Fig 1.
High level view of our evaluation pipeline showing processing steps from raw sensor data sampling to training, testing, and assessing MLAs.
Fig 2.
Sensor data are translated from the device coordinate system to Earth’s, in order to achieve device position independence.
Table 1.
MLAs configurations.
Fig 3.
Time window composed of nf one-second frames which group raw sensor data samples.
The time window slides in 1 frame increments as time passes. f0 is the frame of the current second, f−1 is the frame of the previous second, and so forth down to f−i, where i = nf − 1.
Fig 4.
Attribute vector summarizing a sliding time window ofnf frames, i = nf − 1.
Fig 5.
Aggressive lane change event data captured by the four sensors used in this evaluation.
Table 2.
Driving event types and number of samples.
Fig 6.
Top 5 best AUC assemblies grouped by driving event type as the result of 15 MLA train/test executions with different random seeds.
Values closer to 1.0 are better. Driving events are on the left-hand side and assemblies are on the right-hand side. Assemblies with the best mean AUC are closer to the bottom.