PAMAP2 dataset preprocessed v0.3.0

# Processed PAMAP2 dataset This dataset is based on the [PAMAP2 Dataset for Physical Activity Monitoring](https://archive.ics.uci.edu/ml/datasets/PAMAP2+Physical+Activity+Monitoring). Compared to v0.2.0, this preprocessed dataset contains fewer activities. It only includes: lying, sitting, standing, walking, cycling, vaccuum_cleaning and ironing The data is processed with the code from [this script]https://github.com/NLeSC/mcfly-tutorial/blob/master/utils/tutorial_pamap2.py), with the following function call: ```python columns_to_use = ['hand_acc_16g_x', 'hand_acc_16g_y', 'hand_acc_16g_z', 'ankle_acc_16g_x', 'ankle_acc_16g_y', 'ankle_acc_16g_z', 'chest_acc_16g_x', 'chest_acc_16g_y', 'chest_acc_16g_z'] exclude_activities = [5, 7, 9, 10, 11, 12, 13, 18, 19, 20, 24, 0] outputpath = tutorial_pamap2.fetch_and_preprocess(directory_to_extract_to,columns_to_use, exclude_activities=exclude_activities, val_test_size=(100, 1000)) ``` ## References A. Reiss and D. Stricker. Introducing a New Benchmarked Dataset for Activity Monitoring. The 16th IEEE International Symposium on Wearable Computers (ISWC), 2012.# 预处理后的PAMAP2数据集 本数据集基于[PAMAP2人体活动监测数据集（PAMAP2 Dataset for Physical Activity Monitoring）](https://archive.ics.uci.edu/ml/datasets/PAMAP2+Physical+Activity+Monitoring)。相较于v0.2.0版本，此次预处理后的数据集活动类别有所精简，仅包含以下七类：躺卧、坐姿、站姿、行走、骑行、真空吸尘与熨烫。 本数据集的预处理代码源自[该脚本](https://github.com/NLeSC/mcfly-tutorial/blob/master/utils/tutorial_pamap2.py)，具体函数调用代码如下： python columns_to_use = ['hand_acc_16g_x', 'hand_acc_16g_y', 'hand_acc_16g_z', 'ankle_acc_16g_x', 'ankle_acc_16g_y', 'ankle_acc_16g_z', 'chest_acc_16g_x', 'chest_acc_16g_y', 'chest_acc_16g_z'] exclude_activities = [5, 7, 9, 10, 11, 12, 13, 18, 19, 20, 24, 0] outputpath = tutorial_pamap2.fetch_and_preprocess(directory_to_extract_to,columns_to_use, exclude_activities=exclude_activities, val_test_size=(100, 1000)) ## 参考文献 A. Reiss与D. Stricker. 面向活动监测的新型基准数据集. 第16届IEEE国际可穿戴计算机研讨会（ISWC）, 2012.

搜集汇总

背景与挑战

背景概述

PAMAP2 dataset preprocessed v0.3.0是一个预处理过的物理活动监测数据集，包含7种特定活动（躺、坐、站、走、骑自行车、吸尘和熨烫）的传感器数据，主要来自手、脚踝和胸部的加速度计。该数据集基于PAMAP2原始数据集，通过特定Python脚本进行预处理，排除了其他活动类型。