ChatPPG

PulseLM

PPGTextDOI
PaperCode🤗 HuggingFace

Key facts

Venue
arXiv preprint

Summary

Foundation dataset + PPG–text QA benchmark (not a new PPG encoder). Aggregates 16 public PPG sources into ~1.08M 10 s / 125 Hz segments and ~2.48M closed-ended QA pairs across 12 tasks; baselines couple pretrained PPG encoders (PaPaGei / Pulse-PPG) to LoRA-adapted LLMs.

Datasets used

WESAD
PPGECGIMUTempEDA
PPG-DaLiA
PPGECGIMUTempResp
Long-term ECG and wrist PPG with annotated AF episodes (AFPPGECG)
PPGECGIMU
MIMIC PERform
PPGECGRespABP

Source paper

PulseLM: A Foundation Dataset and Benchmark for PPG-Text Learning