Abstract: A time at which a failure of a noise level meter has occurred is accurately determined. The present invention relates to a noise measuring device including a noise level meter having a main microphone capable of measuring noise, and a sub microphone capable of measuring noise at the same time as the main microphone. The present invention also relates to a failure diagnosing system having the noise measuring device and a failure diagnosing device capable of diagnosing a failure of the main microphone. The present invention also relates to a failure diagnosing method for diagnosing a failure of the main microphone. In the failure diagnosing system and the method, the presence or absence of a failure of the main microphone in the noise level meter is diagnosed based on the comparison between main and sub noise data obtained by the main and sub microphones and respectively in each of a plurality of recording periods.

Abstract: Training data required for further training an AI pre-trained model to be used to identify aircraft can be effectively generated. A training data generation method includes: obtaining two data items among an appearance data item on an aircraft in an image in which a specific route has been imaged, a signal data item on radio waves emitted from the aircraft on the route, and a noise data item indicating noise from the aircraft on the route; identifying an attribute of the aircraft on the route by inputting one of the obtained two data items into a first identification model for identifying the attribute of the aircraft; and generating training data used for training a second identification model for identifying the attribute of the aircraft, by associating the other of the obtained two data items with the attribute of the aircraft on the route identified in the identification step.