Physiological Features and Inertial Features Based Dataset: PIFv3

Description of PIF v3 dataset General Information:
This dataset is acquired using wearable sensors such as ECG Sensor, GSR Sensor, IMU Sensor, ProtoCentral Pulse Express with MAX30102 and max32664, and EMG Sensor from 32 participants with different age, sex, height and weights.

Dataset File Structure:
The dataset is organised so that each subject has a folder. The folders are labelled according to participant identification number (PIDX). Each subject folder contains the following two csv files: PID_X.csv and PID_X_BPM.csv contains the information about the participant electrocardiogram, electromyography, GSR, IMU and Pulse sensor and Label performing 18 activities and Falls.

Features that are extracted in Dataset are:
Datetime, Sys, Dia, HR, Spo2, GSRRaw, Resistance, GSR (kohm), SCL, GSRRMS, GSRMAV, AccX, AccY, AccZ, GyroX, GyroY, GyroZ, Aroll, Apitch, Groll, Gpitch, Gyaw, Combroll, Combpitch, ECGRaw, AvgECG, ampECG, MAX, EMGRaw, EMGRMS, EMGMAV, EMGVAR, EMGSSI, IEMG and Activities.

This dataset also contains a file Participants.xlsx in which the information related to participants Age, Height, Weight, PID number, Gender, Medical History, State, etc are given. Elderly as well as young people performed all the 18 Activities.

Activities: Standing, Left Fall while Standing, Right Fall while Standing, Forward Fall while Standing, Sitting, Left Fall while Sitting, Right Fall while Sitting, Forward Fall while Sitting, Walking, Relaxing, Anxiety, Sad, Motivational, Funny, Pressing Stress Ball, Hand at Rest and Fist.

Videos link that are used to display the participants during data collection to acquire the different emotional values.

Emotions Links
Relaxing https://www.youtube.com/watch?v=0LJtn6yERns&list=PL585q5uwv3PEN4gc1OV9-Z3twsfBBLSbX&index=6&pp=gAQBiAQB
Anxiety https://www.youtube.com/watch?v=we2YF1J6jxg
Sad https://www.youtube.com/watch?v=PdSGSw3wI4Q
Motivational https://www.youtube.com/watch?v=mFMapVqIbuE
Funny https://www.youtube.com/watch?v=jbHaP79UMpE

Related Article: Dhaliwal MK, Sharma R, Bindra N. Analyzing Wearable Data for Diagnosing COVID-19 Using Machine Learning Model. Lect. Notes Electr. Eng., vol. 946, Springer, Singapore; 2023, p. 285–99. https://doi.org/10.1007/978-981-19-5868-7_22.