Physical Activity Prediction Dataset

With the increasing use of wearable devices such as smartwatches, smartphones, wristbands, and more, there is a growing need to understand user patterns and relationships between activities. To address this, we utilized the PAMAP2 Physical Activity Monitoring dataset, which originally comprised data from 18 different physical activities (such as walking, cycling, playing soccer, etc.) performed by 9 subjects wearing 3 inertial measurement units and a heart rate monitor.

This dataset is invaluable for activity recognition and intensity estimation, as well as for developing and applying algorithms for data processing, segmentation, feature extraction, and classification. In order to enhance accessibility, I have made some transformations to the original data, including the addition of a new column called "PeopleId," and merging all the datasets into one comprehensive CSV file.

By utilizing this enriched dataset, you can employ a classifier to accurately predict the specific activity the user is engaged in. This empowers developers and researchers to create innovative applications and systems that can better understand and cater to individual user needs based on their ongoing activities.