Back to results
US 11,348,037 B2Granted
Machine learning-based read channel data detection
AssigneeWestern Digital Technologies, Inc.
InventorsMichael Alex, Xinzhi Xing
Life of this patent
Estimating the term…
Abstract
Technology for improved data detection using machine learning may include a method in which an analog read signal comprising data read from a non-transitory storage medium of the data storage device is received. The analog read signal is processed into a plurality of digital samples. A digital sample from the plurality of digital samples is classified into a category from a plurality of categories using a machine learning algorithm for at least some of the plurality of digital samples. The plurality of digital samples is then decoded based on at least some of the predicted categories.
Claims20
A data storage device, comprising:
- a non-transitory storage medium;
- and
- control circuitry comprising:
- an analog to digital converter (ADC) configured to:
- receive an analog read signal from the non-transitory storage medium;
- and
- convert the analog read signal into a plurality of digital samples;
- a machine learning detector coupled to the ADC and configured to:
- receive the plurality of digital samples from the ADC;
- apply at least one trained machine learning classifier to the plurality of digital sample;
- and
- detect, based on the at least one trained machine learning classifier, bit values for the plurality of digital samples;
- and
- a decoder configured to decode, based on at least some of the detected bit values, the plurality of digital samples to reveal previously encoded data.
11 more elements
A method, comprising:
- receiving, by an analog to digital converter (ADC), an analog read signal from a non-transitory storage medium;
- converting, by the ADC, the analog read signal into a plurality of digital samples;
- receiving, by a machine learning detector coupled to the ADC, the plurality of digital samples from the ADC;
- applying, by the machine learning detector, at least one trained machine learning classifier to the plurality of digital sample;
- detecting, by the machine learning detector and based on the at least one trained machine learning classifier, bit values for the plurality of digital samples;
- and
- decoding, by a decoder and based on at least some of the detected bit values, the plurality of digital samples to reveal previously encoded data.
4 more elements
A data storage device, comprising:
- a non-transitory storage medium;
- and
- control circuitry comprising:
- an analog to digital converter (ADC) configured to:
- receive an analog read signal from the non-transitory storage medium;
- and
- convert the analog read signal into a plurality of digital samples;
- a machine learning detector coupled to the ADC and configured to:
- receive the plurality of digital samples from the ADC;
- apply at least one trained machine learning classifier to the plurality of digital sample;
- and
- detect, based on the at least one trained machine learning classifier, bit probability values for the plurality of digital samples;
- and
- a comparator configured to determine, based on at least some of the bit probability values, previously stored data.
11 more elements
A method, comprising:
- receiving, by an analog to digital converter (ADC), an analog read signal from a non-transitory storage medium;
- converting, by the ADC, the analog read signal into a plurality of digital samples;
- receiving, by a machine learning detector coupled to the ADC, the plurality of digital samples from the ADC;
- applying, by the machine learning detector, at least one trained machine learning classifier to the plurality of digital sample;
- detecting, by the machine learning detector and based on the at least one trained machine learning classifier, bit probability values for the plurality of digital samples;
- and
- determining, based on at least some of the bit probability values, previously stored data.
4 more elements
A data storage device comprising:
- a non-transitory storage medium;
- means for receiving, by an analog to digital converter (ADC), an analog read signal from the non-transitory storage medium;
- means for converting, by the ADC, the analog read signal into a plurality of digital samples;
- means for receiving, by a machine learning detector coupled to the ADC, the plurality of digital samples from the ADC;
- means for applying, by the machine learning detector, at least one trained machine learning classifier to the plurality of digital sample;
- means for detecting, by the machine learning detector and based on the at least one trained machine learning classifier, bit probability values for the plurality of digital samples;
- and
- means for determining, based on at least some of the bit probability values, previously stored data.
5 more elements
Dependencies are inferred from the claim text.