Body Movements Research Articles

Research Advanced in Sarcastic Detection based on Deep Learning

Sarcasm detection is an important task in natural language processing (NLP), which aims to identify ironic intentions in text or discourse. Unlike conventional narratives, satire often uses descriptions that are opposite to the literal meaning to convey humor or criticism, and it is widely used in various scenarios such as social media, comment sections, and forums. Accurately detecting satire is crucial for understanding users' true intentions, while remains an open issue due to the freedom of language expression. Compared to face-to-face communication with the extra tone, facial expressions, and body movements, or an article with background and contextual information, a single satirical comment can hardly provide information for the machine to make a correct judgment, which may mislead the model to recognize the emotions contained in the comment. This article aims to introduce the role of different features in machine learning and deep learning satire detection tasks based on current research in this field. In addition, this article discusses the problems of satire detection and looks forward to its future development direction

Towards a shape-performance integrated digital twin for lumbar spine analysis

Background With significant advancement and demand for digital transformation, the digital twin has been gaining increasing attention as it is capable of establishing real-time mapping between physical space and virtual space. In this work, a digital twin solution is presented to predict the real-time biomechanics of the lumbar spine during human movement. Methods A finite element model (FEM) of the lumbar spine was firstly developed using computed tomography (CT) and constrained by the body movement which calculated by the inverse kinematics algorithm. The Gaussian process regression was utilized to train the predicted results and create the digital twin of the lumbar spine in real-time. Finally, a three-dimensional virtual reality system was developed using Unity3D to display and record the real-time biomechanics performance of the lumbar spine during body movement. Results The evaluation results presented an agreement (R 2 >0.8) between the real-time prediction from digital twin and offline FEM prediction. Conclusions This approach provides an effective method of real-time planning and warning in spine rehabilitation.

Hydrophobic PU fabric with synergistic conductive networks for boosted high sensitivity, wide linear-range wearable strain sensor.

Strain sensing fabrics are able to sense the deformation of the outside world, bringing more accurate and real-time monitoring and feedback to users. However, due to the lack of clear sensing mechanism for high sensitivity and high linearity carbon matrix composites, the preparation of high performance strain sensing fabric weaving is still a major challenge. Here, an elastic polyurethane(PU)-based conductive fabric(GCPU) with high sensitivity, high linearity and good hydrophobicity is prepared by a novel synergistic conductive network strategy. The GCPU fabric consists of graphene sheets(GS)/carbon nanotubes(CNTs) elastic conductive layer and a PU elastic substrate. GS and CNTs can be constructed into a synergistic conductive network, and the fabric is endowed with high conductivity(1.193 S m-1). Simulated equivalent circuits show that GS in the conductive network will break violently under applied strain, making the GCPU fabric extremely sensitive(gauge factor 102). CNTs are spatially distributed in GS lamellae, avoiding the phenomenon that the constructed synergistic conductive network is violently fractured under the applied strain, which leads to the decrease of linearity(0.996). SEBS was used as a dispersant and binder to uniformly disperse and closely bond GS and CNTs into PU fabrics. In addition, the hydrophobicity of SEBS makes the GCPU fabric resistant to water environment(The contact Angle is 123°). Due to the good mechanical stability of GCPU fabric, GCPU fabric has a wide strain range(0-50%) and high cycle stability(over 1000 cycles). In practice, GCPU fabric can accurately simulate and detect the size and deformation motion of human body. Therefore, the successful construction of elastic fabrics with synergistic conductive networks provides a feasible path for the design and manufacture of wearable intelligent fabrics.

Vialess heterogeneous skin patch for multimodal monitoring and stimulation

System-level wearable electronics require to be flexible to ensure conformal contact with the skin, but they also need to integrate rigid and bulky functional components to achieve system-level functionality. As one of integration methods, folding integration offers simplified processing and enhanced functionality through rigid-soft region separation, but so far, it has mainly been applied to modality of electrical sensing and stimulation. This paper introduces a vialess heterogeneous skin patch with multi modalities that separates the soft region and strain-robust region through folded structure. Our system includes electrical and optical modalities for hemodynamic and cardiovascular monitoring, and a force-electrically driven micropump for drug delivery. Each modality is demonstrated through on-demand drug delivery, flexible waveguide-based PPG monitoring, and ECG and body movement monitoring. Wireless data transmission and real-time measurement validate the feedback operation for multi-modalities. This engineered closed-loop platform offers the possibility for broad applications, including cardiovascular monitoring and chronic disease management.

Research on Underground Track Tracking of a New Type Shaft Boring Machine

A trajectory tracking control scheme is proposed in this paper to achieve unmanned underground construction of a new type of shaft boring machine. The body motion model is constructed, and the control relationship between the driving system and the body motion is deduced. MATLAB and Simulink simulate the joint of the track tracking process in the new shaft boring machine. The actual effect of the track tracking control scheme is validated by the track tracking field test of the new shaft boring machine. The results show that the new shaft boring machine can complete various complex track tracking tasks, with the maximum position error being less than 0.005 m. The running track and excavation areas of the boring machine are observed along with the track tracking field test of the new shaft boring machine, demonstrating that the track tracking control scheme makes the new shaft boring machine realize unmanned construction and verifies the co-simulation accuracy. The PID (proportional–integral–derivative control) algorithm can complete complex trajectory tracking tasks and promote the development of unmanned construction technology.

Generating High-Fidelity Clothed Human Dynamics with Temporal Diffusion

Clothed human modeling plays a crucial role in multimedia research, with applications spanning virtual reality, gaming, and fashion design. The goal is to learn clothed human dynamics from observations and then generate humans with high-fidelity clothing details for motion animation. Despite tremendous advancements in clothing shape analysis by existing approaches, the community still faces challenges in generating convincing visual effects of cloth dynamics, maintaining temporally smooth clothing details, and handling diverse clothing patterns. To address these challenges, we introduce ClothDiffuse, a temporal diffusion model that seamlessly integrates three key components into this task: temporal dynamics modeling, iterative refinement, and diversified generation. Our approach begins by using an encoder to extract high-level temporal features from input human body motions. These features are combined with a learnable pixel-aligned garment feature, serving as prior conditions for the shape decoder. The decoder then iteratively denoise Gaussian noise to produce clothing deformations over time on the input unclothed human bodies. To ensure that the results align with observations and adhere to physical plausibility for clothing shape inference, we propose two physics-inspired loss functions that preserve the intra-frame distances and inter-frame forces of clothing points. Additionally, the stochastic nature of the denoising process allows for the generation of diverse and plausible clothing shapes. Experiments show that our approach outperforms state-of-the-art methods in chamfer distance and visual effects, particularly for loose clothing such as dresses and skirts. Furthermore, our approach effectively adapts to out-of-domain clothing types and generate realistic clothes dynamics.

Precision Quaternion Estimation with Partially Norm-Constrained Unscented Kalman Filtering

Abstract Accurate orientation estimation is a key challenge in dynamics and control, particularly for rigid body motion. Quaternions are commonly used to represent rotations due to their computational efficiency, but they must always maintain a unit norm to function correctly. If this constraint is not enforced properly, it can lead to significant errors in orientation estimation. This paper proposes an unscented Kalman filter that ensures the quaternion parameters, a subvector within the state vector, adhere to the unit norm constraint. The proposed method provides a closed-form solution without dividing the state vector into constrained and unconstrained vectors. In simulation studies under high noise conditions, the filter demonstrates significantly improved performance compared to standard unscented and pseudo-unscented Kalman filters, enhancing accuracy during both transient and steady-state phases. These results highlight the importance of enforcing quaternion constraints to reduce mean square error and improve convergence.

Intravenous lidocaine decreased oxygen-desaturation episodes induced by propofol-based sedation for gastrointestinal endoscopy procedures: a prospective, randomized, controlled trial

BackgroundAs a popularly used analgesic adjuvant, intravenous (IV) lidocaine could reduce the consumption of propofol in painless gastrointestinal (GI) endoscopy. However, whether IV lidocaine could affect the incidence of oxygen-desaturation episodes (ODE) during painless GI endoscopy is still unknown. Therefore, we tested the hypothesis that IV lidocaine could decrease the incidence of propofol-induced ODE and involuntary movements in patients during GI endoscopy.MethodsThree hundred twenty-two patients scheduled for GI endoscopy were randomly divided into lidocaine group and control group. After midazolam and sufentanil injection, a bolus of 1.5 mg/kg lidocaine was given and followed by continuous infusion of 4 mg/kg/h in lidocaine group, whereas the same volumes of saline solution in control group. Then, propofol was titrated to produce unconsciousness. The primary outcome was the incidence of ODE during the procedure. The secondary outcomes were the incidence of different degree of hypoxia and corresponding treatments and the involuntary body movements.ResultsA total of 300 patients were finally included in the analysis, 147 patients in lidocaine group and 153 in control group. The incidence of ODE was 22% in lidocaine group and 39% in control group (OR:0.052; 95%CI: 0.284–0.889; P = 0.018). IV lidocaine also improved the occurrence of different degree of hypoxia (P = 0.017) and needed few treatments (P = 0.028). The incidence of involuntary body movements (14% vs 26%, P = 0.013) and adverse circulatory events was decreased by IV lidocaine.ConclusionsIV lidocaine adjuvant to propofol-based sedation could reduce the incidence of oxygen-desaturation episodes and involuntary body movements, with fewer adverse circulatory events.Trial registrationChinese Clinical Trial Registry ChiCTR2100053818. Registered on 30 November 2021.

Frequency of Upper Body Muscular Demands in Contemporary and Ballet Dance Performance: A Cross Sectional Performance Analysis.

Introduction: There is currently little research relating specifically to the muscular strength and endurance requirements of the upper body such as lifts at varying heights, ground floor contact with the hands and inversions such as handstands. Enhanced understanding of muscular demands can inform training program design to build physical tolerance to meet the demand of the activity. The aim of this study was to ascertain the frequency of upper body muscular skills in contemporary and ballet dance performance. Methods: Analysis of 46 individual ballet performers (F = 23, M = 23) from 12 performances (duration 63.5 ± 44.5 minutes) and 44 individual contemporary performers (F = 21, M = 23) from 12 performances (duration 35.7 ± 4.3 minutes) was carried out. Frequency of upper body skills was recorded using Dartfish Easytag-Note and converted to mean frequency per minute of total performance and per performance by genre and by sex. Differences in frequency between genre were analyzed via Mann-Whitney U. Phase two analyzed differences between sex via Mann-Whitney U. Finally, analysis of differences between sex within dance genre was carried out via Wilcoxon signed rank test. Significance was accepted at P < .05. Results: A significant difference was apparent between ballet and contemporary dance for holding own weight (P < .05) with a greater total mean frequency within contemporary performances of 8.50 ± 9.03 compared to a total mean frequency of 1.51 ± 3.13 within ballet performances. Additionally, there was a significant difference for above shoulder assisted lift (P < .05) when comparing male dancers, with male contemporary dancers carrying out significantly more (9.82 ± 8.56) per performance than male ballet dancers (2.33 ± 4.66). A higher mean frequency of below shoulder lifts than above shoulder lifts was also noted, with the majority of above shoulder lifts remaining at eye level. Conclusion: Training programs must prepare dancers for upper body movements that consider differing biomechanical demands of a variety of lifts and inversions.

A multimodal neuroimaging study of cerebrovascular regulation: protocols and insights of combining electroencephalography, functional near-infrared spectroscopy, transcranial Doppler ultrasound, and physiological parameters

Objective. The current paper describes the creation of a simultaneous trimodal neuroimaging protocol. The authors detail their methodological design for a subsequent large-scale study, demonstrate the ability to obtain the expected physiologically induced responses across cerebrovascular domains, and describe the pitfalls experienced when developing this approach.Approach. Electroencephalography (EEG), functional near-infrared spectroscopy (fNIRS), and transcranial Doppler ultrasound (TCD) were combined to provide an assessment of neuronal activity, microvascular oxygenation, and upstream artery velocity, respectively. Real-time blood pressure, capnography, and heart rate were quantified to control for the known confounding influence of cardiorespiratory variables. The EEG-fNIRS-TCD protocol was attached to a 21 year-old male who completed neurovascular coupling/functional hyperemia (finger tapping and 'Where's Waldo/Wally?'), dynamic cerebral autoregulation (squat-stand maneuvers), and cerebrovascular reactivity tasks (end-tidal clamping during hypocapnia/hypercapnia).Main results. In a pilot participant, the Waldo task produced robust hemodynamic responses within the occipital microvasculature and the posterior cerebral artery. A ∼90% decrease in alpha band power was seen in the occipital cortical region compared between the eyes closed and eyes opened protocol, compared to the frontal, central, and parietal regions (∼80% reduction). A modest increase in motor oxygenated hemoglobin was seen during the finger tapping task, with a harmonious alpha decrease of ∼15% across all cortical regions. No change in the middle or posterior cerebral arteries were noted during finger tapping. During cerebral autoregulatory challenges, sinusoidal oscillations were produced in hemodynamics at 0.05 and 0.10 Hz, while a decrease and increase in TCD and fNIRS metrics were elicited during hypocapnia and hypercapnia protocols, respectively.Significance. All neuroimaging modalities have their inherent limitations; however, these can be minimized by employing multimodal neuroimaging approaches. This EEG-fNIRS-TCD protocol enables a comprehensive assessment of cerebrovascular regulation across the association between electrical activity and cerebral hemodynamics during tasks with a mild degree of body and/or head movement.

Smart furniture using radar technology for cardiac health monitoring

The integration of radar technology into smart furniture represents a practical approach to health monitoring, circumventing the concerns regarding user convenience and privacy often encountered by conventional smart home systems. Radar technology’s inherent non-contact methodology, privacy-preserving features, adaptability to diverse environmental conditions, and high precision characteristics collectively establish it a compelling alternative for comprehensive health monitoring within domestic environments. In this paper, we introduce a millimeter (mm)-wave radar system positioned strategically behind a seat, featuring an algorithm capable of identifying unique cardiac waveform patterns for healthy subjects. These patterns are characterized by two peaks followed by a valley in each cycle, which can be correlated to Electrocardiogram (ECG), enabling effective cardiac waveform monitoring. The provided algorithm excels in discerning variations in heart patterns, particularly in individuals with prolonged corrected QT intervals, by minimizing high frequency breathing interference and ensuring accurate pattern recognition. Additionally, this paper addresses the influence of body movements in seated individuals, conducting a comprehensive study on heart rate variability and estimation. Experiment results demonstrate a maximum interbeat intervals (IBI) error of 30 milliseconds and an average relative error of 4.8% in heart rate estimation, showcasing the efficacy of the proposed method utilizing variational mode decomposition and a multi-bin approach.

Backward swimming in elongated-bodied abyssal demersal fishes: Synaphobranchidae, Macrouridae, and Ophidiidae.

The deep-sea demersal fish fauna is characterized by a prevalence of elongated-body forms with long tapering tails. Using baited camera landers at depths of 4500-6300 m in the Pacific Ocean, we observed multiple instances of backward swimming using reverse undulation of the slender body in four species: the cutthroat eel Ilyophis robinsae, abyssal grenadier Coryphaenoides yaquinae, and cusk-eels Bassozetus sp. and Barathrites iris. Backward swimming was used as an escape or repositioning maneuver, reversing for up to seven tail beats before resuming forward swimming in a new direction. The eel I. robinsae reversed with a swimming wave frequency of 0.51-0.95 Hz, wavelength 0.6-0.75 of the body length (L), and large amplitude movements of the head from side to side. C. yaquinae reversed relatively slowly at 0.21-0.52 Hz and wavelength 0.5-0.7 L aided by propulsive movements of the pectoral fins and minimal lateral movement of the head. The ophidiids also used reversed propulsive body waves augmented by paddling with the pectoral fins but with some lateral movement of the head. Pectoral-fin movements in all species were in synchrony with the body movements. The elongated-body form enables backward swimming by reversal of the anguilliform propulsive wave and has the advantage that the fish automatically returns to safety along the path recently traveled. This maneuverability conferred by an elongated body may be a significant factor in selection for body shape in deep-sea fishes.

A flexible wearable sensor based on the multiple interaction and synergistic effect of the hydrogel components with anti-freezing, low swelling for human motion detection and underwater communication.

To meet the increasing demand for wearable sensor in special environment such as low temperature or underwater, a multifunctional ionic conducting hydrogel (Gel/PSAA-Al3+ hydrogel) with anti-freezing and low swelling for human motion detection and underwater communication was prepared using gelatin (Gel), [2-(methacryloyloxy) ethyl] dimethyl-(3-sulfopropyl) ammonium hydroxide (SBMA), acrylamide (AAm), acrylic acid (AAc), and AlCl3. Due to reversible hydrogen bonding, electrostatic interactions and metal coordination crosslinking between the polymer networks, the resulting Gel/PSAA-Al3+ hydrogels present low swelling property in water and exhibit large tensile properties (~1050 %), high tensile strength (~250 kPa) and excellent fatigue resistance. In addition, the hydration capacity of SBMA and AlCl3 endows the Gel/PSAA-Al3+ hydrogel fantastic anti-freezing (-31.58 °C) and water retention properties. Moreover, the electrostatic interaction between SBMA and AlCl3 due to the ion hopping mechanism endows the hydrogel with excellent ionic conductivity (6.38 mS/cm). The Gel/PSAA-Al3+ hydrogel sensors present good biocompatibility and provide a wide operating range (0 %-1050 %), fast response time (229 ms) and recovery time (248 ms), high sensitivity (GF = 1.61) and excellent stability for detecting large and small body movements. The Gel/PSAA-Al3+ hydrogel shows potential applications as a wearable sensor for communication at low temperature or underwater.

Highly Sensitive, Stretchable, and Transparent Multidirectional Wearable Strain Sensors Based on Patterned Vertical Graphene Array

Abstract Since traditional uniaxial strain sensors constructed from isotropic materials mainly focus on identifying strain amplitude without the information of strain direction, multidimensional strain sensors are critical for capturing complex movements, such as human motions. Here, we propose a highly sensitive, stretchable, and transparent multidirectional strain sensor based on patterned vertical graphene array (PVGA) synthesized by plasma-enhanced chemical vapor deposition (PECVD) followed by selective etching and transferring. The obtained PVGA/Polydimethylsiloxane (PDMS) strain sensor exhibits outstanding anisotropic strain sensing performance, including high gauge factor (GF=85.8 at 10% strain), excellent linearity (R2 = 0.99), and outstanding selectivity (|▽|=4.17). Cross-plied PVGA /PDMS strain sensors are also fabricated to demonstrate the application of detecting joint movements of the human body, as well as monitoring wrist motion for controlling a fruit-slicer game in the virtual environment. The sensor’s remarkable multi-dimensional sensing performance confirms their significant potential for diverse applications, notably in wearable electronics, such as personal health sensing, artificial intelligence, human-computer interaction, and soft robotics.

Reinforcement learning-based optimal control of wearable alarms for consistent roadway workers’ reactions to traffic hazards

Recent innovations in roadway construction include work zone intrusion alert (WZIA) systems that detect traffic hazards (e.g., speeding or intruding vehicles) and raise alarms (e.g., sounds, lights) using preset attributes (e.g., volume, duration) to warn human workers-on-foot. Designing alarms raised by wearable warning devices (e.g., smartwatch) for roadway workers remains an emerging area of transportation safety research. As roadway work zones begin to adopt these novel warning systems, issues relating to alarm attributes may persist. Different individuals’ alarm preferences and alarm fatigue towards repeated exposure to constant alarm attributes can lead to decreases in worker vigilance towards traffic hazards. Reinforcement learning (RL)-based controls can adjust alarm attributes in real-time to counteract these issues, ensuring consistent worker reactions. This study proposes an RL-based approach to train agents that control alarm attributes under different reward functions that prioritise different worker safety reactions (e.g., body movement, head turn). Results show that a reward function with equal weight for each type of reaction produces an alarm agent that ensures consistent safe worker reactions to traffic hazards. Findings also inform the future development of RL-based alarms (i.e., fine-tuning) to counteract the lack of safe worker reactions observed in real-world work zones.

A high stretchability fiber based on a synergistic three-dimensional conductive network for wide-range strain sensing.

Fiber strain sensors are promising for constructing high-performance wearable electronic devices due to their light weight, high flexibility and excellent integration. However, the conductivity of most reported fiber strain sensors is severely degraded, following deformation upon stretching, and it is still a considerable challenge to achieve both high conductivity and stretchability. Herein, we have fabricated a fiber strain sensor with high conductivity and stretchability by integrating the AgNPs into the multi-walled carbon nanotube/graphene/thermoplastic polyurethane (MWCNT/GE/TPU) fiber. The tunneling-effect dominated MWCNT/GE layer bridges separated AgNP islands, endowing conductive fibers with the integrity of conductive pathways under large strain. By means of the synergistic effect of a three-dimensional conductive network, the fiber strain sensor of AgNPs/MWCNT/GE/TPU presents not only a high conductivity of 116 S m-1, but also a wide working range of up to 600% and excellent durability (8000 stretching-releasing cycles). Remarkably, benefiting from the crack propagation on the brittle AgNP layer, the fiber strain sensor exhibits a large resistance change in the strain range of 500-600%, and thus high sensitivity with a gauge factor of 545. This fiber strain sensor can monitor human physiological signals and body movement in real-time, including pulse and joint bending, which will contribute to the development of smart textiles and next-generation wearable devices.

BehaVR: User Identification Based on VR Sensor Data

Virtual reality (VR) platforms enable a wide range of applications, however, pose unique privacy risks. In particular, VR devices are equipped with a rich set of sensors that collect personal and sensitive information (e.g., body motion, eye gaze, hand joints, and facial expression). The data from these newly available sensors can be used to uniquely identify a user, even in the absence of explicit identifiers. In this paper, we seek to understand the extent to which a user can be identified based solely on VR sensor data, within and across real-world apps from diverse genres. We consider adversaries with capabilities that range from observing APIs available within a single app (app adversary) to observing all or selected sensor measurements across multiple apps on the VR device (device adversary). To that end, we introduce BehaVR, a framework for collecting and analyzing data from all sensor groups collected by multiple apps running on a VR device. We use BehaVR to collect data from real users that interact with 20 popular real-world apps. We use that data to build machine learning models for user identification within and across apps, with features extracted from available sensor data. We show that these models can identify users with an accuracy of up to 100%, and we reveal the most important features and sensor groups, depending on the functionality of the app and the adversary. To the best of our knowledge, BehaVR is the first to analyze user identification in VR comprehensively, i.e., considering all sensor measurements available on consumer VR devices, collected by multiple real-world, as opposed to custom-made, apps.

Superelastic bamboo cellulose nanofiber based carbon aerogel with layered network microstructure for high sensitivity piezoresistive sensor.

Carbon aerogels, characterized by their high porosity and superior electrical performance, present significant potential for the development of highly sensitive pressure sensors. However, facile and cost-effective fabrication of biomass-based carbon aerogels that concurrently possess high sensitivity, high elasticity, and excellent fatigue resistance remains a formidable challenge. Herein, a piezoresistive sensor with a layered network microstructure (BCNF-rGO-CS) was successfully fabricated using bamboo nanocellulose fiber (BCNF), chitosan (CS), and graphene oxide (GO) as raw materials. The fabrication process involved directional ice-crystal growth and mild hydrothermal reduction methods where the directional ice-crystal growth technique imparted a stable network-like pore structure, while the mild hydrothermal reduction method ensured electrical conductivity without compromising the original properties of the CNF. Taking advantage of the stress transfer properties of the cross-linked network structure, BCNF-rGO-CS exhibited exceptional reversible compressibility (sustaining 80% strain), high fatigue resistance (10,000cycles at 60% strain), and high stress retention (84.6%) over long-term cycling. Furthermore, the BCNF-rGO-CS sensor exhibited notable low-pressure sensitivity, excellent response time (66/76ms), and it was capable of responding to ultra-low pressures of 10Pa. Based on these favorable characteristics, the piezoresistive sensor holds promising prospects for applications in body motion detection, health monitoring, and flexible electronic-skin.

A Case of Respiratory Retraining With Body Movement for Paradoxical Vocal Fold Movement

Paradoxical vocal fold movement (PVFM) is laryngeal motor dysfunction that is associated with many causes. This type involves involuntary vocal fold adduction during inspiration, reduction of the inspiratory flow volume curve and a perception of breathing difficulty. We present a case of 65-year-old male with gradual onset of inspiratory troubles related with PVFM, and observed pre/post transforming respiratory retraining with body movement.

Leveraging Biotensegrity for Sports Performance: An Ecological Dynamics Perspective

Traditional sports science methods typically adopt reductionist approaches, focusing on isolated components of performance. Whilst insightful, reductionist approaches often fail to capture the interconnected nature of athletic movements and environmental interactions. In recent decades, two more holistic approaches, ecological dynamics and biotensegrity, have emerged. Ecological dynamics merges nonlinear dynamical systems theory with ecological psychology, delving into the intricate interplay among an athlete’s perceptual experiences, coordination patterns, and the dynamic sporting environment, providing a contemporary framework for exploring goal-directed behaviour and human adaptability. Biotensegrity, rooted in the tensegrity model, offers a holistic view of body posture and movement, emphasising the distribution of forces and signalling through a dynamic, multi scale network of continuous tension and discontinuous compression. By synthesising biotensegrity with ecological dynamics, we can cast new light on elite sports performance, highlighting the pivotal role of perception-action coupling in athlete-environment interactions. Here, we explore the potential value of integrating these two highly compatible perspectives, with the goal of contributing towards the advancement of athletic performance across various sports disciplines. This integrative framework offers a flexible, nuanced, and individualised approach to understanding sports performance, and represents a promising and relatively uncharted territory in sports science, inviting further research and practical applications.