The plan consists of a training phase and a deployment phase. The training phase boils down to the following steps:

1. Install Android Studio and import MyRunsDataCollector.zip.
2. Load the application on your Android phone.
3. Collect your data, for example, standing, walking, and running, and transform the data to a feature vector consisting of FFTs. Don't panic; low-level signal processing functions such as FFTs will not be written from scratch as we will use existing code to do that. The data will be saved on your phone in a file called features.arff.
4. Create and evaluate an activity recognition classifier using exported data and implement a filter for spurious activity transition removal.
5. Plug the classifier back into the mobile application.

If you don't have an Android phone, or if you want to skip all the steps related to the mobile application, just grab the collected dataset located in data/features.arff and jump directly to the Building a classifier section.