ShimFall&ADL: Triaxial accelerometer fall and activities of daily living detection dataset

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, [e-mail], University of the West of Scotland Prof. Naeem Ramzan, [e-mail], 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"ShimFall&ADL 数据集 V1.0（2020-06-19） 请按以下格式引用："T. Althobaiti、S. Katsigiannis、N. Ramzan. 基于三轴加速度计的跌倒与日常活动检测机器学习方法[J]. 传感器, 2020, 20(13): 3777. DOI: 10.3390/s20133777" 免责声明 尽管本团队已尽全力确保ShimFall&ADL数据集中所包含数据的准确性，但作者与苏格兰西部大学不承担任何明示或默示的保证责任，并免除所有相关责任与赔偿义务（包括但不限于过失责任），对于因本数据集数据存在任何形式、任何原因的不准确或不完整所导致的您可能产生的全部费用、损失、损害（包括间接及继发性损害）及相关成本，概不负责。 2020年，苏格兰西部大学，苏格兰，英国。 联系方式 若您对ShimFall&ADL数据集有任何疑问，请联系： Stamos Katsigiannis博士，邮箱：[e-mail]，苏格兰西部大学 Naeem Ramzan教授，邮箱：[e-mail]，苏格兰西部大学 致谢 作者感谢Md. Hasan Shahriar在其硕士研究生项目期间完成了本数据集的数据采集工作。 数据集概况 ShimFall&ADL数据集包含35名受试者的采集数据，使用佩戴于胸部的Shimmer v2三轴加速度计进行采集，采样率为50Hz。实验在苏格兰西部大学研究实验室的受控环境中开展。本次共招募35名健康青年或中年志愿者作为受试者，年龄介于19至34岁之间，体重范围为52至113kg，身高范围为1.45至1.82m。 受试者完成了以下日常活动（Activities of Daily Living, ADL）：跳跃、躺下、弯腰/拾取物品、就座、从座椅站起、行走。 受试者还完成了以下类型的跌倒动作：陡峭式（硬着陆）、前向（软着陆）、前向（硬着陆）、左侧（软着陆）、左侧（硬着陆）、右侧（软着陆）、右侧（硬着陆）、后向（软着陆）、后向（硬着陆） 数据 数据集中的每个".dat"文件对应一名受试者的一次事件，包含该事件对应的101组加速度计采样数据。文件的每一行对应一组三通道采样数据，x、y、z轴的数值以制表符" "分隔，格式示例如下： 第1行：x1 y1 z1 第2行：x2 y2 z2 …… 第N行：xN yN zN 数据集中的文件命名规则如下： 日常活动类文件：adl_<ADL活动名称>_<受试者ID>.dat 跌倒类文件：<跌倒类型>fall_<soft,hard>_<受试者ID>.dat 示例：文件"adl_standingfromchair_18.dat"对应第18名受试者完成"从座椅站起"日常活动的加速度采集数据；文件"leftfall_soft_11.dat"对应第11名受试者完成软着陆左侧跌倒的加速度采集数据。 附加信息 若需了解ShimFall&ADL数据集的更多创建细节，请参阅相关研究文献："T. Althobaiti、S. Katsigiannis、N. Ramzan. 基于三轴加速度计的跌倒与日常活动检测机器学习方法[J]. 传感器, 2020, 20(13): 3777. DOI: 10.3390/s20133777"