Explore the vast range of titles available.

A crucial role is played by steering-angle prediction in the control of autonomous vehicles (AVs). It mainly includes the prediction and control of the steering angle. However, the prediction accuracy and calculation efficiency of traditional YOLOv5 are limited. For the control of the steering angle, angular velocity is difficult to measure, and the angle control effect is affected by external disturbances and unknown friction. This paper proposes a lightweight steering angle prediction network model called YOLOv5Ms, based on YOLOv5, aiming to achieve accurate prediction while enhancing computational efficiency. Additionally, an adaptive output feedback control scheme with output constraints based on neural networks is proposed to regulate the predicted steering angle using the YOLOv5Ms algorithm effectively. Firstly, given that most lane-line data sets consist of simulated images and lack diversity, a novel lane data set derived from real roads is manually created to train the proposed network model. To improve real-time accuracy in steering-angle prediction and enhance effectiveness in steering control, we update the bounding box regression loss function with the generalized intersection over union (GIoU) to Shape-IoU_Loss as a better-converging regression loss function for bounding-box improvement. The YOLOv5Ms model achieves a 30.34% reduction in weight storage space while simultaneously improving accuracy by 7.38% compared to the YOLOv5s model. Furthermore, an adaptive output feedback control scheme with output constraints based on neural networks is introduced to regulate the predicted steering angle via YOLOv5Ms effectively. Moreover, utilizing the backstepping control method and introducing the Lyapunov barrier function enables us to design an adaptive neural network output feedback controller with output constraints. Finally, a strict stability analysis based on Lyapunov stability theory ensures the boundedness of all signals within the closed-loop system. Numerical simulations and experiments have shown that the proposed method provides a 39.16% better root mean squared error (RMSE) score than traditional backstepping control, and it achieves good estimation performance for angles, angular velocity, and unknown disturbances.

The stable control of wheeled mobile robot (WMR) is crucial for accurate trajectory tracking. However, uncertainty can lead to a decline in WMR tracking performance. The objective of this study is to enhance the trajectory tracking control performance of WMR in uncertain conditions. To achieve this, we present a neural network-based dual closed-loop control system that manages WMR and improves their trajectory tracking capabilities. Firstly, a kinematic model is developed for the WMR to generate virtual velocity based on an adaptive controller in the outer loop. In the inner loop, a dynamic model is established, and the uncertainty is approximated using a neural network. Based on the approximated value from the neural network, an inner loop controller is designed to achieve successful trajectory tracking. Finally, to improve tracking performance, a non-dominated sorting genetic algorithm-II (NSGA-II) algorithm is employed to optimize design parameters. System stability is analyzed using the Lyapunov theory, and the effectiveness of the proposed control scheme is verified by comparing it with different control methods. Compared to previous control studies for WMR, this research presents the following novelties and scientific contributions: 1) In the kinematic controller, an adaptive parameter estimator is integrated into the feedback controller to estimate the unknown parameter. 2) In dynamic controller, a neural network-based control scheme is designed to approximate the lumped disturbances including the unknown parameters and external disturbances. 3) By integrating the NSGA-II with the WMR system, a parametric tuning scheme based on NSGA-II is proposed for optimizing the controller parameters.

The time-varying load inertia is one of the important dynamic characteristics of the power transmission line inspection robots (PTLIRs) in joint space, which can heavily affect the stability of the robot in the inspection process. In this paper, with considering the time-varying characteristics of load inertia, a method for modelling and control of the flexible joint servo system of the PTLIR is studied. First, the control system of the PTLIR is established based on the two inertia system. In order to calculate the load inertia, a dynamic model of the inspection robot is established. Then, the model-based notch filter is designed to improve dynamic performance of the robot, and suppress the vibration amplitude change which caused by the time-varying load inertia. Finally, the comparison of the control performance between the traditional control strategy and the model-based control strategy with notch filter are compared. The simulation results show that the paper can provide an effective tool for modelling and improving the stability of the PTLIR.

Probability information content-based FCA concepts similarity computation method relies on the frequency of concepts in corpus, it takes only the occurrence probability as information content metric to compute FCA concept similarity, which leads to lower accuracy. This article introduces a semantic information content-based method for FCA concept similarity evaluation, in addition to the occurrence probability, it takes the superordinate and subordinate semantic relationship of concepts to measure information content, which makes the generic and specific degree of concepts more accurate. Then the semantic information content similarity can be calculated with the help of an ISA hierarchy which is derived from the domain ontology. The difference between this method and probability information content is that the evaluation of semantic information content is independent of corpus. Furthermore, semantic information content can be used for FCA concept similarity evaluation, and the weighted bipartite graph is also utilized to help improve the efficiency of the similarity evaluation. The experimental results show that this semantic information content based FCA concept similarity computation method improves the accuracy of probabilistic information content based method effectively without loss of time performance.

目的 联合吲哚菁绿清除试验(ICG)和总胆红素留存率(TBARR)建立预测经人工肝治疗的HBV相关慢加急性肝衰竭(HBV-ACLF)患者短期预后的新模型。 方法 回顾性收集2017年6月—2021年7月西南医科大学附属医院感染科收治的136例经人工肝治疗的HBV-ACLF患者的临床资料，据随访3个月时的转归情况分为存活组(n=92)和死亡组(n=44)，检测确诊ACLF时的生化、凝血、吲哚菁绿15分钟滞留率(ICG R15)及肝有效血流量(EHBF)等指标，计算终末期肝病模型(MELD)评分、MELD差值(ΔMELD)、Child-Turcotte-Pugh(CTP)评分、总胆红素清除率(TBCR)、总胆红素反弹率(TBRR)和TBARR。偏态分布的计量资料两组间比较采用Mann-Whitney U检验；计数资料两组间比较则采用χ2检验。应用二分类Logistic回归分析法，构建人工肝治疗HBV-ACLF短期预后的联合预测模型。应用受试者工作特征曲线下面积(AUC)评估各种模型对人工肝治疗HBV-ACLF短期预后判断的准确性，AUC的比较采用Z检验。 结果 死亡组与存活组两组间比较，MELD评分、ΔMELD、CTP评分、ICG R15、EHBF、TBRR、TBARR、中性粒细胞计数、中性粒细胞百分比、淋巴细胞计数、PLT、ALP、GGT、Alb、PT、INR、PTA、总胆红素、前白蛋白、纤维蛋白原、血清Na、年龄及肝性脑病发生率差异均有统计学意义(P值均＜0.05)。多因素Logistic回归分析显示，年龄(OR=1.096，95%CI：1.056~1.137，P＜0.001)、中性粒细胞计数(OR=1.214，95%CI：1.044~1.411，P=0.012)、TBRR(OR=0.989，95%CI：0.982~0.996，P=0.001)、TBARR(OR=1.073，95%CI：1.049~1.098，P＜0.001)、ΔMELD(OR=1.480，95%CI：1.288~1.701，P＜0.001)、CTP评分(OR=2.081，95%CI：1.585~2.732，P＜0.001)以及ICG R15(OR=1.116，95%CI：1.067~1.168，P＜0.001)是经人工肝治疗HBV-ACLF患者短期死亡的独立影响因素。应用二分类Logistic回归分析，构建了4种人工肝治疗HBV-ACLF短期预

The automatic differentiation (AD) in the vanilla physics-informed neural networks (PINNs) is the computational bottleneck for the high-efficiency analysis. The concept of derivative discretization in smoothed particle hydrodynamics (SPH) can provide an accelerated training method for PINNs. In this paper, smoothing kernel physics-informed neural networks (SK-PINNs) are established, which solve differential equations using smoothing kernel discretization. It is a robust framework capable of solving problems in the computational mechanics of complex domains. When the number of collocation points gradually increases, the training speed of SK-PINNs significantly surpasses that of vanilla PINNs. In cases involving large collocation point sets or higher-order problems, SK-PINN training can be up to tens of times faster than vanilla PINN. Additionally, analysis using neural tangent kernel (NTK) theory shows that the convergence rates of SK-PINNs are consistent with those of vanilla PINNs. The superior performance of SK-PINNs is demonstrated through various examples, including regular and complex domains, as well as forward and inverse problems in fluid dynamics and solid mechanics.