Back to results
US 11,888,672 B2Granted
Predicting decodability of received data
AssigneeNokia Technologies Oy
InventorsJakob Hoydis, Vahid Aref, Ahmed Elkelesh, Sebastian Cammerer
Life of this patent
Estimating the term…
Abstract
Different solutions for an apparatus comprising a predictor predicting decodability of received symbols are disclosed. Decoding is performed based on the prediction.
Claims18
An apparatus, comprising:
- at least one processor;
- and
- at least one memory including computer program code, the at least one memory and computer program code configured to, with the at least one processor, cause the apparatus at least to perform:
- receiving modulated symbols over a channel comprising noise variance related to information indicating at least one of signal-to-noise ratio, estimation of channel state information, or a link quality indicator;
- predicting decodability of the modulated symbols based at least upon a decodability complexity by classifying, using a machine learning model, the received modulated symbols to one class of classes indicating complexity of decoding;
- determining, based on the decodability, a decoder to use for decoding the received modulated symbols;
- and
- decoding, by the decoder, the received modulated symbols.
5 more elements
An apparatus, comprising:
- at least one processor;
- and
- at least one memory including computer program code, the at least one memory and computer program code configured to, with the at least one processor, cause the apparatus at least to perform:
- receiving modulated symbols over a channel;
- predicting decodability of the modulated symbols;
- determining, based on the decodability, a decoder to use for decoding the received modulated symbols;
- decoding, by the decoder, the received modulated symbols;
- and
- predicting decodability by determining a predicted number of rounds of decoding needed.
6 more elements
A method, comprising:
- receiving modulated symbols over a channel comprising noise variance related to information indicating at least one of signal-to-noise ratio, estimation of channel state information, or a link quality indicator;
- predicting decodability of the modulated symbols based at least upon a decodability complexity by classifying, using a machine learning model, the received modulated symbols to one class of classes indicating complexity of decoding;
- determining, based on the decodability, a decoder to use for decoding the received modulated symbols;
- and
- decoding, by the decoder, the received modulated symbols.
2 more elements
An apparatus, comprising:
- at least one processor;
- and
- at least one memory including computer program code, the at least one memory and computer program code configured to, with the at least one processor, cause the apparatus at least to perform:
- receiving modulated symbols over a channel;
- predicting decodability of the modulated symbols based at least upon a decodability complexity by classifying, using a machine learning model, the received modulated symbols to one class of classes indicating complexity of decoding;
- determining, based on the decodability, a decoder to use for decoding the received modulated symbols;
- and
- decoding, by the decoder, the received modulated symbols.
5 more elements
Dependencies are inferred from the claim text.