In this paper,we investigate the method of compensating LTS SQUID Gradiometer Systems data.By matching the attitude changes of the pod in fl ight to the anomalies of the magnetic measurement data,we find that the yaw ...In this paper,we investigate the method of compensating LTS SQUID Gradiometer Systems data.By matching the attitude changes of the pod in fl ight to the anomalies of the magnetic measurement data,we find that the yaw attitude changes most dramatically and corresponds best to the magnetic data anomaly interval.Based on this finding,we solved the compensation model using least squares fitting and Huber's parametric fitting.By comparison,we found that the Huber parametric fit not only eliminates the interference introduced by attitude changes but also retains richer anomaly source information and therefore obtains a higher signal-to-noise ratio.The experimental results show that the quality of the magnetometry data obtained by using the compensation method proposed in this paper has been significantly improved,and the mean value of its improvement ratio can reach 118.93.展开更多
Compared with the propulsion mode using the fluctuation or swing of fins,the water-jet propulsion of cephalopods has attracted much attention because of its high swimming speed.This paper introduces a squid-like under...Compared with the propulsion mode using the fluctuation or swing of fins,the water-jet propulsion of cephalopods has attracted much attention because of its high swimming speed.This paper introduces a squid-like underwater thruster based on an origami structure,which can realize water-jet propulsion by changing the shape of its origami structure.At the same time,it is combined with a soft vector nozzle driven by negative pressure for underwater steering.In addition,a triboelectric sensor(TES)is embedded in the origami structure to monitor the shape change of the thruster in real time.The kinematics model of the origami structure is established,and the dihedral angle B_(0)^(4),which can be used to characterize the unique shape of the thruster,is put forward.The dihedral angle B_(0)^(4)is monitored by the TES so that the shape change of the thruster can be feedback in real-time.Prototypes of the thruster and vector nozzle were fabricated,and the maximum error of TES in monitoring the shape of the thruster was less than 4.4%.At the same time,an underwater test platform was built to test the thruster’s propulsion performance and the vector nozzle’s deflection effect.展开更多
Timely and accurate diagnosis of skin diseases is crucial as conventional methods are time-consuming and prone to errors.Traditional trial-and-error approaches often aggregate multiple models without optimization by r...Timely and accurate diagnosis of skin diseases is crucial as conventional methods are time-consuming and prone to errors.Traditional trial-and-error approaches often aggregate multiple models without optimization by resulting in suboptimal performance.To address these challenges,we propose a novel Squid Game OptimizationDimension Reduction-based Ensemble(SGO-DRE)method for the precise diagnosis of skin diseases.Our approach begins by selecting pre-trained models named MobileNetV1,DenseNet201,and Xception for robust feature extraction.These models are enhanced with dimension reduction blocks to improve efficiency.To tackle the aggregation problem of various models,we leverage the Squid Game Optimization(SGO)algorithm,which iteratively searches for the optimal weightage set to assign the appropriate weightage to each individual model within the proposed weighted average aggregation ensemble approach.The proposed ensemble method effectively utilizes the strengths of each model.We evaluated the proposed method using an 8-class skin disease dataset,a 6-class MSLD dataset,and a 4-class MSID dataset,achieving accuracies of 98.71%,96.34%,and 93.46%,respectively.Additionally,we employed visual tools like Grad-CAM,ROC curves,and Precision-Recall curves to interpret the decision making of models and assess its performance.These evaluations ensure that the proposed method not only provides robust results but also enhances interpretability and reliability in clinical decision-making.展开更多
基金Earth Observation and Navigation Special,Research on Low Temperature Superconducting Aeromagnetic Vector Gradient Observation Technology(2021YFB3900201)projectState Key Laboratory of Remote Sensing Science project.
文摘In this paper,we investigate the method of compensating LTS SQUID Gradiometer Systems data.By matching the attitude changes of the pod in fl ight to the anomalies of the magnetic measurement data,we find that the yaw attitude changes most dramatically and corresponds best to the magnetic data anomaly interval.Based on this finding,we solved the compensation model using least squares fitting and Huber's parametric fitting.By comparison,we found that the Huber parametric fit not only eliminates the interference introduced by attitude changes but also retains richer anomaly source information and therefore obtains a higher signal-to-noise ratio.The experimental results show that the quality of the magnetometry data obtained by using the compensation method proposed in this paper has been significantly improved,and the mean value of its improvement ratio can reach 118.93.
文摘Compared with the propulsion mode using the fluctuation or swing of fins,the water-jet propulsion of cephalopods has attracted much attention because of its high swimming speed.This paper introduces a squid-like underwater thruster based on an origami structure,which can realize water-jet propulsion by changing the shape of its origami structure.At the same time,it is combined with a soft vector nozzle driven by negative pressure for underwater steering.In addition,a triboelectric sensor(TES)is embedded in the origami structure to monitor the shape change of the thruster in real time.The kinematics model of the origami structure is established,and the dihedral angle B_(0)^(4),which can be used to characterize the unique shape of the thruster,is put forward.The dihedral angle B_(0)^(4)is monitored by the TES so that the shape change of the thruster can be feedback in real-time.Prototypes of the thruster and vector nozzle were fabricated,and the maximum error of TES in monitoring the shape of the thruster was less than 4.4%.At the same time,an underwater test platform was built to test the thruster’s propulsion performance and the vector nozzle’s deflection effect.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R749)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Timely and accurate diagnosis of skin diseases is crucial as conventional methods are time-consuming and prone to errors.Traditional trial-and-error approaches often aggregate multiple models without optimization by resulting in suboptimal performance.To address these challenges,we propose a novel Squid Game OptimizationDimension Reduction-based Ensemble(SGO-DRE)method for the precise diagnosis of skin diseases.Our approach begins by selecting pre-trained models named MobileNetV1,DenseNet201,and Xception for robust feature extraction.These models are enhanced with dimension reduction blocks to improve efficiency.To tackle the aggregation problem of various models,we leverage the Squid Game Optimization(SGO)algorithm,which iteratively searches for the optimal weightage set to assign the appropriate weightage to each individual model within the proposed weighted average aggregation ensemble approach.The proposed ensemble method effectively utilizes the strengths of each model.We evaluated the proposed method using an 8-class skin disease dataset,a 6-class MSLD dataset,and a 4-class MSID dataset,achieving accuracies of 98.71%,96.34%,and 93.46%,respectively.Additionally,we employed visual tools like Grad-CAM,ROC curves,and Precision-Recall curves to interpret the decision making of models and assess its performance.These evaluations ensure that the proposed method not only provides robust results but also enhances interpretability and reliability in clinical decision-making.
