Page 106 - Read Online

Page 14 of 26 Chang et al. Soft Sci. 2026, 6, 29

APPLICATIONS OF WEARABLE MUSCLE HEALTH MONITORING IN REAL-WORLD SETTINGS
Exercise intensity and training load monitoring
Precise monitoring of exercise intensity and training load is a core link in optimizing training plans,
preventing sports injuries, and enhancing sports performance. It is also a research hotspot and practical
focus in the field of sports science. Traditional load monitoring mostly relies on macro indicators such as
external training volume (such as running volume, number of sets and number of repetitions), which is
difficult to accurately reflect the molecule-level physiological response of athletes and the stress state of their
muscles because of monitoring lag and insufficient data dimensionality. With the rapid development of
wearable sensing technology, biomechanical analysis and artificial intelligence algorithms, a real-time
monitoring system based on multi-dimensional physiological and mechanical signals has emerged. Such a
system can achieve refined and individualized assessment of exercise intensity and training load based on
detailed analyses on neuromuscular function, mechanical load and cardiopulmonary metabolism.

Strength monitoring through sEMG
Load monitoring can be carried out through muscle electrical signals to reflect the activation mode of muscle
groups and the degree of force application, which is the core physiological basis for evaluating exercise
intensity. sEMG and high-density EMG (HD-EMG) technologies, with their non-invasive and real-time
advantages, have become key means to capture neuromuscular activity signals. The form and function of
their equipment are constantly upgrading towards flexibility, high precision, and multi-dimensionality.

For instance, the clothing-grade sEMG technology integrates flexible electrodes into conductive fabric
clothing (such as forearm covers, shorts, etc.), and pairs them with miniaturized signal amplification
modules and on-board computing units to synchronously collect EMG signals from multiple muscle groups.
By analyzing the signal characteristics of target muscle groups under different weight loads, and mapping the
internal muscle load to external training volume (like sets, repetitions and speed), a training intensity range
that conforms to the individual muscle strength level of athletes can be established for “total load”
assessment. It provides precise data support for the dynamic adjustment of training load to avoid long-term
overloading of local muscle groups and reduce muscle strain risk .
[136]

The HD-EMG sleeve integrates up to 150 microelectrodes to achieve high-density and high-resolution EMG
collection from the forearm muscle groups. By using machine learning algorithms to extract and analyze the
features of EMG signals within a 100 ms time window, > 30 gesture movements can be accurately decoded
and continuous joint angle regression prediction can be achieved (prediction error of < 10°), providing a
powerful tool for analyzing the neuromuscular control mechanism underlying decomposed technical
movements. In events with extremely high requirements for movement accuracy such as throwing, hitting,
gymnastics, fencing, and racket sports, HD-EMG can depict the muscle fingerprints of athletes of different
levels (from novices to experts) or the same athlete in different states (from normal to injured and
rehabilitated). By comparing features such as the recruitment sequence of muscle groups and the distribution
of activation intensity, one can quantitatively evaluate technical movements accuracy and rehabilitation
training effects, and this lowers the risk of music-tendon system injuries .
[92]

Mechanical load and run-jump vertical stiffness monitoring
Mechanical load and running and jumping vertical stiffness (resistance of the human body against vertical
deformation upon vertical loading, termed as K ) characterize the mechanical features and elastic state of
vert
the lower limb muscle-tendon system during exercise. Their dynamic changes are closely related to exercise
performance, fatigue degree and injury risk. The popularization of wearable devices such as IMUs and smart
pressure insoles has enabled on-site and real-time monitoring of key mechanical parameters such as contact