depth, utilizing property crime and temperature as key factors.</p>

Risk of intraoperative hemorrhage during cesarean scar ectopic pregnancy surgery: development and validation of an interpretable machine learning prediction model

Risk of intraoperative hemorrhage during cesarean scar ectopic pregnancy surgery: development and validation of an interpretable machine learning prediction model

Forecasting Power Consumption in the DSL Access Network System based on Network Activities by using Machine Learning

The widespread telecommunication networks and Internet services like Digital Subscriber Line (DSL) access has contributed to the growing demand of electricity. With environmental consciousness arising from non-renewable energy sources, coupled with rising demand, industries need to implement green strategies. This research focuses on predicting power consumption in DSL access networks using machine learning approaches. With an emphasis on Very High Bit Rate Digital Subscriber Line 2 (VDSL2) technology, the study investigates DSL modem’s power usage under an ideal and a bridge tap faulty conditions of copper cable along distances ranging from 100 to 1000 meters. The different levels of network activities are generated by IxChariot software and Pearson’s correlation techniques are used to analyse the relationship between power consumption and network activities. Combining the Train-Valid-Test and Random Forest algorithms, a predictive Machine Learning model is developed to forecast the power consumption based on relevant variables. The results show that power consumption tends to increase as the network activities are heavier and the proposed model presents a low minimum absolute error as a good model to forecast the power. It may aid Internet service providers to predict the optimum power limit in the network systems and pursue further investigation on how to reduce electricity use in the telecommunication field.

A Machine Learning Model for Prostate Cancer Prediction in Korean Men

Purpose: Unnecessary prostate biopsies for detecting prostate cancer (PCa) should be minimized. Therefore, this study developed a machine learning (ML) model to predict PCa in Korean men and evaluated its usability.Materials and Methods: We retrospectively analyzed clinical data from 928 patients who underwent prostate biopsies at Kangwon National University Hospital between May 2013 and May 2023. Of these, 377 (41.6%) were diagnosed with PCa, and 551 (59.4%) did not have cancer. For external validation, clinical data from 385 patients aged 48–89 years who underwent prostate biopsies from September 2005 to September 2023 at Wonju Severance Christian Hospital were also included. Twenty-two clinical features were used to develop an ML model to predict PCa. Features were selected based on their contributions to model performance, leading to the inclusion of 15 features. A meta-learner was constructed using logistic regression to predict the probability of PCa, and the classifier was trained and validated on randomly extracted training and test sets at an 8:2 ratio.Results: The prostate health index, prostate volume, age, nodule on digital rectal examination, and prostate-specific antigen were the top 5 features for predicting PCa. The area under the receiver operating characteristic curve (AUC) of the meta-learner logistic regression model was 0.89, and the accuracy, sensitivity, and specificity were 0.828, 0.711, and 0.909, respectively. Our model also showed excellent prediction performance for high-grade PCa, with a Gleason score of 7 or higher and an AUC of 0.903. Furthermore, we evaluated the performance of the model using external cohort clinical data and achieved an AUC of 0.863.Conclusions: Our ML model excelled in predicting PCa, specifically clinically significant PCa. Although extensive cross-validation in other clinical cohorts is needed, this ML model is a promising option for future diagnostics.

Research on Modified Thermal Barrier Coatings Against CMAS Corrosion Driven by Mechanism–Data Hybrid Model

With the development of high-efficiency gas turbine engines and increasing inlet temperatures, the performance of thermal barrier coatings (TBCs) for hot-section components has been more severely challenged. The doping of multi-element rare earth elements significantly improves the thermodynamic properties and chemical compatibility of thermal barrier coatings so that the application performance of coatings in high-temperature environments is enhanced considerably. In this work, the doped coatings prepared by REYSZ (RE = La, Sm, Nd) were investigated and characterized in terms of crystal structure, elastic properties, and thermal–mechanical properties based on the first-principles approach, combined with various empirical and semi-empirical formulations, and a predictive model for resistance to CMAS corrosion based on machine learning approaches. The results showed that the tetragonal phase REYSZ material was mechanically stable, had a large strain damage tolerance, and was not easy to fracture under applied loads and thermal shocks. In terms of CMAS corrosion resistance, the NdYSZ interfacial model had a lower surface energy (3.130 J/m2) and Griffith fracture energy (6.934 J/m2) compared with the conventional YSZ model, and Nd2O3 had the potential to improve the CMAS corrosion resistance of zirconia-based material for thermal barrier coatings. By evaluating the machine learning prediction models, the regression coefficients of the two algorithms were 0.9627 and 0.9740, and both these two prediction models showed high prediction accuracy and strong robustness. Ultimately, this work presented a novel mechanism–data hybrid method, which would facilitate the efficient development of TBC new materials for anti-CMAS corrosion.

Prediction Model and Knowledge Discovery for Roof Stress in Mined-Out Areas Integrating 3D Scanning Image Features

The accurate prediction of roof stress in mined-out areas is crucial for ensuring mine safety. However, existing study methods often overlook the increasingly available image data and fail to balance the model predictive capability with interpretability. To address these issues, this study innovatively integrates 3D laser scanning image features into the prediction of roof stress in mined-out areas. Image features are extracted using pre-trained deep-learning models and combined with traditional geological parameters to construct multiple machine-learning models for prediction. The experimental results demonstrate that models incorporating image features significantly outperform traditional models that rely solely on geological parameters in terms of prediction accuracy, interpretability, and complexity, revealing the critical role of image features in stress prediction. Furthermore, the use of SHapley Additive exPlanations (SHAP) to interpret the random forest model uncovers new domain knowledge, such as the relationship between spatial patterns and stress concentration. This study theoretically validates the effectiveness of image data and effectively balances the predictive capability and interpretability of the model, facilitating knowledge discovery in the field. On a practical level, it also provides guidance for mine safety management.

Multiparametric MRI-based Machine Learning Radiomics for Predicting Treatment Response to Transarterial Chemoembolization Combined with Targeted and Immunotherapy in Unresectable Hepatocellular Carcinoma: A Multicenter Study

Rationale and ObjectivesTo develop and validate multiple machine learning predictive models incorporating clinical features and pretreatment multiparametric magnetic resonance imaging (MRI) radiomic features for predicting treatment response to transarterial chemoembolization combined with molecular targeted therapy plus immunotherapy in unresectable hepatocellular carcinoma (HCC). Materials and methodsThis retrospective study involved 276 patients with unresectable HCC who received combination therapy from 4 medical centers. Patients were divided into one training cohort and two independent external validation cohorts. 16 radiomic features from six multiparametric MRI sequences and 2 clinical features were used to build six machine learning models. The models were evaluated using the area under the curve (AUC), decision curve analysis, and incremental predictive value. ResultsAlpha-fetoprotein and neutrophil-to-lymphocyte ratio are clinical independent predictors of treatment response. In the training cohort and two external validation cohorts, the AUCs and 95% confidence intervals for predicting treatment response were respectively 0.782 (0.673–0.793), 0.695 (0.514–0.708), and 0.679 (0.526–0.719) for the clinical model; 0.942 (0.846–0.932), 0.869 (0.700–0.881), and 0.868 (0.730–0.885) for the radiomics model; and 0.956 (0.859–0.942), 0.895 (0.738–0.903), and 0.892 (0.667–0.828) for the combined clinical-radiomics model. In the three cohorts, the incremental predictive value of the radiomics model over the clinical model was 49.2% (P < 0.001), 28.8% (P < 0.001), and 31.5% (P < 0.001). ConclusionThe combined clinical-radiomics model may provide a reliable and non-invasive tool to predict individual treatment responses and guide and improve clinical decision-making in combination therapy of HCC patients.

Mechanical Behavior and Failure Prediction of Cylindrical Lithium-Ion Batteries under Mechanical Abuse Using Data-Driven Machine Learning

Abstract Mechanical failure prediction of lithium-ion batteries (LIBs) can provide important maintenance information and decision-making reference in battery safety management. However, the complexity of the internal structure of batteries poses challenges to the generalizability and prediction accuracy of traditional mechanical models. In view of these challenges, emerging data-driven methods provide new ideas for failure prediction of LIBs. This study is based on experimental data-driven application of machine learning (ML) models to rapidly predict the mechanical behavior and failure of cylindrical cell under different loading conditions. Mechanical abuse experiments including local indentation, flat compression, and three-point bending experiments were conducted on cylindrical LIB samples, and mechanical failure datasets for cylindrical cells were generated, including displacements, voltages, temperatures, and mechanical forces. Six ML models were used to predict the mechanical behavior of cylindrical batteries, and four metrics were used to evaluate the prediction performance, and the coefficients of determination of Extreme Gradient Boosting (XGBoost) Regression and Random Forest were 0.999, and the root-mean-square errors (RMSE) were lower than 0.015. It is shown that the integrated tree models tested in this study are suitable for the failure prediction of LIBs under the conditions of mechanical abuse. Also, Random Forest prediction model outperforms other ML prediction models with the smallest RMSE values of 0.005, 0.0149, and 0.007 for local indentation, flat compression, and three-point bending, respectively. This work highlights the capability of ML algorithms for LIB safety prediction.

Predictive Modeling in IoT-Driven Agriculture: A Comparative Study of Regression and Classification with LIME Interpretability

Abstract. This study aims to compare the performance of regression and classification machine learning models in crop prediction by analyzing data from IoT-driven agriculture. Linear regression and random forest regression models were used to predict the percentage of root growth dry matter, while logistic regression and support vector machines were employed to classify crop production regions. To enhance model interpretability, the LIME tool was applied to analyze feature importance. The experimental results demonstrate that the models perform well in terms of prediction accuracy, and LIME provided clear feature explanations, helping identify the variables with the greatest impact on prediction outcomes. This research offers data-driven insights for optimizing resource management in smart agricultural systems.

Multi-objective optimization of solar air heater having centerline perforated sine wave baffles using experimental and machine learning based approaches

ABSTRACT The efficiency of smooth surface solar air heaters (SAHs) is often limited by viscous boundary layer formation and aerodynamic constraints, resulting in suboptimal thermal performance. This study introduces a novel enhancement technique using centerline perforated sine wave baffles as turbulators on the SAH surface to improve heat transfer and reduce flow resistance. The current work deals with experimental analysis of solar air heater performance using centerline perforated sine wave baffles placed as turbulators over the surface of solar air heater. Experimental analyses are conducted by varying Reynolds number, relative baffle pitch, relative baffle height, angle of attack, and relative perforation diameter, ranging from 3000 to 18,000, 8 to 14, 0.4 to 0.55, 10° to 45°, and 0.1 to 0.2 respectively. Collected experimental data are utilized to develop predictive machine learning models for Nusselt number, friction factor, and thermo-hydraulic analysis. Several models including Linear Regression, Random Forest, K-Nearest Neighbors, Adaptive Boosting, and Extreme Gradient Boosting are employed, with their performance evaluated using Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, and R2. Extreme Gradient Boosting emerges as the most effective predictive model with an R2 value of 98.2%, alongside Mean Absolute Error and Root Mean Squared Error values of 8.025 and 11.3 respectively. Multi-objective optimization techniques such as Particle Swarm Optimization, Simulated Annealing, Genetic Algorithm, and Hybrid Genetic Algorithm are employed for this purpose. The optimized parameters obtained from Genetic Algorithm include Reynolds number, and values of 17,447, 8.37, 0.48, 25.045, and 0.11 respectively, aiming at maximizing and while minimizing. The results of genetic algorithms are being taken as optimal parameters which resulted in Reynolds number, relative baffle pitch, relative baffle height, angle of attack, and relative perforation diameter as 17,447, 8.37, 0.48, 25.045 and 0.11.

Prognostic effects of glycaemic variability on diastolic heart failure and type 2 diabetes mellitus: insights and 1-year mortality machine learning prediction model

BackgroundDiastolic heart failure (DHF) and type 2 diabetes mellitus (T2DM) often coexist, causing increased mortality rates. Glycaemic variability (GV) exacerbates cardiovascular complications, but its impact on outcomes in patients with DHF and T2DM remains unclear. This study examined the relationships between GV with mortality outcomes, and developed a machine learning (ML) model for long-term mortality in these patients.MethodsPatients with DHF and T2DM were included from the Medical Information Mart for Intensive Care IV, with admissions (2008–2019) as primary analysis cohort and admissions (2020–2022) as external validation cohort. Multivariate Cox proportional hazards models and restricted cubic spline analyses were used to evaluate the associations of GV with 90-day, 1-year, and 3-year all-cause mortality. The primary analysis cohort was split into training and internal validation cohorts, then developing ML models for predicting 1-year all-cause mortality in training cohort, which were validated using the internal and external validation cohorts.Results2,128 patients with DHF and T2DM were included in primary analysis cohort (meidian age 71.0years [IQR: 62.0–79.0]; 46.9% male), 498 patients with DHF and T2DM were included in the external validation cohort (meidian age 75.0years [IQR: 67.0–81.0]; 54.0% male). Multivariate Cox proportional hazards models showed that high GV tertiles were associated with higher risk of 90-day (T2: HR 1.45, 95%CI 1.09–1.93; T3: HR 1.96, 95%CI 1.48–2.60), 1-year (T2: HR 1.25, 95%CI 1.02–1.53; T3: HR 1.54, 95%CI 1.26–1.89), and 3-year (T2: HR 1.31, 95%CI: 1.10–1.56; T3: HR 1.48, 95%CI 1.23–1.77) all-cause mortality, compared with lowest GV tertile. Chronic kidney disease, creatinine, potassium, haemoglobin, and white blood cell were identified as mediators of GV and 1-year all-cause mortality. Additionally, GV and other clinical features were pre-selected to construct ML models. The random forest model performed best, with AUC (0.770) and G-mean (0.591) in internal validation, with AUC (0.753) and G-mean (0.599) in external validation.ConclusionGV was determined as an independent risk factor for short-term and long-term all-cause mortality in patients with DHF and T2DM, with a potential intervention threshold around 25.0%. The ML model incorporating GV demonstrated strong predictive performance for 1-year all-cause mortality, highlighting its importance in early risk stratification management of these patients.

Influence of Modal Decomposition Algorithms on Nonlinear Time Series Machine Learning Prediction Models in Engineering: A Case Study of Subway Tunnel Settlement

The settlement values of subway tunnels during the construction period exhibit significant nonlinear and spatial‒temporal variation characteristics. To overcome the problems of historical data interference and spatiotemporal characteristics in tunnel settlement prediction models, this paper proposes a tunnel settlement prediction method based on data decomposition, reconstruction, and optimization. First, the original data are optimized via the SSA, which has global optimization capability, high noise immunity, and high adaptivity. The original signal is subsequently decomposed into multiple subsignal sequences via a variational modal decomposition (VMD) algorithm combined with a rolling decomposition technique. Finally, the decomposed signals are fed into the machine learning model to construct a high-precision settlement prediction model based on rolling decomposition. The prediction accuracy of different models was analyzed via the measured settlement data during the construction period of the Beijing subway as an example. The results show that the prediction model with the integrated decomposition algorithm reduces the RMSE and MAE by 33% and 37%, respectively, which significantly improves the prediction accuracy and generalization ability of the neural network to meet the demand of practical engineering prediction and simultaneously enhances the risk warning ability of the model.

SCAN: a nanopore-based, cost effective decision-supporting tool for mass screening of aneuploidies

In developed countries, Newborn Screening (NBS) programs aim to detect treatable yet clinically silent disorders. The selection of disorders to be included in NBS considers severity, treatment availability, prevalence, and analysis cost. However, numerous genetic disorders remain excluded from routine testing due to high expenses and specialized equipment requirements. Here we present SCAN, a novel, non-invasive, and cost-effective decision-support tool utilizing nanopore sequencing for estimating proportions of chromosomes responsible for the most common aneuploidies. SCAN combines DNA enrichment (amplification), barcoding, nanopore sequencing, and machine learning predictive modeling. In a proof-of-concept study for Klinefelter Syndrome, SCAN achieved 100% sensitivity, specificity, and accuracy, becoming the world’s first IVD-certified genetic test utilising nanopore sequencing. Further model training shows promise in expanding this assay to detect other chromosomal aneuploidies included in the protocol.