Operating a portable electronic device to detect airplane flight events
A portable electronic device is controlled, for example to selectively activate a flight mode, based on first event data and/or second event data. The first event data is generated by operating a first model for detection of airplane flight events, AFEs, on first sensing data representing ambient pressure. The second event data is generated by operating a second model for detection of AFEs on second sensing data representing own motion or ambient sound. A control method in the portable electronic device generates training data comprising groups of time-aligned data samples from the first event data and the second sensing data, generates an updated second model by use of the training data, and replaces the second model by the updated second model. The control method facilitates adaptation of the portable electronic device to detect airplane flight events in new environments and enables improved robustness when detecting AFEs.
1. A method of controlling a portable electronic device comprising a first module for sensing ambient pressure, and a second module for sensing own motion or ambient sound, the method comprising the steps of:
obtaining first sensing data based on output from the first module;
obtaining second sensing data based on output from the second module;
generating first event data by operating, on the first sensing data, a first model configured to detect a first set of airplane flight events;
generating second event data by operating, on the second sensing data, a second model configured to detect a second set of airplane flight events; and
controlling the portable electronic device based on the first event data and/or the second event data;
said method further comprising: generating training data comprising groups of time-aligned data samples from the first event data and the second sensing data; generating an updated second model by use of the training data; and replacing the second model by the updated second model.
2. The method of claim 1 , wherein the first module comprises or is connected to a pressure sensor.
3. The method of claim 1 , wherein the second module comprises or is connected to one or more of a motion sensor, a vibration sensor, or a sound detector.
4. The method of claim 1 , wherein the first model is a rule-based model.
5. The method of claim 1 , wherein the second model is a data-driven model.
6. The method of claim 1 , wherein said generating training data comprises: generating each of the groups to include a respective set of data samples in the second sensing data, and a respective data sample in the first event data.
7. The method of claim 6 , wherein the respective set of data samples in the second sensing data is deemed to be concurrent with the respective data sample in the first event data.
8. The method of claim 1 , wherein the training data is generated to exclude data samples in the first event data that are deemed unreliable.
9. The method of claim 8 , wherein the data samples in the first event data are deemed unreliable based on at least one of: a reliability score generated by the first model for each data sample in the first event data, or a position associated with each data sample in the first event data by the portable electronic device.
10. The method of claim 1 , wherein said controlling comprises: selectively activating a flight mode of the portable electronic device.