Predicting human motion based on historical motion sequences is a fundamental problem in computer vision,which is at the core of many applications.Existing approaches primarily focus on encoding spatial dependencies a...Predicting human motion based on historical motion sequences is a fundamental problem in computer vision,which is at the core of many applications.Existing approaches primarily focus on encoding spatial dependencies among human joints while ignoring the temporal cues and the complex relationships across non-consecutive frames.These limitations hinder the model’s ability to generate accurate predictions over longer time horizons and in scenarios with complex motion patterns.To address the above problems,we proposed a novel multi-level spatial and temporal learning model,which consists of a Cross Spatial Dependencies Encoding Module(CSM)and a Dynamic Temporal Connection Encoding Module(DTM).Specifically,the CSM is designed to capture complementary local and global spatial dependent information at both the joint level and the joint pair level.We further present DTM to encode diverse temporal evolution contexts and compress motion features to a deep level,enabling the model to capture both short-term and long-term dependencies efficiently.Extensive experiments conducted on the Human 3.6M and CMU Mocap datasets demonstrate that our model achieves state-of-the-art performance in both short-term and long-term predictions,outperforming existing methods by up to 20.3% in accuracy.Furthermore,ablation studies confirm the significant contributions of the CSM and DTM in enhancing prediction accuracy.展开更多
Research on human motion prediction has made significant progress due to its importance in the development of various artificial intelligence applications.However,effectively capturing spatio-temporal features for smo...Research on human motion prediction has made significant progress due to its importance in the development of various artificial intelligence applications.However,effectively capturing spatio-temporal features for smoother and more precise human motion prediction remains a challenge.To address these issues,a robust human motion prediction method via integration of spatial and temporal cues(RISTC)has been proposed.This method captures sufficient spatio-temporal correlation of the observable sequence of human poses by utilizing the spatio-temporal mixed feature extractor(MFE).In multi-layer MFEs,the channel-graph united attention blocks extract the augmented spatial features of the human poses in the channel and spatial dimension.Additionally,multi-scale temporal blocks have been designed to effectively capture complicated and highly dynamic temporal information.Our experiments on the Human3.6M and Carnegie Mellon University motion capture(CMU Mocap)datasets show that the proposed network yields higher prediction accuracy than the state-of-the-art methods.展开更多
Wearable,flexible devices have garnered widespread attention in the realm of human motion and life activity detection.Currently,the development of simple,green,and easily scalable methods for fabricating strain sensor...Wearable,flexible devices have garnered widespread attention in the realm of human motion and life activity detection.Currently,the development of simple,green,and easily scalable methods for fabricating strain sensors still presents significant challenges.In this study,we successfully modified the surface of reduced graphene oxide(rGO)with SnCuNiIn multi-component alloy nanoparticles(MCA NPs),with an average size of 13.29 nm,utilizing a green and facile microwave heating approach.Leveraging the SnCuNiIn MCA NPs/rGO powder,we formulated a conductive ink based on water and ethylene glycol,which,when screen-printed,yielded conductive patterns with a minimum resistivity of 4.366 mΩ·cm.Strain sensors produced using this ink demonstrate exceptional performance,demonstrating favorable resistance change rates during a single bending process that meets practical application requirements,and enduring 5000 bending cycles with a resistance change of less than 5%.These sensors exhibited a high gauge factor(GF_(max)=52.7)and outstanding cycling stability.Lastly,strain sensors are employed to monitor human normal life activities and motion states,showcasing significant potential for application in wearable electronic products.展开更多
Highly sensitive sensors with extensive applications are extremely desired in the next-generation wearable electronics for human motion monitoring,human-machine interface and intelligent robotics,while singlefunctiona...Highly sensitive sensors with extensive applications are extremely desired in the next-generation wearable electronics for human motion monitoring,human-machine interface and intelligent robotics,while singlefunctional pressure sensors cannot fulfill the growing demands of modern technological advances.Herein,an all-fabric and multilayered piezoresistive sensor based on conductive metal-organic frame-work/layered double hydroxide(cMOF/LDH)hetero-nanoforest is demonstrated to achieve multiple applications including pulse detection,joint motion detection,sound detection and information transmission.Benefiting from the synergism of cMOF/LDH hetero-nanoforest and multilayered structure,the sensor exhibits a high sensitivity(1.61×10^(9)kPa^(−1))over a broad pressure range(0-100 kPa),a fast response/recovery time(71 ms/71 ms)and a low detection limit(18 Pa),as well as reliable dynamic stability(8000 cycles).It is gratifying to note that the introduction of cMOFs endows the sensor with the potential to detect the concentration of NH_(3)(1-100 ppm)and sunlight intensity(10-100 mW cm^(−2)).This work shows great potential in multifunctional sensing,which enlightens a strategy for advancing the development process of highly sensitive intelligent wearable devices.展开更多
Due to the dynamic stiffness characteristics of human joints, it is easy to cause impact and disturbance on normal movements during exoskeleton assistance. This not only brings strict requirements for exoskeleton cont...Due to the dynamic stiffness characteristics of human joints, it is easy to cause impact and disturbance on normal movements during exoskeleton assistance. This not only brings strict requirements for exoskeleton control design, but also makes it difficult to improve assistive level. The Variable Stiffness Actuator (VSA), as a physical variable stiffness mechanism, has the characteristics of dynamic stiffness adjustment and high stiffness control bandwidth, which is in line with the stiffness matching experiment. However, there are still few works exploring the assistive human stiffness matching experiment based on VSA. Therefore, this paper designs a hip exoskeleton based on VSA actuator and studies CPG human motion phase recognition algorithm. Firstly, this paper puts forward the requirements of variable stiffness experimental design and the output torque and variable stiffness dynamic response standards based on human lower limb motion parameters. Plate springs are used as elastic elements to establish the mechanical principle of variable stiffness, and a small variable stiffness actuator is designed based on the plate spring. Then the corresponding theoretical dynamic model is established and analyzed. Starting from the CPG phase recognition algorithm, this paper uses perturbation theory to expand the first-order CPG unit, obtains the phase convergence equation and verifies the phase convergence when using hip joint angle as the input signal with the same frequency, and then expands the second-order CPG unit under the premise of circular limit cycle and analyzes the frequency convergence criterion. Afterwards, this paper extracts the plate spring modal from Abaqus and generates the neutral file of the flexible body model to import into Adams, and conducts torque-stiffness one-way loading and reciprocating loading experiments on the variable stiffness mechanism. After that, Simulink is used to verify the validity of the criterion. Finally, based on the above criterions, the signal mean value is removed using feedback structure to complete the phase recognition algorithm for the human hip joint angle signal, and the convergence is verified using actual human walking data on flat ground.展开更多
For traditional piezoelectric sensors based on poled ceramics,a low curie tem-perature(T_(c))is a fatal flaw due to the depolarization phenomenon.However,in this study,we find the low T_(c) would be a benefit for flex...For traditional piezoelectric sensors based on poled ceramics,a low curie tem-perature(T_(c))is a fatal flaw due to the depolarization phenomenon.However,in this study,we find the low T_(c) would be a benefit for flex-ible piezoelectric sensors because small alterations of force trig-ger large changes in polarization.BaTi_(0.88)Sn_(0.12)O_(3)(BTS)with high piezoelectric coefficient and low T_(c) close to human body temperature is taken as an example for materials of this kind.Continuous piezo-electric BTS films were deposited on the flexible glass fiber fabrics(GFF),self-powered sensors based on the ultra-thin,superflexible,and polarization-free BTS-GFF/PVDF composite piezoelectric films are used for human motion sensing.In the low force region(1-9 N),the sensors have the outstanding performance with voltage sensitivity of 1.23 V N^(−1) and current sensitivity of 41.0 nA N^(−1).The BTS-GFF/PVDF sensors can be used to detect the tiny forces of falling water drops,finger joint motion,tiny surface deformation,and fatigue driving with high sensitivity.This work provides a new paradigm for the preparation of superflexible,highly sensitive and wearable self-powered piezoelectric sensors,and this kind of sensors will have a broad application prospect in the fields of medical rehabilitation,human motion monitoring,and intelligent robot.展开更多
Nonverbal and noncontact behaviors play a significant role in allowing service robots to structure their interactions withhumans.In this paper, a novel human-mimic mechanism of robot’s navigational skills was propose...Nonverbal and noncontact behaviors play a significant role in allowing service robots to structure their interactions withhumans.In this paper, a novel human-mimic mechanism of robot’s navigational skills was proposed for developing sociallyacceptable robotic etiquette.Based on the sociological and physiological concerns of interpersonal interactions in movement,several criteria in navigation were represented by constraints and incorporated into a unified probabilistic cost grid for safemotion planning and control, followed by an emphasis on the prediction of the human’s movement for adjusting the robot’spre-collision navigational strategy.The human motion prediction utilizes a clustering-based algorithm for modeling humans’indoor motion patterns as well as the combination of the long-term and short-term tendency prediction that takes into accountthe uncertainties of both velocity and heading direction.Both simulation and real-world experiments verified the effectivenessand reliability of the method to ensure human’s safety and comfort in navigation.A statistical user trials study was also given tovalidate the users’favorable views of the human-friendly navigational behavior.展开更多
Ultra-wideband(UWB)through-wall radar has a wide range of applications in non-contact human information detection and monitoring.With the integration of machine learning technology,its potential prospects include the ...Ultra-wideband(UWB)through-wall radar has a wide range of applications in non-contact human information detection and monitoring.With the integration of machine learning technology,its potential prospects include the physiological monitoring of patients in the hospital environment and the daily monitoring at home.Although many target detection methods of UWB through-wall radar based on machine learning have been proposed,there is a lack of an opensource dataset to evaluate the performance of the algorithm.This published dataset is measured by impulse radio UWB(IR-UWB)through-wall radar system.Three test subjects are measured in different environments and several defined motion status.Using the presented dataset,we propose a human-motion-status recognition method using a convolutional neural network(CNN),and the detailed dataset partition method and the recognition process flow are given.On the well-trained network,the recognition accuracy of testing data for three kinds of motion status is higher than 99.7%.The dataset presented in this paper considers a simple environment.Therefore,we call on all organizations in the UWB radar field to cooperate to build opensource datasets to further promote the development of UWB through-wall radar.展开更多
Human motion analysis consists of real-time monitoring and recording of human body’s kinematics. It is very essential to track ambulatory and dailylife human motion, which is crucial for many applications and discipl...Human motion analysis consists of real-time monitoring and recording of human body’s kinematics. It is very essential to track ambulatory and dailylife human motion, which is crucial for many applications and disciplines.Electronic textiles(e-textiles) afford a valid alternative to traditional solidstate sensors due to their merits of low cost, lightweight, flexibility, and feasibility to fit various human bodies. In this mini-review, textile-based sensor platforms and human motion analysis are well discussed in Section 1.Second, theoretical principles of textile-based strain sensors are introduced including resistive, capacitive, and piezoelectrical sensors. Section 3 focuses on various types of textile materials that are functionalized as sensing systems by intrinsic or extrinsic modifications. Section 4 summaries various types of e-textile-based strain sensors for human motion analysis. The final two sections mainly present perspectives and challenges, and conclusions,respectively.展开更多
A lightweight multi-layer residual temporal convolutional network model(RTCN)is proposed to target the highly complex kinematics and temporal correlation of human motion.RTCN uses 1-D convolution to efficiently obtain...A lightweight multi-layer residual temporal convolutional network model(RTCN)is proposed to target the highly complex kinematics and temporal correlation of human motion.RTCN uses 1-D convolution to efficiently obtain the spatial structure information of human motion and extract the correlation in the time series of human motion.The residual structure is applied to the proposed network model to alleviate the problem of gradient disappearance in the deep network.Experiments on the Human 3.6M dataset demonstrate that the proposed method effectively reduces the errors of motion prediction compared with previous methods,especially of long-term prediction.展开更多
A modified random walk model for human motion is proposed to investigate characteristics of 60GHz indoor office propagation.Compared with the classic random walk model,the movement tendency in the walking process is t...A modified random walk model for human motion is proposed to investigate characteristics of 60GHz indoor office propagation.Compared with the classic random walk model,the movement tendency in the walking process is taken into account in the modified model.Based on the proposed model,path gains of the propagation environment are simulated under a variety of settings by using a ray tracing method.Simulation results and analysis show that human motion is a major source of disturbance to the indoor office propagation and results in performance degradation in some areas.展开更多
The key pose frames of a human motion pose sequence,play an important role in the compression,retrieval and semantic analysis of continuous human motion.The current available clustering methods in literatures are diff...The key pose frames of a human motion pose sequence,play an important role in the compression,retrieval and semantic analysis of continuous human motion.The current available clustering methods in literatures are difficult to determine the number of key pose frames automatically,and may destroy the postures’ temporal relationships while extracting key frames.To deal with this problem,this paper proposes a new key pose frames extraction method on the basis of 3D space distances of joint points and the improved X-means clustering algorithm.According to the proposed extraction method,the final key pose frame sequence could be obtained by describing the posture of human body with space distance of particular joint points and then the time-constraint X-mean algorithm is applied to cluster and filtrate the posture sequence.The experimental results show that the proposed method can automatically determine the number of key frames and save the temporal characteristics of motion frames according to the motion pose sequence.展开更多
Flexible strain sensor has promising features in successful application of health monitoring, electronic skins and smart robotics, etc.Here, we report an ultrasensitive strain sensor with a novel crack-wrinkle structu...Flexible strain sensor has promising features in successful application of health monitoring, electronic skins and smart robotics, etc.Here, we report an ultrasensitive strain sensor with a novel crack-wrinkle structure(CWS) based on graphite nanoplates(GNPs)/thermoplastic urethane(TPU)/polydimethylsiloxane(PDMS) nanocomposite. The CWS is constructed by pressing and dragging GNP layer on TPU substrate,followed by encapsulating with PDMS as a protective layer. On the basis of the area statistics, the ratio of the crack and wrinkle structures accounts for 31.8% and 9.5%, respectively. When the sensor is stretched, the cracks fracture, the wrinkles could reduce the unrecoverable destruction of cracks, resulting in an excellent recoverability and stability. Based on introduction of the designed CWS in the sensor, the hysteresis effect is limited effectively. The CWS sensor possesses a satisfactory sensitivity(GF=750 under 24% strain), an ultralow detectable limit(strain=0.1%) and a short respond time of 90 ms. For the sensing service behaviors, the CWS sensor exhibits an ultrahigh durability(high stability>2×10^(4) stretching-releasing cycles). The excellent practicality of CWS sensor is demonstrated through various human motion tests,including vigorous exercises of various joint bending, and subtle motions of phonation, facial movements and wrist pulse. The present CWS sensor shows great developing potential in the field of cost-effective, portable and high-performance electronic skins.展开更多
Cameras can reliably detect human motions in a normal environment, but they are usually affected by sudden illumination changes and complex conditions, which are the major obstacles to the reliability and robustness o...Cameras can reliably detect human motions in a normal environment, but they are usually affected by sudden illumination changes and complex conditions, which are the major obstacles to the reliability and robustness of the system. To solve this problem, a novel integration method was proposed to combine hi-static ultra-wideband radar and cameras. In this recognition system, two cameras are used to localize the object＇s region, regions while a radar is used to obtain its 3D motion models on a mobile robot. The recognition results can be matched in the 3D motion library in order to recognize its motions. To confirm the effectiveness of the proposed method, the experimental results of recognition using vision sensors and those of recognition using the integration method were compared in different environments. Higher correct-recognition rate is achieved in the experiment.展开更多
Batch processing mode is widely used in the training process of human motiun recognition. After training, the motion elassitier usually remains invariable. However, if the classifier is to be expanded, all historical ...Batch processing mode is widely used in the training process of human motiun recognition. After training, the motion elassitier usually remains invariable. However, if the classifier is to be expanded, all historical data must be gathered for retraining. This consumes a huge amount of storage space, and the new training process will be more complicated. In this paper, we use an incremental learning method to model the motion classifier. A weighted decision tree is proposed to help illustrate the process, and the probability sampling method is also used. The resuhs show that with continuous learning, the motion classifier is more precise. The average classification precision for the weighted decision tree was 88.43% in a typical test. Incremental learning consumes much less time than the batch processing mode when the input training data comes continuously.展开更多
The main objectives were to (1) calculate the total volatile organic compounds (TVOCs) inhalation dose, (2) analyze the proportions of human’s inhaled contaminant dose from different sources, and (3) present a newly ...The main objectives were to (1) calculate the total volatile organic compounds (TVOCs) inhalation dose, (2) analyze the proportions of human’s inhaled contaminant dose from different sources, and (3) present a newly defined ratio of relative inhalation dose level (RIDL) to assess indoor air quality (IAQ). A user defined function based on CFD (computational fluid dynamics) was developed, which integrated human motion model with TVOCs emission model in a high sidewall air supply ventilation mode. Based on simulation results of 10 cases, it is shown that the spatial concentration distribution of TVOCs is affected by human motion. TVOCs diffusion characteristic of building material is the most effective way to impact the TVOCs inhalation dose. From the RIDL index, case A-2 has the most serious IAQ problem, while case D-1 is of the best IAQ.展开更多
In recent years,human motion prediction has become an active research topic in computer vision.However,owing to the complexity and stochastic nature of human motion,it remains a challenging problem.In previous works,h...In recent years,human motion prediction has become an active research topic in computer vision.However,owing to the complexity and stochastic nature of human motion,it remains a challenging problem.In previous works,human motion prediction has always been treated as a typical inter-sequence problem,and most works have aimed to capture the temporal dependence between successive frames.However,although these approaches focused on the effects of the temporal dimension,they rarely considered the correlation between different joints in space.Thus,the spatio-temporal coupling of human joints is considered,to propose a novel spatio-temporal network based on a transformer and a gragh convolutional network(GCN)(STTG-Net).The temporal transformer is used to capture the global temporal dependencies,and the spatial GCN module is used to establish local spatial correlations between the joints for each frame.To overcome the problems of error accumulation and discontinuity in the motion prediction,a revision method based on fusion strategy is also proposed,in which the current prediction frame is fused with the previous frame.The experimental results show that the proposed prediction method has less prediction error and the prediction motion is smoother than previous prediction methods.The effectiveness of the proposed method is also demonstrated comparing it with the state-of-the-art method on the Human3.6 M dataset.展开更多
The advancement of wearable devices continues to face the challenge of ensuring a sustainable power supply.Traditional human motion energy harvesters often suffer from low energy harvesting efficiency due to their rel...The advancement of wearable devices continues to face the challenge of ensuring a sustainable power supply.Traditional human motion energy harvesters often suffer from low energy harvesting efficiency due to their reliance on a single energy source.This study presents a novel pendulum inertial electromagnetic energy harvester(PI-EEH)to harvest multiplesource low-frequency human motion energy.The PI-EEH can simultaneously harvest both the leg swing energy and the foot impact energy during walking.A horizontal universal pendulum,combined with a frequency-up conversion mechanism,transforms irregular human motion into unidirectional high-frequency rotation.The output performance of the PI-EEH is evaluated through both theoretical analysis and experimental testing.A treadmill test is also conducted across various motion speeds to illustrate the benefits of PI-EEH.The peak power of PI-EEH can reach 54 mW at a speed of 3 km/h.Additionally,the PI-EEH can easily supply power for some wearable devices,like a GPS module and an acceleration sensor.The designed PIEEH offers a viable approach to harvesting energy from multiple-source human motion,which will have broad prospects in smart healthcare and IoT applications.展开更多
Extensive research has explored human motion generation,but the generated sequences are influenced by different motion styles.For instance,the act of walking with joy and sorrow evokes distinct effects on a character...Extensive research has explored human motion generation,but the generated sequences are influenced by different motion styles.For instance,the act of walking with joy and sorrow evokes distinct effects on a character’s motion.Due to the difficulties in motion capture with styles,the available data for style research are also limited.To address the problems,we propose ASMNet,an action and style-conditioned motion generative network.This network ensures that the generated human motion sequences not only comply with the provided action label but also exhibit distinctive stylistic features.To extract motion features from human motion sequences,we design a spatial temporal extractor.Moreover,we use the adaptive instance normalization layer to inject style into the target motion.Our results are comparable to state-of-the-art approaches and display a substantial advantage in both quantitative and qualitative evaluations.The code is available at https://github.com/ZongYingLi/ASMNet.git.展开更多
Quantitative analysis of gait parameters,such as stride frequency and step speed,is essential for optimizing physical exercise for the human body.However,the current electronic sensors used in human motion monitoring ...Quantitative analysis of gait parameters,such as stride frequency and step speed,is essential for optimizing physical exercise for the human body.However,the current electronic sensors used in human motion monitoring remain constrained by factors such as battery life and accuracy.This study developed a self-powered gait analysis system(SGAS)based on a triboelectric nanogenerator(TENG)fabricated electrospun composite nanofibers for motion monitoring and gait analysis for regulating exercise programs.The SGAS consists of a sensing module,a charging module,a data acquisition and processing module,and an Internet of Things(IoT)platform.Within the sensing module,two specialized sensing units,TENG-S1 and TENG-S2,are positioned at the forefoot and heel to generate synchronized signals in tandem with the user's footsteps.These signals are instrumental for real-time step count and step speed monitoring.The output of the two TENG units is significantly improved by systematically investigating and optimizing the electrospun composite nanofibers'composition,strength,and wear resistance.Additionally,a charge amplifier circuit is implemented to process the raw voltage signal,consequently bolstering the reliability of the sensing signal.This refined data is then ready for further reading and calculation by the micro-controller unit(MCU)during the signal transmission process.Finally,the well-conditioned signals are wirelessly transmitted to the IoT platform for data analysis,storage,and visualization,enhancing human motion monitoring.展开更多
基金supported by the Urgent Need for Overseas Talent Project of Jiangxi Province(Grant No.20223BCJ25040)the Thousand Talents Plan of Jiangxi Province(Grant No.jxsg2023101085)+3 种基金the National Natural Science Foundation of China(Grant No.62106093)the Natural Science Foundation of Jiangxi(Grant Nos.20224BAB212011,20232BAB212008,20242BAB25078,and 20232BAB202051)The Youth Talent Cultivation Innovation Fund Project of Nanchang University(Grant No.XX202506030015)funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R759),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Predicting human motion based on historical motion sequences is a fundamental problem in computer vision,which is at the core of many applications.Existing approaches primarily focus on encoding spatial dependencies among human joints while ignoring the temporal cues and the complex relationships across non-consecutive frames.These limitations hinder the model’s ability to generate accurate predictions over longer time horizons and in scenarios with complex motion patterns.To address the above problems,we proposed a novel multi-level spatial and temporal learning model,which consists of a Cross Spatial Dependencies Encoding Module(CSM)and a Dynamic Temporal Connection Encoding Module(DTM).Specifically,the CSM is designed to capture complementary local and global spatial dependent information at both the joint level and the joint pair level.We further present DTM to encode diverse temporal evolution contexts and compress motion features to a deep level,enabling the model to capture both short-term and long-term dependencies efficiently.Extensive experiments conducted on the Human 3.6M and CMU Mocap datasets demonstrate that our model achieves state-of-the-art performance in both short-term and long-term predictions,outperforming existing methods by up to 20.3% in accuracy.Furthermore,ablation studies confirm the significant contributions of the CSM and DTM in enhancing prediction accuracy.
基金supported by the National Key R&D Program of China(No.2018YFB1305200)the Natural Science Foundation of Zhejiang Province(No.LGG21F030011)。
文摘Research on human motion prediction has made significant progress due to its importance in the development of various artificial intelligence applications.However,effectively capturing spatio-temporal features for smoother and more precise human motion prediction remains a challenge.To address these issues,a robust human motion prediction method via integration of spatial and temporal cues(RISTC)has been proposed.This method captures sufficient spatio-temporal correlation of the observable sequence of human poses by utilizing the spatio-temporal mixed feature extractor(MFE).In multi-layer MFEs,the channel-graph united attention blocks extract the augmented spatial features of the human poses in the channel and spatial dimension.Additionally,multi-scale temporal blocks have been designed to effectively capture complicated and highly dynamic temporal information.Our experiments on the Human3.6M and Carnegie Mellon University motion capture(CMU Mocap)datasets show that the proposed network yields higher prediction accuracy than the state-of-the-art methods.
基金financially supported by Heilongjiang Provincial Natural Science Foundation of China(No.YQ2022E024)the National Natural Science Foundation of China(No.52375327)。
文摘Wearable,flexible devices have garnered widespread attention in the realm of human motion and life activity detection.Currently,the development of simple,green,and easily scalable methods for fabricating strain sensors still presents significant challenges.In this study,we successfully modified the surface of reduced graphene oxide(rGO)with SnCuNiIn multi-component alloy nanoparticles(MCA NPs),with an average size of 13.29 nm,utilizing a green and facile microwave heating approach.Leveraging the SnCuNiIn MCA NPs/rGO powder,we formulated a conductive ink based on water and ethylene glycol,which,when screen-printed,yielded conductive patterns with a minimum resistivity of 4.366 mΩ·cm.Strain sensors produced using this ink demonstrate exceptional performance,demonstrating favorable resistance change rates during a single bending process that meets practical application requirements,and enduring 5000 bending cycles with a resistance change of less than 5%.These sensors exhibited a high gauge factor(GF_(max)=52.7)and outstanding cycling stability.Lastly,strain sensors are employed to monitor human normal life activities and motion states,showcasing significant potential for application in wearable electronic products.
基金supported by the National Natural Science Foundation of China(Nos.52271209 and 51762013)the Key Project of Hebei Natural Science Foundation(No.E20202201030)+5 种基金the Beijing-Tianjin-Hebei Collaborative Innovation Community Construction Project(No.21344301D)the Second Batch of Young Talent of Hebei Province(Nos.70280016160250 and 70280011808)the Key Fund in Hebei Province Department of Education China(No.ZD2021014)the Central Government Guide Local Funding Projects for Scientific and Technological Development(Nos.216Z4404G and 206Z4402G)the Interdisciplinary Research Program of Natural Science of Hebei University(No.DXK202107)the Government Foundation of Clinical Medicine Talents Training Program of Hebei Province(No.361007).
文摘Highly sensitive sensors with extensive applications are extremely desired in the next-generation wearable electronics for human motion monitoring,human-machine interface and intelligent robotics,while singlefunctional pressure sensors cannot fulfill the growing demands of modern technological advances.Herein,an all-fabric and multilayered piezoresistive sensor based on conductive metal-organic frame-work/layered double hydroxide(cMOF/LDH)hetero-nanoforest is demonstrated to achieve multiple applications including pulse detection,joint motion detection,sound detection and information transmission.Benefiting from the synergism of cMOF/LDH hetero-nanoforest and multilayered structure,the sensor exhibits a high sensitivity(1.61×10^(9)kPa^(−1))over a broad pressure range(0-100 kPa),a fast response/recovery time(71 ms/71 ms)and a low detection limit(18 Pa),as well as reliable dynamic stability(8000 cycles).It is gratifying to note that the introduction of cMOFs endows the sensor with the potential to detect the concentration of NH_(3)(1-100 ppm)and sunlight intensity(10-100 mW cm^(−2)).This work shows great potential in multifunctional sensing,which enlightens a strategy for advancing the development process of highly sensitive intelligent wearable devices.
文摘Due to the dynamic stiffness characteristics of human joints, it is easy to cause impact and disturbance on normal movements during exoskeleton assistance. This not only brings strict requirements for exoskeleton control design, but also makes it difficult to improve assistive level. The Variable Stiffness Actuator (VSA), as a physical variable stiffness mechanism, has the characteristics of dynamic stiffness adjustment and high stiffness control bandwidth, which is in line with the stiffness matching experiment. However, there are still few works exploring the assistive human stiffness matching experiment based on VSA. Therefore, this paper designs a hip exoskeleton based on VSA actuator and studies CPG human motion phase recognition algorithm. Firstly, this paper puts forward the requirements of variable stiffness experimental design and the output torque and variable stiffness dynamic response standards based on human lower limb motion parameters. Plate springs are used as elastic elements to establish the mechanical principle of variable stiffness, and a small variable stiffness actuator is designed based on the plate spring. Then the corresponding theoretical dynamic model is established and analyzed. Starting from the CPG phase recognition algorithm, this paper uses perturbation theory to expand the first-order CPG unit, obtains the phase convergence equation and verifies the phase convergence when using hip joint angle as the input signal with the same frequency, and then expands the second-order CPG unit under the premise of circular limit cycle and analyzes the frequency convergence criterion. Afterwards, this paper extracts the plate spring modal from Abaqus and generates the neutral file of the flexible body model to import into Adams, and conducts torque-stiffness one-way loading and reciprocating loading experiments on the variable stiffness mechanism. After that, Simulink is used to verify the validity of the criterion. Finally, based on the above criterions, the signal mean value is removed using feedback structure to complete the phase recognition algorithm for the human hip joint angle signal, and the convergence is verified using actual human walking data on flat ground.
基金This work is financially supported by the basic research project of science and technology of Shanghai(No.20JC1415000)National Natural Science Foundation of China(Nos.11874257 and 52032012)the Fund for Science and Technology Innovation of Shanghai Jiao Tong University.
文摘For traditional piezoelectric sensors based on poled ceramics,a low curie tem-perature(T_(c))is a fatal flaw due to the depolarization phenomenon.However,in this study,we find the low T_(c) would be a benefit for flex-ible piezoelectric sensors because small alterations of force trig-ger large changes in polarization.BaTi_(0.88)Sn_(0.12)O_(3)(BTS)with high piezoelectric coefficient and low T_(c) close to human body temperature is taken as an example for materials of this kind.Continuous piezo-electric BTS films were deposited on the flexible glass fiber fabrics(GFF),self-powered sensors based on the ultra-thin,superflexible,and polarization-free BTS-GFF/PVDF composite piezoelectric films are used for human motion sensing.In the low force region(1-9 N),the sensors have the outstanding performance with voltage sensitivity of 1.23 V N^(−1) and current sensitivity of 41.0 nA N^(−1).The BTS-GFF/PVDF sensors can be used to detect the tiny forces of falling water drops,finger joint motion,tiny surface deformation,and fatigue driving with high sensitivity.This work provides a new paradigm for the preparation of superflexible,highly sensitive and wearable self-powered piezoelectric sensors,and this kind of sensors will have a broad application prospect in the fields of medical rehabilitation,human motion monitoring,and intelligent robot.
基金supported by the National High Technology Research and Development Program(863 Program)of China(Grant No.2006AA040202 and No.2007AA041703)the National Natural Science Foundation of China(Grant No.60805032)
文摘Nonverbal and noncontact behaviors play a significant role in allowing service robots to structure their interactions withhumans.In this paper, a novel human-mimic mechanism of robot’s navigational skills was proposed for developing sociallyacceptable robotic etiquette.Based on the sociological and physiological concerns of interpersonal interactions in movement,several criteria in navigation were represented by constraints and incorporated into a unified probabilistic cost grid for safemotion planning and control, followed by an emphasis on the prediction of the human’s movement for adjusting the robot’spre-collision navigational strategy.The human motion prediction utilizes a clustering-based algorithm for modeling humans’indoor motion patterns as well as the combination of the long-term and short-term tendency prediction that takes into accountthe uncertainties of both velocity and heading direction.Both simulation and real-world experiments verified the effectivenessand reliability of the method to ensure human’s safety and comfort in navigation.A statistical user trials study was also given tovalidate the users’favorable views of the human-friendly navigational behavior.
基金This work was supported by the National Key Research and Development Program of China(2018YFC0810202)the National Defence Pre-research Foundation of China(61404130119).
文摘Ultra-wideband(UWB)through-wall radar has a wide range of applications in non-contact human information detection and monitoring.With the integration of machine learning technology,its potential prospects include the physiological monitoring of patients in the hospital environment and the daily monitoring at home.Although many target detection methods of UWB through-wall radar based on machine learning have been proposed,there is a lack of an opensource dataset to evaluate the performance of the algorithm.This published dataset is measured by impulse radio UWB(IR-UWB)through-wall radar system.Three test subjects are measured in different environments and several defined motion status.Using the presented dataset,we propose a human-motion-status recognition method using a convolutional neural network(CNN),and the detailed dataset partition method and the recognition process flow are given.On the well-trained network,the recognition accuracy of testing data for three kinds of motion status is higher than 99.7%.The dataset presented in this paper considers a simple environment.Therefore,we call on all organizations in the UWB radar field to cooperate to build opensource datasets to further promote the development of UWB through-wall radar.
基金financial support from the Fundamental Research Funds for the Central Universities(19D110106,19D110112,19D110110)the National Natural Science Foundation of China(No.51603036)+3 种基金Young Elite Scientists Sponsorship Program by CAST(2017QNRC001)the“DHU Distinguished Young Professor Program.”supported by the Initial Research Funds for Young Teachers of Donghua Universitysponsored by Shanghai Sailing Program(19YF1400800)
文摘Human motion analysis consists of real-time monitoring and recording of human body’s kinematics. It is very essential to track ambulatory and dailylife human motion, which is crucial for many applications and disciplines.Electronic textiles(e-textiles) afford a valid alternative to traditional solidstate sensors due to their merits of low cost, lightweight, flexibility, and feasibility to fit various human bodies. In this mini-review, textile-based sensor platforms and human motion analysis are well discussed in Section 1.Second, theoretical principles of textile-based strain sensors are introduced including resistive, capacitive, and piezoelectrical sensors. Section 3 focuses on various types of textile materials that are functionalized as sensing systems by intrinsic or extrinsic modifications. Section 4 summaries various types of e-textile-based strain sensors for human motion analysis. The final two sections mainly present perspectives and challenges, and conclusions,respectively.
文摘A lightweight multi-layer residual temporal convolutional network model(RTCN)is proposed to target the highly complex kinematics and temporal correlation of human motion.RTCN uses 1-D convolution to efficiently obtain the spatial structure information of human motion and extract the correlation in the time series of human motion.The residual structure is applied to the proposed network model to alleviate the problem of gradient disappearance in the deep network.Experiments on the Human 3.6M dataset demonstrate that the proposed method effectively reduces the errors of motion prediction compared with previous methods,especially of long-term prediction.
基金Supported by the National Natural Science Foundation of China(61172073)Program for New Century Excellent Talents of the Ministry of Education(NCET-12-0766)+1 种基金the Open Research Fund of National Mobile Communications Research Laboratory,Southeast University(2012D19)the Fundamental Research Funds for the Central Universities(2013JBZ001)
文摘A modified random walk model for human motion is proposed to investigate characteristics of 60GHz indoor office propagation.Compared with the classic random walk model,the movement tendency in the walking process is taken into account in the modified model.Based on the proposed model,path gains of the propagation environment are simulated under a variety of settings by using a ray tracing method.Simulation results and analysis show that human motion is a major source of disturbance to the indoor office propagation and results in performance degradation in some areas.
基金Supported by the National Natural Science Foundation of China(61303127)Project of Science and Technology Department of Sichuan Province(2014SZ0223,2014GZ0100,2015GZ0212)+1 种基金Key Program of Education Department of Sichuan Province(11ZA130,13ZA0169)Postgraduate Innovation Fund Project by Southwest University of Science and Technology(15ycx057)
文摘The key pose frames of a human motion pose sequence,play an important role in the compression,retrieval and semantic analysis of continuous human motion.The current available clustering methods in literatures are difficult to determine the number of key pose frames automatically,and may destroy the postures’ temporal relationships while extracting key frames.To deal with this problem,this paper proposes a new key pose frames extraction method on the basis of 3D space distances of joint points and the improved X-means clustering algorithm.According to the proposed extraction method,the final key pose frame sequence could be obtained by describing the posture of human body with space distance of particular joint points and then the time-constraint X-mean algorithm is applied to cluster and filtrate the posture sequence.The experimental results show that the proposed method can automatically determine the number of key frames and save the temporal characteristics of motion frames according to the motion pose sequence.
基金financially supported by the National Natural Science Foundation of China (Nos. 51773183 and U1804133)National Natural Science Foundation of China-Henan Province Joint Funds (No. U1604253)+1 种基金Henan Province University Innovation Talents Support Program (No. 20HASTIT001)Innovation Team of Colleges and Universities in Henan Province(No. 20IRTSTHN002)。
文摘Flexible strain sensor has promising features in successful application of health monitoring, electronic skins and smart robotics, etc.Here, we report an ultrasensitive strain sensor with a novel crack-wrinkle structure(CWS) based on graphite nanoplates(GNPs)/thermoplastic urethane(TPU)/polydimethylsiloxane(PDMS) nanocomposite. The CWS is constructed by pressing and dragging GNP layer on TPU substrate,followed by encapsulating with PDMS as a protective layer. On the basis of the area statistics, the ratio of the crack and wrinkle structures accounts for 31.8% and 9.5%, respectively. When the sensor is stretched, the cracks fracture, the wrinkles could reduce the unrecoverable destruction of cracks, resulting in an excellent recoverability and stability. Based on introduction of the designed CWS in the sensor, the hysteresis effect is limited effectively. The CWS sensor possesses a satisfactory sensitivity(GF=750 under 24% strain), an ultralow detectable limit(strain=0.1%) and a short respond time of 90 ms. For the sensing service behaviors, the CWS sensor exhibits an ultrahigh durability(high stability>2×10^(4) stretching-releasing cycles). The excellent practicality of CWS sensor is demonstrated through various human motion tests,including vigorous exercises of various joint bending, and subtle motions of phonation, facial movements and wrist pulse. The present CWS sensor shows great developing potential in the field of cost-effective, portable and high-performance electronic skins.
基金Supported by National Natural Science Foundation of China(No.50875193)
文摘Cameras can reliably detect human motions in a normal environment, but they are usually affected by sudden illumination changes and complex conditions, which are the major obstacles to the reliability and robustness of the system. To solve this problem, a novel integration method was proposed to combine hi-static ultra-wideband radar and cameras. In this recognition system, two cameras are used to localize the object＇s region, regions while a radar is used to obtain its 3D motion models on a mobile robot. The recognition results can be matched in the 3D motion library in order to recognize its motions. To confirm the effectiveness of the proposed method, the experimental results of recognition using vision sensors and those of recognition using the integration method were compared in different environments. Higher correct-recognition rate is achieved in the experiment.
基金partly supported by the National Natural Science Foundation of China under Grant 61573242the Projects from Science and Technology Commission of Shanghai Municipality under Grant No.13511501302,No.14511100300,and No.15511105100+1 种基金Shanghai Pujiang Program under Grant No.14PJ1405000ZTE Industry-Academia-Research Cooperation Funds
文摘Batch processing mode is widely used in the training process of human motiun recognition. After training, the motion elassitier usually remains invariable. However, if the classifier is to be expanded, all historical data must be gathered for retraining. This consumes a huge amount of storage space, and the new training process will be more complicated. In this paper, we use an incremental learning method to model the motion classifier. A weighted decision tree is proposed to help illustrate the process, and the probability sampling method is also used. The resuhs show that with continuous learning, the motion classifier is more precise. The average classification precision for the weighted decision tree was 88.43% in a typical test. Incremental learning consumes much less time than the batch processing mode when the input training data comes continuously.
基金Projects(2006BAJ02A08, 2006BAJ02A05) supported by the National Science and Technology Pillar Program Project during the 11th Five-Year Plan PeriodProject(2007-209) supported by the Excellent Youth Teacher of Ministry of Education of China
文摘The main objectives were to (1) calculate the total volatile organic compounds (TVOCs) inhalation dose, (2) analyze the proportions of human’s inhaled contaminant dose from different sources, and (3) present a newly defined ratio of relative inhalation dose level (RIDL) to assess indoor air quality (IAQ). A user defined function based on CFD (computational fluid dynamics) was developed, which integrated human motion model with TVOCs emission model in a high sidewall air supply ventilation mode. Based on simulation results of 10 cases, it is shown that the spatial concentration distribution of TVOCs is affected by human motion. TVOCs diffusion characteristic of building material is the most effective way to impact the TVOCs inhalation dose. From the RIDL index, case A-2 has the most serious IAQ problem, while case D-1 is of the best IAQ.
基金This work was supported in part by the Key Program of NSFC(Grant No.U1908214)Program for Innovative Research Team in University of Liaoning Province(LT2020015)+1 种基金the Support Plan for Key Field Innovation Team of Dalian(2021RT06)the Science and Technology Innovation Fund of Dalian(Grant No.2020JJ25CY001).
文摘In recent years,human motion prediction has become an active research topic in computer vision.However,owing to the complexity and stochastic nature of human motion,it remains a challenging problem.In previous works,human motion prediction has always been treated as a typical inter-sequence problem,and most works have aimed to capture the temporal dependence between successive frames.However,although these approaches focused on the effects of the temporal dimension,they rarely considered the correlation between different joints in space.Thus,the spatio-temporal coupling of human joints is considered,to propose a novel spatio-temporal network based on a transformer and a gragh convolutional network(GCN)(STTG-Net).The temporal transformer is used to capture the global temporal dependencies,and the spatial GCN module is used to establish local spatial correlations between the joints for each frame.To overcome the problems of error accumulation and discontinuity in the motion prediction,a revision method based on fusion strategy is also proposed,in which the current prediction frame is fused with the previous frame.The experimental results show that the proposed prediction method has less prediction error and the prediction motion is smoother than previous prediction methods.The effectiveness of the proposed method is also demonstrated comparing it with the state-of-the-art method on the Human3.6 M dataset.
基金the support from the National Natural Science Foundation of China(Grant No.12232014)the Fundamental Research Funds for the Central Universities(Grant No.N2403027)the Ten Thousand Talents。
文摘The advancement of wearable devices continues to face the challenge of ensuring a sustainable power supply.Traditional human motion energy harvesters often suffer from low energy harvesting efficiency due to their reliance on a single energy source.This study presents a novel pendulum inertial electromagnetic energy harvester(PI-EEH)to harvest multiplesource low-frequency human motion energy.The PI-EEH can simultaneously harvest both the leg swing energy and the foot impact energy during walking.A horizontal universal pendulum,combined with a frequency-up conversion mechanism,transforms irregular human motion into unidirectional high-frequency rotation.The output performance of the PI-EEH is evaluated through both theoretical analysis and experimental testing.A treadmill test is also conducted across various motion speeds to illustrate the benefits of PI-EEH.The peak power of PI-EEH can reach 54 mW at a speed of 3 km/h.Additionally,the PI-EEH can easily supply power for some wearable devices,like a GPS module and an acceleration sensor.The designed PIEEH offers a viable approach to harvesting energy from multiple-source human motion,which will have broad prospects in smart healthcare and IoT applications.
基金supported by National Natural Science Foundation of China(No.62203476)Natural Science Foundation of Shenzhen(No.JCYJ20230807120801002).
文摘Extensive research has explored human motion generation,but the generated sequences are influenced by different motion styles.For instance,the act of walking with joy and sorrow evokes distinct effects on a character’s motion.Due to the difficulties in motion capture with styles,the available data for style research are also limited.To address the problems,we propose ASMNet,an action and style-conditioned motion generative network.This network ensures that the generated human motion sequences not only comply with the provided action label but also exhibit distinctive stylistic features.To extract motion features from human motion sequences,we design a spatial temporal extractor.Moreover,we use the adaptive instance normalization layer to inject style into the target motion.Our results are comparable to state-of-the-art approaches and display a substantial advantage in both quantitative and qualitative evaluations.The code is available at https://github.com/ZongYingLi/ASMNet.git.
基金supported by the National Natural Science Foundation of China(62004083)the Fundamental Research Funds for the Central Universities(21622410)。
文摘Quantitative analysis of gait parameters,such as stride frequency and step speed,is essential for optimizing physical exercise for the human body.However,the current electronic sensors used in human motion monitoring remain constrained by factors such as battery life and accuracy.This study developed a self-powered gait analysis system(SGAS)based on a triboelectric nanogenerator(TENG)fabricated electrospun composite nanofibers for motion monitoring and gait analysis for regulating exercise programs.The SGAS consists of a sensing module,a charging module,a data acquisition and processing module,and an Internet of Things(IoT)platform.Within the sensing module,two specialized sensing units,TENG-S1 and TENG-S2,are positioned at the forefoot and heel to generate synchronized signals in tandem with the user's footsteps.These signals are instrumental for real-time step count and step speed monitoring.The output of the two TENG units is significantly improved by systematically investigating and optimizing the electrospun composite nanofibers'composition,strength,and wear resistance.Additionally,a charge amplifier circuit is implemented to process the raw voltage signal,consequently bolstering the reliability of the sensing signal.This refined data is then ready for further reading and calculation by the micro-controller unit(MCU)during the signal transmission process.Finally,the well-conditioned signals are wirelessly transmitted to the IoT platform for data analysis,storage,and visualization,enhancing human motion monitoring.
