NetherlandsForensicInstitute/NFI_FARED_IMU

NFI_FARED数据集是荷兰法医研究所发布的法医活动识别数据集，作为论文《Hi-OSCAR: Hierarchical Open-set Classifier for Human Activity Recognition》的一部分。该数据集包含两种形式的数据：来自佩戴在受试者身上的iPhone的数字痕迹和来自佩戴在身体上的惯性测量单元（IMU）的原始传感器信号。此数据集和README文件涉及IMU数据。数字痕迹数据可在另一链接获取。NFI_FARED包含来自14名参与者（8名男性，6名女性，年龄26.6±8.8岁）的加速度计、陀螺仪和气压数据。参与者佩戴了两个IMU设备，一个在主导手腕，另一个在背部。数据存储在各自的文件夹中，CSV文件包含实际的传感器数据，文件命名遵循特定约定。CSV文件包含17列，详细记录了传感器读数和活动标签。活动标签包括站立、坐、行走、跑步等多种活动。未标记的活动来自记录会话中未跟踪的时刻。部分参与者未能完成全部实验，因此他们的数据由其他参与者补充。

The NFI_FARED dataset is a Forensic Activity Recognition Dataset published by the Netherlands Forensic Institute, as part of the paper Hi-OSCAR: Hierarchical Open-set Classifier for Human Activity Recognition. It includes two forms of data: Digital Traces from iPhones worn on the subjects bodies and raw sensor signals from body-worn Inertial Measurement Units (IMUs). This dataset and README refer to the IMU data. The Digital Trace data is available separately. NFI_FARED contains accelerometer, gyroscope, and air pressure data from 14 participants (8 male, 6 female, aged 26.6 ± 8.8 years). Two IMU devices were worn, one on the dominant wrist and the other on the back. Data is stored in respective folders, with CSV files containing the actual sensor data following a specific naming convention. The CSV files contain 17 columns detailing sensor readings and activity labels. Activity labels include standing, sitting, walking, running, and more. Rows labeled no activity are from untracked moments in the recording sessions. Some subjects did not complete all experiments, so their data was supplemented by other participants.