Inferring hidden forcing in a biological oscillator using Kolmogorov-Arnold networks
Researchers have developed a novel method using Kolmogorov-Arnold networks to infer hidden forces driving biological systems from limited observational data. This approach was successfully applied to reconstruct the muscular forcing behind avian respiratory dynamics using only air-sac pressure measurements. The findings reveal a complex, two-phase activation pattern in expiratory muscles, validating the technique's ability to uncover latent physical structures and driving variables in partially observed dynamical systems. AI
IMPACT This research demonstrates a new data-driven method for inferring underlying physical laws and unobserved forces in complex systems, potentially applicable to various scientific domains.