An apparatus comprising circuitry configured to: receive a plurality of signal samples, wherein at least two of the signal samples are received on different carrier frequencies or over different durations; convert the plurality of signal samples to a common data format that stores as entries the samples, a stored entry corresponding to a sample measured with a carrier frequency, a time, and a receive antenna; generate entries of the common data format that are missing due to a sample not being measured with a carrier frequency, time, and receive antenna; wherein the entries of the common data format are ranked, wherein a higher ranking entry is considered more relevant than a relatively lower ranking entry; and generate at least one positioning measurement with a machine learning model, based on the entries of the common data format and the ranking of the entries of the common data format.