Kolmogorov–Arnold Networks: Comparative Analysis of Polynomial Bases for ECG Time-Series Forecasting
Document Type
Article
Publication Date
Spring 5-1-2026
Abstract
This study examines four Kolmogorov-Arnold Networks (KANs) variations where B-splines were replaced with polynomials as approximation functions—Chebyshev, Hermite, and Legendre—for electrocardiogram forecasting on the MIT-BIH arrhythmia dataset. The existing architectures of KAN variants were surveyed and compared to the suggested models. In our research, all networks have a three-layer structure and are trained using different polynomial classes instead of B-splines to approximate the learnable activation functions. Our findings reveal an accuracy-efficiency trade-off: locally supported B-splines improve predictive precision, whereas globalpolynomial KANs have a better accuracy-to-cost ratio, making them appealing for resource-constrained time-series applications.
Recommended Citation
Aymen, F., Pester, A., Muttardi, M., Mostafa, N. (2026). Kolmogorov–Arnold Networks: Comparative Analysis of Polynomial Bases for ECG Time-Series Forecasting. In: Bhateja, V., Tang, J., Peer, P. (eds) AI for Knowledge Synthesis and Predictions. FICTA 2025. Smart Innovation, Systems and Technologies, vol 480. Springer, Cham. https://doi.org/10.1007/978-3-032-20121-8_23