Back to results
US 12,582,350 B1Granted
Respiration waveform generation for sleep stage estimation in a contactless manner using millimeter wave radar
AssigneeAmazon Technologies, Inc.
InventorsDurgaprasad Kashinath Shamain, Amit Kachroo, Morris Yuanhsiang Hsu
Life of this patent
Estimating the term…
Abstract
A computing device for monitoring a sleep stage of a user in a contactless manner includes a processor, a radar unit, and a memory. The processor executes instructions from memory to cause the computing device to perform a series of signal processing methodologies on the waveforms received from the radar unit to accurately determine the sleep stage of the user in a contactless manner.
Claims17
An electronic device comprising:
- at least one processor;
- a radar unit communicatively coupled with the at least one processor;
- and
- a memory storing instructions that, when executed by the at least one processor, cause the electronic device to:
- detect a presence of a human within an area of interest of the radar unit;
- receive a first dataset indicative of the human resting in a first position;
- receive a second dataset indicative of the human resting in the first position;
- determine that the first dataset has a higher signal-to-noise ratio value than the second dataset;
- determine that the first dataset includes a first portion that has a first polarity and a second portion that has a second polarity;
- modify the second portion to have the first polarity to generate a modified first dataset;
- determine a phase shift between the first portion and the second portion and compensate for the phase shift, wherein the first portion and second portion are consecutive portions;
- combine the first portion with the second portion to form a combined first dataset;
- and
- determine a sleep stage associated with the human based on a shape of the combined first dataset, wherein determining the sleep stage comprises comparing the shape of the combined first dataset to known waveforms that are associated with different sleep stages.
11 more elements
A method comprising:
- operating a radar unit of an electronic device;
- receiving, by a processor coupled to the radar unit, a first dataset of a human resting in a first resting position;
- receiving a second dataset of the human resting in the first resting position;
- determining the first dataset has a higher signal-to-noise ratio value than the second dataset;
- determining that the first dataset has a first segment that has a first polarity and a second segment that has a second polarity;
- modifying the second segment of the first dataset to have the first polarity;
- determining, by the processor, a phase shift between the first segment and the second segment in the first dataset, wherein the first segment and second segment are consecutive segments in the first dataset;
- compensating for the phase shift and combining the first segment with the second segment to form a combined dataset;
- and
- determining a sleep stage of the human based on a shape of the combined dataset, wherein determining the sleep stage comprises comparing the shape of the combined dataset to known waveforms that are associated with different sleep stages.
7 more elements
An electronic device comprising:
- a housing;
- a processor within the housing;
- and
- a pulsed radar unit within the housing and coupled to the processor;
- a memory operatively coupled to the processor, the memory storing instructions that, when executed by the processor, cause the electronic device to:
- receive a first dataset indicative of a human resting in a first position;
- receive a second dataset indicative of the human resting in the first position;
- determine that the first dataset has a higher signal-to-noise ratio value than the second dataset;
- determine that the first dataset includes a first portion that has a first polarity and a second portion that has a second polarity;
- modify the second portion to have the first polarity to generate a modified first dataset;
- determine a phase shift between the first portion and the second portion and compensate for the phase shift, wherein the first portion and second portion are consecutive portions;
- and
- combine the first portion with the second portion to form a combined first dataset;
- and
- determine a sleep stage associated with the human based on a shape of the combined first dataset, wherein determining the sleep stage comprises comparing the shape of the combined first dataset to known waveforms that are associated with different sleep stages.
12 more elements
Dependencies are inferred from the claim text.