PAMAP2 体力活动监测数据集

Data Set Information: PAMAP2体力活动监测数据集包含9名佩戴3个惯性测量装置和心率监测器的受试者进行的18种不同体力活动（如步行、骑自行车、踢足球等）的数据。该数据集可用于活动识别和强度估计，同时开发和应用数据处理、分割、特征提取和分类算法。 ** Sensors ** 3 Colibri wireless inertial measurement units (IMU): - sampling frequency: 100Hz - position of the sensors: - 1 IMU over the wrist on the dominant arm - 1 IMU on the chest - 1 IMU on the dominant side's ankle HR-monitor: - sampling frequency: ~9Hz ** Data collection protocol ** Each of the subjects had to follow a protocol, containing 12 different activities. The folder a€?Protocola€? contains these recordings by subject. Furthermore, some of the subjects also performed a few optional activities. The folder a€?Optionala€? contains these recordings by subject. ** Data files ** Raw sensory data can be found in space-separated text-files (.dat), 1 data file per subject per session (protocol or optional). Missing values are indicated with NaN. One line in the data files correspond to one timestamped and labeled instance of sensory data. The data files contain 54 columns: each line consists of a timestamp, an activity label (the ground truth) and 52 attributes of raw sensory data. Attribute Information: The 54 columns in the data files are organized as follows: 1. timestamp (s) 2. activityID (see below for the mapping to the activities) 3. heart rate (bpm) 4-20. IMU hand 21-37. IMU chest 38-54. IMU ankle The IMU sensory data contains the following columns: 1. temperature (?°C) 2-4. 3D-acceleration data (ms-2), scale: ?±16g, resolution: 13-bit 5-7. 3D-acceleration data (ms-2), scale: ?±6g, resolution: 13-bit 8-10. 3D-gyroscope data (rad/s) 11-13. 3D-magnetometer data (??T) 14-17. orientation (invalid in this data collection) List of activityIDs and corresponding activities: 1 lying 2 sitting 3 standing 4 walking 5 running 6 cycling 7 Nordic walking 9 watching TV 10 computer work 11 car driving 12 ascending stairs 13 descending stairs 16 vacuum cleaning 17 ironing 18 folding laundry 19 house cleaning 20 playing soccer 24 rope jumping 0 other (transient activities) Relevant Papers: The following two publications describe the dataset and provide a baseline benchmark on various tasks of physical activity recognition and intensity estimation: [1] A. Reiss and D. Stricker. Introducing a New Benchmarked Dataset for Activity Monitoring. The 16th IEEE International Symposium on Wearable Computers (ISWC), 2012. [2] A. Reiss and D. Stricker. Creating and Benchmarking a New Dataset for Physical Activity Monitoring. The 5th Workshop on Affect and Behaviour Related Assistance (ABRA), 2012. Further information (detailed description of the protocol and the various activities, statistics of the dataset, the subjects, etc.) can be found in the documentation attached to the dataset. Please refer to the file readme.pdf. Citation Request: This dataset is freely available for academic research, there are no (legal or other) constraints on using the data for scientific purposes. We would appreciate referencing one of the below publications ([1] or [2]) if you use this dataset. If you have any questions or suggestions, please contact Attila Reiss ([firstname].[lastname]@dfki.de). Also, please let us know if you have any publications that uses this dataset. We recommend to refer to this dataset as the a€?PAMAP2 Dataseta€? or the a€?PAMAP2 Physical Activity Monitoring Dataseta. [1] A. Reiss and D. Stricker. Introducing a New Benchmarked Dataset for Activity Monitoring. The 16th IEEE International Symposium on Wearable Computers (ISWC), 2012. [2] A. Reiss and D. Stricker. Creating and Benchmarking a New Dataset for Physical Activity Monitoring. The 5th Workshop on Affect and Behaviour Related Assistance (ABRA), 2012.