Labeled Raw PPG Signals Measured Using Wearable Sensor-kit

Listed in Datasets

By Tiberius Wehrly1, Deena Alabed1, Mireille Boutin1

Purdue University

Photoplethysmogram (PPG) signals collected from nine subjects in a still seated position, measured using Asiawill Pulse Heart Rate sensor implemented in an Arduino-based wearable sensor-kit.

Version 1.0 - published on 03 May 2019 doi:10.4231/1BE9-YY17 - cite this Archived on 03 Jun 2019

Licensed under CC0 1.0 Universal


This data is part of the Wearable Sensor-kit to Characterize Affect project. It was measured using an Arduino-based wireless, wearable device that consists of several biosensors attached to a wrist brace. It was designed and built for the purpose of measuring students' biometrics. 

The PPG signals were measured using Asiawill Pulse Heart Rate Sensor Module from the ring finger of the left hand for nine healthy participants in a still seated position. The duration of data acquisition varied between 20 to 40 minutes. 

PPG signals consist of systolic and diastolic peaks. The interval between two systolic peaks corresponds to one heart pulse. We labeled the PPG heart pulses as "good" or "bad" based on the presense of the peaks as follows: 

  • A "good" pulse is when both systolic and diastolic peaks are identifiable. The pulse is assigned to class "1"
  • A "bad" pulse is when either of the peaks is missing or if the signal is very noisy. The pulse is assigned to class "0".


Cite this work

Researchers should cite this work as follows:


The Purdue University Research Repository (PURR) is a university core research facility provided by the Purdue University Libraries, the Office of the Executive Vice President for Research and Partnerships, and Information Technology at Purdue (ITaP).