ShimFall&ADL dataset Version 1.0 (2020-06-19) Please cite as: "T. Althobaiti, S. Katsigiannis, N. Ramzan, Triaxial accelerometer-based Fall and Activities of Daily Life detection using machine learning, Sensors, 20(13), 3777, 2020. doi: 10.3390/s20133777" Disclaimer While every care has been taken to ensure the accuracy of the data included in the ShimFall&ADL dataset, the authors and the University of the West of Scotland do not provide any guaranties and disclaim all responsibility and all liability (including without limitation, liability in negligence) for all expenses, losses, damages (including indirect or consequential damage) and costs which you might incur as a result of the provided data being inaccurate or incomplete in any way and for any reason. 2020, University of the West of Scotland, Scotland, United Kingdom. Contact For inquiries regarding the ShimFall&ADL dataset, please contact: Dr Stamos Katsigiannis, Stamos.Katsigiannis@uws.ac.uk, University of the West of Scotland Prof. Naeem Ramzan, Naeem.Ramzan@uws.ac.uk, University of the West of Scotland Acknowledgment The authors would like to thank Md. Hasan Shahriar for the data collection under his MSc project. Dataset summary The ShimFall&ADL dataset contains recordings from 35 individuals, acquired using a chest-strapped Shimmer v2 tri-axial accelerometer, recording at a 50Hz sampling rate. Experiments were conducted in a controlled environment at a research lab in the University of the West of Scotland. Thirty five (35) healthy individuals were recruited among young or mid-aged volunteers, aged between 19 and 34 years old, having a body weight between 52 and 113 kg, and a body height between 1.45 and 1.82 m. Participants performed the following activities of daily living (ADL): Jumping Lying down Bending/picking up Sitting to a chair Standing up from a chair Walking Participants performed the following falls: Steep (hard) Front (soft) Front (hard) Left (soft) Left (hard) Right (soft) Right (hard) Back (soft) Back (hard) Data Each ".dat" file in the dataset corresponds to one event for one individual and contains 101 accelerometer samples corresponding to the event. Each row of the file corresponds to one 3-channel sample, dividing the x, y, z axes values using the "\t" character, as follows: Row 1: x1\ty1\tz1 Row 2: x2\ty2\tz2 ... Row N: xN\tyN\tzN The files within the dataset are named as follows: adl_<ADL activity>_<Participant ID>.dat <Fall Type>fall_<soft,hard>_<Participant ID>.dat For example, the file "adl_standingfromchair_18.dat" corresponds to the accelerometer recording of the 18th participant, performing the "standing up from chair" ADL. The file, "leftfall_soft_11.dat" corresponds to the accelerometer recording of the 11th participant, performing a soft left fall. Additional information For additional information regarding the creation of the ShimFall&ADL dataset, please refer to the associated publication: "T. Althobaiti, S. Katsigiannis, N. Ramzan, Triaxial accelerometer-based Fall and Activities of Daily Life detection using machine learning, Sensors, 20(13), 3777, 2020. doi: 10.3390/s20133777"