Superior Predictive Capability Research Articles

Exploring the factors influencing the intention to clothing and textiles recycling among Chinese college students': a study based on TPB and VBN.

Recycling apparel and fabrics is essential for preserving resources and protecting the environment, providing considerable global advantages for ecology and society. This study sought to explore the participation of Chinese college students in the recycling of clothing and fabrics by combining the Theory of Planned Behavior (TPB), the Value-Belief-Norm theory (VBN), self-identity, school education, and perceived policy effectiveness to create a comprehensive model. A total of 1,027 valid samples were obtained through stratified sampling and random sampling, primarily sourced from Eastern China, and analyzed through Structural Equation Modeling (SEM) utilizing AMOS. The results of the research suggested the following: (1) College students' biospheric values emerged as the most influential factor in predicting their inclination to participate in recycling behavior. (2) VBN (encompassing biospheric and altruistic values) and self-identity significantly contributed to shaping attitude and perceived behavioral control, which in turn impacted individuals' intention to participate in recycling. (3) School education exerted a stronger moderating influence than perceived policy effectiveness on the relationship between attitude, perceived behavioral control, and intention. The comprehensive model proposed in this study demonstrated superior predictive capability in explaining college students' willingness to participate in clothing and textiles recycling. It has been proven to be practical and effective. Lastly, schools should promote the practice of clothing and textiles recycling, cultivate good values, and utilize the power of social influence to encourage college students to participate in clothing and textiles recycling. The government should improve relevant laws and regulations, collaborate with academia, and adopt measures like incentives to create a pro-environment atmosphere.

A novel attention-based cross-modal transfer learning framework for predicting cardiovascular disease

Cardiovascular disease (CVD) remains a leading cause of death globally, presenting significant challenges in early detection and treatment. The complexity of CVD arises from its multifaceted nature, influenced by a combination of genetic, environmental, and lifestyle factors. Traditional diagnostic approaches often struggle to effectively integrate and interpret the heterogeneous data associated with CVD. Addressing this challenge, we introduce a novel Attention-Based Cross-Modal (ABCM) transfer learning framework. This framework innovatively merges diverse data types, including clinical records, medical imagery, and genetic information, through an attention-driven mechanism. This mechanism adeptly identifies and focuses on the most pertinent attributes from each data source, thereby enhancing the model’s ability to discern intricate interrelationships among various data types. Our extensive testing and validation demonstrate that the ABCM framework significantly surpasses traditional single-source models and other advanced multi-source methods in predicting CVD. Specifically, our approach achieves an accuracy of 93.5%, precision of 92.0%, recall of 94.5%, and an impressive area under the curve (AUC) of 97.2%. These results not only underscore the superior predictive capability of our model but also highlight its potential in offering more accurate and early detection of CVD. The integration of cross-modal data through attention-based mechanisms provides a deeper understanding of the disease, paving the way for more informed clinical decision-making and personalized patient care.

Enhancing early-stage cell culture process development efficiency using an integrated approach of high-throughput miniaturized bioreactors and definitive screening design

Rapidly expanding pipelines in biopharmaceutical industry and increasingly stringent requirements from regulatory agencies call for a more efficient and rational study design at early-stage cell culture process development. Recent developments in high-throughput bioreactor system and design of experiments (DoE) enable cell culture process development sector to meet such demand by integrating both technological advances. In this study, we compared varied forms of fractional factorial designs (FFDs) and definitive screening design (DSD) covering key process parameters such as temperature shift target, temperature shift timing, feed strategy, pH, dissolved oxygen, harvest time and additives in Ambr® 15 bioreactors to better understand the initial cell culture process and thus optimize it. Results showed that DSD was more effective and efficient in detecting both main and quadratic effects comparing to FFDs. Comparison of varied available model development strategies revealed that two-stage forward regression combined with corrected Akaike's information criterion (AICc) and least absolute shrinkage and selection operator (LASSO) regression combined with self-validated ensembled models (SVEM) offered superior predictive capability. Moreover, key DoE regularities was evaluated for their validity. In conclusion, DSD is a suitable experimental design for the early-stage cell culture process development if quadratic effects might exist. Statistical models derived based on DSD-based dataset could be applied for predictive optimization of antibody producing bioprocess while regularities such as effect heredity and effect hierarchy might be relaxed considering higher-order interaction effects are more likely to existed for a cell-based biological system.

Comparison of Carotid Ultrasound Parameters in Patients with Rheumatoid Arthritis and Control Subjects: A Cross-sectional Study

Introduction: Rheumatoid Arthritis (RA) is considered one of the risk factors for Cardiovascular Disease (CVD). Carotid ultrasound is used to assess the extent of subclinical atherosclerosis in patients with RA. Very few studies have evaluated all carotid ultrasound findings, such as Carotid Intima-media Thickness (CIMT), carotid diameters like Luminal Diameter (LD) and Interadventitial Diameter (IAD), and plaque characteristics in patients with RA. Aim: To assess and compare the various carotid parameters in RA patients with controls and also to evaluate their association with age and duration of onset of the disease. Materials and Methods: A single-centre cross-sectional study was conducted at the Department of Radiology, GCS Medical College and Hospital, Ahmedabad, Gujarat, India, involving 40 patients with RA (Group-RA) and 40 controls (Group-C). Patients were further divided into three age subgroups. Carotid ultrasound parameters like CIMT, LD, IAD, and plaque were evaluated in both groups. Continuous variables were analysed using the t-test, and categorical data were analysed using the Chi-squared test. A p-value of < 0.05 was considered statistically significant. Results: Age- and sex-matched controls were included with 28 females and 12 males in both the study groups. The mean LD and IAD were significantly higher in the RA group than in controls (Mean LD- 5.88±0.97 mm vs 5.26±1.08 mm with p=0.009; Mean IAD- 6.85±0.89 mm vs 6.30±0.87 mm with p=0.006). The mean CIMT was higher in the RA group but not statistically significant (0.57±0.13 mm vs 0.54±0.12 mm with p=0.256). Further subgroup analysis showed that all carotid parameters were statistically significant in the 31-60 years age group as compared to 18-30 years and 61-80 years subgroups. The effect of the duration of the disease (>5 years) on the carotid parameters was also significantly higher in the 30-60 age group (p<0.001). Conclusion: The present study showed that various carotid ultrasound parameters can be used as a screening tool in the follow-up of RA patients to detect early changes in atherosclerosis, with LD and IAD having superior predictive capability. The study further showed that carotid ultrasound parameters have a better predictive value in the 31-60 years age group.

Prognostic Impact of the Tricuspid Annular Plane Systolic Excursion/Pulmonary Arterial Systolic Pressure Ratio in Acute Pulmonary Embolism.

Currently available risk stratification models for acute pulmonary embolism (PE) include hemodynamic status, cardiac biomarkers, right ventricle (RV) dysfunction on imaging, and clinical scores. Focusing on the length-tension relationship of the ventricle might have a superior predictive capability over RV dysfunction in terms of mortality and classification of patients with acute PE. In this study, our hypothesis suggests that the tricuspid annular plane systolic excursion (TAPSE)/systolic pulmonary artery pressure (sPAP) ratio has superior predictive capability for in-hospital mortality in patients with acute PE compared to TAPSE or sPAP as distinct measures. This single-center study comprised retrospectively evaluated 703 patients referred to our tertiary cardiovascular center with acute PE. We divided patients into quartiles based on the TAPSE/sPAP ratio. Different models were developed to quantify the predictive relationship between in-hospital death and echocardiographic measurements. A base model was created with variables including risk status and RV/LV ratio >1. Then, to evaluate the predictive contribution of each measurement; TAPSE/sPAP, TAPSE, and sPAP were sequentially added to the base model. After that, the performance of each model was evaluated. Predictive and discriminative power was the highest in model containing TAPSE/sPAP. There was still a significant inverse association between TAPSE/sPAP and the risk of in-hospital death even after adjusting for risk status and RV/LV ratio >1. Receiver operating characteristic curve analysis for TAPSE/sPAP revealed the best cut-off value as 0.34. The outcomes of our study reveal that the ratio of TAPSE/sPAP serves as a more potent predictor of mortality than either of the 2 measurements taken separately. The interpretation and utilization of the TAPSE/sPAP cut-off value in acute PE can assist in identifying patients at risk of deterioration and guide the consideration of more intensive treatment options across all risk groups.

The association of triglyceride-glucose index and combined obesity indicators with chest pain and risk of cardiovascular disease in American population with pre-diabetes or diabetes.

To investigate the correlation of the triglyceride-glucose (TyG) index and its combined obesity indicators with chest pain and cardiovascular disease (CVD) in the pre-diabetes and diabetes population. This cross-sectional investigation encompassed 6488 participants with diabetes and pre-diabetes who participated in the National Health and Nutrition Examination Survey (NHANES) between 2007 and 2016. The association of the TyG and combined obesity index with chest pain and CVD was investigated using weighted logistic regression models and restricted cubic spline (RCS) analysis. The receiver operating characteristic (ROC) curve analysis was performed to compare different indicators. In multivariate logistic regression fully adjusted for confounding variables, our analyses revealed significant associations between TyG, TyG-BMI, TyG-WC, and TyG-WHtR and chest pain, with adjusted ORs (95% CI) of 1.21 (1.05, 1.39), 1.06 (1.01, 1.11), 1.08 (1.04, 1.14), and 1.27 (1.08, 1.48), respectively. For total-CVD, the adjusted ORs (95% CI) were 1.32 (1.08, 1.61), 1.10 (1.03, 1.17), 1.13 (1.06, 1.19), and 1.63 (1.35, 1.97), respectively, among which TyG, TyG-WC, and TyG-WHtR present curvilinear associations in RCS analysis (all P-nonlinear < 0.05). Furthermore, the ROC curve showed that TyG-WC had the most robust predictive efficacy for total-CVD, coronary heart disease (CHD), and myocardial infarction (MI), while TyG-WHtR had the best predictive ability for angina and heart failure. There are significant associations of TyG and its related indicators with chest pain and total-CVD among the pathoglycemia population. TyG-WC and TyG-WHtR demonstrated superior predictive capability for the incidence of cardiovascular events.

Association between weight-adjusted-waist index and gynecologic cancers: a population-based study.

This study aims to analyze the association between the weight-adjusted waist index (WWI) and the risk of gynecologic cancers, using data collected from the National Health and Nutrition Examination Survey (NHANES) from 2011 to 2016. We employed multiple logistic regression analysis to investigate the relationship between WWI and risk of gynecologic cancers. Subsequent subgroup analyses were performed on specific populations of interest. A restricted cubic spline model was used to explore potential non-linear relationships. Additionally, the effectiveness of WWI in predicting sarcopenia was assessed through Receiver Operating Characteristic (ROC) curve analysis. K-fold cross-validation was applied for model assessment. Among the 4,144 participants, 98 self-reported having gynecologic cancers. In the fully adjusted model, WWI was significantly associated with the prevalence of gynecologic cancers (OR = 1.38, 95% CI: 1.02-1.88, p = 0.0344). Our findings indicate a linear positive association between WWI and the risk of gynecologic cancers. Subgroup analysis revealed that WWI had the strongest association with cervical cancer (OR = 1.46, 95% CI: 0.97-2.18, p = 0.0354) and endometrial cancer (OR = 1.39, 95% CI: 0.81-2.39, p = 0.0142). No significant association was found between WWI and the risk of ovarian cancer (OR = 1.16, 95% CI: 0.48-2.72, p = 0.5359). Restricted cubic spline analysis confirmed a linear relationship between WWI and the risk of cervical, endometrial, and ovarian cancers. ROC curve analysis demonstrated that WWI had superior predictive capability for gynecologic cancers. Elevated levels of WWI were significantly associated with an increased risk of gynecologic cancers in American women, displaying a stronger association than other obesity markers. Therefore, WWI may serve as a distinct and valuable biomarker for assessing the risk of gynecologic cancers, particularly cervical and endometrial cancers.

Design of some potent non-toxic Autoimmune disorder inhibitors based on 2D-QSAR, CoMFA, molecular docking, and molecular dynamics investigations

Current clinical research suggests that inhibitors of protein arginine deiminase 4 (PAD4), major histocompatibility complex (MHC) class II HLA-DQ-ALPHA chain, and thyrotropin receptor (or TSH receptor) which are of biological and therapeutic interest, may show potential in treating rheumatoid arthritis, type 1 diabetes, Graves' disease and other autoimmune disorder. In the present study, a comprehensive analysis was conducted on a collection of 32 compounds concerning their anti-rheumatoid arthritis activity as inhibitors of PAD4. This analysis represents the first instance in which these compounds were computationally examined, employing an in-silico approach that considered 2D-3D QSAR modeling, and molecular docking and was further validated through molecular dynamics and ADMET properties assessment. A credible 2D QSAR (Q_LOO^2 ​= ​0.6611 and R^2 ​= ​0.7535) model was constructed and verified using an external validation test set, Y-randomization, variance inflation factor (VIF), mean effect (MF), and William's plot applicability domain (AD). Ligand-based alignment was implemented in the 3D-QSAR examination. The outcomes demonstrated that CoMFA (uvepls) (Q2LOO ​= ​0.5877; R2 ​= ​0.9983) possess remarkable stability and foresight. The internal validation indicated that CoMFA (uvepls) MIFs display superior predictive capability compared to COMFA (ffdsel). Structural criteria determined by the contour maps of the model and molecular docking simulations were strategically employed to computationally develop 10 new, non-toxic autoimmune disease inhibitors with increased efficacy. Docking tests were done on the newly developed compounds to illustrate their binding mechanism and to identify critical interaction residues inside the active region of rheumatoid arthritis (PDB id: 3BLU). In addition, docking results of the selected designed compounds inside the active sites of type 1 diabetes receptor (6DFX), and Graves' disease receptor (4QT5) demonstrated their rheumatoid arthritis (PDB id: 3BLU) selectivity. A molecular dynamics simulation and binding free energy calculations using the MM/GBSA technique confirmed the stability of the proposed compound D4 inside the rheumatoid arthritis (3BLU) receptor active site. In summary, the results of our investigation might give considerable insight into the future design and development of new autoimmune disease inhibitors.

An improved stacking-based model for wave height prediction

&lt;p&gt;Wave height prediction is hampered by the volatility and unpredictability of ocean data. Traditional single predictors are inadequate in capturing this complexity, and weighted fusion methods fail to consider inter-model correlations, resulting in suboptimal performance. To overcome these challenges, we presented an improved stacking-based model that combined the long short-term memory (LSTM) network with extremely randomized trees (ET) for wave height prediction. Initially, features with weak correlation to wave height were excluded using the Pearson correlation coefficient. Subsequently, a stacking ensemble tailored for time series cross-validation was deployed, employing LSTM and ET as base learners to capture temporal and feature-specific patterns, respectively. Lasso regression was utilized as the meta-learner, harmonizing these insights to improve accuracy by leveraging the strengths of each model across different dimensions of the data. Validation using datasets from four buoy stations demonstrated the superior predictive capability of our proposed model over single predictors such as temporal convolutional networks (TCN) and XGBoost, and fusion methods like LSTM-ET-BP.&lt;/p&gt;

A Physics-Guided Bi-Fidelity Fourier-Featured Operator Learning Framework for Predicting Time Evolution of Drag and Lift Coefficients

In the pursuit of accurate experimental and computational data while minimizing effort, there is a constant need for high-fidelity results. However, achieving such results often requires significant computational resources. To address this challenge, this paper proposes a deep operator learning-based framework that requires a limited high-fidelity dataset for training. We introduce a novel physics-guided, bi-fidelity, Fourier-featured deep operator network (DeepONet) framework that effectively combines low- and high-fidelity datasets, leveraging the strengths of each. In our methodology, we begin by designing a physics-guided Fourier-featured DeepONet, drawing inspiration from the intrinsic physical behavior of the target solution. Subsequently, we train this network to primarily learn the low-fidelity solution, utilizing an extensive dataset. This process ensures a comprehensive grasp of the foundational solution patterns. Following this foundational learning, the low-fidelity deep operator network’s output is enhanced using a physics-guided Fourier-featured residual deep operator network. This network refines the initial low-fidelity output, achieving the high-fidelity solution by employing a small high-fidelity dataset for training. Notably, in our framework, we employ the Fourier feature network as the trunk network for the DeepONets, given its proficiency in capturing and learning the oscillatory nature of the target solution with high precision. We validate our approach using a well-known 2D benchmark cylinder problem, which aims to predict the time trajectories of lift and drag coefficients. The results highlight that the physics-guided Fourier-featured deep operator network, serving as a foundational building block of our framework, possesses superior predictive capability for the lift and drag coefficients compared to its data-driven counterparts. The bi-fidelity learning framework, built upon the physics-guided Fourier-featured deep operator, accurately forecasts the time trajectories of lift and drag coefficients. A thorough evaluation of the proposed bi-fidelity framework confirms that our approach closely matches the high-fidelity solution, with an error rate under 2%. This confirms the effectiveness and reliability of our framework, particularly given the limited high-fidelity dataset used during training.

Comparison of TNM AJCC/UICC 8th with JES 11th staging systems for prognostic prediction in patients with esophageal squamous cell carcinoma who underwent radical (chemo) radiotherapy in China.

The aim of the study was to compare the prognostic prediction performances of the American Joint Committee on Cancer (AJCC)/Union for International Cancer Control (UICC) 8th staging system and the Japan Esophageal Society (JES) 11th staging system for patients with esophageal squamous cell carcinoma who underwent radical (chemo) radiotherapy. In total, 574 patients were enrolled and categorized according to the tumor, node metastasis (TNM) AJCC/UICC 8th and JES 11th editions. Survival rates and disease-free survival were computed using the Kaplan-Meier technique. The log-rank test was used for survival difference analysis. (1) The 8th AJCC/UICC N staging exhibited significant stratification for overall survival (OS) and progression-free survival (PFS). JES 11th showed significant OS stratification, but PFS was not well-stratified for N2-N4. (2) Both staging systems demonstrated significant stratification for OS and PFS. (3) AJCC/UICC 8th TNM staging yielded significantly well-stratified OS and PFS in the differing staging group. JES 11th failed to stratify OS and PFS for stages III and IVA. (4) AJCC/UICC 8th TNM stratified OS and PFS significantly well for lower and middle region tumors, whereas JES 11th inadequately stratified stages III and IVA. (5) Significant multivariable analysis results indicated that AJCC/UICC 8th independently predicted poor OS and PFS. In Chinese patients with esophageal squamous cell carcinoma who underwent radical (chemo) radiotherapy, the AJCC/UICC 8th edition exhibited superior prognostic prediction capabilities compared with the JES 11th edition.

Enhanced Restaurant Rating Predictions: A Study of Linear and Ensemble Regression Methods

In this study, we investigate the application of various regression techniques to predict restaurant ratings based on a comprehensive Zomato dataset. The dataset encompasses 51,717 entries with features such as restaurant type, location, cuisine, and cost estimates. We employed four regression models: Linear Regression, CatBoost Regressor, Random Forest Regressor, and Decision Tree Regressor, to evaluate their performance in predicting ratings. The models were assessed using the R-squared (R²) metric to determine their effectiveness. The Random Forest Regressor achieved the highest R² score of 0.875, indicating its superior predictive capability. The CatBoost Regressor also performed well, demonstrating the effectiveness of gradient boosting methods. The study provides insights into the performance of various regression models and highlights the advantages of ensemble methods for accurate restaurant rating predictions.

Factors Influencing Functional Coronary Artery Ischemia: A Gender-Specific Predictive Model.

The objective of this study was to explore factors that impact functional coronary artery ischemia (FCAI) and develop a gender-specific prognostic model that could serve as a benchmark for predicting FCAI in clinical practice. A cumulative total of 330 patients were enrolled comprising 634 main and branch coronary, consisting of 179 men (359 coronary arteries) and 151 women (275 coronary arteries). Based on the computed tomography-fractional flow reserve (CT-FFR), the coronary arteries of male and female patients were classified into the non-ischemic group (CT-FFR ≥ 0.80) and the ischemic group (CT-FFR < 0.80). We screened for factors related to the CT-FFR values of the coronary arteries in male and female patients and developed corresponding gender-specific models. In male patients, the correlation between FCAI and several indicators, including white blood cell (WBC) count, left anterior descending artery (LAD) lesions, pericoronary fat attenuation index (FAI), and the degree of coronary artery stenosis, was found to be statistically significant. A predictive model was developed using these factors, yielding an area under the curve (AUC) value of 0.812, with a P value of < 0.001 and a 95% confidence interval (CI) ranging from 0.767 to 0.857. This model demonstrated superior predictive capability compared to any individual indicators mentioned above. Significant correlations with FCAI were observed in female patients for hemoglobin (Hb), systolic blood pressure (SBP), FAI, and the degree of coronary artery stenosis. The predictive model, derived from these factors, exhibited robust performance with an area under the curve (AUC) value of 0.818, a P value of < 0.001, and a 95% confidence interval (CI) ranging from 0.764 to 0.872. Gender disparities exist in the factors affecting FCAI, underscoring the need for a gender-specific predictive model to enhance the precision of FCAI prediction.

Remaining Useful Life Estimation of Turbofan Engines with Deep Learning Using Change-Point Detection Based Labeling and Feature Engineering

Accurate remaining useful life (RUL) prediction is one of the most challenging problems in the prognostics of turbofan engines. Recently, RUL prediction methods for turbofan engines mainly involve data-driven models. Preprocessing the sensor data is essential for the performance of the prognostic models. Most studies on turbofan engines use piecewise linear (PwL) labeling, which starts with a constant initial RUL value in normal/healthy operating time. In this study, we designed a prognostic procedure that includes difference-based feature construction, change-point-detection-based PwL labeling, and a 1D-CNN-LSTM (one-dimensional–convolutional neural network–long short-term memory) hybrid neural network model for RUL prediction. The procedure was evaluated on the subset FD001 of the C-MAPSS dataset. The proposed procedure was compared with machine learning and deep learning models with and without the new difference feature. Also, the results were compared with the studies that used similar labeling approaches. Our analysis of the numerical results underscores the clear superiority of the proposed 1D-CNN-LSTM model with the difference feature in RUL prediction, with a score of 437.2 and an RMSE value of 16.1. This result illustrates the superior predictive capability of the 1D-CNN-LSTM model, which outperformed traditional machine learning methods and one of the earliest deep learning methods. These findings emphasize the superior predictive capability of the 1D-CNN-LSTM model and underline the potential of the feature engineering process for more accurate and robust RUL prediction in the context of turbofan engine prognostics.

Monitoring leaf area index of the sown mixture pasture through UAV multispectral image and texture characteristics

Leaf area index (LAI) is an important phenotypic trait closely related to photosynthesis, respiration, and water utilization. In recent years, unmanned aerial vehicles (UAVs) multispectral capabilities enable the acquisition of spectral information from visible light to near infrared, facilitating vegetation growth monitoring. This study aims to explore the methodology of combining vegetation indices, color indices, texture information, and ecological factors based on UAV multispectral images to enhance the accuracy of the sown mixture pasture LAI estimation. A field experiment involving 13 mixed sowing combinations of alfalfa (Medicago sativa L.), tall fescue (Festuca elata Keng ex E. Alexeev) and plantain (Plantaga lanceolata L.) was conducted out. Multiple linear regression, Bagging algorithm, support vector machine (SVM), random forest algorithm (RF), KNN algorithm, and back propagation neural network (BP) were used to construct the LAI prediction model. The results showed that combining vegetation index (VI) + color index (CI) + normalized difference texture index (NDTI), and ecological factors (EF) could enhance the accuracy of LAI estimation. The sensitive characteristic combinations for alfalfa, tall fescue, and plantain were found to be NDRE (Normalized difference red-edge index) + NGBDI (Normalized green–blue difference index) + (B) MEA-(G) HOM (Blue band Mean - Green band Homogeneity) + DTR (Daily temperature difference), MSR (Modified simple ratio) + NGRDI (Normalized green–red difference index) + (G) COR-(R) VAR (Green band Correlation – Red band Variance) + DTR (Daily temperature difference)), and MSR (Modified simple ratio) + ExG (Excess green) + (G) SEM-(G) MEA (Green band Second-order moment – Green band Mean) + DTR (Daily temperature difference), respectively. RF exhibited superior prediction capability, further enhancing the accuracy of forage LAI prediction. The alfalfa, tall fescue, and plantain obtained coefficient of determination (R2) of 0.83, 0.79 and 0.79, root mean squared error (RMSE) of 0.50, 0.58 and 0.70, and mean absolute error (MAE) of 0.36, 0.45 and 0.55, respectively. These findings provide valuable insights for the estimation of leaf area index of the sown mixture pasture through UAV multispectral images and texture characteristics.

Estimating the Quality of the Most Popular Machine Learning Algorithms for Landslide Susceptibility Mapping in 2018 Mw 7.5 Palu Earthquake

The Mw 7.5 Palu earthquake that occurred on 28 September 2018 (UTC 10:02) on Sulawesi Island, Indonesia, triggered approximately 15,600 landslides, causing about 4000 fatalities and widespread destruction. The primary objective of this study is to perform landslide susceptibility mapping (LSM) associated with this event and assess the performance of the most widely used machine learning algorithms of logistic regression (LR) and random forest (RF). Eight controlling factors were considered, including elevation, hillslope gradient, aspect, relief, distance to rivers, peak ground velocity (PGV), peak ground acceleration (PGA), and lithology. To evaluate model uncertainty, training samples were randomly selected and used to establish the models 20 times, resulting in 20 susceptibility maps for different models. The quality of the landslide susceptibility maps was evaluated using several metrics, including the mean landslide susceptibility index (LSI), modelling uncertainty, and predictive accuracy. The results demonstrate that both models effectively capture the actual distribution of landslides, with areas exhibiting high LSI predominantly concentrated on both sides of the seismogenic fault. The RF model exhibits less sensitivity to changes in training samples, whereas the LR model displays significant variation in LSI with sample changes. Overall, both models demonstrate satisfactory performance; however, the RF model exhibits superior predictive capability compared to the LR model.

A super-grid approach for LES combustion closure using the Linear Eddy Model

LES–LEM is a simulation approach for turbulent combustion in which the stochastic Linear Eddy Model (LEM) is used for sub-grid mixing and combustion closure in Large-Eddy Simulation (LES). LEM resolves, along a one-dimensional line, all spatial and temporal scales, provides on-the-fly local turbulent flame statistics, captures finite rate chemistry effects and directly incorporates turbulence-chemistry interaction. However, the approach is computationally expensive as it requires advancing an LEM-line in each LES cell. This paper introduces a novel turbulent combustion closure model for LES using LEM to address this issue. It involves coarse-graining the LES mesh to generate a coarse- level ‘super-grid’ comprised of cell-clusters. Each cell-cluster, instead of each LES cell, then contains a single LEM domain. This domain advances the combined advection–reaction–diffusion solution and also provides suitably conditioned statistics for thermochemical scalars such as species mass fractions. Local LES-filtered thermochemical states are then obtained by probability-density-function (PDF) weighted integration of binned conditionally averaged scalars, akin to standard presumed PDF approaches for reactive LES but with physics-based determination of the full thermochemical state for particular values of the conditioning variables. The proposed method is termed ‘super-grid LEM’ or ‘SG-LEM’. The paper describes LEM reaction–diffusion advancement, the LEM representation of turbulent advection, a novel splicing algorithm (a key feature of LES–LEM) formulated for the super-grid approach, a wall treatment, and a thermochemical LES closure procedure. To validate the proposed model, a pressure-based solver was developed using the OpenFOAM library and tested on a premixed ethylene flame stabilised over a backward facing step, a setup for which some DNS data is available. SG-LEM provides high resolution flame structures, temperature and mass fractions suitable for LES thermochemical closure. Additionally, it provides reaction-rate data at the coarse level, a unique feature compared to other mapping-type closure methods. Quantitative comparisons are made between the proposed model and time-averaged DNS data, focussing on velocity, temperature and species mass fraction. Results show good agreement downstream of the step. Furthermore, comparison with an equivalent Partially-Stirred Reactor (PaSR) simulation demonstrates the superior predictive capability of SG-LEM. Additionally, the paper briefly examines the sensitivity of the model to coarse-graining parameters and finally, explores computational efficiency highlighting the substantial speedup achieved when compared to the standard LES–LEM approach with potentially significant speedup relative to PaSR closure for the intensely turbulent regimes of principal interest.

Inverse design of electromagnetically induced transparency(EIT) metasurface based on deep convolutional generative adversarial network

With the increasing complexity of electromagnetically induced transparency (EIT) metasurface structure and the limitations of traditional optimization methods, there is an urgent need for an advanced design approach to accelerate the design of complex EIT metasurface. In this study, we propose an improved deep learning model based on deep convolutional generative adversarial network (DCGAN) to simplify the design process of EIT metasurface. The proposed model enables the optimization of metasurface with eight structural parameters, obtaining single-band or dual-band EIT effects for y polarization incidence. The training of the network model achieves convergence with a mean square error (MSE) of 0.2 for the generator and 0.41 for the discriminator. The average errors between the predicted results and the target parameters are within 0.6 μm. The relative spectral error (RSE) is utilized to quantify the deviation between the simulated spectra obtained from the predicted structures and the target spectra, exhibiting a minimum RSE of 6.26%. Furthermore, comparisons between the proposed model and two other convolutional neural networks validate the superior prediction capability and higher accuracy of our proposed model.

D-dimer-albumin ratio (DAR) as a new biomarker for predicting preoperative deep vein thrombosis after geriatric hip fracture patients

PurposeHip fractures in the elderly are complicated by preoperative deep vein thrombosis (DVT). The objective of this study is to determine the usefulness of blood-based biomarkers, particularly the D-dimer-albumin ratio (DAR), in predicting preoperative DVT.MethodsA retrospective observational study was carried out on 1149 patients from a single hospital, and subsequently validated on an additional 626 patients from a separate hospital. The aim was to evaluate the prognostic and predictive value of 10 biomarkers, with a specific emphasis on DAR, in both cohorts. The primary measure of interest was the occurrence of preoperative DVT.ResultsThe ratio of D-dimer to albumin demonstrated superior predictive capability for preoperative DVT in older patients with hip fractures compared to other biomarkers (AUC = 0.677). Using the optimal cutoff point of 0.24, high DAR was significantly associated with preoperative DVT (OR 3.45, 95% CI 2.00–5.95). Notably, all the DAR definitions detailed above were successfully validated in an external, independent cohort.ConclusionsDAR may be a valuable biomarker for predicting preoperative DVT in elderly patients with hip fractures.

Artificial intelligence learning landscape of triple-negative breast cancer uncovers new opportunities for enhancing outcomes and immunotherapy responses

Triple-negative breast cancer (TNBC) is a relatively aggressive breast cancer subtype due to tumor relapse, drug resistance, and multi-organ metastatic properties. Identifying reliable biomarkers to predict prognosis and precisely guide TNBC immunotherapy is still an unmet clinical need. To address this issue, we successfully constructed a novel 25 machine learning (ML) algorithms-based immune infiltrating cell (IIC) associated signature of TNBC (MLIIC), achieved by multiple transcriptome data of purified immune cells, TNBC cell lines, and TNBC entities. The TSI index was employed to determine IIC-RNAs that were accompanied by an expression pattern of upregulation in immune cells and downregulation in TNBC cells. LassoLR, Boruta, Xgboost, SVM, RF, and Pamr were utilized for further obtaining the optimal IIC-RNAs. Following univariate Cox regression analysis, LassoCox, CoxBoost, and RSF were utilized for the dimensionality reduction of IIC-RNAs from a prognostic perspective. RSF, Ranger, ObliqueRSF, Rpart, CoxPH, SurvivalSVM, CoxBoost, GlmBoost, SuperPC, StepwiseCox, Enet, LassoCox, CForest, Akritas, BlackBoost, PlsRcox, SurvReg, GBM, and CTree were used for determining the most potent MLIIC signature. Consequently, this MLIIC signature was correlated significantly with survival status validated by four independent TNBC cohorts. Also, the MLIIC signature had a superior predictive capability for TNBC prognosis, compared with 148 previously reported signatures. In addition, MLIIC signature scores developed by immunofluorescent staining of tissue arrays from TNBC patients showed a substantial prognostic value. In TNBC immunotherapy, the low MLIIC profile demonstrated significant immune-responsive efficacy in a dataset of multiple cancer types. MLIIC signature could also predict m6A epigenetic regulation which controls T cell homeostasis. Therefore, this well-established MLIIC signature is a robust predictive indicator for TNBC prognosis and the benefit of immunotherapy, thus providing an efficient tool for combating TNBC.