sEMG-Based Robust Recognition of Grasping Postures with a Machine Learning Approach for Low-Cost Hand Control.

The design and control of artificial hands remains a challenge in engineering. Popular prostheses are bio-mechanically simple with restricted manipulation capabilities, as advanced devices are pricy or abandoned due to their difficult communication with the hand. For social robots, the interpretation of human intention is key for their integration in daily life. This can be achieved with machine learning (ML) algorithms, which are barely used for grasping posture recognition. This work proposes an ML approach to recognize nine hand postures, representing 90% of the activities of daily living in real time using an sEMG human-robot interface (HRI). Data from 20 subjects wearing a Myo armband (8 sEMG signals) were gathered from the NinaPro DS5 and from experimental tests with the YCB Object Set, and they were used jointly in the development of a simple multi-layer perceptron in MATLAB, with a global percentage success of 73% using only two features. GPU-based implementations were run to select the best architecture, with generalization capabilities, robustness-versus-electrode shift, low memory expense, and real-time performance. This architecture enables the implementation of grasping posture recognition in low-cost devices, aimed at the development of affordable functional prostheses and HRI for social robots.

Measurement of Sedentary Behavior-The Outcomes of the Angle for Posture Estimation (APE) Method.

Hip-worn accelerometers are commonly used to assess habitual physical activity, but their accuracy in precisely measuring sedentary behavior (SB) is generally considered low. The angle for postural estimation (APE) method has shown promising accuracy in SB measurement. This method relies on the constant nature of Earth's gravity and the assumption that walking posture is typically upright. This study investigated how cardiorespiratory fitness (CRF) and body mass index (BMI) are related to APE output. A total of 3475 participants with adequate accelerometer wear time were categorized into three groups according to CRF or BMI. Participants in low CRF and high BMI groups spent more time in reclining and lying postures (APE ≥ 30°) and less time in sitting and standing postures (APE < 30°) than the other groups. Furthermore, the strongest partial Spearman correlation with CRF (r = 0.284) and BMI (r = -0.320) was observed for APE values typical for standing. The findings underscore the utility of the APE method in studying associations between SB and health outcomes. Importantly, this study emphasizes the necessity of reserving the term "sedentary behavior" for studies wherein the classification of SB is based on both intensity and posture.

Plantar load distribution with centers of gravity balance and rearfoot posture in daily lives of Taiwanese college elite table tennis players: a cross-sectional study.

Background: Table tennis is an asymmetric sport involving the powerful forward swing of the upper limbs depends on the solid support of the lower limbs. The foot drive really affects the weight balance and stroke accuracy even though the distance and momentum of the lower limb displacement are limited within a limited range. Given that previous research on table tennis has typically focused on the footwork and stroke performance of professional players, the study aimed to investigate the daily static and dynamic plantar load distribution as well as the centers of gravity balance and rearfoot posture among Taiwanese college elite table tennis players. Methods: This is a cross-sectional study of 70 elite male table tennis players (age: 20.0 ± 0.9 years; height: 173.4 ± 5.1 cm, weight: 67.6 ± 5.3 kg, experience: 10.0 ± 1.6 years) and 77 amateur table tennis players of the same gender (age: 20.1 ± 0.8 years, height: 167.4 ± 4.4 cm, weight: 64.3 ± 4.0 kg, experience: 4.4 ± 1.2 years) from Taiwanese universities. The JC Mat optical plantar pressure analyzer was applied to determine the plantar load distribution along with arch index (AI) and centers of gravity balance. Assessment of rearfoot postural alignment was mainly used to contrast the performance of the centers of gravity balance. Results: The static arch indices of both feet in the elite group were symmetrical and considered normal arches (AI: 0.22 ± 0.07) during their non-training and non-competition daily lives. Their static plantar loads were symmetrically concentrated on the bipedal lateral metatarsals (P < 0.05) as well as shifted to the medial and lateral heels (P < 0.05) and the lateral metatarsals (P < 0.05) during the walking midstance phase. Additionally, the plantar loads were mainly applied to the bipedal medial (P < 0.01) and lateral heels (P < 0.05) during the transitional changes between both states. Elite athletes had symmetrical and evenly distributed centers of gravity on both feet (left: 50.03 ± 4.47%; right: 49.97 ± 4.47%) when standing statically, along with symmetrical rearfoot angles and neutral position of the subtalar joint (left: 2.73 ± 2.30°; right: 2.70 ± 2.32°) even though they were statistically lower than those of the amateur athletes (P < 0.05). Conclusions: The daily static and dynamic foot patterns of Taiwanese college elite table tennis players were characterized by plantar load distribution on the lateral metatarsals and the entire calcaneus along with balanced centers of gravity and normal rearfoot posture. This foot and posture layout outlines the excellent athletic performance of the foot and ankle in professional athletes. Portions of this text were previously published as part of a preprint (https://doi.org/10.21203/rs.3.rs-2993403/v1).

Machine learning-based detection of acute psychosocial stress from body posture and movements.

Investigating acute stress responses is crucial to understanding the underlying mechanisms of stress. Current stress assessment methods include self-reports that can be biased and biomarkers that are often based on complex laboratory procedures. A promising additional modality for stress assessment might be the observation of body movements, which are affected by negative emotions and threatening situations. In this paper, we investigated the relationship between acute psychosocial stress induction and body posture and movements. We collected motion data from N = 59 individuals over two studies (Pilot Study: N = 20, Main Study: N = 39) using inertial measurement unit (IMU)-based motion capture suits. In both studies, individuals underwent the Trier Social Stress Test (TSST) and a stress-free control condition (friendly-TSST; f-TSST) in randomized order. Our results show that acute stress induction leads to a reproducible freezing behavior, characterized by less overall motion as well as more and longer periods of no movement. Based on these data, we trained machine learning pipelines to detect acute stress solely from movement information, achieving an accuracy of 75.0 ± 17.7 % (Pilot Study) and 73.4 ± 7.7 % (Main Study). This, for the first time, suggests that body posture and movements can be used to detect whether individuals are exposed to acute psychosocial stress. While more studies are needed to further validate our approach, we are convinced that motion information can be a valuable extension to the existing biomarkers and can help to obtain a more holistic picture of the human stress response. Our work is the first to systematically explore the use of full-body body posture and movement to gain novel insights into the human stress response and its effects on the body and mind.

An enhanced real-time human pose estimation method based on modified YOLOv8 framework.

The objective of human pose estimation (HPE) derived from deep learning aims to accurately estimate and predict the human body posture in images or videos via the utilization of deep neural networks. However, the accuracy of real-time HPE tasks is still to be improved due to factors such as partial occlusion of body parts and limited receptive field of the model. To alleviate the accuracy loss caused by these issues, this paper proposes a real-time HPE model called CCAM - Person based on the YOLOv8 framework. Specifically, we have improved the backbone and neck of the YOLOv8x-pose real-time HPE model to alleviate the feature loss and receptive field constraints. Secondly, we introduce the context coordinate attention module (CCAM) to augment the model's focus on salient features, reduce background noise interference, alleviate key point regression failure caused by limb occlusion, and improve the accuracy of pose estimation. Our approach attains competitive results on multiple metrics of two open-source datasets, MS COCO 2017 and CrowdPose. Compared with the baseline model YOLOv8x-pose, CCAM-Person improves the average precision by 2.8% and 3.5% on the two datasets, respectively.

Brownian processes in human motor control support descending neural velocity commands.

The motor neuroscience literature suggests that the central nervous system may encode some motor commands in terms of velocity. In this work, we tackle the question: what consequences would velocity commands produce at the behavioral level? Considering the ubiquitous presence of noise in the neuromusculoskeletal system, we predict that velocity commands affected by stationary noise would produce "random walks", also known as Brownian processes, in position. Brownian motions are distinctively characterized by a linearly growing variance and a power spectral density that declines in inverse proportion to frequency. This work first shows that these Brownian processes are indeed observed in unbounded motion tasks e.g., rotating a crank. We further predict that such growing variance would still be present, but bounded, in tasks requiring a constant posture e.g., maintaining a static hand position or quietly standing. This hypothesis was also confirmed by experimental observations. A series of descriptive models are investigated to justify the observed behavior. Interestingly, one of the models capable of accounting for all the experimental results must feature forward-path velocity commands corrupted by stationary noise. The results of this work provide behavioral support for the hypothesis that humans plan the motion components of their actions in terms of velocity.

Analysis of the obstetrician's posture and movements during a simulated forceps delivery.

BACKGROUND: The objective of this study was to identify and qualify, by means of a three-dimensional kinematic analysis, the postures and movements of obstetricians during a simulated forceps birth, and then to study the association of the obstetricians' experience with the technique adopted. METHOD: Fifty-seven volunteer obstetricians, 20 from the Limoges and 37 from the Poitiers University hospitals, were included in this multi-centric study. They were classified into 3 groups: beginners, intermediates, and experts, beginners having performed fewer than 10 forceps deliveries in real conditions, intermediates between 10 and 100, and experts more than 100. The posture and movements of the obstetricians were recorded between December 2020 and March 2021 using an optoelectronic motion capture system during simulated forceps births. Joint angles qualifying these postures and movements were analysed between the three phases of the foetal traction. These phases were defined by the passage of a virtual point associated with the forceps blade through two anatomical planes: the mid-pelvis and the pelvic outlet. Then, a consolidated ascending hierarchical classification (AHC) was applied to these data in order to objectify the existence of groups of similar behaviours. RESULTS: The AHC distinguished four different postures adopted when crossing the first plane and three different traction techniques. 48% of the beginners adopted one of the two raised posture, 22% being raised without trunk flexion and 26% raised with trunk flexion. Conversely, 58% of the experts positioned themselves in a "chevalier servant" posture (going down on one knee) and 25% in a "squatting" posture before initiating traction. The results also show that the joint movement amplitude tends to reduce with the level of expertise. CONCLUSION: Forceps delivery was performed in different ways, with the experienced obstetricians favouring postures that enabled observation at the level of the maternal perineum and techniques reducing movement amplitude. The first perspective of this work is to relate these different techniques to the traction force generated. The results of these studies have the potential to contribute to the training of obstetricians in forceps delivery, and to improve the safety of women and newborns.

Electrocardiographic and Autonomic Nervous System Changes after Changes in the Posture of Children and Adolescents with Duchenne Muscular Dystrophy. / Alterações Eletrocardiográficas e do Sistema Nervoso Autônomo com a Mudança de Postura em Crianças e Adolescentes com Distrofia Muscular de Duchenne.

BACKGROUND: Duchenne Muscular Dystrophy (DMD) is a rare inherited neuromuscular disease. At first, cardiac involvement may be asymptomatic. Therefore, assessing patients using non-invasive methods can help detect any changes. OBJECTIVES: Analyze the electrocardiogram (ECG) test and heart rate variability (HRV) of the DMD group and compare the information with that of the age-matched control group. METHODS: A prospective study with 27 male patients with DMD (11.9 years old), who underwent clinical evaluation, ECG, echocardiogram, and Holter monitoring. ECG (200% increase) was assessed by two independent observers. HRV was measured over time (24 h) and in the frequency domain, in the supine and sitting positions. The healthy group consisted of nine patients (11.0 years old). A value of p < 0.05 was considered statistically significant. RESULTS: The mean ejection fraction (EF) was 60% (34 to 71%). The Kappa coefficient for ECG measurements ranged from 0.64 to 1.00. An increase in the R/S ratio in V1 was observed in 25.9% of the subjects, pathological Q wave in 29.6%, and fragmented QRS in 22.2% in inferior/high lateral regions, with a negative correlation with EF (p = 0.006). There was low HRV, without the influence of any variable, including treatment. With the change in position, there was an increase in HR (p = 0.004), but there was no change in HRV. The LF/HF ratio was 2.7 in the DMD group and 0.7 in the control group (p = 0.002). CONCLUSIONS: In DMD subjects, prominent R waves in V1 and changes in the inferior/high lateral regions occurred in almost 30% of the cases. Lower vagal tone was observed without the influence of the variables age, ejection fraction, QT dispersion, and treatment. Despite the increase in HR, there was no adequate HRV response to the change in position.

FUNDAMENTO: Distrofia Muscular de Duchenne (DMD) é uma doença neuromuscular hereditária rara. O acometimento cardíaco inicial pode ser assintomático. Portanto, a avaliação por métodos não invasivos pode auxiliar sua abordagem. OBJETIVOS: Analisar o eletrocardiograma (ECG) e a variabilidade da frequência cardíaca (VFC) do grupo com DMD, e comparar com a do grupo controle pareado por idade. MÉTODOS: Estudo prospectivo com 27 pacientes masculinos com DMD (idade de 11,9 anos) que foram submetidos à avaliação clínica, ECG, ecocardiograma e Holter. ECG (aumento de 200%) foi avaliado por dois observadores independentes. VFC foi feita no domínio do tempo (24 h) e da frequência na posição supina e sentada. O grupo saudável foi de nove pacientes (11,0 anos). Um valor de p < 0,05 foi considerado estatisticamente significante. RESULTADOS: A média da fração de ejeção (FE) foi de 60% (34 a 71%). O coeficiente de Kappa para as medidas do ECG variou de 0,64 a 1,00. Foram verificados aumento da relação R/S em V1 em 25,9%, onda Q patológica em 29,6% e QRS fragmentado em 22,2% em regiões inferior/lateral alta, este com correlação negativa com FE (p = 0,006). Houve baixa VFC, sem influência de nenhuma variável, inclusive tratamento. Com a mudança da posição, houve aumento da FC (p = 0,004), porém não houve alteração da VFC. A relação LF/HF foi de 2,7 na DMD e de 0,7 no controle (p = 0,002). CONCLUSÕES: Nos participantes com DMD, as ondas R proeminentes em V1 e alterações nas regiões inferior/lateral alta ocorreram em quase 30% dos casos. Houve menor tônus vagal sem influência das variáveis idade, fração de ejeção, dispersão do QT e tratamento. Apesar do aumento da FC, não houve resposta adequada da VFC com a mudança de posição.

Is larger eccentric utilization ratio associated with poorer rate of force development in squat jump? An exploratory study.

This exploratory study examines the relationship between the eccentric utilization ratio (EUR) and the rate of force development (RFD) in squat jumps (SJ). EUR, a key metric in sports science, compares performance in countermovement jumps (CMJ) and squat jumps (SJ). The study hypothesizes that a higher EUR is associated with a poorer RFD in SJ. Basketball and soccer players, long-distance runners, alongside physical education students (209 men; age: 23.2 ± 4.95 years and 104 women; age: 22.7 ± 4.42 years) participated. The EUR was calculated from jump height, peak force and peak power. The results indicated a small to moderate but significant negative correlation between EUR based on peak force or peak power and RFD in SJ (r = -.41 and -.27), suggesting that a higher EUR might be linked to a diminished ability to rapidly develop force in SJ. Thus, a higher EUR may not indicate superior athletic performance.

An affordable and immersive virtual reality-based exercise therapy in forward head posture.

Forward Head Posture (FHP) is one of the most commonly occurring musculoskeletal abnormalities. Despite exercise therapy being an effective approach for FHP treatment, it can be long, monotonous, and tedious. Virtual reality (VR) can be used as an innovative solution to address these challenges. We designed an affordable and immersive VR-based exercise therapy (VRET) system for FHP correction. The VRET contents (i.e., exercises and VR scenarios) were determined by physiotherapists and game designers at the focus group meetings. Hardware requirements include a VR box, smartphone, and sensors (i.e., a smartphone accelerometer and an affordable Inertial Measurement Unit (IMU)) to measure head motions and transfer them via Wi-Fi to the VRET system. The IMU was designed using the MPU6050, Arduino Nano, and ESP8266-01S. Gwet's AC1, Game Experience Questionnaires (GEQ), and System Usability Scale (SUS) were used to measure intra-rater reliability, user experience, and system usability, respectively. The determined exercises, including Capital Flexion-Extension and Chin Tuck, were designed in the form of a shooting game. A physiotherapist and twenty-one FHP individuals took part in evaluating the system. High precision was obtained for the designed IMU (i.e., pitch and roll < 0.1° and yaw < 1.3 °). Gwet's AC1 and SUS results showed very good intra-rater reliability (coefficient = 0.892) and excellent usability (score = 87.14), respectively. According to the mean scores of the GEQ, participants were confident about competence, immersion, flow, and positive affect components. The development of low-cost VRET systems for FHP correction is a step towards facilitating rehabilitation challenges by providing positive experiences for users as well as helping them perform therapeutic exercises correctly.

Influence of age on the relation between body position and noninvasively acquired intracranial pulse waves.

The capacitive measurement of the head's dielectric properties has been recently proposed as a noninvasive method for deriving surrogates of craniospinal compliance (CC), a parameter used in the evaluation of space-occupying neurological disorders. With the higher prevalence of such disorders in the older compared to the younger population, data on the head's dielectric properties of older healthy individuals would be of particularly high value before assessing pathologic changes. However, so far only measurements on young volunteers (< 30 years) were reported. In the present study, we have investigated the capacitively obtained electric signal known as W in older healthy individuals. Thirteen healthy subjects aged > 60 years were included in the study. W was acquired in the resting state (supine horizontal position), and during head-up and head-down tilting. AMP, the peak-to-valley amplitude of W related to cardiac action, was extracted from W. AMP was higher in this older cohort compared to the previously investigated younger one (0°: 5965 ± 1677 arbitrary units (au)). During head-up tilting, AMP decreased (+ 60°: 4446 ± 1620 au, P < 0.001), whereas it increased during head-down tilting (- 30°: 7600 ± 2123 au, P < 0.001), as also observed in the younger cohort. Our observation that AMP, a metric potentially reflective of CC, is higher in the older compared to the younger cohort aligns with the expected decrease of CC with age. Furthermore, the robustness of AMP is reinforced by the consistent relative changes observed during tilt testing in both cohorts.

The modified Lyon's position: an alternative approach to robotic thymectomy.

The conventional supine position for robotic thymectomy may present challenges in accessing the lower thymic horns, particularly in cases requiring extensive resection of mediastinal fat. To address this issue, the authors advocate for a lateral patient position during the procedure, emphasizing optimized access to the thymic horns and improved procedural efficacy. The lateral approach involves specific trocar placements and port arrangements to minimize conflicts between instruments. This report proposes an innovative approach to robotic thymectomy for patients diagnosed with thymoma or thymic hyperplasia associated with myasthenia gravis.

Human estimates of descending objects' motion are more accurate than those of ascending objects regardless of gravity information.

Humans can accurately estimate and track object motion, even if it accelerates. Research shows that humans exhibit superior estimation and tracking performance for descending (falling) than ascending (rising) objects. Previous studies presented ascending and descending targets along the gravitational and body axes in an upright posture. Thus, it is unclear whether humans rely on congruent information between the direction of the target motion and gravity or the direction of the target motion and longitudinal body axes. Two experiments were conducted to explore these possibilities. In Experiment 1, participants estimated the arrival time at a goal for both upward and downward motion of targets along the longitudinal body axis in the upright (both axes of target motion and gravity congruent) and supine (both axes incongruent) postures. In Experiment 2, smooth pursuit eye movements were assessed while tracking both targets in the same postures. Arrival time estimation and smooth pursuit eye movement performance were consistently more accurate for downward target motion than for upward motion, irrespective of posture. These findings suggest that the visual experience of seeing an object moving along an observer's leg side in everyday life may influence the ability to accurately estimate and track the descending object's motion.

Craniocervical posture in patients with skeletal malocclusion and its correlation with craniofacial morphology during different growth periods.

The association between craniocervical posture and craniofacial structures in the various sagittal skeletal malocclusion during different growth stages has been the focus of intense interest in fields of orthodontics, but it has not been conclusively demonstrated. Thus, this study aimed to investigate the association between craniofacial morphology and craniocervical posture in patients with sagittal skeletal malocclusion during different growth periods. A total of 150 from a large pool of cephalograms qualified for the inclusion and exclusion were evaluated and classified into three groups according to the Cervical Vertebral Maturation (CVM) by examining the morphological modifications of the second through fourth cervical vertebrae, each group consisted of 50 cephalograms. In each growth period, for the comparison of head and cervical posture differences among various skeletal classes, the radiographs were further subdivided into skeletal Class I (0° < ANB < 5°, n = 16), skeletal Class II (ANB ≥ 5°, n = 18), and skeletal Class III (0° ≤ ANB, n = 16) on the basis of their ANB angle. There was no significant difference in gender (P > 0.05). Some variables were found to be significant during pubertal growth and later in patients with sagittal skeletal malocclusion (P < 0.05). Most indicators describing craniocervical posture were largest in skeletal Class II and smallest in skeletal Class III during the peak growth periods and later. Cervical inclination variables were greater in skeletal Class III than in skeletal Class II. Variables of craniofacial morphology and craniocervical posture are more correlated during the pubertal growth period and later in patients with sagittal skeletal malocclusion. A tendency is an indication of the close interrelationship that a more extended head was in skeletal Class II while a flexed head was in skeletal Class III. Nevertheless, with the considerations of some limitations involved in this study, further longitudinal studies with large samples are required to elucidate the relationship clearly.

The Impact of Forward Head Posture on Neck and Ankle Joint Position Sense: A Cross-Sectional Study.

BACKGROUND: Forward head posture (FHP) decreases the neck position sense and creates tension in the neck muscles, which inversely affects the mechanics of the distal joints through body myofascia. Thus, this study investigated the effects of FHP on neck and ankle joint position sense, and conducted a comparison between the joint position sense of the right and left ankle. METHODS: Fifty-seven subjects were assigned according to the craniovertebral angle (CVA) into the FHP group (CVA <49°; n = 27) or the control group (CVA >49°; n = 30). Head and ankle joint repositioning accuracy was measured by using a cervical range-of-motion device and an isokinetic dynamometer, respectively. RESULTS: There was a significant increase in the joint position error (JPE) of the cervical flexion, extension, and right and left side bending motions of the FHP group compared to the control group (P < .05). There were significant increases in the JPE of the right and left ankle dorsiflexion and plantarflexion of the FHP group compared to the healthy group (P < .05). Moreover, the JPE of the right ankle dorsiflexion and plantarflexion of the FHP group were significantly higher than the left ankle (P < .05). CONCLUSIONS: The FHP decreases the position sense of cervical flexion, extension, and right and left side bending motions, and the plantarflexion and dorsiflexion of both ankle joints, especially the right ankle joint.

Relationships of Sagittal Skeletal Discrepancy, Natural Head Position, and Craniocervical Posture in Pakistani Children.

OBJECTIVE: To assess the natural head position (NHP), mean sagittal skeletal discrepancy, and craniocervical posture in children presenting to tertiary care hospital. STUDY DESIGN: Observational study. Place and Duration of the Study: Department of Orthodontics, Karachi Medical and Dental College, Karachi, Pakistan, from January to April 2022. METHODOLOGY: A total of 121 participants, of either gender aged 11 to 15 years, were selected for this study. The mean age of the participants was 13.4 ± 1.2 years, and their average Frankfort mandibular plane angles (FH/ML) were recorded. Data collection took place following approval from the Ethics Review Board (ERB), and verbal informed consent was obtained from all participants. Cephalometric radiographs were taken in the natural head position (NHP) for all 121 participants. Based on their ANB angles, the participants were categorised into skeletal classes I, II, and III. The study assessed and compared variables such as head posture, craniocervical posture, and sagittal craniofacial morphology. RESULTS: The study included a sample of 121 children with a mean age of 13.4 ± 1.2 years. Among the participants, 58% were males, while 42% were females. Based on their ANB angles, participants were classified into skeletal classes I (n=44), II (n=73), and III (n=4). The correlation analysis between craniofacial posture, natural head position, and sagittal skeletal classes (I, II, and III) did not reveal any statistically significant results. Moreover, within each skeletal class, there were no significant differences observed in craniocervical posture between males and females when considering demographic variables. CONCLUSION: This study indicates that there is no discernible difference in the craniocervical posture of young Pakistani children aged 11 to 15 years, regardless of gender, in relation to skeletal relationships in classes I, II, and III. These findings suggest that sagittal skeletal discrepancies may not significantly impact craniocervical posture in this particular age group. KEY WORDS: Craniocervical posture, Sagittal discrepancy, Natural head position.

Automatic diagnosis of depression based on attention mechanism and feature pyramid model.

Currently, most diagnoses of depression are evaluated by medical professionals, with the results of these evaluations influenced by the subjective judgment of physicians. Physiological studies have shown that depressed patients display facial movements, head posture, and gaze direction disorders. To accurately diagnose the degree of depression of patients, this paper proposes a comprehensive framework, Cross-Channel Attentional Depression Detection Network, which can automatically diagnose the degree of depression of patients by inputting information from the facial images of depressed patients. Specifically, the comprehensive framework is composed of three main modules: (1) Face key point detection and cropping for video images based on Multi-Task Convolutional Neural Network. (2) The improved Feature Pyramid Networks model can fuse shallow features and deep features in video images and reduce the loss of miniscule features. (3) A proposed Cross-Channel Attention Convolutional Neural Network can enhance the interaction between tensor channel layers. Compared to other methods for automatic depression identification, a superior method was obtained by conducting extensive experiments on the depression dataset AVEC 2014, where the Root Mean Square Error and the Mean Absolute Error were 8.65 and 6.66, respectively.

The Impact of Postures and Moving Directions in Fire Evacuation in a Low-Visibility Environment.

Walking speed is a significant aspect of evacuation efficiency, and this speed varies during fire emergencies due to individual physical abilities. However, in evacuations, it is not always possible to keep an upright posture, hence atypical postures, such as stoop walking or crawling, may be required for survival. In this study, a novel 3D passive vision-aided inertial system (3D PVINS) for indoor positioning was used to track the movement of 20 volunteers during an evacuation in a low visibility environment. Participants' walking speeds using trunk flexion, trunk-knee flexion, and upright postures were measured. The investigations were carried out under emergency and non-emergency scenarios in vertical and horizontal directions, respectively. Results show that different moving directions led to a roughly 43.90% speed reduction, while posture accounted for over 17%. Gender, one of the key categories in evacuation models, accounted for less than 10% of the differences in speed. The speeds of participants under emergency scenarios when compared to non-emergency scenarios was also found to increase by 53.92-60% when moving in the horizontal direction, and by about 48.28-50% when moving in the vertical direction and descending downstairs. Our results also support the social force theory of the warming-up period, as well as the effect of panic on the facilitating occupants' moving speed.

Joint knee loads during squat with constant or variable resistance in males. A clinical trial.

BACKGROUND: In the squat movement, the use of constant resistance (CR) generates greater compression and shear forces close to 90° of knee flexion, increasing joint overload. However, when used variable resistance (VR) there is no consensus about the effect of knee joint load. The aim of this study was to compare knee torques using constant or variable resistance during the squat exercise. METHODS: Twenty-one healthy male subjects (mean age, 24 [SD, 3] years; height, 1.76 [SD, 0.04] m), who practice squats during strength training routine. Were simultaneously record data from the platform force and tridimensional kinematic to obtain torques around knee. 15 repetitions were performed up to maximum knee flexion with the use of variable (RV) or constant (CR) resistance in a single session. RESULTS: Significant differences regarding the angles only in the sagittal plane at the end of the ascending phase of the squat, with less knee extension in the VR condition. In the sagittal and frontal planes, lower values of extensor and abductor torque were found in the VR condition at the angles of greater knee flexion. CONCLUSION: The use of variable resistance compared to constant resistance seems to be an alternative to be considered when the objective is to minimize the internal loads on the knee joint in exercises such as the squat in amplitudes of greater flexion. This study indicated that VR helps subjects who are learning the squat movement, enabling the application of this knowledge in physical therapy or physical training clinics.

Lower-Limb Myoelectric Calibration Postures for Transtibial Prostheses.

The use of an agonist-antagonist muscle pair for myoelectric control of a transtibial prosthesis requires normalizing the myoelectric signals and identifying their co-contraction signature. Extensive literature has explored the relationship between body posture and lower-limb muscle activation level using surface electromyography (EMG), but it is unknown how these relationships hold after amputation. Using a virtual tracking task, this study compares the effect of three different calibration postures (seated, standing, dynamic) on user tracking ability while in two tracking postures (seated, standing) for 18 able-bodied (AB) subjects and 9 subjects with transtibial (TT) amputation. As expected, AB subjects produced statistically significant differences in muscle activation for gastrocnemius (GAS) when seated vs. standing during calibration (p = 8.8e-4), but not for tibialis anterior (TA) (p = 0.76). TT subjects, however, showed no significant differences in GAS or TA between seated and standing (p = 0.90, 0.60 respectively). It was also determined that normalizing EMG by the global maximum signal observed (standard in biomechanic analysis) is undesirable for myoelectric control. For best general results with this framework, calibration in both seated and dynamic postures is recommended, taking the normalization information from the seated posture and the narrowest co-contraction slopes from the two.