Event detection

Overall description of collected data and algorithm of identifying

Data gathered by Telematics SDK:

1. GPS (1hz)

2. Data from gyroscope, magnetometer, and accelerometer (60hz)

3. Data on whether the device is locked and the screen is on

4. All data is depersonalised

Description of event detection algorithms:

Speeding

1. At each driving moment Telematics SDK collects the user's speed

2. This data is compared with the existing speed limits provided by our partners (Location platforms: HERE, Google, etc.)

3. We detect at which points there was speeding and than combine detected time intervals into events with a minimum duration of 3 seconds and maximum gap of 5 seconds between them

4. Variables influencing the rating:

   • Event duration

   • Speed limit

   • Speed

Phone usage

1. Phone usage is detected by ML model, the main input is the data from (2) and (3)

2. We detect at which points there was phone usage and than combine detected time intervals into events with a minimum duration of 3 seconds and maximum gap of 20 seconds between them

3. Variables influencing the rating:

   • Event duration

   • Speed

Acceleration

1. User's phone reads data of item (2).

2. Our algorithms continuously adapt phone axes to calculate correct accelerations.

3. The resulting accelerations in the direction of movement are transformed into an event if the driver has accelerated >3 m/s2.

4. We detect at which points there was acceleration and than combine detected time intervals into events with a minimum duration of 0.6 seconds and maximum gap of 3 seconds between them.

5. Variables influencing the rating:

   • Event duration

   • Acceleration value

   • Speed

Braking (Deceleration)

1. User's phone reads data of item (2)

2. Our algorithms continuously adapt phone axes to calculate correct decelerations

3. The resulting decelerations in the direction of travel are transformed into an event if the driver has slowed down >3.2 m/s2.

4. We detect at which points there was deceleration and than combine detected time intervals into events with a minimum duration of 0.6 seconds and maximum gap of 3 seconds between them.

5. Variables influencing the rating:

   • Event duration

   • Deceleration value

   • Speed

Cornering

1. User's phone reads data of item (2).

2. Our algorithms continuously adapt phone axes to calculate correct accelerations.

3. The resulting accelerations in the direction of motion are transformed into an event if the perpendicular acceleration to the direction of motion >4.2 m/s2.

4. We detect at which points there was acceleration and than combine detected time intervals into events with a minimum duration of 0.6 seconds and maximum gap of 3 seconds between them.

5. Variables influencing the rating:

   • Event duration

   • Deceleration value

   • Speed