Explore the vast range of titles available.

A tracking control algorithm for autonomous vehicles using state expansion is proposed. This algorithm, based on a three degrees of freedom (3-DOF) vehicle lateral dynamics model, extends the state variables of the traditional model predictive control (MPC) algorithm to an input-output dual feedback form based on the state expansion method. A dual feedback model predictive control (DF-MPC) algorithm was constructed. Based on this, taking the current speed and the curvature of the reference trajectory as the system input, and using the fuzzy control algorithm to dynamically adjust the prediction range of the DF-MPC trajectory tracking controller in real time, a variable predictive horizon double feedback model predictive control (VDF-MPC) trajectory tracking control method for autonomous vehicle was established. Through MATLAB/Simulink-CarSim joint simulation, the reliability of the established VDF-MPC trajectory tracking control method was verified.

Objectives: This study aimed to identify variables contributing to the prediction of national security awareness among university students in the Kingdom of Saudi Arabia.   Methods: The sample comprised 395 male and female students from Imam Muhammad bin Saud Islamic University, with a mean age of 19.85 years and a standard deviation of 1.11. The research utilized scales of national security awareness, psychological security, critical thinking, quality of life, national belonging, and intellectual extremism. Structural Equation Modeling (Path Analysis) was employed to analyze the data.   Results: The study revealed that national security awareness can be statistically predicted based on the examined variables, namely critical thinking, quality of life, and national belonging, across all participants. National belonging emerged as the most influential variable in predicting national security awareness, followed by critical thinking and quality of life. Additionally, there were no differences in the contributing variables according to gender and academic qualifications.   Conclusion: The findings were discussed and interpreted, highlighting the importance of national belonging, critical thinking, and quality of life in predicting national security awareness among university students. The study concluded with suggestions and recommendations for enhancing national security awareness through targeted interventions focusing on these key variables.

A parametric Adaptive Model Predictive Controller (AMPC) based on Particle Swarm Optimization-Back Propagation (PSO-BP) neural network has been developed in this paper, the primary focus is on improving the trajectory tracking performance of autonomous vehicles under varying road conditions. The PSO-BP neural network is employed for real-time adjustment of the controller's predictive horizon and sampling time. A vehicle dynamics model is established and an improved tracking control algorithm involving road curvature feedforward is proposed. In the design of AMPC, the real-time update of tire lateral stiffness is achieved through the adoption of the Recursive Least Squares (RLS) method, ensuring the precision of trajectory tracking for the vehicle under varying operating conditions. The simulation platform, which combines Carsim and Simulink, was employed for validating the proposed approach. The findings reveal that the proposed controller can promptly adjust the predictive horizon and sampling time according to the vehicle's state. Through the employed estimation strategy, real-time adjustments of tire lateral stiffness are achieved, allowing for dynamic alterations of vehicle speed and front wheel angle in response to road curvature. As a result, this approach significantly enhances control accuracy and lateral steering stability, especially in large curvature conditions.

Stock index forecasting has always been an interesting subject for investors and related scholars. Accurately stock index forecasting can provide some helpful suggestions for investors and keep financial markets stable. In this study, a new forecasting system, including point prediction and interval prediction, has been proposed to predict the stock index. For obtaining a better predictive effect, multiple influencing variables are also considered in the novel model. More specifically, in the point prediction models, this study applies gradient boosting decision tree (GBDT) to choose some variables related to the stock index by determining their contribution to accurate prediction. Next, an autoencoder (AE) is utilized to reduce the dimensionality of screened factors for the purpose of reducing the effect of noise and improving the efficiency of forecasting. These reconstructed features are all inputted into bidirectional long short-term memory (BiLSTM) to do point prediction. The interval prediction is based on point prediction results and Gaussian process regression (GPR), intended to quantitative uncertainty of the variables. This study chooses the Chinese stock index including the Shanghai Securities Composite Index (SSEC), Shenzhen Composite Index (SZI) and China Securities Index 300 (CSI300) to demonstrate the validity of the innovative hybrid model. Furthermore, this study also selects some other models for comparison. Evaluating the performance of the novel hybrid model, it could be considered as a valid way to do stock index forecasting.

Introduction Open globe injuries (OGI) represent a main preventable reason for blindness and visual impairment, particularly in developing countries. The goal of this study is evaluating key variables affecting the prognosis of open globe injuries and validating internally and comparing different machine learning models to estimate final visual acuity. Materials and methods We reviewed three hundred patients with open globe injuries receiving treatment at Khatam-Al-Anbia Hospital in Iran from 2020 to 2022. Age, sex, type of trauma, initial VA grade, relative afferent pupillary defect (RAPD), zone of trauma, traumatic cataract, traumatic optic neuropathy (TON), intraocular foreign body (IOFB), retinal detachment (RD), endophthalmitis, and ocular trauma score (OTS) grade were the input features. We calculated univariate and multivariate regression models to assess the association of different features with visual acuity (VA) outcomes. We predicted visual acuity using ten supervised machine learning algorithms including multinomial logistic regression (MLR), support vector machines (SVM), K-nearest neighbors (KNN), naïve bayes (NB), decision tree (DT), random forest (RF), bagging (BG), adaptive boosting (ADA), artificial neural networks (ANN), and extreme gradient boosting (XGB). Accuracy, positive predictive value (PPV), recall, F-score, brier score (BS), Matthew correlation coefficient (MCC), receiver operating characteristic (AUC-ROC), and calibration plot were used to assess how well machine learning algorithms performed in predicting the final VA. Results The artificial neural network (ANN) model had the best accuracy to predict the final VA. The sensitivity, F1 score, PPV, accuracy, and MCC of the ANN model were 0.81, 0.85, 0.89, 0.93, and 0.81, respectively. In addition, the estimated AUC-ROC and AUR-PRC of the ANN model for OGI patients were 0.96 and 0.91, respectively. The brier score and calibration log-loss for the ANN model was 0.201 and 0.232, respectively. Conclusion As classic and ensemble ML models were compared, results shows that the ANN model was the best. As a result, the framework that has been presented may be regarded as a good substitute for predicting the final VA in OGI patients. Excellent predictive accuracy was shown by the open globe injury model developed in this study, which should be helpful to provide clinical advice to patients and making clinical decisions concerning the management of open globe injuries.

Machine learning methods have recently been used widely for mineral prospectivity mapping. However, few studies have focused on the determination of variables for mineral prospectivity prediction using such methods. Here, we present a comparative study using supervised and unsupervised methods to determine predictive variables (PVs). First, based on a mineral deposit model, 12 variables were created including information about granite, fault and strata, and information from geochemical and geophysical surveys. Second, recursive feature elimination (RFE) and sparse principal components analysis (SPCA) were used to determine the PVs for mineral prospectivity prediction. Third, the weights-of-evidence and Random Forest methods were used to integrate the PVs to generate a probability map of mineral prospectivity. Finally, the receiver operating characteristic curve was used to evaluate the performance of the PVs for indicating mineral prospectivity. The variable strata buffer, granite buffer, stratigraphic entropy, derivative norm of magnetic data, and fault buffer were selected as PVs by SPCA, whereas the derivative norm of magnetic data, fault buffer, geochemical anomalies, and strata number were selected as PVs by the RFE method. The results demonstrate that PV determination is a necessary step for mineral prospectivity mapping because it can improve the performance of mineral prospectivity prediction.

Splenectomy is a vital treatment method for hypersplenism with portal hypertension. However, portal venous system thrombosis (PVST) is a serious problem after splenectomy. Therefore, constructing an effective visual risk prediction model is important for preventing, diagnosing, and treating early PVST in hepatolenticular degeneration (HLD) surgical patients. Between January 2016 and December 2021, 309 HLD patients were selected. The data were split into a development set (215 cases from January 2016 to December 2019) and a validation set (94 cases from January 2019 to December 2021). Patients' clinical characteristics and laboratory examinations were obtained from electronic medical record system, and PVST was diagnosed using Doppler ultrasound. Univariate and multivariate logistic regression analyses were used to establish the prediction model by variables filtered by LASSO regression, and a nomogram was drawn. The area under the curve (AUC) of receiver operating characteristic (ROC) curve and Hosmer-Lemeshow goodness-of-fit test were used to evaluate the differentiation and calibration of the model. Clinical net benefit was evaluated by using decision curve analysis (DCA). The 36-month survival of PVST was studied as well. Seven predictive variables were screened out using LASSO regression analysis, including grade, POD14D-dimer (Postoperative day 14 D-dimer), POD7PLT (Postoperative day 7 platelet), PVD (portal vein diameter), PVV (portal vein velocity), PVF (portal vein flow), and SVD (splenic vein diameter). Multivariate logistic regression analysis revealed that all seven predictive variables had predictive values ( < 0.05). According to the prediction variables, the diagnosis model and predictive nomogram of PVST cases were constructed. The AUC under the ROC curve obtained from the prediction model was 0.812 (95% CI: 0.756-0.869) in the development set and 0.839 (95% CI: 0.756-0.921) in the validation set. Hosmer-Lemeshow goodness-of-fit test fitted well ( = 0.858 for development set; = 0.137 for validation set). The nomogram model was found to be clinically useful by DCA. The 36-month survival rate of three sites of PVST was significantly different from that of one ( = 0.047) and two sites ( = 0.023). The proposed nomogram-based prediction model can predict postoperative PVST. Meanwhile, an earlier intervention should be performed on three sites of PVST.

Introduction This paper develops a methodology and defines a measure that can be used to separate subjects that received an experimental therapy into those that benefitted from those that did not in recent‐onset type 1 diabetes. Benefit means a slowing (or arresting) the decline in beta‐cell function over time. The measure can be applied to comparing treatment arms from a clinical trial or to response at the individual level. Methods An analysis of covariance model was fitted to the 12‐month area under the curve C‐peptide following a 2‐hour mixed meal tolerance test from 492 individuals enrolled on five TrialNet studies of recent‐onset type 1 diabetes. Significant predictors in the model were age and C‐peptide at study entry. The observed minus the model‐based expected C‐peptide value (quantitative response, QR) is defined to reflect the effect of the therapy. Results A comparison of the primary hypothesis test for each study included and a t test of the QR value by treatment group were comparable. The results were also confirmed for a new TrialNet study, independent of the set of studies used to derive the model. With our proposed analytical method and using QR as the end‐point, we conducted simulation studies, to estimate statistical power in detecting a biomarker that expresses differential treatment effect. The QR in its continuous form provided the greatest statistical power when compared to several ways of defining responder/non‐responder using various QR thresholds. Conclusions This paper illustrates the use of the QR, as a measure of the magnitude of treatment effect at the aggregate and subject‐level. We show that the QR distribution by treatment group provides a better sense of the treatment effect than simply giving the mean estimates. Using the QR in its continuous form is shown to have higher statistical power in comparison with dichotomized categorization. This paper proposes a quantitative end‐point in the study of recent‐onset type 1 diabetes that measures the effect of a treatment on the stimulated C‐peptide of an individual patient and, in the aggregate, discriminate those who benefited (responders) from those who did not (non‐responders). The quantitative response measure can be used to evaluate promising biomarkers or other prognostic characteristics and is defined by the difference between the observed and expected C‐peptide levels.

We determined which variables are predictive of normal-weight (N) Chilean 4-year-olds developing overweight/obesity when entering primary school. This study used national data of preschoolers (PK, age 4) in 2011 through 2015, and the same children in the first grade (1st G, age 6) in 2013 through 2017. We formed longitudinal cohorts considering PK as the baseline and 1st G as the follow-up and included anthropometric, socio-demographic, and health variables in PK and anthropometry in the 1st G. We report the percentage N who remained N at follow-up (N-N) or gained excessive weight (N-OW) and (N-OB), by sex. We ran univariate logistic regressions to determine for each variable, its association with gaining excessive weight (N-OW + OB), incorporating significant variables (p < 0.001) in multivariate logistic regression. A total of 483,509 (251,150 girls) of PK had anthropometry in the 1st G. In PK, 22% of the children were obese; in the 1st G (24.8% and 19.7% in boys and girls, respectively). Of normal-weight children, 30% developed OW + OB. The predictive variables were: Being born macrosomic, attending a very vulnerable school, being indigenous, the mother’s low schooling, and the child being cared for by the grandmother after school. In this study, the factors predicting that normal-weight preschoolers gain excessive weight gain in a short period of time are mostly related to poverty. Prevention should focus on this population.

In the field of macro-level safety studies, road traffic safety is significantly related to socioeconomic factors, such as population, number of vehicles, and Gross Domestic Product (GDP). Due to different levels of economic and urbanization, the influence of the predictive factors on traffic safety measurements can differ between cities (or regions). However, such region-level or city-level heterogeneities have not been adequately concerned in previous studies. The objective of this paper is to adopt a novel approach for traffic safety analysis with a dataset containing multiple target variables and samples from different subpopulations. Based on a dataset with annual traffic safety and socioeconomic measurements from 36 major cities in China, we estimate single-output regression models, multi-output regression models, and clustering-based regression models. The results indicate that the 36 cities can be clustered into a metropolitan city class and a non-metropolitan city class, and the class-specified models can notably improve the goodness-of-fit and the interpretability of city-level heterogeneities. Specifically, we note that the effect of primary and secondary industrial GDP on traffic safety is opposite to that of tertiary industrial GDP in the metropolitan city class, while the effects of the two decomposed GDP on traffic safety are consistent in the non-metropolitan city class. We also note that the population has a positive effect on the number of fatalities and the number of injures in metropolitan cities but has no significant influence on traffic safety in non-metropolitan cities.