Precise and robust three-dimensional object detection(3DOD)presents a promising opportunity in the field of mobile robot(MR)navigation.Monocular 3DOD techniques typically involve extending existing twodimensional obje...Precise and robust three-dimensional object detection(3DOD)presents a promising opportunity in the field of mobile robot(MR)navigation.Monocular 3DOD techniques typically involve extending existing twodimensional object detection(2DOD)frameworks to predict the three-dimensional bounding box(3DBB)of objects captured in 2D RGB images.However,these methods often require multiple images,making them less feasible for various real-time scenarios.To address these challenges,the emergence of agile convolutional neural networks(CNNs)capable of inferring depth froma single image opens a new avenue for investigation.The paper proposes a novel ELDENet network designed to produce cost-effective 3DBounding Box Estimation(3D-BBE)froma single image.This novel framework comprises the PP-LCNet as the encoder and a fast convolutional decoder.Additionally,this integration includes a Squeeze-Exploit(SE)module utilizing the Math Kernel Library for Deep Neural Networks(MKLDNN)optimizer to enhance convolutional efficiency and streamline model size during effective training.Meanwhile,the proposed multi-scale sub-pixel decoder generates high-quality depth maps while maintaining a compact structure.Furthermore,the generated depthmaps provide a clear perspective with distance details of objects in the environment.These depth insights are combined with 2DOD for precise evaluation of 3D Bounding Boxes(3DBB),facilitating scene understanding and optimal route planning for mobile robots.Based on the estimated object center of the 3DBB,the Deep Reinforcement Learning(DRL)-based obstacle avoidance strategy for MRs is developed.Experimental results demonstrate that our model achieves state-of-the-art performance across three datasets:NYU-V2,KITTI,and Cityscapes.Overall,this framework shows significant potential for adaptation in intelligent mechatronic systems,particularly in developing knowledge-driven systems for mobile robot navigation.展开更多
By analyzing the bus operation environment and accounting for prediction uncertainties,a bus arrival interval prediction model was developed utilizing a gated recur-rent unit(GRU)neural network.To reduce the impact of...By analyzing the bus operation environment and accounting for prediction uncertainties,a bus arrival interval prediction model was developed utilizing a gated recur-rent unit(GRU)neural network.To reduce the impact of irrelevant data and boost prediction accuracy,an attention mechanism was integrated into the point model to concen-trate on important input sequence information.Based on the point predictions,the lower upper bound estimation(LUBE)method was used,providing a range for the bus interval times predicted by the model.The model was vali-dated using data from 169 bus routes in Nanchang,Jiangxi Province.The results indicated that the attention-GRU model outperformed neural network,long short-term memory and GRU models.Compared with the Bootstrap method,the LUBE method has a narrower average interval width.The coverage width-based criterion(CWC)was reduced by 8.1%,2.2%,and 5.7%at confidence levels of 85%,90%,and 95%,respectively,during the off-peak period,and by 23.2%,26.9%,and 27.3%at confidence levels of 85%,90%,and 95%,respectively,during the peak period.Therefore,it can accurately describe the fluctuation range in bus arrival times with higher accuracy and stability.展开更多
Assume that L is a non-negative self-adjoint operator on L^(2)(ℝ^(n))with its heat kernels satisfying the so-called Gaussian upper bound estimate and that X is a ball quasi-Banach function space onℝ^(n) satisfying som...Assume that L is a non-negative self-adjoint operator on L^(2)(ℝ^(n))with its heat kernels satisfying the so-called Gaussian upper bound estimate and that X is a ball quasi-Banach function space onℝ^(n) satisfying some mild assumptions.Let HX,L(ℝ^(n))be the Hardy space associated with both X and L,which is defined by the Lusin area function related to the semigroup generated by L.In this article,the authors establish various maximal function characterizations of the Hardy space HX,L(ℝ^(n))and then apply these characterizations to obtain the solvability of the related Cauchy problem.These results have a wide range of generality and,in particular,the specific spaces X to which these results can be applied include the weighted space,the variable space,the mixed-norm space,the Orlicz space,the Orlicz-slice space,and the Morrey space.Moreover,the obtained maximal function characterizations of the mixed-norm Hardy space,the Orlicz-slice Hardy space,and the Morrey-Hardy space associated with L are completely new.展开更多
Single-index model offers the greater flexibility of modelling than generalized linear models and also retains the interpretability of the model to some extent. Although many standard approaches such as kernels or pen...Single-index model offers the greater flexibility of modelling than generalized linear models and also retains the interpretability of the model to some extent. Although many standard approaches such as kernels or penalized/smooothing splines were proposed to estimate smooth link function, they cannot approximate complicated unknown link functions together with the corresponding derivatives effectively due to their poor approximation ability for a finite sample size. To alleviate this problem, this paper proposes a semiparametric least squares estimation approach for a single-index model using the rectifier quadratic unit (ReQU) activated deep neural networks, called deep semiparametric least squares (DSLS) estimation method. Under some regularity conditions, we show non-asymptotic properties of the proposed DSLS estimator, and evidence that the index coefficient estimator can achieve the semiparametric efficiency. In particular, we obtain the consistency and the convergence rate of the proposed DSLS estimator when response variable is conditionally sub-exponential. This is an attempt to incorporate deep learning technique into semiparametrically efficient estimation in a single index model. Several simulation studies and a real example data analysis are conducted to illustrate the proposed DSLS estimator.展开更多
This work investigates a simple and practical bio-immune optimization approach to solve a kind of chance-constrained programming problem without known noisy attributes, after probing into a lower bound estimate of sam...This work investigates a simple and practical bio-immune optimization approach to solve a kind of chance-constrained programming problem without known noisy attributes, after probing into a lower bound estimate of sample size for any random variable. Such approach mainly consists of sample allocation, evaluation, proliferation and mutation. The former two, depending on a lower bound estimate acquired, not only decide the sample size of random variable and the importance level of each evolving B cell, but also ensure that such B cell is evaluated with low computational cost; the third makes diverse B cells participate in evolution and suppresses the influence of noise; the last, which associates with the information on population diversity and fitness inheritance, creates diverse and high-affinity B cells. Under such approach, three similar immune algorithms are derived after selecting different mutation rules. The experiments, by comparison against two valuable genetic algorithms, have illustrated that these immune algorithms are competitive optimizers capable of effectively executing noisy compensation and searching for the desired optimal reliable solution.展开更多
This paper introduces a four-dimensional （4D） segmented disc dynamo which possesses coexisting hidden attractors with one stable equilibrium or a line equilibrium when parameters vary. In addition, by choosing an ap...This paper introduces a four-dimensional （4D） segmented disc dynamo which possesses coexisting hidden attractors with one stable equilibrium or a line equilibrium when parameters vary. In addition, by choosing an appropriate bifurcation parameter, the paper proves that Hopf bifurcation and pitchfork bifurcation occur in the system. The ultimate bound is also estimated. Some numerical investigations are also exploited to demonstrate and visualize the corresponding theoretical results.展开更多
A finite element asymptotic analysis for determining the lower bound dynamic buckling estimates of imperfection-sensitive structures under step load of infinite duration is presented. The lower bound dynamic buckling ...A finite element asymptotic analysis for determining the lower bound dynamic buckling estimates of imperfection-sensitive structures under step load of infinite duration is presented. The lower bound dynamic buckling loads and the corresponding displacements are sought in the form of asymptotic expansions based on the static stability criterion and they can be determined by solving numerically (FEM) several linear problems with a single nonsingular sub-stiffness matrix.展开更多
By the construction of a Cauchy sequence in a Banach space and the global bounded estimate of solution,we obtain the global existence and the bounded estimate of solution of BBM-Burgers equation without the viscous te...By the construction of a Cauchy sequence in a Banach space and the global bounded estimate of solution,we obtain the global existence and the bounded estimate of solution of BBM-Burgers equation without the viscous term ut ＋∑ n j=1 fj（u）xj-γ1△ut＋γ3△2u=0with large initial date in 4-dimension space.展开更多
Recently Guo introduced integrated Meyer -Konig and Zeller operators and studied the rate of convergence for function of bounded variation. In this note we give a sharp estimate for these operators.
In high-level synthesis of VLSI circuits, good lower bound prediction canefficiently narrow down the large space of possible designs. Previous approaches predict the lowerbound by relaxing or even ignoring the precede...In high-level synthesis of VLSI circuits, good lower bound prediction canefficiently narrow down the large space of possible designs. Previous approaches predict the lowerbound by relaxing or even ignoring the precedence constraints of the data flow graph (DFG), andresult in inaccuracy of the lower bound. The loop folding and conditional branch were also notconsidered. In this paper, a new stepwise refinement algorithm is proposed, which takesconsideration of precedence constraints of the DFG to estimate the lower bound of hardware resourcesunder time constraints. Processing techniques to handle multi-cycle, chaining, pipelining, as wellas loop folding and mutual exclusion among conditional branches are also incorporated in thealgorithm. Experimental results show that the algorithm can produce a very tight and close tooptimal lower bound in reasonable computation time.展开更多
We present the convergence analysis of the rectangular Morley element scheme utilised on the second order problem in arbitrary dimensions. Specifically, we prove that the convergence of the scheme is of （D（h） order...We present the convergence analysis of the rectangular Morley element scheme utilised on the second order problem in arbitrary dimensions. Specifically, we prove that the convergence of the scheme is of （D（h） order in energy norm and of O（h2） order in L2 norm on general d-rectangular triangulations. Moreover, when the triangulation is uniform, the convergence rate can be of O（h2） order in energy norm, and the convergence rate in L2 norm is still of O（h2） order, which cannot be improved. Numerical examples are presented to demonstrate our theoretical results.展开更多
This paper addresses the asymptotic control problem of uncertain multi-input and multi-output(MIMO)nonlinear systems.The considered MIMO systems contain unknown virtual control coefficients(UVCCs)and state constraints...This paper addresses the asymptotic control problem of uncertain multi-input and multi-output(MIMO)nonlinear systems.The considered MIMO systems contain unknown virtual control coefficients(UVCCs)and state constraints.Acreative Lyapunov function by associating with the lower bounds of UVCCs is presented to counteract the adverse effect deriving from UVCCs.The state constraints are ensured by utilising the barrier Lyapunov function.Moreover,the asymptotic tracking controller is recursively constructed by combining the backstepping technique with fuzzy logic systems.The remarkable character of the designed controller is that the asymptotic tracking performance can be achieved by introducing some smooth functions into adaptive backstepping procedure.In contrast to the existing results,the conditions on the UVCCs are relaxed.Finally,the new control design is illustrated by a practical example.展开更多
文摘Precise and robust three-dimensional object detection(3DOD)presents a promising opportunity in the field of mobile robot(MR)navigation.Monocular 3DOD techniques typically involve extending existing twodimensional object detection(2DOD)frameworks to predict the three-dimensional bounding box(3DBB)of objects captured in 2D RGB images.However,these methods often require multiple images,making them less feasible for various real-time scenarios.To address these challenges,the emergence of agile convolutional neural networks(CNNs)capable of inferring depth froma single image opens a new avenue for investigation.The paper proposes a novel ELDENet network designed to produce cost-effective 3DBounding Box Estimation(3D-BBE)froma single image.This novel framework comprises the PP-LCNet as the encoder and a fast convolutional decoder.Additionally,this integration includes a Squeeze-Exploit(SE)module utilizing the Math Kernel Library for Deep Neural Networks(MKLDNN)optimizer to enhance convolutional efficiency and streamline model size during effective training.Meanwhile,the proposed multi-scale sub-pixel decoder generates high-quality depth maps while maintaining a compact structure.Furthermore,the generated depthmaps provide a clear perspective with distance details of objects in the environment.These depth insights are combined with 2DOD for precise evaluation of 3D Bounding Boxes(3DBB),facilitating scene understanding and optimal route planning for mobile robots.Based on the estimated object center of the 3DBB,the Deep Reinforcement Learning(DRL)-based obstacle avoidance strategy for MRs is developed.Experimental results demonstrate that our model achieves state-of-the-art performance across three datasets:NYU-V2,KITTI,and Cityscapes.Overall,this framework shows significant potential for adaptation in intelligent mechatronic systems,particularly in developing knowledge-driven systems for mobile robot navigation.
基金The National Natural Science Foundation of China(No.52162042)General Science and Technology Project of Jiangxi Provincial Department of Transportation(No.2024YB039).
文摘By analyzing the bus operation environment and accounting for prediction uncertainties,a bus arrival interval prediction model was developed utilizing a gated recur-rent unit(GRU)neural network.To reduce the impact of irrelevant data and boost prediction accuracy,an attention mechanism was integrated into the point model to concen-trate on important input sequence information.Based on the point predictions,the lower upper bound estimation(LUBE)method was used,providing a range for the bus interval times predicted by the model.The model was vali-dated using data from 169 bus routes in Nanchang,Jiangxi Province.The results indicated that the attention-GRU model outperformed neural network,long short-term memory and GRU models.Compared with the Bootstrap method,the LUBE method has a narrower average interval width.The coverage width-based criterion(CWC)was reduced by 8.1%,2.2%,and 5.7%at confidence levels of 85%,90%,and 95%,respectively,during the off-peak period,and by 23.2%,26.9%,and 27.3%at confidence levels of 85%,90%,and 95%,respectively,during the peak period.Therefore,it can accurately describe the fluctuation range in bus arrival times with higher accuracy and stability.
基金supported by the National Key Research and Development Program of China(2020YFA0712900)the National Natural Science Foundation of China(12371093,12071197,12122102 and 12071431)+2 种基金the Key Project of Gansu Provincial National Science Foundation(23JRRA1022)the Fundamental Research Funds for the Central Universities(2233300008 and lzujbky-2021-ey18)the Innovative Groups of Basic Research in Gansu Province(22JR5RA391).
文摘Assume that L is a non-negative self-adjoint operator on L^(2)(ℝ^(n))with its heat kernels satisfying the so-called Gaussian upper bound estimate and that X is a ball quasi-Banach function space onℝ^(n) satisfying some mild assumptions.Let HX,L(ℝ^(n))be the Hardy space associated with both X and L,which is defined by the Lusin area function related to the semigroup generated by L.In this article,the authors establish various maximal function characterizations of the Hardy space HX,L(ℝ^(n))and then apply these characterizations to obtain the solvability of the related Cauchy problem.These results have a wide range of generality and,in particular,the specific spaces X to which these results can be applied include the weighted space,the variable space,the mixed-norm space,the Orlicz space,the Orlicz-slice space,and the Morrey space.Moreover,the obtained maximal function characterizations of the mixed-norm Hardy space,the Orlicz-slice Hardy space,and the Morrey-Hardy space associated with L are completely new.
基金Supported by the National Natural Science Foundation of China (Grant No. 12271472)。
文摘Single-index model offers the greater flexibility of modelling than generalized linear models and also retains the interpretability of the model to some extent. Although many standard approaches such as kernels or penalized/smooothing splines were proposed to estimate smooth link function, they cannot approximate complicated unknown link functions together with the corresponding derivatives effectively due to their poor approximation ability for a finite sample size. To alleviate this problem, this paper proposes a semiparametric least squares estimation approach for a single-index model using the rectifier quadratic unit (ReQU) activated deep neural networks, called deep semiparametric least squares (DSLS) estimation method. Under some regularity conditions, we show non-asymptotic properties of the proposed DSLS estimator, and evidence that the index coefficient estimator can achieve the semiparametric efficiency. In particular, we obtain the consistency and the convergence rate of the proposed DSLS estimator when response variable is conditionally sub-exponential. This is an attempt to incorporate deep learning technique into semiparametrically efficient estimation in a single index model. Several simulation studies and a real example data analysis are conducted to illustrate the proposed DSLS estimator.
基金supported in part by National Natural Science Foundation of China(Nos.61563009 and 61065010)Doctoral Fund of Ministry of Education of China(No.20125201110003)
文摘This work investigates a simple and practical bio-immune optimization approach to solve a kind of chance-constrained programming problem without known noisy attributes, after probing into a lower bound estimate of sample size for any random variable. Such approach mainly consists of sample allocation, evaluation, proliferation and mutation. The former two, depending on a lower bound estimate acquired, not only decide the sample size of random variable and the importance level of each evolving B cell, but also ensure that such B cell is evaluated with low computational cost; the third makes diverse B cells participate in evolution and suppresses the influence of noise; the last, which associates with the information on population diversity and fitness inheritance, creates diverse and high-affinity B cells. Under such approach, three similar immune algorithms are derived after selecting different mutation rules. The experiments, by comparison against two valuable genetic algorithms, have illustrated that these immune algorithms are competitive optimizers capable of effectively executing noisy compensation and searching for the desired optimal reliable solution.
基金supported by the National Natural Science Foundation of China(Grant No.11671149)
文摘This paper introduces a four-dimensional （4D） segmented disc dynamo which possesses coexisting hidden attractors with one stable equilibrium or a line equilibrium when parameters vary. In addition, by choosing an appropriate bifurcation parameter, the paper proves that Hopf bifurcation and pitchfork bifurcation occur in the system. The ultimate bound is also estimated. Some numerical investigations are also exploited to demonstrate and visualize the corresponding theoretical results.
基金The project supported by the State Education Commission of China
文摘A finite element asymptotic analysis for determining the lower bound dynamic buckling estimates of imperfection-sensitive structures under step load of infinite duration is presented. The lower bound dynamic buckling loads and the corresponding displacements are sought in the form of asymptotic expansions based on the static stability criterion and they can be determined by solving numerically (FEM) several linear problems with a single nonsingular sub-stiffness matrix.
基金Supported by the National Natural Science Foundation of China(11571092)
文摘By the construction of a Cauchy sequence in a Banach space and the global bounded estimate of solution,we obtain the global existence and the bounded estimate of solution of BBM-Burgers equation without the viscous term ut ＋∑ n j=1 fj（u）xj-γ1△ut＋γ3△2u=0with large initial date in 4-dimension space.
基金Research supported by Council of Scientific and Industrial Research, India under award no.9/143(163)/91-EER-
文摘Recently Guo introduced integrated Meyer -Konig and Zeller operators and studied the rate of convergence for function of bounded variation. In this note we give a sharp estimate for these operators.
文摘In high-level synthesis of VLSI circuits, good lower bound prediction canefficiently narrow down the large space of possible designs. Previous approaches predict the lowerbound by relaxing or even ignoring the precedence constraints of the data flow graph (DFG), andresult in inaccuracy of the lower bound. The loop folding and conditional branch were also notconsidered. In this paper, a new stepwise refinement algorithm is proposed, which takesconsideration of precedence constraints of the DFG to estimate the lower bound of hardware resourcesunder time constraints. Processing techniques to handle multi-cycle, chaining, pipelining, as wellas loop folding and mutual exclusion among conditional branches are also incorporated in thealgorithm. Experimental results show that the algorithm can produce a very tight and close tooptimal lower bound in reasonable computation time.
基金supported by National Natural Science Foundation of China (Grant Nos. 11471026, 11271035, 91430213, 11421101 and 11101415)
文摘We present the convergence analysis of the rectangular Morley element scheme utilised on the second order problem in arbitrary dimensions. Specifically, we prove that the convergence of the scheme is of （D（h） order in energy norm and of O（h2） order in L2 norm on general d-rectangular triangulations. Moreover, when the triangulation is uniform, the convergence rate can be of O（h2） order in energy norm, and the convergence rate in L2 norm is still of O（h2） order, which cannot be improved. Numerical examples are presented to demonstrate our theoretical results.
基金supported in part by the National Natural Science Foundation of China under grant numbers 52171299 and 61803116,62173103in part by the Fundamental Research Funds for the Central Universities of China under grant number 3072022JC0402.
文摘This paper addresses the asymptotic control problem of uncertain multi-input and multi-output(MIMO)nonlinear systems.The considered MIMO systems contain unknown virtual control coefficients(UVCCs)and state constraints.Acreative Lyapunov function by associating with the lower bounds of UVCCs is presented to counteract the adverse effect deriving from UVCCs.The state constraints are ensured by utilising the barrier Lyapunov function.Moreover,the asymptotic tracking controller is recursively constructed by combining the backstepping technique with fuzzy logic systems.The remarkable character of the designed controller is that the asymptotic tracking performance can be achieved by introducing some smooth functions into adaptive backstepping procedure.In contrast to the existing results,the conditions on the UVCCs are relaxed.Finally,the new control design is illustrated by a practical example.
