Characteristics Of Human Motion Research Articles

An RFID-Based Method for Multi-Person Respiratory Monitoring.

Respiratory monitoring is widely used in the field of health care. Traditional respiratory monitoring methods bring much inconvenience to users. In recent years, a great number of respiratory monitoring methods based on wireless technology have emerged, but multi-person respiratory monitoring is still very challenging; therefore, this paper explores multi-person respiratory monitoring. Firstly, the characteristics of human respiratory movement have been analyzed, and a suitable tag deployment method for respiratory monitoring is proposed. Secondly, aiming at the ambiguity and entanglement of radio frequency identification (RFID) phase data, a method of removal of phase ambiguity and phase wrapping is given. Then, in order to monitor multi-person respiration in a noisy environment, the frequency extraction method and waveform reconstruction method of multi-person respiration are proposed. Finally, the feasibility of the method is verified by experiments.

Optimum trajectory learning in musculoskeletal systems with model predictive control and deep reinforcement learning

From the computational point of view, musculoskeletal control is the problem of controlling high degrees of freedom and dynamic multi-body system that is driven by redundant muscle units. A critical challenge in the control perspective of skeletal joints with antagonistic muscle pairs is finding methods robust to address this ill-posed nonlinear problem. To address this computational problem, we implemented a twofold optimization and learning framework to be specialized in addressing the redundancies in the muscle control . In the first part, we used model predictive control to obtain energy efficient skeletal trajectories to mimick human movements. The second part is to use deep reinforcement learning to obtain a sequence of stimulus to be given to muscles in order to obtain the skeletal trajectories with muscle control. We observed that the desired stimulus to muscles is only efficiently constructed by integrating the state and control input in a closed-loop setting as it resembles the proprioceptive integration in the spinal cord circuits. In this work, we showed how a variety of different reference trajectories can be obtained with optimal control and how these reference trajectories are mapped to the musculoskeletal control with deep reinforcement learning. Starting from the characteristics of human arm movement to obstacle avoidance experiment, our simulation results confirm the capabilities of our optimization and learning framework for a variety of dynamic movement trajectories. In summary, the proposed framework is offering a pipeline to complement the lack of experiments to record human motion-capture data as well as study the activation range of muscles to replicate the specific trajectory of interest. Using the trajectories from optimal control as a reference signal for reinforcement learning implementation has allowed us to acquire optimum and human-like behaviour of the musculoskeletal system which provides a framework to study human movement in-silico experiments. The present framework can also allow studying upper-arm rehabilitation with assistive robots given that one can use healthy subject movement recordings as reference to work on the control architecture of assistive robotics in order to compensate behavioural deficiencies. Hence, the framework opens to possibility of replicating or complementing labour-intensive, time-consuming and costly experiments with human subjects in the field of movement studies and digital twin of rehabilitation.

Representation for action recognition with motion vector termed as: SDQIO

The active human action motion characteristics from moving areas within a particular spectrum are conveyed by the information extraction domain of video data. Meanwhile, most of the video data frequencies are encoded with silent information that has significant redundancy, resulting in low processing efficiency in conventional video models that accept raw frames as input. Human action recognition remains challenging for the computer vision domain in videos. To address this issue, this study introduces SDQIO, a novel video content extractor that focuses on obtaining multiscale and multidimensional motion information for fast action detection. The ultimate goal of our SDQIO is to develop an effective action recognition module (SDQIO) by identifying five distinct types of action capture operators and extensively assessing their effects on movement prediction over short and long periods. Our SDQIO uses a multi-differentiation modeling approach to gather motion-type information over the whole clip. Extensive experiments revealed that our technique outperforms all other action recognition algorithms by a significant margin on standard action datasets, attaining state-of-the-art and equivalent outcomes.

A Human Motion Function Rehabilitation Monitoring System Based on Data Mining

Human motion interaction technologies have evolved to a new level with the development of traditional reality technology as science and technology have developed. Fully interactive and human motion interaction technologies are becoming more common in fields such as medical rehabilitation and military simulations. Human motion is at the heart of all activity, and motion analysis and human motion are critical theoretical disciplines. Identification is based on behavior and motion in human motion, with attributes such as effectiveness, intelligence, potent interaction, and rich expression data. When studying human movement, many researchers now prefer this method. However, this study was conducted with insufficient suggestions for real-time human motion function assessment, rehabilitation, and improvement. The development of an information monitoring system for human motion function rehabilitation can be used to evaluate the efficacy of patient rehabilitation training. A human motion function rehabilitation monitoring system is created using an effective and thorough design methodology. The system is made up of the rehabilitation monitoring terminal, the human motion function monitoring module, and the medical center monitoring system. Therefore, the motion-based data mining technique is better for the human motion function rehabilitation monitoring system. The normalized proportion of motion features will assist in the creation of a database for human motion mining. The nonlinear classification function is used in this paper to scientifically categorize human motion features to implement data mining techniques for monitoring human motion function rehabilitation. The effectiveness of patient rehabilitation is significantly increased by the use of a human motion-based rehabilitation monitoring system.

Biomechanical Characterization of Human GAIT Using EMG Parameters

Predicting and analysing individual muscle forces during walking can give a good perspective of anatomical, physiological, and neurological characteristics of human movement. It can help analyse neuromuscular impairments of skeletal system and provide an understanding on how lower limb assistive devices affect wearer’s body, as these assistive devices are vital to assist people with disabilities to carry their daily activities with ease. Estimating force from EMG allows us to assess the contribution of an individual muscle to the over-all force applied by a group of muscles. This finding helps in understanding muscle dynamics during walking, which can serve as input for assistive devices. Thus, electromyography signals (EMG) can be an excellent choice for force estimation in kinesiological studies. This study aims to predict individual muscle force from EMG during walking. The right gastrocnemius lateralis muscle of a 23-year-old-male subject with no neurological/muscular disorder was analysed at normal walking. Two approaches were used to predict forces from EMG using MATLAB. The forces obtained were compared with force predicted using OpenSim. The main parameters used for prediction were muscle length, muscle velocity, pennation angle, and isometric force, along with EMG.

Implementation of a real-time fall detection system based on hybrid threshold analysis algorithm and machine learning algorithm.

With the increasing global aging population, the health of the elderly has become a global concern. Accidental falls, as one of the major causes of health and safety issues affecting the elderly, can cause serious hazards. In this paper, a fall detection system is proposed to be able to deliver timely information after a fall. The acceleration and angular velocity time series extracted from motion were used to describe human motion features. Hybrid threshold analysis algorithm and machine learning algorithm are used for classification between falls and activities of daily living (ADLs). The fall detection results showed 98.55% accuracy, 98.16% sensitivity, and 98.73% specificity. The result is higher than the single-threshold algorithm and slightly lower than the machine learning algorithm. In addition, the hybrid algorithm of fall detection in this paper is to put the threshold analysis algorithm in the edge device for calculation and put the machine learning algorithm in the cloud server for calculation. Since the single machine learning algorithm needs to transmit data to the cloud server all the time, the hybrid algorithm has lower power consumption than machine learning algorithms, and the average alarm time is shorter, making it more suitable for actual systems.

Characteristics of human movement and injury in a side collision between the front of a small car and a bicycle

ObjectiveOur research groups have studied the movement and injury characteristics of the human body in a side collision between the front of a small car and a pedestrian. This study discusses the movement and injury characteristics of the human body in a side collision between the front of a small car and bicycle. MethodsA total of 31 cases of traffic accidents caused by small car collisions when riding a bicycle across a road were collected. Through on-site inspection and trace inspection of the accident vehicles and bicycles, the speed of the car during the collision was calculated, the collision relationship between the small car and bicycle was determined, and the injury site and degree were determined through autopsy. The car speed was divided into two groups: <60 km/h and >60 km/h. Injuries of the skull, cervical spine, ribs, pelvis, femur and tibiofibular were analysed, and the correlations with the height of the bicycle controller, the height of the bicycle seat, the height of the car hood and the length of hood were discussed. PC-Crash was used for simulation analysis to further clarify the injury process. ResultsThe ratio of the height of the bicycle seat to the height of the hood plus the length of the hood in the windshield-damaged group was larger than that in the undamaged windshield group (P < 0.05). No cervical fracture was found when V < 60 km/h, and 52.94% of cases had cervical fracture when V > 60 km/h. The ratio of the height of the bicycle seat to the height of the hood in the pelvic fracture group was smaller than that in the nonpelvic fracture group (P < 0.05). The incidence of tibiofibular fracture was less than 65%. ConclusionsWhen a side impact between a car front and a bicycle occurs, the resulting human injury is related not only to the speed but also to the height of the bicycle seat and the height and length of the hood of the car. The incidence of tibiofibular fractures was significantly lower than that of small car front-pedestrian side impacts.

Human Behavior Recognition in Outdoor Sports Based on the Local Error Model and Convolutional Neural Network.

With the rapid development of the Internet, various electronic products based on computer vision play an increasingly important role in people's daily lives. As one of the important topics of computer vision, human action recognition has become the main research hotspot in this field in recent years. The human motion recognition algorithm based on the convolutional neural network can realize the automatic extraction and learning of human motion features and achieve good classification performance. However, deep convolutional neural networks usually have a large number of layers, a large number of parameters, and a large memory footprint, while embedded wearable devices have limited memory space. Based on the traditional cross-entropy error-based training mode, the parameters of all hidden layers must be kept in memory and cannot be released until the end of forward and reverse error propagation. As a result, the memory used to store the parameters of the hidden layer cannot be released and reused, and the memory utilization efficiency is low, which leads to the backhaul locking problem, limiting the deployment and execution of deep convolutional neural networks on wearable sensor devices. Based on this, this topic designs a local error convolutional neural network model for human motion recognition tasks. Compared with the traditional global error, the local error constructed in this paper can train the convolutional neural network layer by layer, and the parameters of each layer can be trained independently according to the local error and does not depend on the gradient propagation of adjacent upper and lower layers. As a result, the memory used to store all hidden layer parameters can be released in advance without waiting for the end of forward and backward propagation, avoiding the problem of backhaul locking, and improving the memory utilization of convolutional neural networks deployed on embedded wearable devices.

Application of Cloud Service-Oriented Heterogeneous Execution Scheduling and VR Technology in Dance Video Teaching

Cloud computing is the result of the revolution in information technology and a massively complex computing system. As a model for business computing, cloud computing aims to facilitate resource sharing and collaborative work, meet the service needs of users, and generate revenue for cloud service providers. How to reasonably allocate cloud resources, efficiently manage and schedule massive application tasks in real time, reduce the cost of users, and increase the income of cloud service providers on the basis of ensuring the load balance of the cloud computing system and enhancing the utilization of cloud resources is, therefore, one of the research hotspots in the current cloud computing environment. Simultaneously, with the rapid development of human motion simulation and virtual reality technologies, the natural cooperation between humans and computers has become the primary focus of computer science research. The motion capture system is able to track, detect, capture, and record real-time human motion. By analyzing the captured three-dimensional data, we can determine the various characteristics of human motion posture at various times. Due to the potential research and practical value of motion capture technology, it is predominantly used in cutting-edge fields such as animation video production, rehabilitation medicine, sports training, and game software development, thereby effectively realizing the connection between the three-dimensional world and the real world. However, the combination of motion capture technology and educational activities is not universally applicable. This research proposes an approach to dance posture analysis based on matching feature vectors, which can be applied to dance teaching and significantly improves the quality of education and teaching activities. For the purpose of this study, it will be determined whether the combination of dance instruction-based motion capture technology and education is effective and feasible.

Human-Gait-Based Tracking Control for Lower Limb Exoskeleton Robot

Research shows that it is practical for the normal human movement mechanism to assist the patients with stroke in robot-assisted gait rehabilitation. In passive training, the effect of rehabilitation training for patients can be improved by imitating normal human walking. To make the lower limb exoskeleton robot (LLER) move like a normal human, a tracking control scheme based on human gait data is proposed in this paper. The real human gait data is obtained from healthy subjects using a three-dimensional motion capture platform (3DMCP). Furthermore, the normal human motion characteristics are adopted to enhance the scientificity and effectiveness of assistant rehabilitation training using LLER. An adaptive radial basis function network (ARBFN) controller based on feed-forward control is presented to improve the trajectory tracking accuracy and tracking performance of the control system, where the ARBFN controller is deployed to predict the uncertain model parameters. The feed-forward controller based on the tracking errors is used to compensate for the input torque of LLER. The effectiveness of the presented control scheme is confirmed by simulation results based on experimental data.

Analysis and Correction of Wrong Technical Actions in Juvenile Sports Training Based on Deep Learning.

Scientific analysis of students' incorrect actions in class, as well as timely and effective correction, is frequently an important link in the PE process. At the same time, it is an important symbol for assessing a teacher's teaching level and quality. In this paper, the analysis and correction model of sports wrong technical movements is built using DCNN to address shortcomings in the process of detecting wrong movements in PE and training. This article is based on CNN and has been enhanced by DL. The model learns both manual and DL features; the manual features use an improved dense trajectory, the DL features use CNN based on motion information, and the generalization ability of the kernel support vector machine is used to fuse the two. The simulation results show that the accuracy of the wrong action judgment of this method can reach 92.16 percent, which is 4.6 percent higher than the method of combining NN with region prediction and 5.7 percent higher than the method of detecting image matching score. This method can accurately describe the characteristics of human motion and identify incorrect movements, improve the ability of judging and correcting incorrect movements in sports training, and help athletes improve their sports level.

Application of Deep Convolution Network Algorithm in Sports Video Hot Spot Detection.

Sports videos are blowing up over the internet with enriching material life and the higher pursuit of spiritual life of people. Thus, automatically identifying and detecting helpful information from videos have arisen as a relatively novel research direction. Accordingly, the present work proposes a Human Pose Estimation (HPE) model to automatically classify sports videos and detect hot spots in videos to solve the deficiency of traditional algorithms. Firstly, Deep Learning (DL) is introduced. Then, amounts of human motion features are extracted by the Region Proposal Network (RPN). Next, an HPE model is implemented based on Deep Convolutional Neural Network (DCNN). Finally, the HPE model is applied to motion recognition and video classification in sports videos. The research findings corroborate that an effective and accurate HPE model can be implemented using the DCNN to recognize and classify videos effectively. Meanwhile, Big Data Technology (BDT) is applied to count the playing amounts of various sports videos. It is convinced that the HPE model based on DCNN can effectively and accurately classify the sports videos and then provide a basis for the following statistics of various sports videos by BDT. Finally, a new outlook is proposed to apply new technology in the entertainment industry.

Complexity Graph-Based Multilabel Classification Method of Human Action in Rope Skipping Scene

Aiming at the problem of insufficient accuracy of multilabel classification of human action at present, a multilabel classification method of human action in the rope skipping scene is proposed. It realizes feature recognition and classification by collecting human action features in the scene of skipping rope movement and uses RNN to optimize the human action feature recognition algorithm. On the basis of feature recognition, the characteristics of human movement in the rope skipping scene are classified, the confidence map of the key point position is obtained by using the Gaussian modeling method, and the action multilabel classification is realized. Finally, experiments show that the multilabel classification method of human action in rope skipping scene has high accuracy and fully meets the research requirements.

Kinematics study of a 10 degrees-of-freedom lower extremity exoskeleton for crutch-less walking rehabilitation.

Wearable lower extremity exoskeletons can provide walking assistance for the physical rehabilitation of paralyzed individuals. However, most of the existing exoskeletons require crutches to maintain balance, thus a self-balancing type is needed to improve applicability. The purpose of this work is to study the kinematic characteristics of a novel lower extremity exoskeleton for crutch-less walking rehabilitation, and evaluate the movement performance through practical experiments. Based on the human lower limb structure and movement characteristics, a fully actuated 10 degrees-of-freedom (DoF) lower extremity exoskeleton was proposed. The kinematic characteristics of the exoskeleton were analyzed by the D-H method and geometric method, and the model validity was verified through simulations and experiments. The closed-form solutions for both forward and inverse kinematics models were obtained. The consistent results of theoretical calculation and numerical simulation have shown the accuracy of the established models. The practical experiments regarding six trials have demonstrated the movement performance of the proposed exoskeleton, including sit, stance, leg extension/flexion, and left/right swing. The kinematic characteristics of the proposed 10-DoF lower extremity exoskeleton are similar to the human lower limb, and it could meet the motion demands of crutch-less walking rehabilitation.

Return Strategy and Machine Learning Optimization of Tennis Sports Robot for Human Motion Recognition.

At present, there are many kinds of intelligent training equipment in tennis sports, but they all need human control. If a single tennis player uses the robot to return the ball, it will save some human resources. This study aims to improve the recognition rate of tennis sports robots in the return action and the return strategy. The human-oriented motion recognition of the tennis sports robot is taken as the starting point to recognize and analyze the return action of the tennis sports robot. The OpenPose traversal dataset is used to recognize and extract human motion features of tennis sports robots under different classifications. According to the return characteristics of the tennis sports robot, the method of tennis return strategy based on the support vector machine (SVM) is established, and the SVM algorithm in machine learning is optimized. Finally, the return strategy of tennis sports robots under eight return actions is analyzed and studied. The results reveal that the tennis sports robot based on the SVM-Optimization (SVM-O) algorithm has the highest return recognition rate, and the average return recognition rate is 88.61%. The error rates of the backswing, forward swing, and volatilization are high in the return strategy of tennis sports robots. The preparation action, backswing, and volatilization can achieve more objective results in the analysis of the return strategy, which is more than 90%. With the increase of iteration times, the effect of the model simulation experiment based on SVM-O is the best. It suggests that the algorithm proposed has a reliable accuracy of the return strategy of tennis sports robots, which meets the research requirements. Human motion recognition is integrated with the return motion of tennis sports robots. The application of the SVM-O algorithm to the return action recognition of tennis sports robots has good practicability in the return action recognition of tennis sports robot and solves the problem that the optimization algorithm cannot be applied to the real-time requirements. It has important research significance for the application of an optimized SVM algorithm in sports action recognition.

Analysis and Evaluation on the Harmfulness of Sports Dance Based on Intelligent Computing

With the rapid development of motion analysis and editing technology, more and more animation technologies based on real human motion analysis are widely used in games, medicine, film and television, sports, and other fields. The role of this technology in the teaching system of sports dance arrangement cannot be ignored. This paper studies the application of intelligent algorithm in injury analysis of sports dance choreography and puts forward a smooth and natural motion editing method which is more in line with the characteristics of human motion. The square spherical surface intelligent algorithm is used to naturally transition the rotation posture of each frame of human joint, and the action modification of computer-aided dance choreography system is more in line with the real action of human body. Simulation results show that interframe data can be used for the same type of dance. Different types of dance arrangement can adopt the method of inserting a new framework between the two dance movements, so as to finally meet the needs of sports dance coaches and students to observe their own dance movements in an all-round way, so as to facilitate the arrangement and modification of sports dance movement design. It provides a certain reference for the application and development of virtual technology in the field of sports and greatly improves the current situation of sports dance teaching equipment. Through animation simulation technology, we can effectively avoid the injury caused by dangerous movements, provide a way of observation and improvement for coaches’ dance teaching, and effectively improve the training effect. Compared with traditional dance choreography methods, the intelligent algorithm in this study can make the animation display of sports dance more coherent and realistic and effectively solve the needs of current events observation and modification in sports dance choreography. It can produce complex movements with simple movements and help teachers arrange and teach sports dance. Avoid the accidental injury caused by the limitation of time and space in traditional teaching and realize the modernization and intelligence of physical education teaching.

Fast Recognition Algorithm for Human Motion Posture Using Multimodal Bioinformation Fusion

To address the problems of low feature extraction accuracy, large bias of human motion pose recognition and posture recognition error, poor recognition effect, and low recognition rate of traditional human motion posture fast recognition algorithm, we propose a human motion posture fast recognition algorithm using multimodal bioinformation fusion. First, wavelet packet decomposition with sample entropy is used to extract the human motion posture hand features such as kurtosis, time domain feature skewness, and frequency domain feature electromyogram (EMG) integral value and time domain features such as mean, standard deviation, and interquartile distance of leg motion amplitude. Second, after normalizing the two features, the human hand and leg motion feature set is obtained, and finally the feature set is used to construct a human motion posture fast recognition model based on multimodal bioinformation fusion, and the feature set is input into the recognition model, which completes the fusion of human motion posture information by improving the typical correlation analysis method, and the fusion result is used as the input of the minimum distance classifier to achieve human motion posture fast recognition. The results show that the proposed algorithm has high accuracy of feature extraction, small bias of human motion posture recognition, the posture recognition error is -0.21∼0.02, the recognition rate is always above 95%, and the practical application effect is good.

Human hand motion prediction based on feature grouping and deep learning: Pipe skid maintenance example

Human-robot collaboration has gained popularity in various construction applications. The key to a successful human-robot collaboration at the same construction workplace is the delicate algorithm for predicting human motions to strengthen the robot's situational awareness, i.e., robot-human awareness. Most existing approaches have focused on predicting human motions based on repetitive patterns of human behaviors in well-defined task contexts, such as specific object picking tasks, for a relatively short period of time. These methods can hardly capture the “pattern inconsistency” of human actions, i.e., the differences across people in terms of motion features and even for the same person at different time points of the task. This paper proposes an analytical pipeline that segments and clusters the human inconsistent behaviors into different pattern groups and builds separate human motion pattern prediction models correspondingly. The proposed method, Human Motion Feature Grouping and Prediction (HMFGP), quantifies the spatiotemporal relationship between gaze focus and hand movement trajectories, segments the raw data based on the detected gaze-hand relationship pattern changes, and clusters the matched gaze-hand data segments into several pattern groups based on the pattern similarity of the gaze-hand relationships. Then a time series Deep Learning method is used to predict hand motions based on gaze focus trajectories for each of the pattern groups. The gaze and hand motion data of a human subject experiment (n = 120) for pipe skid maintenance was used to test the prediction performance of HMFGP. The result shows that HMFGP can significantly improve the accuracy of human hand motion prediction and help quantity different patterns of human motions for specific analyses.

Image Recognition and Extraction of Students' Human Motion Features Based on Graph Neural Network.

In order to improve students' overall subhealth behavior, teenagers' physical health problems have attracted more and more attention. The state clearly requires students to increase the number and frequency of exercise in school. In order to study the physical changes in the process of students' sports and the impact on their health caused by a sports injury, a student human motion feature image recognition based on a graph neural network is proposed in this paper. This paper combines image recognition technology with graphic neural network management and uses image recognition technology to detect and track targets. It also analyzes the health changes of students in sports and the influencing factors of physical subhealth in classroom learning. The results show that image recognition technology can accurately analyze the process of cervical spine injury and sports injury in students' classroom activities. It provides accurate experimental data for analyzing students' physical health and effective suggestions for promoting students' healthy development. Compared with the traditional image recognition and analysis results, the advantage of using a graph neural network to manage the detection and tracking results is that a graph neural network is used to manage the detection and tracking results, and the visual expression of students' physical health test data is completed.

Daily Human Mobility: A Reproduction Model and Insights from the Energy Concept

Human movements have raised broad attention, and many models have been developed to reproduce them. However, most studies focus on reproducing the statistical properties of human mobility, such as the travel distance and the visiting frequency. In this paper, a two-step Markov Chain model is proposed to generate daily human movements, and spatial and spatiotemporal attributes of reproduced mobility are examined. In the first step, people’s statuses in the next time slot are conditioned on their previous travel patterns; and in the second step, individual location in such a slot is probabilistically determined based on his/her status. Our model successfully reproduces the spatial and spatiotemporal characteristics of human daily movements, and the result indicates that people’s future statuses can be inferred based on travel patterns they made, regardless of exactly where they have traveled, and when trips happen. We also revisit the energy concept, and show that the energy expenditure is stable over years. This idea is further used to predict the proportion of long-distance trips for each year, which gives insights into the probabilities of statuses in the next time slot. Finally, we interpret the constant energy expenditure as the constant ‘cost’ over years.