Density-based Neural Temporal Point Processes for Heartbeat Dynamics
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911290140655616 |
|---|---|
| author | Subramanian, Sandya Ramsundar, Bharath |
| author_facet | Subramanian, Sandya Ramsundar, Bharath |
| contents | Temporal point processes (TPPs) provide a natural mathematical framework for modeling heartbeats due to capturing underlying physiological inductive biases. In this work, we apply density-based neural TPPs to model heartbeat dynamics from 18 subjects. We adapt a goodness-of-fit framework from classical point process literature to Neural TPPs and use it to optimize hyperparameters, identify appropriate training sequence lengths to capture temporal dependencies, and demonstrate zero-shot predictive capability on heartbeat data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22096 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Density-based Neural Temporal Point Processes for Heartbeat Dynamics Subramanian, Sandya Ramsundar, Bharath Tissues and Organs Signal Processing Applications Temporal point processes (TPPs) provide a natural mathematical framework for modeling heartbeats due to capturing underlying physiological inductive biases. In this work, we apply density-based neural TPPs to model heartbeat dynamics from 18 subjects. We adapt a goodness-of-fit framework from classical point process literature to Neural TPPs and use it to optimize hyperparameters, identify appropriate training sequence lengths to capture temporal dependencies, and demonstrate zero-shot predictive capability on heartbeat data. |
| title | Density-based Neural Temporal Point Processes for Heartbeat Dynamics |
| topic | Tissues and Organs Signal Processing Applications |
| url | https://arxiv.org/abs/2511.22096 |