In response to the numerous challenges faced by traditional human pose recognition methods in practical applications, such as dense targets, severe edge occlusion, limited application scenarios, complex backgrounds, and poor recognition accuracy when targets are occluded, this paper proposes a YOLO-Pose algorithm for human pose estimation. The specific improvements are divided into four parts. Firstly, in the Backbone section of the YOLO-Pose model, lightweight GhostNet modules are introduced to reduce the model\'s parameter count and computational requirements, making it suitable for deployment on unmanned aerial vehicles (UAVs). Secondly, the ACmix attention mechanism is integrated into the Neck section to improve detection speed during object judgment and localization. Furthermore, in the Head section, key points are optimized using coordinate attention mechanisms, significantly enhancing key point localization accuracy. Lastly, the paper improves the loss function and confidence function to enhance the model\'s robustness. Experimental results demonstrate that the improved model achieves a 95.58% improvement in mAP50 and a 69.54% improvement in mAP50-95 compared to the original model, with a reduction of 14.6 M parameters. The model achieves a detection speed of 19.9 ms per image, optimized by 30% and 39.5% compared to the original model. Comparisons with other algorithms such as Faster R-CNN, SSD, YOLOv4, and YOLOv7 demonstrate varying degrees of performance improvement.

OCCUPATIONAL APPLICATIONS\"Overassistive\" robots can adversely impact long-term human-robot collaboration in the workplace, leading to risks of worker complacency, reduced workforce skill sets, and diminished situational awareness. Ergonomics practitioners should thus be cautious about solely targeting widely adopted metrics for improving human-robot collaboration, such as user trust and comfort. By contrast, introducing variability and adaptation into a collaborative robot\'s behavior could prove vital in preventing the negative consequences of overreliance and overtrust in an autonomous partner. This work reported here explored how instilling variability into physical human-robot collaboration can have a measurably positive effect on ergonomics in a repetitive task. A review of principles related to this notion of \"stimulating\" robot behavior is also provided to further inform ergonomics practitioners of existing human-robot collaboration frameworks.
Background: Collaborative robots, or cobots, are becoming ubiquitous in occupational settings due to benefits that include improved worker safety and increased productivity. Existing research on human-robot collaboration in industry has made progress in enhancing workers’ psychophysical states, by optimizing measures of ergonomics risk factors, such as human posture, comfort, and cognitive workload. However, short-term objectives for robotic assistance may conflict with the worker’s long-term preferences, needs, and overall wellbeing.Purpose: To investigate the ergonomic advantages and disadvantages of employing a collaborative robotics framework that intentionally imposes variability in the robot’s behavior to stimulate the human partner’s psychophysical state.Methods: A review of “overassistance” within human-robot collaboration and methods of addressing this phenomenon via adaptive automation. In adaptive approaches, the robot assistance may even challenge the user to better achieve a long-term objective while partially conflicting with their short-term task goals. Common themes across these approaches were extracted to motivate and support the proposed idea of stimulating robot behavior in physical human-robot collaboration.Results: Experimental evidence to justify stimulating robot behavior is presented through a human-robot handover study. A robot handover policy that regularly injects variability into the object transfer location led to significantly larger dynamics in the torso rotations and center of mass of human receivers compared to an “overassistive” policy that constrains receiver motion. Crucially, the stimulating handover policy also generated improvements in widely used ergonomics risk indicators of human posture.Conclusions: Our findings underscore the potential ergonomic benefits of a cobot’s actions imposing variability in a user’s responsive behavior, rather than indirectly restricting human behavior by optimizing the immediate task objective. Therefore, a transition from cobot policies that optimize instantaneous measures of ergonomics to those that continuously engage users could hold promise for human-robot collaboration in occupational settings characterized by repeated interactions.

Human posture recognition technology is widely used in the fields of healthcare, human-computer interaction, and sports. The use of a Frequency-Modulated Continuous Wave (FMCW) millimetre-wave (MMW) radar sensor in measuring human posture characteristics data is of great significance because of its robust and strong recognition capabilities. This paper demonstrates how human posture characteristics data are measured, classified, and identified using FMCW techniques. First of all, the characteristics data of human posture is measured with the MMW radar sensors. Secondly, the point cloud data for human posture is generated, considering both the dynamic and static features of the reflected signal from the human body, which not only greatly reduces the environmental noise but also strengthens the reflection of the detected target. Lastly, six different machine learning models are applied for posture classification based on the generated point cloud data. To comparatively evaluate the proper model for point cloud data classification procedure-in addition to using the traditional index-the Kappa index was introduced to eliminate the effect due to the uncontrollable imbalance of the sampling data. These results support our conclusion that among the six machine learning algorithms implemented in this paper, the multi-layer perceptron (MLP) method is regarded as the most promising classifier.

OBJECTIVE: There is a high demand on spinal surgery in patients with Parkinson\'s disease (PD) but the results are sobering. Although detailed clinical and radiological diagnostics were carried out with great effort and expense, the biodynamic properties of the spine of PD patients have never been considered. We propose a noninvasive method to quantify the impairment of motion abilities in patients with PD.
METHODS: We present an analytical cross-sectional study of 21 patients with severe PD. All patients underwent a biodynamic assessment during a standardized movement-choreography. Thus, individual spinal motion profiles of each patient were objectively assessed and compared with a large comparative cohort of individuals without PD. Moreover, clinical scores to quantify motor function and lumbar back pain were collected and X-ray scans of the spine in standing position were taken and analysed.
RESULTS: Biodynamic measurement showed that 36.9% of the assessed motions of all PD patients were severely impaired. Men were generally more functionally impaired than women, in 52% of all motion parameters. The neurological and radiological diagnostics recorded pathological values, of which UPDRS-III ON correlated with findings of the biodynamics assessment (R = 0.52, p = 0.02).
CONCLUSIONS: The decision to operate on a PD patient\'s spine is far-reaching and requires careful consideration. Neurological and radiological scores did not correlate with the biodynamics of the spine. The resulting motion profile could be used as individual predictive factor to estimate whether patients are eligible for spinal surgery or alternative therapies.

One-in-five people suffer from chronic low back pain (LBP). The incidence of this disease has doubled since 1950s and affects not only the elderly, but also the young population. However, the mechanism of LBP is still unknown. A possible location where the LBP may develop is the facet joint and it has been revealed that the intervertebral disc (IVD) nucleotomy may be a trigger for LBP. The aim of the present study was to investigate the influence of IVD nucleotomy on the load sharing in the spinal facet joint under the loading scenarios of different postures. Finite element (FE) models of the intact and nucleotomised L4 - L5 spinal segments were generated from the clinical CT images. Seven human postures, including upright, 5° extension, 5° flexion, ± 6° lateral bending and ± 2° axial rotation, were simulated. The resultant forces in the fact joint were compared between the intact and the nucleotomised cases. It was revealed that the IVD nucleotomy significantly increased the forces in the facet joints under the loading scenarios of upright, 5° extension and 5° flexion. The IVD nucleotomy increased the force in the ipsilateral facet joint but decreased the force on the contralateral side under the loading scenarios of ± 2° axial rotation. However, the IVD nucleotomy made little influence on the resultant forces in both facet joints in the postures of ± 6° lateral bending. In conclusion, the IVD nucleotomy can cause an increase in the overall force in the facet joint, and thus may serve as a possible explanation for the LBP and a main contributing factor for the pain complaints.

Sacral slope and lumbar lordosis (LL) have been studied extensively in recent years via X-ray examinations and strongly correlate with each other. This raises, first, the question of the reproducibility of this correlation in multiple standing phases and, second, if this correlation can be achieved using non-radiological measurement tools.
This study aimed (1) to determine the extent to which the back-shape measurements correspond to the correlations between the sacral slope and LL found in previous radiological investigations, (2) to identify a possible effect of age and gender on this correlation, and (3) to evaluate the extent to which this correlation is affected by repeated standing phases.
This is an observational cohort study.
A total of 410 asymptomatic subjects (non-athletes), 21 asymptomatic soccer players (athletes), and 176 patients with low back pain (LBP) were included.
The correlation between sacrum orientation (SO) and LL was determined in six repetitive upright standing postures.
A non-invasive strain-gauge based measuring system was used.
Back-shape measurements yielded a similar correlation to that measured in previous X-ray examinations. The coefficient of determination (R2) between SO and LL ranged between 0.76 and 0.79 for the asymptomatic cohort. Athletes showed the strongest correlation (0.76≤R2≤0.84). For patients with LBP, the correlation substantially decreased (0.18≤R2≤0.39). R2 was not strongly affected by repeated standing phases.
The correlation between SO and LL can be assessed by surface measurements of the back shape and is not influenced by natural variations in the standing posture.

An irreproducible standing posture can lead to mis-interpretation of radiological measurements, wrong diagnoses and possibly unnecessary treatment. This study aimed to evaluate the differences in lumbar lordosis and sacrum orientation in six repetitive upright standing postures of 353 asymptomatic subjects (including 332 non-athletes and 21 athletes - soccer players) and 83 low back pain (LBP) patients using a non-invasive back-shape measurement device. In the standing position, all investigated cohorts displayed a large inter-subject variability in sacrum orientation (∼40°) and lumbar lordosis (∼53°). In the asymptomatic cohort (non-athletes), 51% of the subjects showed variations in lumbar lordosis of 10-20% in six repeated standing phases and 29% showed variations of even more than 20%. In the sacrum orientation, 53% of all asymptomatic subjects revealed variations of >20% and 31% of even more than 30%. It can be concluded that standing is highly individual and poorly reproducible. The reproducibility was independent of age, gender, body height and weight. LBP patients and athletes showed a similar variability as the asymptomatic cohort. The number of standing phases performed showed no positive effect on the reproducibility. Therefore, the variability in standing is not predictable but random, and thus does not reflect an individual specific behavioral pattern which can be reduced, for example, by repeated standing phases.

The purpose of this study was to test the hypothesis that the center of pressure (COP) velocity reflects the center of mass (COM) acceleration due to a large derivative gain in the neural control system during quiet standing. Twenty-seven young (27.2±4.5 years) and twenty-three elderly (66.2±5.0 years) subjects participated in this study. Each subject was requested to stand quietly on a force plate for five trials, each 90 s long. The COP and COM displacements, the COP and COM velocities, and the COM acceleration were acquired via a force plate and a laser displacement sensor. The amount of fluctuation of each variable was quantified using the root mean square. Following the experimental study, a simulation study was executed to investigate the experimental findings. The experimental results revealed that the COP velocity was correlated with the COM velocity, but more highly correlated with the COM acceleration. The equation of motion of the inverted pendulum model, however, accounts only for the correlation between the COP and COM velocities. These experimental results can be meaningfully explained by the simulation study, which indicated that the neural motor command presumably contains a significant portion that is proportional to body velocity. In conclusion, the COP velocity fluctuation reflects the COM acceleration fluctuation rather than the COM velocity fluctuation, implying that the neural motor command controlling quiet standing posture contains a significant portion that is proportional to body velocity.