Human Posture Research Articles

Current Positions of the Collegial Bodies of the FAS Russia on Issues of Appeal Against Decisions on Cases of Violations of Antimonopoly Requirements for Trading, Request for Quotations of Prices for Goods, Request for Proposals

The current approaches of the collegial bodies of the Federal Antimonopoly Service to the consideration of cases of violations of antimonopoly requirements for trading, request for quotations of prices for goods, request for proposals established by Art. 17 of the Federal Law of 26.07.2006 No. 135-FZ "On Protection of Competition" (hereinafter referred to as the Law on Protection of Competition).The positions of the collegial bodies of the FAS Russia are of particular importance both for territorial antimonopoly bodies and for courts in cases of violations of antimonopoly laws and, of course, make a significant contribution to the development of antimonopoly law enforcement practice and maintaining its uniformity.In order to analyze the current positions of the Federal Antimonopoly Service of Russia on various issues of antimonopoly law enforcement in the most comprehensive and needs-based law enforcement practice, a number of cases examined by the collegial bodies of this department in the second half of 2023 were studied

ASSESSING MUSCULOSKELETAL DISORDERS (MSDS) OF WORKERS OF FIRED CLAY BRICKS INDUSTRY

Ergonomics is important for sustainable development in many fields, including architecture, health, product design, safety, and workplace design. Ergonomic assessments are essential in the workplace to prevent musculoskeletal disorders (MSDs). Currently, Indonesia has a standardized ergonomic assessment, SNI 9011:2021. This assessment standard is widely used to evaluate human posture. This study aims to evaluate the position of a traditional brick-maker in which the posture identification system is based on the SNI 9011:2021. This study employed a cross-sectional design with a sample of workers in conventional brick manufacturing. The primary findings of this study were visual ergonomic assessment for posture identification, identification of ergonomic assessment categories with high risk in brick manufacturing, and the prevalence of nagging pain among workers in the brick moulding and drying process. To reduce occupational ergonomic risk, particularly for brick-making workers, ergonomic intervention is required in the form of additional work aids such as chairs. This has been shown to reduce the evaluation score based on SNI 9011: 2021, thereby reducing the occurrence of musculoskeletal disorders

Deep Learning Driven Human Posture Location in Physical Education Teaching

Deep Learning Driven Human Posture Location in Physical Education Teaching

A three-dimensional human motion pose recognition algorithm based on graph convolutional networks

In the task of three-dimensional human motion posture recognition, there are problems such as target loss, inaccurate target positioning, and high computational complexity. This article designs a recognition evaluation algorithm to address these issues. Design a LiteHRNet model for extracting skeleton sequences from action videos, and propose a graph convolutional structure that combines residual networks and attention mechanisms. This network can effectively enhance the expression ability of node key features. Introducing second-order velocity information and spatial position information of joint points to improve positioning accuracy. Improve the TCN and Transformer network models to simultaneously extract local and long-term features throughout the entire model, and more accurately model the temporal correlation between nodes in the entire action sequence. The fusion of Transformer networks can reduce the computational complexity of the model while ensuring its accuracy. The experiment shows that the model has good evaluation performance on multiple datasets.

Work procedure action recognition based on skeleton and video features

In the field of industrial engineering, traditional methods for analyzing manufacturing process actions have limitations such as time-consuming, labor-intensive, and experience-dependent. To address these challenges in action analysis, we propose an intelligent action recognition method based on both skeleton and video features, aiming to replace manual decomposition of action elements. The MediaPipe framework is used for human posture estimation to obtain the skeleton sequence, and the CNN-GRU model is constructed action recognition based on skeleton features. For hand movements involving the use of industrial gloves, an enhanced TimeSformer video understanding model is introduced for action recognition based on video features. This improvement incorporates uniform attention and external attention mechanisms, resulting in enhanced model performance. The final experimental validation for the self-constructed process action dataset shows that the online detection speed of the skeleton action recognition model reaches 25 FPS, and the accuracy of the end-to-end video action recognition model is improved by 10.5 percentage points compared to the base model.

MiSleep: Human Sleep Posture Identification from Deep Learning Augmented Millimeter-wave Wireless Systems

In this work, we propose MiSleep , a deep learning augmented millimeter-wave (mmWave) wireless system to monitor human sleep posture by predicting the 3D location of the body joints of a person during sleep. Unlike existing vision- or wearable-based sleep monitoring systems, MiSleep is not privacy-invasive and does not require users to wear anything on their body. MiSleep leverages knowledge of human anatomical features and deep learning models to solve challenges in existing mmWave devices with low-resolution and aliased imaging and specularity in signals. MiSleep builds the model by learning the relationship between mmWave reflected signals and body postures from thousands of existing samples. Since a practical sleep also involves sudden toss-turns, which could introduce errors in posture prediction, MiSleep designs a state machine based on the reflected signals to classify the sleeping states into rest or toss-turn and predict the posture only during the rest states. We evaluate MiSleep with real data collected from Commercial-Off-The-Shelf mmWave devices for eight volunteers of diverse ages, genders, and heights performing different sleep postures . We observe that MiSleep identifies the toss-turn events start time and duration within 1.25 s and 1.7 s of the ground truth, respectively, and predicts the 3D location of body joints with a median error of 1.3 cm only and can perform even under the blankets, with accuracy on par with the existing vision-based system, unlocking the potential of mmWave systems for privacy-noninvasive at-home healthcare applications.

Peculiarities of property rights protection, their specific application to objects

The article examines the issue of the specifics of the protection of property rights, the specifics of their application to objects.
 Article 13 of the Constitution of Ukraine declares that the fundamental principle of in the field of protection of property rights there is a provision that the state provides equal protection of all subjects of property rights. In recent years, the question of protection of property rights has gained important theoretical and practical importance. The analysis of modern judicial practice shows that there is no unified position of judicial bodies on the resolution of disputes related to the violation of property rights. Courts of general jurisdiction and commercial courts, when considering disputes related to the protection of violated rights, ambiguously apply the norms of current legislation, therefore, the uncertainty of judicial authorities in the matter of the uniform application of the provisions of civil law to disputes of this category leads to the violation of the constitutional rights of owners.
 It is emphasized that the protection of property rights is a complex of civil legal means, which are aimed, on the one hand, at ensuring the normal economic use of property and maintaining property rights in an intact state, and, on the other hand, at restoring violated property relations, overcoming obstacles to their normal functioning and compensation for damages caused to the owner.
 As a conclusion, it is said that the protection of property rights acts as an independent subjective right that arises at the moment when there is a threat of its violation or dispute. This right includes powers, each of which involves the active implementation of positive actions.
 In the field of legal relations related to the protection of property rights, the objects of protection are directly the rights to certain objects. It is these rights that can be violated by other persons, and it is for their protection that the civil law provides for various means that a person can use to protect his violated or disputed rights, which are subject to protection by the law of interests.
 Subjects of legal relations related to the protection of property rights are, on the one hand, persons who have property rights to a specific object, and persons who retain property in accordance with relevant contracts or laws, and who, accordingly to legal norms, have the right to demand protection of their violated subjective rights. On the other hand, these are persons whose actions led to the unlawful violation of subjective rights to property objects.

Consent of a lawyer's client to the processing of his personal data as part of the exercise of the right to a lawyer's request

This article discusses theoretical and practical issues regarding the possibility of a lawyer obtaining information with limited access, in particular, information that contains the personal data of his client. The position is argued, according to which although the right to request a lawyer is a professional right of a lawyer, at the same time, taking into account the peculiarity of the information requested by him, which contains personal data of another person (confidential information), it is necessary to take into account the requirements of special legislation on the protection of personal data, primarily regarding stating the legal grounds (purpose) and the "convincing” need to obtain them.
 Within the framework of this study, attention is paid to the problematic issues of determining the essence of the lawyer's client's consent to the processing of his personal data through the lens of the lawyer's right to request. It is concluded that the possibility of obtaining information directly related to the lawyer's client and containing his personal data is conditioned by his giving the lawyer the appropriate consent to this.
 The requirements of the law and the position of the self-governing bodies of lawyers regarding the necessity (feasibility) of the lawyer obtaining consent to the processing of his personal data from the client are investigated. Attention is drawn to the fact that based on the absence of clear requirements in the legislation on the protection of personal data regarding the form of the above­mentioned consent, the position of the Bar Council of Ukraine is correct, according to which it should be set out in a separate clause of the contract on the provision of legal assistance, which can also be concluded in electronic form , and further provision of this contract (excerpt from it) is sufficient for obtaining confidential information about the lawyer's client.
 To achieve the goal, the author used research methods that are characteristic primarily of legal science. This research was conducted using, in particular, systemic-structural and dialectical methods of learning legal reality, which provided an opportunity to analyze the essence of the lawyer's right to receive information containing his client's personal data and the need to obtain the latter's consent to their processing.

Nexus between green human resource management practices and corporate social responsibility: does transformational leadership make difference?

Purpose The purpose of this study was to investigate the connection between green human resource management (GHRM) and corporate social responsibility (CSR). In addition, this study also investigates how the impact of GHRM varies depending on the extent of transformational leadership. Design/methodology/approach Adopting a quantitative approach, the sample consists of 376 employees who hold leadership positions in the academic body and those who work in human resources units at universities who won the Web Metric Award. Findings Results have shown that all GHRM practices were found to have a significant and positive effect on CSR. In addition, the findings revealed that transformational leadership positively moderates the relationship between GHRM and CSR. Originality/value The findings of this study contribute to the existing body of knowledge by providing empirical evidence of the positive relationship between GHRM practices, transformational leadership and CSR performance. In addition, the study highlights the moderating influence of transformational leadership on the relationship between GHRM and CSR, suggesting that transformational leadership can increase the efficacy of GHRM practices in promoting CSR outcomes.

Using Electric Stimulation of the Spinal Muscles and Electromyography during Motor Tasks for Evaluation of the Role in Development and Progression of Adolescent Idiopathic Scoliosis.

Introduction: The role of the spinal muscles in scoliogenesis is not fully substantiated. Do they act scoliogenic (inducing scoliosis) or counteract scoliosis in adolescent idiopathic scoliosis (AIS)? In this study, we will examine this by using selectively placed Transcutaneous Electric Stimulation (TES) combined with a cinematic radiographic technique and by performing electromyographic (EMG) evaluations during various motor tasks. Method: This is a cross-sectional study of subjects with small-curve AIS. Using cinematic radiography, they were evaluated dynamically either under electrical stimulation or when performing motor tasks of left and right lateral bending and rotation whilst measuring the muscle activity by EMG. Results: Forty-five patients with AIS were included as subjects. Five subjects volunteered for TES and six subjects performed the motor tasks with EMG. At the initial visual evaluation, and when stimulated with TES, the frontal plane spatial positions of the vertebral bodies showed discrete changes without an apparent pattern. However, analyzing the spatial positions when calibrated, we found that the spinal muscles exert a compressive 'response' with a minor change in the Cobb angle (CA) in small-curve AIS (CA = 10-20°). In larger curves (CA > 20°), TES induced a 'larger deformity' with a relative four-fold change in the CA compared to small-curve AIS with a ratio of 0.6. When evaluating local amplitude (peak) or cumulative (mean) EMG signals, we were unable to find consistent asymmetries. However, one subject had rapid progression and one regressed to a straight spine. When adding the absolute EMG ratios for all four motor tasks, the subject with progression had almost 10-fold less summed EMG ratios, and the subject with regression had more than 3-fold higher summed EMG ratios. Discussion: Based on these findings, we suggest that the spinal muscles in small-curve AIS have a stabilizing function maintaining a straight spine and keeping it in the midline. When deformities are larger (CA > 20°), the spine muscle curve exerts a scoliogenic 'response'. This suggests that the role of the muscles converts from counteracting AIS and stabilizing the spine to being scoliogenic for a CA of more than 20°. Moreover, we interpret higher EMG ratios as heightened asymmetric spinal muscle activity when the spinal muscles try to balance the spine to maintain or correct the deformity. When progression occurs, this is preceded or accompanied by decreased EMG ratios. These findings must be substantiated by larger studies.

Analysis and Improvement of the Application of Playground Sports Posture Detection Technology in Physical Education Teaching and Training

INTORDUCTION: The goal of human posture detection technology applied in the field of sports is to realise the indexing of sports norms, to provide scientific guidance for training and teaching, which is of great significance to improve the quality of sports.OBJECITVES: Aiming at the problems of incomplete features, low accuracy and low real-time performance of sports posture detection and recognition methods.METHODS: In this paper, a method of sports pose detection based on snow melting heuristic optimisation algorithm of deep limit learning machine network is proposed. Firstly, by analyzing the process of motion pose detection, extracting the feature coordinates of Blaze-Pose and Blaze-Hands key nodes, and constructing the motion pose detection recognition system; then, optimizing the parameters of the deep extreme learning machine network through the snow-melt optimization algorithm, and constructing the motion pose detection recognition model; finally, through simulation experiments and analysis, the accuracy of the proposed method's motion pose detection recognition can reach 95% and the recognition time is less than 0.01 s.RESULTS: The results show that the proposed method improves the recognition accuracy precision, robustness and real-time performance.CONCLUSION: The problem of poor generalisation, low accuracy and insufficient real-time performance of the recognition application of the motion pose detection and recognition method is solved.

Predicting preferred motorcycle riding postures to support human factors/ergonomic trade-off analyses within a multi-objective optimisation-based digital human model

Digital human models (DHM) can predict how users might interact with new vehicle geometry during early-stage design, an important precursor to conducting trade-off analyses. However, predicting human postures requires assumptions about which performance criteria best predict realistic postures. Focusing on the design of motorcycles, we do not know what performance criteria drive preferred riding postures. Addressing this gap, we aimed to identify which performance criteria and corresponding weightings best predicted preferred motorcycle riding postures when using a DHM. To address our aim, we surveyed the literature to find experimental data specifying joint angles that correspond to preferred riding postures. We then deployed a response surface methodology to determine which performance criteria and weightings optimally predicted the preferred riding postures when using a DHM. Weighting the minimisation of the discomfort performance criteria (an aggregate of joint range of motion, displacement from neutral and joint torque) best predicted preferred motorcycle riding postures.

Geometry-driven self-supervision for 3D human pose estimation

Although 3D human pose estimation has recently made strides, it is still difficult to precisely recreate a 3D human posture from a single image without the aid of 3D annotation for the following reasons. Firstly, the process of reconstruction inherently suffers from ambiguity, as multiple 3D poses can be projected onto the same 2D pose. Secondly, accurately measuring camera rotation without laborious camera calibration is a difficult task. While some approaches attempt to address these issues using traditional computer vision algorithms, they are not differentiable and cannot be optimized through training. This paper introduces two modules that explicitly leverage geometry to overcome these challenges, without requiring any 3D ground-truth or camera parameters. The first module, known as the relative depth estimation module, effectively mitigates depth ambiguity by narrowing down the possible depths for each joint to only two candidates. The second module, referred to as the differentiable pose alignment module, calculates camera rotation by aligning poses from different views. The use of these geometrically interpretable modules reduces the complexity of training and yields superior performance. By adopting our proposed method, we achieve state-of-the-art results on standard benchmark datasets, surpassing other self-supervised methods and even outperforming several fully-supervised approaches that heavily rely on 3D annotations.

Hierarchical Context-Based Emotion Recognition With Scene Graphs.

For a better intention inference, we often try to figure out the emotional states of other people in social communications. Many studies on affective computing have been carried out to infer emotions through perceiving human states, i.e., facial expression and body posture. Such methods are skillful in a controlled environment. However, it often leads to misestimation due to the deficiency of effective inputs in unconstrained circumstances, that is, where context-aware emotion recognition appeared. We take inspiration from the advanced reasoning pattern of humans in perceived emotion recognition and propose the hierarchical context-based emotion recognition method with scene graphs. We propose to extract three contexts from the image, i.e., the entity context, the global context, and the scene context. The scene context contains abstract information about entity labels and their relationships. It is similar to the information processing of the human visual sensing mechanism. After that, these contexts are further fused to perform emotion recognition. We carried out a bunch of experiments on the widely used context-aware emotion datasets, i.e., CAER-S, EMOTIC, and BOdy Language Dataset (BoLD). We demonstrate that the hierarchical contexts can benefit emotion recognition by improving the accuracy of the SOTA score from 84.82% to 90.83% on CAER-S. The ablation experiments show that hierarchical contexts provide complementary information. Our method improves the F1 score of the SOTA result from 29.33% to 30.24% (C-F1) on EMOTIC. We also build the image-based emotion recognition task with BoLD-Img from BoLD and obtain a better emotion recognition score (ERS) score of 0.2153.

RESEARCH ON HUMAN POSTURE RECOGNITION METHOD BASED ON DEEP LEARNING

The dynamic recognition of human posture has very broad application prospects in fields such as human–computer interaction and virtual reality. A new method for dynamic recognition of human posture is proposed within the theoretical framework of deep learning. In our method, historical image information of human posture, current image information of human posture, and association information between each image are included as inputs in the deep learning process. Afterwards, the input information is formed into time series information and feature series information, which are then fused by the attention mechanism module. Finally, the dynamic recognition results of human posture are obtained through convolution operation. Experimental research was conducted on the AMASS dataset, and the results showed that our method can achieve better results in dynamic recognition of human posture, with both indicators superior to the other three methods. At the same time, our method has a fast convergence speed and the loss function remains low and continuously decreases during the deep learning process.

ANALYSIS OF HUMAN LOWER LIMB DYNAMICS AND GAIT RECONSTRUCTION

In order to achieve gait reconstruction of human posture, a 7-degree-of-freedom model of the human lower limbs is proposed. On the basis of this model, dynamic analysis was conducted and the Lagrange equation of the human lower limb dynamic system was constructed. In the process of solving the kinetic energy–potential energy relationship of the Lagrange equation, the angular solutions of each joint were obtained. Based on actual data, common gait patterns of human lower limbs were presented, and gait reconstruction experiments were conducted. The experimental results show that under the human lower limb model and dynamic analysis method constructed in this paper, the variation curves of the hip joint, knee joint, and ankle joint of the human lower limb have been effectively reconstructed.

Multi-sensor fusion federated learning method of human posture recognition for dual-arm nursing robots

Human posture estimation plays a significant role in the growth of intelligent nursing robot, a field that demands high accuracy and respect for privacy. Nevertheless, traditional approaches to enhancing data-driven studies in this domain often face challenges, primarily due to privacy concerns in sensitive healthcare environments. Federated Learning rises as the solution to the problem, as it not only improves the model learning ability but also protects the data privacy. In this paper, we proposed a Federated Learning Human Posture Recognition (FL-HPR) framework according to image and point cloud fusion. FL-HPR significantly enhances the information flow in the global model while ensuring the data privacy in local models, the benefits highlight the framework’s potential in sensitive applications. Furthermore, the key innovation of FL-HPR is the optimization of the local dynamic graph edge convolution network of robot, which improves the recognition accuracy of individual body limb and enhance overall robustness. Experiments on Non-IID datasets illustrate that the presented FL-HPR remarkably outperforms non-federated learning methods, suggesting its potential to improve the accuracy of human joint estimation. The breakthrough indicates that the proposed FL-HPR can be integrated into the intelligent nursing robot in practical applications. For further explorations, the open-source code and videos are available at https://github.com/Hebut-LEVO/FL-HPR.

Improved Competitive Neural Network for Classification of Human Postures Based on Data fom RGB-D Sensors

The cognitive goal of this paper is to assess whether marker‐less motion capture systems provide sufficient data to recognize human postures in the side view. The research goal is to develop a new posture classification method that allows for analysing human activities using data recorded by RGB‐D sensors. The method is insensi tive to recorded activity duration and gives satisfactory results for the sagittal plane. An improved competitive Neural Network (cNN) was used. The method of preprocessing the data is first discussed. Then, a method for classifying human postures is presented. Finally, classification quality using various distance metrics is assessed.The data sets covering the selection of human activities have been created. Postures typical for these activities have been identified using the classifying neural network. The classification quality obtained using the proposed cNN network and two other popular neural networks were compared. The results confirmed the advantage of cNN network. The developed method makes it possible to recognize human postures by observing movement in the sagittal plane.

A Flexible Wearable Sensor Based on Laser-Induced Graphene for High-Precision Fine Motion Capture for Pilots.

There has been a significant shift in research focus in recent years toward laser-induced graphene (LIG), which is a high-performance material with immense potential for use in energy storage, ultrahydrophobic water applications, and electronic devices. In particular, LIG has demonstrated considerable potential in the field of high-precision human motion posture capture using flexible sensing materials. In this study, we investigated the surface morphology evolution and performance of LIG formed by varying the laser energy accumulation times. Further, to capture human motion posture, we evaluated the performance of highly accurate flexible wearable sensors based on LIG. The experimental results showed that the sensors prepared using LIG exhibited exceptional flexibility and mechanical performance when the laser energy accumulation was optimized three times. They exhibited remarkable attributes, such as high sensitivity (~41.4), a low detection limit (0.05%), a rapid time response (response time of ~150 ms; relaxation time of ~100 ms), and excellent response stability even after 2000 s at a strain of 1.0% or 8.0%. These findings unequivocally show that flexible wearable sensors based on LIG have significant potential for capturing human motion posture, wrist pulse rates, and eye blinking patterns. Moreover, the sensors can capture various physiological signals for pilots to provide real-time capturing.

Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence.

Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data. Methods: Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation. Results: Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples. Conclusion: This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain.