PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Continuous lower limb biomechanics prediction via prior-informed lightweight marker-GMformer

2026-02-10
(Press-News.org)

The dynamic analysis of lower limb biomechanics is crucial for understanding gait, posture, and load distribution, which are foundational for controlling assistive robots like exoskeletons and intelligent prostheses. Traditional methods, including invasive musculoskeletal measurements, while providing precise data, are costly, intrusive, and technically complex, limiting their widespread application. To overcome these limitations, noninvasive approaches, such as musculoskeletal multibody dynamics simulations (MMDS), have been proposed. These simulations combine data from noninvasive sensors like motion capture systems and force plates to model the internal forces and moments of the body. “However, MMDS frameworks face issues related to their dependence on force plates, their high computational demand, and their limited ability to provide real-time feedback, which is essential for dynamic applications such as robot control.” said the author Hao Zhou, a researcher at Shenzhen Institutes of Advanced Technology, “Therefore, we propose a lightweight and computationally efficient deep learning model, the Marker GMformer, to address these challenges. This model integrates prior anatomical knowledge and spatiotemporal features, and can continuously predict lower limb biomechanical data in real-time.”

Marker-GMformer is a lightweight deep learning model specifically designed to predict multi-joint kinematics, joint torques, and three-dimensional ground reaction forces (GRFs) of the lower limbs from labeled trajectory data. The architecture of Marker-GMformer primarily consists of a temporal block, a spatial block, and a temporal embedding layer. The spatial block combines a Graph Convolutional Network (GCN) and a Multi-Layer Perceptron (MLP) module to extract local and global features of the lower limb anatomy. By constructing an adjacency matrix that reflects skeletal connectivity, GCN can capture spatial correlations between markers and integrate anatomical prior information. The temporal block employs an improved Transformer model to extract global temporal features from the marker coordinate time series. Through the ProbSparse self-attention mechanism, redundant computations are reduced, thereby enhancing computational efficiency and enabling the processing of longer time series data. In traditional Transformer models, time series are typically encoded by time steps, whereas in Marker-GMformer, each marker of the entire time series is treated as a separate token and embedded through a fully connected layer. This approach enhances the model's ability to extract temporal features. Simultaneously, by facilitating information flow between the spatial and temporal blocks, Marker-GMformer can effectively learn spatial-temporal dependencies, accurately predicting kinematics, dynamic variables, and ground reaction forces of the lower limbs.

The Marker-GMformer model successfully predicted lower limb multi-joint angles, joint moments, and 3D ground reaction forces (GRFs) across 13 different motion patterns. The predicted results were highly consistent with those from traditional musculoskeletal dynamics simulations (MMDS) and force plate measurements, showing excellent accuracy: The correlation coefficients for all predicted variables were greater than 0.97, indicating a strong linear relationship between the predictions and actual data. The RMSE for joint angles was 1.95°, joint moments was 0.099 N·m/kg, and for GRFs was 0.036 body weight, indicating the model's high prediction accuracy. The model had low computational complexity, enabling real-time inference suitable for applications requiring fast feedback (such as robotic control and real-time lower limb biomechanics monitoring). Marker-GMformer performed exceptionally well in various motion patterns, particularly in walking, running, and inclined walking, where the prediction accuracy was highest. However, for more dynamic movements like squatting, vertical jumping, and hopping, the accuracy of the predictions was lower, especially for some moments (like hip moments) and ground reaction forces (APGRF), where larger errors were observed.

Overall, Marker-GMformer model has significant advantages, especially in its feasibility for real-time applications. Compared to traditional musculoskeletal dynamics simulations (MMDS), Marker-GMformer only relies on marker trajectory data, eliminating the need for force plates or complex modeling platforms, greatly simplifying data collection and computation. By combining anatomical prior knowledge with spatiotemporal feature extraction, Marker-GMformer performs excellently across various motion patterns, providing high-accuracy predictions while reducing computational load, making it ideal for real-time feedback and control tasks, such as robotic control and lower limb biomechanics monitoring. “To further enhance the accuracy of Marker-GMformer, particularly its performance in dynamic tasks, we will explore enhancing the diversity of the model's dataset in the future by incorporating more data on extreme dynamic or non-periodic movements. Additionally, by incorporating physical constraints or biomechanical prior knowledge to ensure a smooth transition of torques and ground reaction forces, the physical rationality and stability of the model may be further improved.” said Hao Zhou.

Authors of the paper include Hao Zhou, Yinghu Peng, Xiaohui Li, Xueyan Lyu, Hongfei Zou, Xu Yong, Dahua Shou, Guanglin Li, and Lin Wang.

This work was supported by the National Key Research and Development Program of China [grant number 2024YFE0216500]; the Shenzhen Strategic Emerging Industry Support Plans [grant number XMHT20230115002]; the Shenzhen Sustainable Development Sci-Tech project [grant number KCXFZ20230731093501003]; the Shenzhen Science and Technology Program [grant number KQTD20210811090217009]; and the Shenzhen Science and Technology Program [grant number JCYJ20240813154923031].

The paper, “Continuous Lower Limb Biomechanics Prediction via Prior-Informed Lightweight Marker-GMformer” was published in the journal Cyborg and Bionic Systems on Jan 15, 2026, at DOI: 10.34133/cbsystems.0476.

END



ELSE PRESS RELEASES FROM THIS DATE:

Researchers discover genetic link to Barrett’s esophagus offering new hope for esophageal cancer patients

2026-02-10
CLEVELAND—Case Western Reserve University researchers have made a significant breakthrough in understanding Barrett’s esophagus, a precancerous condition that dramatically increases the risk of developing esophageal adenocarcinoma, one of the fastest-spreading and deadliest forms of cancer. In a new study, they’ve discovered how inherited genetic abnormalities increase the chance of developing Barrett's esophagus by weakening the esophageal lining, making it more susceptible to harm caused by stomach bile acid. Barrett’s esophagus occurs when the normal lining of the food pipe (the tube connecting your mouth to your stomach) ...

Endocrine Society announces inaugural Rare Endocrine Disease Fellows Series

2026-02-10
WASHINGTON—The Endocrine Society is pleased to announce its Rare Endocrine Disease (RED) Fellows Series, a program designed to equip early career physicians with the knowledge and practical skills needed to improve outcomes for people living with rare endocrine diseases. The program was developed in partnership with the National Organization for Rare Disorders (NORD) and addresses critical gaps in awareness, diagnosis and care of rare endocrine diseases. The program consists of two core components:   An ...

New AI model improves accuracy of food contamination detection

2026-02-10
Researchers have significantly enhanced an artificial intelligence tool used to rapidly detect bacterial contamination in food by eliminating misclassifications of food debris that looks like bacteria. Current methods to detect contamination of foods such as leafy greens, meat and cheese, which typically involve cultivating bacteria, often require specialized expertise and are time consuming — taking several days to a week. Luyao Ma, an assistant professor at Oregon State University, and her collaborators from the University of California, Davis, Korea University and Florida State University, have developed a deep learning-based model for rapid detection and ...

Egalitarianism among hunter-gatherers

2026-02-10
Hunter-gatherers like the Hadza of Tanzania are famous for their egalitarianism. A resource redistribution experiment conducted with the Hadza suggests many tolerate inequality—as long as it benefits themselves. Duncan N.E. Stibbard-Hawkes, Kris M. Smith, and colleagues asked 117 Hadza adults to redistribute food resources between themselves and an unspecified campmate after receiving either advantageous or disadvantageous initial allocations. Unlike many previous redistribution experiments, participants ...

AI-Powered R&D Acceleration: Insilico Medicine and CMS announce multiple collaborations in central nervous system and autoimmune diseases

2026-02-10
February 10, 2026 – Insilico Medicine (“Insilico”, 03696.HK), a clinical-stage biotechnology company driven by generative artificial intelligence (AI), China Medical System Holdings Limited (“CMS”, 867.HK/8A8.SG), an open-platform innovative company linking pharmaceutical innovation and commercialization with strong product lifecycle management capability, today announced a series of AI‑empowered drug discovery collaborations across multiple projects in the fields of central nervous system and autoimmune diseases. According to the collaboration agreement, the two ...

AI-generated arguments are persuasive, even when labeled

2026-02-10
Labeling content as AI-generated does not make it less persuasive than human-authored or unlabeled content, according to a study. Isabel O. Gallegos and colleagues conducted a survey experiment with 1,601 Americans to test whether authorship labels affect the persuasiveness of AI-generated messages about public policies. Participants viewed an AI-generated message about one of four policy issues, including geoengineering, drug importation, college athlete salaries, and social media platform liability. Participants were randomly assigned to see the message labeled as created by an expert ...

New study reveals floods are the biggest drivers of plastic pollution in rivers

2026-02-10
Plastic pollution has become a major global environmental concern as modern societies rely increasingly on plastic products. Much of this plastic waste eventually reaches the ocean, with rivers acting as the main transport routes from urban, agricultural, and other landscapes, thereby affecting the lives of marine organisms. Over time, larger plastic items break down into smaller pieces known as microplastics (less than 5 millimeters) and mesoplastics (between 5 and 25 millimeters). These particles can spread ...

Novel framework for real-time bedside heart rate variability analysis

2026-02-10
Real-time and early detection of minute changes in the functioning of the cardiovascular system is crucial for managing critically ill patients, such as newborns and older adults, and can significantly affect their outcomes. Heart rate variability (HRV) is the minute, yet normal, fluctuations between consecutive heartbeats, usually measured through the electrocardiogram (ECG). HRV is a well-established, quantitative, and noninvasive measure for assessing autonomic nervous system activity. However, despite its high value for patient monitoring ...

Dogs and cats help spread an invasive flatworm species

2026-02-10
A study published in the journal PeerJ, conducted by a researcher from the Institute of Systematics, Evolution and Biodiversity (ISYEB) at the French National Museum of Natural History, in collaboration with a researcher from James Cook University in Australia, reveals that domestic animals are involved in the transport of an invasive flatworm species in France. Terrestrial flatworms (Platyhelminthes) are invasive species that primarily spread through the transport of plants, largely driven by human activities. However, one question remained unanswered: how do these very slow-moving animals manage to colonize ...

Long COVID linked to Alzheimer’s disease mechanisms

2026-02-10
The increased size of, and lesser blood supply to, a key brain structure in patients with Long COVID tracks with known blood markers of Alzheimer’s disease and greater levels of dementia, a new study finds.  Led by NYU Langone Health researchers, the study concerns the choroid plexus (CP), a network of blood vessels lined by cells that produce cerebrospinal fluid, which cushions the brain and forms a protective barrier between the fluid and the bloodstream. The CP regulates immune system responses (inflammation) and waste clearance in the brain. Past studies show that the COVID-19 virus can damage the cells lining ...

LAST 30 PRESS RELEASES:

Endocrine Society announces inaugural Rare Endocrine Disease Fellows Program

Sensorimotor integration by targeted priming in muscles with electromyography-driven electro-vibro-feedback in robot-assisted wrist/hand rehabilitation after stroke

New dual-action compound reduces pancreatic cancer cell growth

Wastewater reveals increase in new synthetic opioids during major New Orleans events

Do cash transfers lead to traumatic injury or death?

Eva Vailionis, MS, CGC is presented the 2026 ACMG Foundation Genetic Counselor Best Abstract Award by The ACMG Foundation

Where did that raindrop come from? Tracing the movement of water molecules using isotopes

Planting tree belts on wet farmland comes with an overlooked trade-off

Continuous lower limb biomechanics prediction via prior-informed lightweight marker-GMformer

Researchers discover genetic link to Barrett’s esophagus offering new hope for esophageal cancer patients

Endocrine Society announces inaugural Rare Endocrine Disease Fellows Series

New AI model improves accuracy of food contamination detection

Egalitarianism among hunter-gatherers

AI-Powered R&D Acceleration: Insilico Medicine and CMS announce multiple collaborations in central nervous system and autoimmune diseases

AI-generated arguments are persuasive, even when labeled

New study reveals floods are the biggest drivers of plastic pollution in rivers

Novel framework for real-time bedside heart rate variability analysis

Dogs and cats help spread an invasive flatworm species

Long COVID linked to Alzheimer’s disease mechanisms

Study reveals how chills develop and support the body's defense against infection

Half of the world’s coral reefs suffered major bleaching during the 2014–2017 global heatwave

AI stethoscope can help spot ‘silent epidemic’ of heart valve disease earlier than GPs, study suggests

Researchers rebuild microscopic circadian clock that can control genes

Controlled “oxidative spark”: a surprising ally in brain repair

Football-sized fossil creature may have been one of the first land animals to eat its veggies

Study finds mindfulness enables more effective endoscopies in awake patients

Young scientists from across the UK shortlisted for largest unrestricted science prize

Bison hunters abandoned long-used site 1,100 years ago to adapt to changing climate

Parents of children with medical complexity report major challenges with at-home medical devices

The nonlinear Hall effect induced by electrochemical intercalation in MoS2 thin flake devices

[Press-News.org] Continuous lower limb biomechanics prediction via prior-informed lightweight marker-GMformer