Paper Reading AI Learner

Attractor Domain Theory: A Mathematical Framework for Cardiovascular Attractor Analysis with Wearable Photoplethysmography Validation

2026-10-22 23:54:33
Timothy Oladunni, Farouk Ganiyu Adewumi

Abstract

The cardiac attractor provides a phase-space representation of cardiovascular dynamics reconstructed from scalar observations under standard delay-embedding conditions. We introduce Attractor Domain Theory (ADT), a theory in which linked mathematical transformations expose distinct properties of reconstructed dynamics: the Geometry Domain is obtained through the delay-reconstruction transformation, while Ergodic and Variational transformations act on that geometry to characterize long-horizon organization and localized finite-time deformation. Thus, ADT specifies a three-representation operator architecture for reconstructed dynamics rather than retrospectively grouping existing nonlinear features; the architecture is proposed as an operational organization, not as a uniqueness or exhaustiveness theorem. A Conditional Domain Decomposition quantifies endpoint-specific incremental information with an explicit residual, and a domain-transformation impossibility theorem establishes that a property cannot be exactly recovered when an operator maps property-distinct inputs to the same representation. Empirical evaluation includes PPG analysis across 176{,}742 segments with 18 patient-level held-out BIDMC records (AUC 0.757 [0.686--0.828]) and an independent ECG analysis of 5{,}000 PTB-XL records (AUC 0.719 [0.686--0.750]). Cross-observation transfer is property-specific: the Lyapunov exponent shows subject-level ECG--PPG agreement ($\rho=0.703$, 95\% CI [0.503, 0.836]), whereas the predicted class-wide separation of invariant and observation-coupled descriptors is not supported ($p=0.54$). These results provide empirical support for attractor-domain analysis across cardiovascular measurements while leaving cross-observation recoverability as a property-specific empirical question.

Abstract (translated)

URL

https://arxiv.org/abs/2606.22039

PDF

https://arxiv.org/pdf/2606.22039.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot