This study proposes a pose estimation-convolutional neural network-bidirectional gated recurrent unit(PSECNN-BiGRU)fusion model for human posture recognition to address low accuracy issues in abnormal posture recognit...This study proposes a pose estimation-convolutional neural network-bidirectional gated recurrent unit(PSECNN-BiGRU)fusion model for human posture recognition to address low accuracy issues in abnormal posture recognition due to the loss of some feature information and the deterioration of comprehensive performance in model detection in complex home environments.Firstly,the deep convolutional network is integrated with the Mediapipe framework to extract high-precision,multi-dimensional information from the key points of the human skeleton,thereby obtaining a human posture feature set.Thereafter,a double-layer BiGRU algorithm is utilized to extract multi-layer,bidirectional temporal features from the human posture feature set,and a CNN network with an exponential linear unit(ELU)activation function is adopted to perform deep convolution of the feature map to extract the spatial feature of the human posture.Furthermore,a squeeze and excitation networks(SENet)module is introduced to adaptively learn the importance weights of each channel,enhancing the network’s focus on important features.Finally,comparative experiments are performed on available datasets,including the public human activity recognition using smartphone dataset(UCIHAR),the public human activity recognition 70 plus dataset(HAR70PLUS),and the independently developed home abnormal behavior recognition dataset(HABRD)created by the authors’team.The results show that the average accuracy of the proposed PSE-CNN-BiGRU fusion model for human posture recognition is 99.56%,89.42%,and 98.90%,respectively,which are 5.24%,5.83%,and 3.19%higher than the average accuracy of the five models proposed in the comparative literature,including CNN,GRU,and others.The F1-score for abnormal posture recognition reaches 98.84%(heartache),97.18%(fall),99.6%(bellyache),and 98.27%(climbing)on the self-builtHABRDdataset,thus verifying the effectiveness,generalization,and robustness of the proposed model in enhancing human posture recognition.展开更多
The human pose paradigm is estimated using a transformer-based multi-branch multidimensional directed the three-dimensional(3D)method that takes into account self-occlusion,badly posedness,and a lack of depth data in ...The human pose paradigm is estimated using a transformer-based multi-branch multidimensional directed the three-dimensional(3D)method that takes into account self-occlusion,badly posedness,and a lack of depth data in the per-frame 3D posture estimation from two-dimensional(2D)mapping to 3D mapping.Firstly,by examining the relationship between the movements of different bones in the human body,four virtual skeletons are proposed to enhance the cyclic constraints of limb joints.Then,multiple parameters describing the skeleton are fused and projected into a high-dimensional space.Utilizing a multi-branch network,motion features between bones and overall motion features are extracted to mitigate the drift error in the estimation results.Furthermore,the estimated relative depth is projected into 3D space,and the error is calculated against real 3D data,forming a loss function along with the relative depth error.This article adopts the average joint pixel error as the primary performance metric.Compared to the benchmark approach,the estimation findings indicate an increase in average precision of 1.8 mm within the Human3.6M sample.展开更多
Shimmy can reduce the service life of the nose landing gear, affect ride comfort, and even cause fuselage damage leading to aircraft crashes. Taking a light aircraft as the research object, the torsional freedom of la...Shimmy can reduce the service life of the nose landing gear, affect ride comfort, and even cause fuselage damage leading to aircraft crashes. Taking a light aircraft as the research object, the torsional freedom of landing gear around strut axis and lateral deformation of tire are considered. Since the landing gear shimmy is a nonlinear system, a nonlinear mechanical model of the front landing gear shimmy is established. Sobol index method is proposed to analyze the influence of structural parameters on the stability region of the nose landing gear, and Routh-Huritz criterion is used to verify the reliability of the analysis results of Sobol index method. We analyse the effect of torsional stiffness of strut, caster length, rated initial tire inflation pressure, rake angle, and vertical force on the stability region of theront landing gear. And the research shows that the optimization of the torsional stiffness of the strut and the caster length of the nose landing gear should be emphasized, and the influence of vertical force on the stability region of the nose landing gear should be paid attention to.展开更多
A proper landing posture is significant to the reduction of both the im-pact force acting on the human body and the injury at landing.In this paper theimpact force acting on human feet is studied.The subjects were 3 m...A proper landing posture is significant to the reduction of both the im-pact force acting on the human body and the injury at landing.In this paper theimpact force acting on human feet is studied.The subjects were 3 maleparachuters.The experiments were performed by means of high-speed photography and amotor analyzer.The experimental results are as follows:(1)When the subjectjumped from two platforms 1.0m and 1.5m in height,a vertical impact force onthe feet in half-squat posture was larger than in side spin posture.(2)When thesubject jumped from the platform 1.0m high,the feet gained a horizontal impactforce in the half-squat posture,larger than in the side spin posture.When thesubject jumped from the platform 1.5m high,the horizontal impact force pro-duced by both of the above-mentioned postures were just the same,which needsfurther research.(3)In terms of reducing the impact force acting on the feet,theside spin posture is better than the half-squat posture.展开更多
Over the years,the continuous development of new technology has promoted research in the field of posture recognition and also made the application field of posture recognition have been greatly expanded.The purpose o...Over the years,the continuous development of new technology has promoted research in the field of posture recognition and also made the application field of posture recognition have been greatly expanded.The purpose of this paper is to introduce the latest methods of posture recognition and review the various techniques and algorithms of posture recognition in recent years,such as scale-invariant feature transform,histogram of oriented gradients,support vectormachine(SVM),Gaussian mixturemodel,dynamic time warping,hiddenMarkovmodel(HMM),lightweight network,convolutional neural network(CNN).We also investigate improved methods of CNN,such as stacked hourglass networks,multi-stage pose estimation networks,convolutional posemachines,and high-resolution nets.The general process and datasets of posture recognition are analyzed and summarized,and several improved CNNmethods and threemain recognition techniques are compared.In addition,the applications of advanced neural networks in posture recognition,such as transfer learning,ensemble learning,graph neural networks,and explainable deep neural networks,are introduced.It was found that CNN has achieved great success in posture recognition and is favored by researchers.Still,a more in-depth research is needed in feature extraction,information fusion,and other aspects.Among classification methods,HMM and SVM are the most widely used,and lightweight network gradually attracts the attention of researchers.In addition,due to the lack of 3Dbenchmark data sets,data generation is a critical research direction.展开更多
In this paper, we study autonomous landing scene recognition with knowledge transfer for drones. Considering the difficulties in aerial remote sensing, especially that some scenes are extremely similar, or the same sc...In this paper, we study autonomous landing scene recognition with knowledge transfer for drones. Considering the difficulties in aerial remote sensing, especially that some scenes are extremely similar, or the same scene has different representations in different altitudes, we employ a deep convolutional neural network(CNN) based on knowledge transfer and fine-tuning to solve the problem. Then, LandingScenes-7 dataset is established and divided into seven classes. Moreover, there is still a novelty detection problem in the classifier, and we address this by excluding other landing scenes using the approach of thresholding in the prediction stage. We employ the transfer learning method based on ResNeXt-50 backbone with the adaptive momentum(ADAM) optimization algorithm. We also compare ResNet-50 backbone and the momentum stochastic gradient descent(SGD) optimizer. Experiment results show that ResNeXt-50 based on the ADAM optimization algorithm has better performance. With a pre-trained model and fine-tuning, it can achieve 97.845 0% top-1 accuracy on the LandingScenes-7dataset, paving the way for drones to autonomously learn landing scenes.展开更多
Considering the unmanned aerial vehicle(UAV) three-dimensional(3D) posture, a novel 3D non-stationary geometry-based stochastic model(GBSM) is proposed for multiple-input multipleoutput(MIMO) UAV-to-vehicle(U2V) chann...Considering the unmanned aerial vehicle(UAV) three-dimensional(3D) posture, a novel 3D non-stationary geometry-based stochastic model(GBSM) is proposed for multiple-input multipleoutput(MIMO) UAV-to-vehicle(U2V) channels. It consists of a line-of-sight(Lo S) and non-line-of-sight(NLo S) components. The factor of fuselage posture is considered by introducing a time-variant 3D posture matrix. Some important statistical properties, i.e.the temporal autocorrelation function(ACF) and spatial cross correlation function(CCF), are derived and investigated. Simulation results show that the fuselage posture has significant impact on the U2V channel characteristic and aggravate the non-stationarity. The agreements between analytical, simulated, and measured results verify the correctness of proposed model and derivations. Moreover, it is demonstrated that the proposed model is also compatible to the existing GBSM without considering fuselage posture.展开更多
To detect the improper sitting posture of a person sitting on a chair,a posture detection system using machine learning classification has been proposed in this work.The addressed problem correlates to the third Susta...To detect the improper sitting posture of a person sitting on a chair,a posture detection system using machine learning classification has been proposed in this work.The addressed problem correlates to the third Sustainable Development Goal(SDG),ensuring healthy lives and promoting well-being for all ages,as specified by the World Health Organization(WHO).An improper sitting position can be fatal if one sits for a long time in the wrong position,and it can be dangerous for ulcers and lower spine discomfort.This novel study includes a practical implementation of a cushion consisting of a grid of 3×3 force-sensitive resistors(FSR)embedded to read the pressure of the person sitting on it.Additionally,the Body Mass Index(BMI)has been included to increase the resilience of the system across individual physical variances and to identify the incorrect postures(backward,front,left,and right-leaning)based on the five machine learning algorithms:ensemble boosted trees,ensemble bagged trees,ensemble subspace K-Nearest Neighbors(KNN),ensemble subspace discriminant,and ensemble RUSBoosted trees.The proposed arrangement is novel as existing works have only provided simulations without practical implementation,whereas we have implemented the proposed design in Simulink.The results validate the proposed sensor placements,and the machine learning(ML)model reaches a maximum accuracy of 99.99%,which considerably outperforms the existing works.The proposed concept is valuable as it makes it easier for people in workplaces or even at individual household levels to work for long periods without suffering from severe harmful effects from poor posture.展开更多
This paper presents a novel control approach for achieving robust posture control in legged locomotion,specifically for SLIP-like bipedal running and quadrupedal bounding with trunk stabilization.The approach is based...This paper presents a novel control approach for achieving robust posture control in legged locomotion,specifically for SLIP-like bipedal running and quadrupedal bounding with trunk stabilization.The approach is based on the virtual pendulum concept observed in human and animal locomotion experiments,which redirects ground reaction forces to a virtual support point called the Virtual Pivot Point(VPP)during the stance phase.Using the hybrid averaging theorem,we prove the upright posture stability of bipedal running with a fixed VPP position and propose a VPP angle feedback controller for online VPP adjustment to improve performance and convergence speed.Additionally,we present the first application of the VPP concept to quadrupedal posture control and design a VPP position feedback control law to enhance robustness in quadrupedal bounding.We evaluate the effectiveness of the proposed VPP-based controllers through various simulations,demonstrating their effectiveness in posture control of both bipedal running and quadrupedal bounding.The performance of the VPP-based control approach is further validated through experimental validation on a quadruped robot,SCIT Dog,for stable bounding motion generation at different forward speeds.展开更多
Dairy farm management is crucial to maintain the longevity of the farm,and poor dairy youngstock or calf management could lead to gradually deteriorating calf health,which often causes premature death.This was found t...Dairy farm management is crucial to maintain the longevity of the farm,and poor dairy youngstock or calf management could lead to gradually deteriorating calf health,which often causes premature death.This was found to be the most neglected part among the management workflows in Malaysia and has caused continuous loss over the recent years.Calf posture recognition is one of the effective methods to monitor calf behaviour and health state,which can be achieved by monitoring the calf behaviours of standing and lying where the former depicts active calf,and the latter,passive calf.Calf posture recognition module is an important component of some automated calf monitoring systems,as the system requires the calf to be in a standing posture before proceeding to the next stage of monitoring,or at the very least,to monitor the activeness of the calves.Calf posture such as standing or resting can easily be distinguished by human eye,however,to be recognized by a machine,it will require more complicated frameworks,particularly one that involves a deep learning neural networks model.Large number of highquality images are required to train a deep learning model for such tasks.In this paper,multiple ConvolutionalNeuralNetwork(CNN)architectures were compared,and the residual network(ResNet)model(specifically,ResNet-50)was ultimately chosen due to its simplicity,great performance,and decent inference time.Two ResNet-50 models having the exact same architecture and configuration have been trained on two different image datasets respectively sourced by separate cameras placed at different angle.There were two camera placements to use for comparison because camera placements can significantly impact the quality of the images,which is highly correlated to the deep learning model performance.After model training,the performance for both CNN models were 99.7%and 99.99%accuracies,respectively,and is adequate for a real-time calf monitoring system.展开更多
Purpose:To determine the effect of unanticipated mid-flight medial-lateral external perturbation of the upper or lower trunk on anterior cruciate ligament(ACL)loading variable s during jump-landings.Methods:Thirty-two...Purpose:To determine the effect of unanticipated mid-flight medial-lateral external perturbation of the upper or lower trunk on anterior cruciate ligament(ACL)loading variable s during jump-landings.Methods:Thirty-two participants performed double-leg vertical jump-landings while bilateral kinematics and kinetics were collected under 6conditions(upper or lower trunk perturbation locations;no,left,or right perturbation directions).Two customized catapult apparatuses were created to apply pushing perturbation to participants near the maximal jump height.Results:The ball contacted participants near the center of mass for the lower-trunk conditions and approximately 23 cm above the center of mass for the upper-trunk conditions.Under upper-trunk perturbation,the contralateral leg demonstrated significantly smaller knee flexion angles at initial contact and greater peak knee abduction angles,peak vertical ground reaction forces,peak knee extension moments,and peak knee adduction moments compared to other legs among all conditions.Under lower-trunk perturbation,the contralateral leg showed significantly smaller knee flexion angles at initial contact and increased peak vertical ground reaction forces and peak knee extension moments compared to legs in the no-perturbation conditions.Conclusion:Mid-flight external trunk pushing perturbation increased ACL loading variables for the leg contralateral to the perturbation.The uppertrunk perturbation resulted in greater changes in ACL loading variables compared to the lower-trunk perturbation,likely due to trunk and ipsilateral leg rotation and more laterally located center of mass relative to the contralateral leg.These findings may help us understand the mechanisms of indirect-contact ACL injuries and develop jump-landing training strategies under mid-flight trunk perturbation to better prevent ACL injury.展开更多
This paper proposed a novel multi-motion wheel-leg-separated quadruped robot that can adapt to both the structured and unstructured grounds.The models of the positive/inverse position,velocity,acceleration,and workspa...This paper proposed a novel multi-motion wheel-leg-separated quadruped robot that can adapt to both the structured and unstructured grounds.The models of the positive/inverse position,velocity,acceleration,and workspace of the single leg mechanism in the quadruped robot were established.A single leg complex dynamic model of the quadruped robot is derived,considering the mass and inertial force of all the components in the mechanical leg.Combined with the human jumping law in situ,the jumping trajectory of the single leg was planned.To reduce landing impact,a soft landing strategy based on motion planning was proposed by simulating human knee bending and buffering action.The change law of the kinetic energy and momentum of all the links in the single leg mechanism during the jump process was studied,and the influencing factors of jump height were analyzed to realize the height control of the jump.Single leg jumping dynamics model was established,and a dynamic control strategy for trajectory tracking with foot force compensation was proposed.In Adams and MATLAB/Simulink software,the jump simulation of single leg mechanism was carried out.The prototype of quadruped robot was developed,and the jumping experiment of the single leg mechanism was tested.The robot's single leg bionic jumping and soft landing control are realized.展开更多
The plume-surface interaction(PSI)is a common phenomenon that describes the environment surrounding the landers resulting from the impingement of hot rocket exhaust on the regolith of planetary bodies.The PSI will cau...The plume-surface interaction(PSI)is a common phenomenon that describes the environment surrounding the landers resulting from the impingement of hot rocket exhaust on the regolith of planetary bodies.The PSI will cause obscuration,erosion of the planetary surface,and high-speed spreading of dust or high-energy ejecta streams,which will induce risks to a safe landing and cause damage to payloads on the landers or to nearby assets.Safe landings and the subsequent scientific goals of deep-space exploration in China call for a comprehensive understanding of the PSI process,including the plume flow mechanics,erosion mechanism,and ejecta dynamics.In addition,the landing crater caused by the plume provides a unique and insightful perspective on the understanding of PSI.In particular,the PSI can be used directly to constrain the composition,structure,and mechanical properties of the surface and subsurface soil.In this study,we conducted a systematic review of the phenomenology and terrestrial tests of PSI:we analyzed the critical factors in the PSI process and compared the differences in PSI phenomena between lunar and Martian conditions;we also reviewed the main erosion mechanisms and the evolution and development of terrestrial tests on PSI.We discuss the problems with PSI,challenges of terrestrial tests,and prospects of PSI,and we show the preliminary results obtained from the landing crater caused by the PSI of Tianwen-1.From analysis of the camera images and digital elevation model reconstructions,we concluded that the landing of Tianwen-1 caused the deepest crater(depth>40 cm)on a planetary surface reported to date and revealed stratigraphic layers in the subsurface of Martian soil.We further constrained the lower bounds of the mechanical properties of Martian soil by a slope stability analysis of the Tianwen-1 landing crater.The PSI may offer promising opportunities to obtain greater insights into planetary science,including the subsurface structure,mineral composition,and properties of soil.展开更多
基金funded by the Henan Provincial Science and Technology Research Project(222102210086)the Starry Sky Creative Space Innovation Space Innovation Incubation Project of Zhengzhou University of Light Industry(2023ZCKJ211).
文摘This study proposes a pose estimation-convolutional neural network-bidirectional gated recurrent unit(PSECNN-BiGRU)fusion model for human posture recognition to address low accuracy issues in abnormal posture recognition due to the loss of some feature information and the deterioration of comprehensive performance in model detection in complex home environments.Firstly,the deep convolutional network is integrated with the Mediapipe framework to extract high-precision,multi-dimensional information from the key points of the human skeleton,thereby obtaining a human posture feature set.Thereafter,a double-layer BiGRU algorithm is utilized to extract multi-layer,bidirectional temporal features from the human posture feature set,and a CNN network with an exponential linear unit(ELU)activation function is adopted to perform deep convolution of the feature map to extract the spatial feature of the human posture.Furthermore,a squeeze and excitation networks(SENet)module is introduced to adaptively learn the importance weights of each channel,enhancing the network’s focus on important features.Finally,comparative experiments are performed on available datasets,including the public human activity recognition using smartphone dataset(UCIHAR),the public human activity recognition 70 plus dataset(HAR70PLUS),and the independently developed home abnormal behavior recognition dataset(HABRD)created by the authors’team.The results show that the average accuracy of the proposed PSE-CNN-BiGRU fusion model for human posture recognition is 99.56%,89.42%,and 98.90%,respectively,which are 5.24%,5.83%,and 3.19%higher than the average accuracy of the five models proposed in the comparative literature,including CNN,GRU,and others.The F1-score for abnormal posture recognition reaches 98.84%(heartache),97.18%(fall),99.6%(bellyache),and 98.27%(climbing)on the self-builtHABRDdataset,thus verifying the effectiveness,generalization,and robustness of the proposed model in enhancing human posture recognition.
基金supported by the Medical Special Cultivation Project of Anhui University of Science and Technology(Grant No.YZ2023H2B013)the Anhui Provincial Key Research and Development Project(Grant No.2022i01020015)the Open Project of Key Laboratory of Conveyance Equipment(East China Jiaotong University),Ministry of Education(KLCE2022-01).
文摘The human pose paradigm is estimated using a transformer-based multi-branch multidimensional directed the three-dimensional(3D)method that takes into account self-occlusion,badly posedness,and a lack of depth data in the per-frame 3D posture estimation from two-dimensional(2D)mapping to 3D mapping.Firstly,by examining the relationship between the movements of different bones in the human body,four virtual skeletons are proposed to enhance the cyclic constraints of limb joints.Then,multiple parameters describing the skeleton are fused and projected into a high-dimensional space.Utilizing a multi-branch network,motion features between bones and overall motion features are extracted to mitigate the drift error in the estimation results.Furthermore,the estimated relative depth is projected into 3D space,and the error is calculated against real 3D data,forming a loss function along with the relative depth error.This article adopts the average joint pixel error as the primary performance metric.Compared to the benchmark approach,the estimation findings indicate an increase in average precision of 1.8 mm within the Human3.6M sample.
文摘Shimmy can reduce the service life of the nose landing gear, affect ride comfort, and even cause fuselage damage leading to aircraft crashes. Taking a light aircraft as the research object, the torsional freedom of landing gear around strut axis and lateral deformation of tire are considered. Since the landing gear shimmy is a nonlinear system, a nonlinear mechanical model of the front landing gear shimmy is established. Sobol index method is proposed to analyze the influence of structural parameters on the stability region of the nose landing gear, and Routh-Huritz criterion is used to verify the reliability of the analysis results of Sobol index method. We analyse the effect of torsional stiffness of strut, caster length, rated initial tire inflation pressure, rake angle, and vertical force on the stability region of theront landing gear. And the research shows that the optimization of the torsional stiffness of the strut and the caster length of the nose landing gear should be emphasized, and the influence of vertical force on the stability region of the nose landing gear should be paid attention to.
文摘A proper landing posture is significant to the reduction of both the im-pact force acting on the human body and the injury at landing.In this paper theimpact force acting on human feet is studied.The subjects were 3 maleparachuters.The experiments were performed by means of high-speed photography and amotor analyzer.The experimental results are as follows:(1)When the subjectjumped from two platforms 1.0m and 1.5m in height,a vertical impact force onthe feet in half-squat posture was larger than in side spin posture.(2)When thesubject jumped from the platform 1.0m high,the feet gained a horizontal impactforce in the half-squat posture,larger than in the side spin posture.When thesubject jumped from the platform 1.5m high,the horizontal impact force pro-duced by both of the above-mentioned postures were just the same,which needsfurther research.(3)In terms of reducing the impact force acting on the feet,theside spin posture is better than the half-squat posture.
基金supported by British Heart Foundation Accelerator Award,UK(AA/18/3/34220)Royal Society International Exchanges Cost Share Award,UK(RP202G0230)+7 种基金Hope Foundation for Cancer Research,UK(RM60G0680)Medical Research Council Confidence in Concept Award,UK(MC_PC_17171)Sino-UK Industrial Fund,UK(RP202G0289)Global Challenges Research Fund(GCRF),UK(P202PF11)LIAS Pioneering Partnerships award,UK(P202ED10)Data Science Enhancement Fund,UK(P202RE237)Fight for Sight,UK(24NN201)Sino-UK Education Fund,UK(OP202006).
文摘Over the years,the continuous development of new technology has promoted research in the field of posture recognition and also made the application field of posture recognition have been greatly expanded.The purpose of this paper is to introduce the latest methods of posture recognition and review the various techniques and algorithms of posture recognition in recent years,such as scale-invariant feature transform,histogram of oriented gradients,support vectormachine(SVM),Gaussian mixturemodel,dynamic time warping,hiddenMarkovmodel(HMM),lightweight network,convolutional neural network(CNN).We also investigate improved methods of CNN,such as stacked hourglass networks,multi-stage pose estimation networks,convolutional posemachines,and high-resolution nets.The general process and datasets of posture recognition are analyzed and summarized,and several improved CNNmethods and threemain recognition techniques are compared.In addition,the applications of advanced neural networks in posture recognition,such as transfer learning,ensemble learning,graph neural networks,and explainable deep neural networks,are introduced.It was found that CNN has achieved great success in posture recognition and is favored by researchers.Still,a more in-depth research is needed in feature extraction,information fusion,and other aspects.Among classification methods,HMM and SVM are the most widely used,and lightweight network gradually attracts the attention of researchers.In addition,due to the lack of 3Dbenchmark data sets,data generation is a critical research direction.
基金supported by the National Natural Science Foundation of China (62103104)the China Postdoctoral Science Foundation(2021M690615)。
文摘In this paper, we study autonomous landing scene recognition with knowledge transfer for drones. Considering the difficulties in aerial remote sensing, especially that some scenes are extremely similar, or the same scene has different representations in different altitudes, we employ a deep convolutional neural network(CNN) based on knowledge transfer and fine-tuning to solve the problem. Then, LandingScenes-7 dataset is established and divided into seven classes. Moreover, there is still a novelty detection problem in the classifier, and we address this by excluding other landing scenes using the approach of thresholding in the prediction stage. We employ the transfer learning method based on ResNeXt-50 backbone with the adaptive momentum(ADAM) optimization algorithm. We also compare ResNet-50 backbone and the momentum stochastic gradient descent(SGD) optimizer. Experiment results show that ResNeXt-50 based on the ADAM optimization algorithm has better performance. With a pre-trained model and fine-tuning, it can achieve 97.845 0% top-1 accuracy on the LandingScenes-7dataset, paving the way for drones to autonomously learn landing scenes.
基金supported by the National Natural Science Foundation of China,No.62271250the National Key Scientific Instrument and Equipment Development Project,No.61827801+3 种基金Key Technologies R&D Program of Jiangsu(Prospective and Key Technologies for Industry),No.BE2022067,BE2022067-1 and BE2022067-3the Natural Science Foundation of Jiangsu Province,No.BK20211182the open research fund of National Mobile Communications Research Laboratory,Southeast University,No.2022D04the Experimental technology research and development,No.SYJS202304Z。
文摘Considering the unmanned aerial vehicle(UAV) three-dimensional(3D) posture, a novel 3D non-stationary geometry-based stochastic model(GBSM) is proposed for multiple-input multipleoutput(MIMO) UAV-to-vehicle(U2V) channels. It consists of a line-of-sight(Lo S) and non-line-of-sight(NLo S) components. The factor of fuselage posture is considered by introducing a time-variant 3D posture matrix. Some important statistical properties, i.e.the temporal autocorrelation function(ACF) and spatial cross correlation function(CCF), are derived and investigated. Simulation results show that the fuselage posture has significant impact on the U2V channel characteristic and aggravate the non-stationarity. The agreements between analytical, simulated, and measured results verify the correctness of proposed model and derivations. Moreover, it is demonstrated that the proposed model is also compatible to the existing GBSM without considering fuselage posture.
文摘To detect the improper sitting posture of a person sitting on a chair,a posture detection system using machine learning classification has been proposed in this work.The addressed problem correlates to the third Sustainable Development Goal(SDG),ensuring healthy lives and promoting well-being for all ages,as specified by the World Health Organization(WHO).An improper sitting position can be fatal if one sits for a long time in the wrong position,and it can be dangerous for ulcers and lower spine discomfort.This novel study includes a practical implementation of a cushion consisting of a grid of 3×3 force-sensitive resistors(FSR)embedded to read the pressure of the person sitting on it.Additionally,the Body Mass Index(BMI)has been included to increase the resilience of the system across individual physical variances and to identify the incorrect postures(backward,front,left,and right-leaning)based on the five machine learning algorithms:ensemble boosted trees,ensemble bagged trees,ensemble subspace K-Nearest Neighbors(KNN),ensemble subspace discriminant,and ensemble RUSBoosted trees.The proposed arrangement is novel as existing works have only provided simulations without practical implementation,whereas we have implemented the proposed design in Simulink.The results validate the proposed sensor placements,and the machine learning(ML)model reaches a maximum accuracy of 99.99%,which considerably outperforms the existing works.The proposed concept is valuable as it makes it easier for people in workplaces or even at individual household levels to work for long periods without suffering from severe harmful effects from poor posture.
基金This work was supported by the Touyan Innovation Program of Heilongjiang Province.
文摘This paper presents a novel control approach for achieving robust posture control in legged locomotion,specifically for SLIP-like bipedal running and quadrupedal bounding with trunk stabilization.The approach is based on the virtual pendulum concept observed in human and animal locomotion experiments,which redirects ground reaction forces to a virtual support point called the Virtual Pivot Point(VPP)during the stance phase.Using the hybrid averaging theorem,we prove the upright posture stability of bipedal running with a fixed VPP position and propose a VPP angle feedback controller for online VPP adjustment to improve performance and convergence speed.Additionally,we present the first application of the VPP concept to quadrupedal posture control and design a VPP position feedback control law to enhance robustness in quadrupedal bounding.We evaluate the effectiveness of the proposed VPP-based controllers through various simulations,demonstrating their effectiveness in posture control of both bipedal running and quadrupedal bounding.The performance of the VPP-based control approach is further validated through experimental validation on a quadruped robot,SCIT Dog,for stable bounding motion generation at different forward speeds.
基金funded under the Malaysian Young Researchers grant scheme(MRUN-MYRGS)Vote number:5539500(Universiti Putra Malaysia)Title:Precision surveillance system to support dairy young stock rearing decisions(NMN).
文摘Dairy farm management is crucial to maintain the longevity of the farm,and poor dairy youngstock or calf management could lead to gradually deteriorating calf health,which often causes premature death.This was found to be the most neglected part among the management workflows in Malaysia and has caused continuous loss over the recent years.Calf posture recognition is one of the effective methods to monitor calf behaviour and health state,which can be achieved by monitoring the calf behaviours of standing and lying where the former depicts active calf,and the latter,passive calf.Calf posture recognition module is an important component of some automated calf monitoring systems,as the system requires the calf to be in a standing posture before proceeding to the next stage of monitoring,or at the very least,to monitor the activeness of the calves.Calf posture such as standing or resting can easily be distinguished by human eye,however,to be recognized by a machine,it will require more complicated frameworks,particularly one that involves a deep learning neural networks model.Large number of highquality images are required to train a deep learning model for such tasks.In this paper,multiple ConvolutionalNeuralNetwork(CNN)architectures were compared,and the residual network(ResNet)model(specifically,ResNet-50)was ultimately chosen due to its simplicity,great performance,and decent inference time.Two ResNet-50 models having the exact same architecture and configuration have been trained on two different image datasets respectively sourced by separate cameras placed at different angle.There were two camera placements to use for comparison because camera placements can significantly impact the quality of the images,which is highly correlated to the deep learning model performance.After model training,the performance for both CNN models were 99.7%and 99.99%accuracies,respectively,and is adequate for a real-time calf monitoring system.
基金supported by the National Science Foundation(1933409)the China Scholarship Council+1 种基金a student research grant from the International Society of Biomechanics in Sportsthe Wyoming IDeA Networks for Biomedical Research Excellence,supported by the National Institutes of Health(P20GM103432)。
文摘Purpose:To determine the effect of unanticipated mid-flight medial-lateral external perturbation of the upper or lower trunk on anterior cruciate ligament(ACL)loading variable s during jump-landings.Methods:Thirty-two participants performed double-leg vertical jump-landings while bilateral kinematics and kinetics were collected under 6conditions(upper or lower trunk perturbation locations;no,left,or right perturbation directions).Two customized catapult apparatuses were created to apply pushing perturbation to participants near the maximal jump height.Results:The ball contacted participants near the center of mass for the lower-trunk conditions and approximately 23 cm above the center of mass for the upper-trunk conditions.Under upper-trunk perturbation,the contralateral leg demonstrated significantly smaller knee flexion angles at initial contact and greater peak knee abduction angles,peak vertical ground reaction forces,peak knee extension moments,and peak knee adduction moments compared to other legs among all conditions.Under lower-trunk perturbation,the contralateral leg showed significantly smaller knee flexion angles at initial contact and increased peak vertical ground reaction forces and peak knee extension moments compared to legs in the no-perturbation conditions.Conclusion:Mid-flight external trunk pushing perturbation increased ACL loading variables for the leg contralateral to the perturbation.The uppertrunk perturbation resulted in greater changes in ACL loading variables compared to the lower-trunk perturbation,likely due to trunk and ipsilateral leg rotation and more laterally located center of mass relative to the contralateral leg.These findings may help us understand the mechanisms of indirect-contact ACL injuries and develop jump-landing training strategies under mid-flight trunk perturbation to better prevent ACL injury.
基金This work was supported by the National Nature Science Foundation of China(Grant No.51905367)the Foundation of Applied Basic Research General Youth Program of Shanxi(Grant No.201901D211011)the Scientific and Technological Innovation Programs of Higher Education Institutions of Shanxi(Grant No.2019L0176).
文摘This paper proposed a novel multi-motion wheel-leg-separated quadruped robot that can adapt to both the structured and unstructured grounds.The models of the positive/inverse position,velocity,acceleration,and workspace of the single leg mechanism in the quadruped robot were established.A single leg complex dynamic model of the quadruped robot is derived,considering the mass and inertial force of all the components in the mechanical leg.Combined with the human jumping law in situ,the jumping trajectory of the single leg was planned.To reduce landing impact,a soft landing strategy based on motion planning was proposed by simulating human knee bending and buffering action.The change law of the kinetic energy and momentum of all the links in the single leg mechanism during the jump process was studied,and the influencing factors of jump height were analyzed to realize the height control of the jump.Single leg jumping dynamics model was established,and a dynamic control strategy for trajectory tracking with foot force compensation was proposed.In Adams and MATLAB/Simulink software,the jump simulation of single leg mechanism was carried out.The prototype of quadruped robot was developed,and the jumping experiment of the single leg mechanism was tested.The robot's single leg bionic jumping and soft landing control are realized.
基金supported by the National Natural Science Foundation of China(Grant 42230111)the Key Research Program of the Institute of Geology and Geophysics,CAS(Mars Mission,Grant IGGCAS-202102)+1 种基金the Key Research Program of the Institute of Geology and Geophysics,CAS(Grant IGGCAS-201904)the CAS Key Technology Talent Program.
文摘The plume-surface interaction(PSI)is a common phenomenon that describes the environment surrounding the landers resulting from the impingement of hot rocket exhaust on the regolith of planetary bodies.The PSI will cause obscuration,erosion of the planetary surface,and high-speed spreading of dust or high-energy ejecta streams,which will induce risks to a safe landing and cause damage to payloads on the landers or to nearby assets.Safe landings and the subsequent scientific goals of deep-space exploration in China call for a comprehensive understanding of the PSI process,including the plume flow mechanics,erosion mechanism,and ejecta dynamics.In addition,the landing crater caused by the plume provides a unique and insightful perspective on the understanding of PSI.In particular,the PSI can be used directly to constrain the composition,structure,and mechanical properties of the surface and subsurface soil.In this study,we conducted a systematic review of the phenomenology and terrestrial tests of PSI:we analyzed the critical factors in the PSI process and compared the differences in PSI phenomena between lunar and Martian conditions;we also reviewed the main erosion mechanisms and the evolution and development of terrestrial tests on PSI.We discuss the problems with PSI,challenges of terrestrial tests,and prospects of PSI,and we show the preliminary results obtained from the landing crater caused by the PSI of Tianwen-1.From analysis of the camera images and digital elevation model reconstructions,we concluded that the landing of Tianwen-1 caused the deepest crater(depth>40 cm)on a planetary surface reported to date and revealed stratigraphic layers in the subsurface of Martian soil.We further constrained the lower bounds of the mechanical properties of Martian soil by a slope stability analysis of the Tianwen-1 landing crater.The PSI may offer promising opportunities to obtain greater insights into planetary science,including the subsurface structure,mineral composition,and properties of soil.