Flow-TAG improves curve fitting and compresses ECG signals accurately
Flow-TAG: Flow-based conditional latent transport for accurate spline approximation and data compression
Computational Geometry
Summary
Turning messy data points into smooth, usable curves is important for engineers and designers. The authors created flow-TAG, a tool that learns how best to map curves for smoother, more accurate shapes using a special model called a generative flow with a 1D U-Net. This tool is better at handling noisy data and works on curves it hasn’t seen before. It also helps compress heart signal data efficiently while keeping distortion low, which is useful for wearable health devices.
What this means in practice
- •For computer-aided design engineers: Produce more accurate and noise-resistant spline curves for engineering and manufacturing workflows.
- •For wearable device developers: Compress ECG signals with high efficiency and low distortion to extend storage and battery life on health monitors.$Commercial implications: Enables building wearable ECG devices with better data compression, improving device performance and patient monitoring.
Authors
Roman Pavelkin, Luis A. Zavala-Mondragon, Fons van der Sommen
Abstract
Robust curve fitting is essential in computer-aided design for transforming noisy, discrete data into accurate geometric models that ensure numerical stability across engineering workflows. B-spline models have become the industry standard for this task, offering a flexible and reliable framework characterized by local control and smooth shape representation. This paper presents flow-TAG--a data-driven framework based on a generative flow model with a 1D U-Net backbone capable of mapping the geometry of a curve to the optimal parametrization for cubic B-splines. By leveraging learned geometric patterns, flow-TAG exhibits superior parameterization performance, robustness to noise in the input data, and strong generalization capability to previously unseen 2D and 3D curves drawn from distinct data distributions. Flow-TAG yields fitted curves that achieve the lower root-mean-square error (55% lower on average) and Hausdorff distance (52% lower on average) relative to state-of-the-art data-driven methods. In addition, we investigate the practical applicability of our generative framework in the compression of ECG signals for wearable devices. The proposed compression setup provides a compression ratio of 13 with the signal distortion of around 5%, which is acceptable in the field.