Human Activity Dataset Generation - Smartphone-Based Human Activity Recognition - page 61

4.2.3 Data Recording
MotoLog was the first Android app we developed for capturing and storing data from
the smartphone inertial sensors and it was created for carrying out the HAR experi-
ments. It also performs real-time visualization of the inertial signals (accelerometer,
gyroscope and magnetometer) on the smartphone screen. The app also allows to
visualize the experiment recordings offline. Figure 4.4 shows a screenshot of the app
showing online and offline visualization modes.
For its basic operation, the app requests access to the three inertial sensors which
periodically provide readings at a frequency equal or higher than aminimumspecified
(50Hz in our case). A periodic task is then in charge of collecting these readings from
the enabled sensors along with their timestamps. Subsequently, all the inertial data is
handled as an output stream and stored in a log file. At the same time a visualization
module performs the graphs that display the available data.
The smartphone was located on the users waist using a belt provided with a case
as it is shown in Fig. 4.5 a. The phone always faced the same direction with respect to
the case in order to maintain the same orientation of the triaxial sensors coordinate
axis (Fig. 4.5 b).
Fig. 4.4 Screenshots of the smartphone MotoLog app for the recording of the inertial data from
smartphone accelerometer, gyroscope and magnetometer. a Preview of main screen and b visual-
ization of recorded files
Fig. 4.5 SGSII casing: a the smartphone case and belt used for the experiments and b arrows show
the axis orientation of the inertial sensors