Capturing Sensor Data

Now it’s time to collect some examples of the event you are trying to detect. The slide demo project contains several pre-collected sensor data files. This means you can skip this step if you’d like, but it is suggested you capture at least one example of an event so that you understand the basic collection concepts.

  1. After opening your project, click Switch Modes and open Capture mode

../../_images/image_9.png

Configure your device

It is important you collect your sensor data with the same sensor configuration that you plan to use for your event detection sensor. Collecting data with different settings can cause unexpected results depending on various aspects like sensor orientation and sensor calibration settings. The pre-made slide demo project already has a sensor configuration called Sensor 1 that was used to create the project.

It is also important that you configure the device with the same sample rate frequency you plan on using in your final product.

  1. Click Find Devices to connect to your device over BLE

../../_images/image_10.png

Adding Events of Interest and Metadata Labels

If you haven’t already done so, make sure to read Data Collection Planning to learn about determining your events of interest and metadata. If you are using the Slide Demo project labels have already been setup.

The following these steps are optional. You can skip to Recording Raw Sensor Data below.

  1. (Optional) Click Add Labels or Add Metadata to create new event labels or metadata

../../_images/image_12.png
  1. (Optional) Right-click on the Label or Metadata to see options for editing your labels

../../_images/image_13.png
  1. (Optional) Click the + Icon to create new metadata or labels

../../_images/image_14.png

Recording Raw Sensor Data

After connecting to your device and selecting an event click Begin Recording and the DCL will start recording the live sensor stream. Once you stop recording the DCL will automatically save the file to your local hard drive and upload it to the cloud.

At this point you will want to capture several examples of the event you are trying to detect. This allows for variation in the examples, which will make a more robust sensor application.

../../_images/image_15.png