2026-10-13T03:23:24Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33992962 2026-09-25T05:20:41Z category_450 portal_316 item_type_3 month_year_09_2026

Supplementary file 1_Higher-dimensional embedding of time-series data for machine learning.zip Karan Singh (576731) Pingal Pratyush Nath (22274779) Urbasi Sinha (4686715) Aninda Sinha (22274782) Knowledge Representation and Machine Learning CNN ECG image encoding orthogonal polynomials time-series embedding Introduction<p>Deep learning has revolutionized image analysis, yet most clinical biosignals, especially multi-lead electrocardiograms (ECGs), remain one-dimensional and awkward for modern vision models.</p>Methods<p>We introduce an orthogonal-polynomial imaging (OPI) framework that encodes 12-lead ECGs into a single two-dimensional image through an invertible transformation prior to coarse-graining, producing compact image representations that retain sufficient information for accurate classification. We benchmark the proposed representation against established architectures including ResNet, Transformers, and 1D temporal convolutional models on large-scale PhysioNet ECG datasets.</p>Results<p>Our results demonstrate that OPI-based image representations achieve highly competitive classification performance while preserving diagnostically relevant temporal and cross-lead information.</p>Discussion<p>The framework bridges raw multi-channel biosignals and standard image-based learning architectures without representation loss prior to coarse-graining, offering an effective, scalable, and physics-inspired representation for automated cardiac diagnostics.</p> 2026-09-25T05:20:41Z Dataset Dataset 10.3389/frai.2026.1874928.s001 https://figshare.com/articles/dataset/Supplementary_file_1_Higher-dimensional_embedding_of_time-series_data_for_machine_learning_zip/33992962 CC BY 4.0