Stroke detection sensor
AssigneeUman Sense AB
InventorsPetter Ericson, Johan Wasselius, Karl Astrom, Rikard Berthilsson
Life of this patent
Estimating the term…
Abstract
A stroke detection apparatus for determining that a stroke is occurring or has recently occurred to a user, wherein the apparatus comprises a data processing device comprising a processor and at least one wearable sensor configured to be worn by a user and configured to transmit a movement data of the user to the data processing device. The data processing device is configured to process the movement data to determine a first probability of a user stroke over a first time period and a second probability of a user stroke over a second time period. A stroke detection signal is then generated in dependence on at least the first probability and second probability.
Claims8
A stroke detection apparatus comprising:
- at least one wearable sensor configured to be worn by a user and configured to generate a movement data of the user, the at least one wearable sensor comprising,
- a sensor package configured to measure an acceleration of the user,
- a data processing device comprising a system memory, and
- a power source configured to power the data processing device,
- the sensor package configured to transmit the movement data to the data processing device, the data processing device configured to cause the stroke detection apparatus to:
- receive the movement data,
- filter the movement data to remove acceleration resulting from gravitational force,
- process the movement data to determine a probability of a user stroke, the probability indicates a percentage chance of stroke occurrence, and
- store the movement data on the system memory at a fidelity dependent on the probability of the user stroke,
- wherein the fidelity of the stored movement data comprises at least one of a sample rate, a sample size, or a bit rate of the movement data,
- wherein when the probability of the user stroke is determined to be below a first probability threshold, the stroke detection apparatus is further configured to
- operate in a first mode where the movement data is stored at a first fidelity,
- wherein when the probability of the user stroke is determined to be above the first probability threshold, the stroke detection apparatus is configured to
- operate in a second mode where the movement data is stored at a second fidelity,
- wherein the first probability threshold is a determined percentage chance of stroke occurrence, and
- wherein the second fidelity is higher than the first fidelity, to reduce power consumption from the power source in the first mode.
A method for generating a stroke detection signal comprising:
- generating, using at least one wearable sensor device configured to be worn by a user, a movement data of the user;
- transmitting the movement data to a processing device being powered by a power source;
- receiving the movement data at the processing device;
- filtering the movement data to remove acceleration resulting from gravitational force;
- processing the movement data at the processing device to determine a probability of a user stroke, the probability indicates a percentage chance of stroke occurrence, the method further comprising,
- storing the movement data at a fidelity dependent on the probability of the user stroke, wherein the fidelity of the stored movement data comprises at least one of a sample rate, a sample size, or a bit rate;
- in a first operating mode, storing the movement data at a first fidelity on a system memory of the data processing device when the probability of a user stroke is determined to be below a first threshold;
- and
- in a second operating mode, storing the movement data at a second fidelity on the system memory when the probability of a user stroke is determined to be above the first threshold,
- wherein the first probability threshold is a determined percentage chance of stroke occurrence, and
- wherein the second fidelity is higher than the first fidelity, to reduce power consumption from the power source in the first operating mode.
Dependencies are inferred from the claim text.