An Approach for Human Posture Recognition Based on the Fusion PSE-CNN-BiGRU Model

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.

Sleep Posture Classification Using RGB and Thermal Cameras Based on Deep Learning Model

Sleep posture surveillance is crucial for patient comfort,yet current systems face difficulties in providing compre-hensive studies due to the obstruction caused by blankets.Precise posture assessment remains challenging because of the complex nature of the human body and variations in sleep patterns.Consequently,this study introduces an innovative method utilizing RGB and thermal cameras for comprehensive posture classification,thereby enhancing the analysis of body position and comfort.This method begins by capturing a dataset of sleep postures in the form of videos using RGB and thermal cameras,which depict six commonly adopted postures:supine,left log,right log,prone head,prone left,and prone right.The study involves 10 participants under two conditions:with and without blankets.Initially,the database is normalized into a video frame.The subsequent step entails training a fine-tuned,pretrained Visual Geometry Group(VGG16)and ResNet50 model.In the third phase,the extracted features are utilized for classification.The fourth step of the proposed approach employs a serial fusion technique based on the normal distribution to merge the vectors derived from both the RGB and thermal datasets.Finally,the fused vectors are passed to machine learning classifiers for final classification.The dataset,which includes human sleep postures used in this study’s experiments,achieved a 96.7%accuracy rate using the Quadratic Support Vector Machine(QSVM)without the blanket.Moreover,the Linear SVM,when utilized with a blanket,attained an accuracy of 96%.When normal distribution serial fusion was applied to the blanket features,it resulted in a remarkable average accuracy of 99%.

Posture Detection of Heart Disease Using Multi-Head Attention Vision Hybrid(MHAVH)Model

Cardiovascular disease is the leading cause of death globally.This disease causes loss of heart muscles and is also responsible for the death of heart cells,sometimes damaging their functionality.A person’s life may depend on receiving timely assistance as soon as possible.Thus,minimizing the death ratio can be achieved by early detection of heart attack(HA)symptoms.In the United States alone,an estimated 610,000 people die fromheart attacks each year,accounting for one in every four fatalities.However,by identifying and reporting heart attack symptoms early on,it is possible to reduce damage and save many lives significantly.Our objective is to devise an algorithm aimed at helping individuals,particularly elderly individuals living independently,to safeguard their lives.To address these challenges,we employ deep learning techniques.We have utilized a vision transformer(ViT)to address this problem.However,it has a significant overhead cost due to its memory consumption and computational complexity because of scaling dot-product attention.Also,since transformer performance typically relies on large-scale or adequate data,adapting ViT for smaller datasets is more challenging.In response,we propose a three-in-one steam model,theMulti-Head Attention Vision Hybrid(MHAVH).Thismodel integrates a real-time posture recognition framework to identify chest pain postures indicative of heart attacks using transfer learning techniques,such as ResNet-50 and VGG-16,renowned for their robust feature extraction capabilities.By incorporatingmultiple heads into the vision transformer to generate additional metrics and enhance heart-detection capabilities,we leverage a 2019 posture-based dataset comprising RGB images,a novel creation by the author that marks the first dataset tailored for posture-based heart attack detection.Given the limited online data availability,we segmented this dataset into gender categories(male and female)and conducted testing on both segmented and original datasets.The training accuracy of our model reached an impressive 99.77%.Upon testing,the accuracy for male and female datasets was recorded at 92.87%and 75.47%,respectively.The combined dataset accuracy is 93.96%,showcasing a commendable performance overall.Our proposed approach demonstrates versatility in accommodating small and large datasets,offering promising prospects for real-world applications.

Method for the posture control of bionic mechanical wheel-legged vehicles in hilly and mountainous areas

In response to the weaknesses of traditional agricultural equipment chassis with poor environmental adaptability and inferior mobility, a novel unmanned agricultural machinery chassis has been developed that can operate stably and efficiently under various complex terrain conditions. Initially, a new wheel-legged structure was designed by drawing inspiration from the motion principles of grasshopper hind legs and combining them with pneumatic-hydraulic linkage mechanisms. Kinematic analysis was conducted on this wheel-legged configuration by utilizing the D-H parameter method, which revealed that its end effector has a travel range of 0-450 mm in the X-direction, 0-840 mm in the Y-direction, and 0-770 mm in the Z-direction, thereby providing the structural foundation for features such as independent four-wheel steering, adjustable wheel track, automatic vehicle body elevation adjustment, and maintaining a level body posture on different slopes. Subsequently, theoretical analysis and structural parameter calculations were completed to design each subsystem of the unmanned chassis. Further, kinematic analysis of the wheel-legged unmanned chassis was carried out using RecurDyn, which substantiated the feasibility of achieving functions like slope leveling and autonomous obstacle negotiation. An omnidirectional leveling control system was also established, taking into account factors such as pitch angle, roll angle, virtual leg deployment, and center of gravity height. Joint simulations using Adams and Matlab were performed on the wheel-legged unmanned chassis, comparing its leveling performance with that of a PID control system. The results indicated that the maximum absolute value of leveling error was 1.08° for the pitch angle and 1.19° for the roll angle, while the standard deviations were 0.216 47° for the pitch angle and 0.176 22° for the roll angle, demonstrating that the wheel-legged unmanned chassis surpassed the PID control system in leveling performance, thus validating the correctness and feasibility of its full-directional body posture leveling control in complex environments. Finally, the wheel-legged unmanned chassis was fabricated, assembled, and subjected to in-place leveling and ground clearance adjustment tests. The experimental outcomes showed that the vehicle was capable of achieving in-place leveling with response speed and leveling accuracy meeting practical operational requirements under the action of the posture control system. Moreover, the adjustable ground clearance proved sufficient to meet the demands of actual obstacle crossing scenarios.

Multi-Branch High-Dimensional Guided Transformer-Based 3D Human Posture Estimation

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.

Fusion of Convolutional Self-Attention and Cross-Dimensional Feature Transformationfor Human Posture Estimation

Human posture estimation is a prominent research topic in the fields of human-com-puter interaction,motion recognition,and other intelligent applications.However,achieving highaccuracy in key point localization,which is crucial for intelligent applications,contradicts the lowdetection accuracy of human posture detection models in practical scenarios.To address this issue,a human pose estimation network called AT-HRNet has been proposed,which combines convolu-tional self-attention and cross-dimensional feature transformation.AT-HRNet captures significantfeature information from various regions in an adaptive manner,aggregating them through convolu-tional operations within the local receptive domain.The residual structures TripNeck and Trip-Block of the high-resolution network are designed to further refine the key point locations,wherethe attention weight is adjusted by a cross-dimensional interaction to obtain more features.To vali-date the effectiveness of this network,AT-HRNet was evaluated using the COCO2017 dataset.Theresults show that AT-HRNet outperforms HRNet by improving 3.2%in mAP,4.0%in AP75,and3.9%in AP^(M).This suggests that AT-HRNet can offer more beneficial solutions for human posture estimation.

Computer Vision-Based Human Body Posture Correction System

With the development of technology and the progress of life,more and more people,regardless of entertainment,learning,or work,cannot do without computer desks and cannot put down their mobile phones.Due to prolonged sitting and often neglecting the importance of posture,incorrect posture can often lead to health problems such as hunchback,lumbar muscle strain,and shoulder and neck pain over time.To address this issue,we designed a computer vision-based human body posture detection system.The system utilizes YOLOv8 technology to accurately locate key points of the human body skeleton,and then analyzes the coordinate positions and depth information of these key points to establish a criterion for distinguishing different postures.With the assistance of an SVM classifier,the system achieves an average recognition rate of 95%.Finally,we successfully deployed the posture detection system on Raspberry Pi hardware and conducted extensive testing.The test results demonstrate that the system can effectively detect various postures and provide real-time reminders to users to correct poor posture,demonstrating good practicality and stability.

A Survey on Artificial Intelligence in Posture Recognition

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.

A Realistic 3D Non-Stationary Channel Model for UAV-to-Vehicle Communications Incorporating Fuselage Posture

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.

Force Sensitive Resistors-Based Real-Time Posture Detection System Using Machine Learning Algorithms

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.

Calf Posture Recognition Using Convolutional Neural Network

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.

Investigation of compensatory postures with videofluoromanometry in dysphagia patients

AIM: To investigate the effectiveness of head compensatory postures to ensure safe oropharyngeal transit. METHODS: A total of 321 dysphagia patients were enrolled and assessed with videofluoromanometry (VFM). The dysphagia patients were classified as follows: safe transit; penetration without aspiration; aspiration before, during or after swallowing; multiple aspirations and no transit. The patients with aspiration or no transit were tested with VFM to determine whether compensatory postures could correct their swallowing disorder. RESULTS: VFM revealed penetration without aspiration in 71 patients (22.1%); aspiration before swallowing in 17 patients (5.3%); aspiration during swallowing in 32 patients (10%); aspiration after swallowing in 21 patients (6.5%); multiple aspirations in six patients (1.9%); no transit in five patients (1.6%); and safe transit in 169 patients (52.6%). Compensatory postures guaranteed a safe transit in 66/75 (88%) patients with aspiration or no transit. A chin-down posture achieved a safe swallow in 42/75 (56%) patients, a head-turned posture in 19/75 (25.3%) and a hyperextended head posture in 5/75 (6.7%). The compensatory postures were not effective in 9/75 (12%) cases. CONCLUSION: VFM allows the speech-language therapist to choose the most effective compensatory posture without a trial-and-error process and check the effectiveness of the posture.

Digital Evaluation of Sitting Posture Comfort in Human-vehicle System under Industry 4.0 Framework

Most of the previous studies on the vibration ride comfort of the human-vehicle system were focused only on one or two aspects of the investigation. A hybrid approach which integrates all kinds of investigation methods in real environment and virtual environment is described. The real experimental environment includes the WBV（whole body vibration） test, questionnaires for human subjective sensation and motion capture. The virtual experimental environment includes the theoretical calculation on simplified 5-DOF human body vibration model, the vibration simulation and analysis within ADAMS/VibrationTM module, and the digital human biomechanics and occupational health analysis in Jack software. While the real experimental environment provides realistic and accurate test results, it also serves as core and validation for the virtual experimental environment. The virtual experimental environment takes full advantages of current available vibration simulation and digital human modelling software, and makes it possible to evaluate the sitting posture comfort in a human-vehicle system with various human anthropometric parameters. How this digital evaluation system for car seat comfort design is fitted in the Industry 4.0 framework is also proposed.

A Human Body Posture Recognition Algorithm Based on BP Neural Network for Wireless Body Area Networks

Human body posture recognition has attracted considerable attention in recent years in wireless body area networks(WBAN). In order to precisely recognize human body posture,many recognition algorithms have been proposed.However, the recognition rate is relatively low. In this paper, we apply back propagation(BP) neural network as a classifier to recognizing human body posture, where signals are collected from VG350 acceleration sensor and a posture signal collection system based on WBAN is designed. Human body signal vector magnitude(SVM) and tri-axial acceleration sensor data are used to describe the human body postures. We are able to recognize 4postures: Walk, Run, Squat and Sit. Our posture recognition rate is up to 91.67%. Furthermore, we find an implied relationship between hidden layer neurons and the posture recognition rate. The proposed human body posture recognition algorithm lays the foundation for the subsequent applications.

Research on Passive Locating Method Using Phase Rate of Change with Variant Posture of the Observer

Technology of passive location has broad prospects in applications. In this paper, the method using the phase rate of change for the single observer passive location is introduced based on existing methods. One can obtain the direction of the target with phase information of two orthogonal interferometers on the observer and the radial distance with the corresponding phase rate of change. Then the target can be located with high speed and precision. A locating approach is given when the flying posture of t...

Motion/Posture Modeling and Simulation Verification of Physically Handicapped in Manufacturing System Design

Non-obstacle design is critical to tailor physically handicapped workers in manufacturing system. Simultaneous consideration of variability in physically disabled users, machines and environment of the manufacturing system is extremely complex and generally requires modeling of physically handicapped interaction with the system. Most current modeling either concentrates on the task results or functional disability. The integration of physical constraints with task constraints is far more complex because of functional disability and its extended influence on adjacent body parts. A framework is proposed to integrate the two constraints and thus model the specific behavior of the physical handicapped in virtual environment generated by product specifications. Within the framework a simplified model of physical disabled body is constructed, and body motion is generated based on 3 levels of constraints（effecter constraints, kinematics constraints and physical constraints）. The kinematics and dynamic calculations are made and optimized based on the weighting manipulated by the kinematics constraints and dynamic constraints. With object transferring task as example, the model is validated in Jack 6.0. Modelled task motion elements except for squatting and overreaching well matched with captured motion elements. The proposed modeling method can model the complex behavior of the physically handicapped by integrating both task and physical disability constraints.

Design and Efficacy of Surgery for Horizontal Idiopathic Nystagmus with Abnormal Head Posture and Strabismus

The design and efficacy of surgery for horizontal idiopathic nystagmus （HIN） with abnormal head posture and strabismus were investigated. Different surgical procedures were selected according to the angle of head turn in 44 cases of HIN with abnormal head posture and strabismus. For patients with a head turn of 15° or less, the Anderson procedure was used; the yoke muscles were recessed upon slow-phase. For patients with a head turn between 15° and 25°, the surgery was designed as a Kestenbaum 5-4-4-5 procedure. For patients with a head turn of 25° or more, the surgery was designed as a Parks 5-8-6-7 procedure. The surgery to correct the abnormal head posture was performed on the fixating eye while that to correct the deviation was then performed on the non-fixating eye at the same time. The amount of surgery of the horizontal rectus muscles on the nonfixating eye was sum of the angle of head turn and the degree of deviation, which was calculated as follows： recession/resection amount of medial and lateral rectis/2×5=angle of head turn±degree of deviation. The results showed as follows： （1） Visual acuity： the visual acuity in the primary ocular position increased two lines or more in 35 patients, accounting for 79.55%. Nine patients had no or only one-line improvement, accounting for 20.45% of the entire study population; （2） The degree of deviation in the primary ocular position： 37 cases had a normal primary ocular position or the degree of deviation ≤8△ after surgery, accounting for 84.09%. Six patients had a residual degree of deviation of 8△―15△, accounting for 13.64%. One patient had a residual degree of deviation 〉20△, accounting for 2.27% of the patients examined; （3） Abnormal head posture： 34 patients had a normal head posture or a head turn of less than 5°, accounting for 72.27%. Eight patients had a residual head turn of 5°―15°, accounting for 18.18%. Two patients had a head turn of 15°― 25°, accounting for 4.55%. It was concluded that different surgical procedures based on the angle of head turn and the relationship between deviation and null zone can eliminate anomalous head posture, correct deviation, and improve vision acuity in the primary ocular position simultaneously.

Investigation of blood pulse PPG signal regulation on toe effect of body posture and lower limb height

Objective: To study the regulation of blood pulse volume via photoplethysmography (PPG) signal detected from toe, while the lower limb is passively raised in different height positions. Methods: Use a modified non-invasive PPG technique to detect the blood pulse signal on toe with infrared (IR) photo sensor. A protocol consisting of two postures, i.e., supine and 45° reclining, was designed to conduct laboratory trial in this study. During the period of performing the protocol of these postures, the lower limb was passively raised from the heights of 10 cm to 60 cm randomly and individually with sponge blocks underneath the foot. Results: In the supine posture, the higher the foot was passively raised, the more the blood PPG signal decreased. In the 45° reclining posture, the blood PPG signal increased at the beginning and then decreased in the foot height position from 10 cm to 60 cm. In both postures the normalized AC signal changes significantly while the normalized DC signal changes little. Conclusion: The toe PPG signals can obviously indicate the regulated blood volume change with the designated postural procedures due to the heart level position.

Technological advancements in the analysis of human motion and posture management through digital devices

Technological development of motion and posture analyses is rapidly progressing,especially in rehabilitation settings and sport biomechanics.Consequently,clear discrimination among different measurement systems is required to diversify their use as needed.This review aims to resume the currently used motion and posture analysis systems,clarify and suggest the appropriate approaches suitable for specific cases or contexts.The currently gold standard systems of motion analysis,widely used in clinical settings,present several limitations related to marker placement or long procedure time.Fully automated and markerless systems are overcoming these drawbacks for conducting biomechanical studies,especially outside laboratories.Similarly,new posture analysis techniques are emerging,often driven by the need for fast and non-invasive methods to obtain high-precision results.These new technologies have also become effective for children or adolescents with non-specific back pain and postural insufficiencies.The evolutions of these methods aim to standardize measurements and provide manageable tools in clinical practice for the early diagnosis of musculoskeletal pathologies and to monitor daily improvements of each patient.Herein,these devices and their uses are described,providing researchers,clinicians,orthopedics,physical therapists,and sports coaches an effective guide to use new technologies in their practice as instruments of diagnosis,therapy,and prevention.

Posture Maintenance Control of 2-Link Object By Nonprehensile Two-Cooperative-Arm Robot Without Compensating Friction

In this paper, a method to posture maintenance control of 2-link object by nonprehensile two-cooperative-arm robot without compensating friction is proposed. In details, a mathematical model of the 2-link object is firstly built. Based on the model, stable regions for holding motion of nonprehensile two-cooperative-arm robot are obtained while the 2-link object is kept stable on the robot arms with static friction. Among the obtained stable regions, the robust pairs of orientation angles of the 2-link object are found. Under the robust orientation angles, a feedback control system is designed to control the arms to maintain the 2-link object's posture while it is being held or lifted up. Finally, experimental results are shown to verify the effectiveness of the proposed method.