Granted Patent B2

US 12,702,326 · App. 17/415,183 · Granted Aug 11, 2026

Inventors: Petter Ericson (Limhamn, SE); Johan Wasselius (Lund, SE); Karl Astrom (Lund, SE); Rikard Berthilsson (Furulund, SE)

Assignee: UMAN SENSE AB

A61B5/11A61B5/162A61B5/4064A61B5/4094A61B5/681A61B5/6824A61B5/6828A61B5/7275A61B5/747A61B5/7475G16H40/67

Abstract

Claims (37)

1 . 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.

2 . The stroke detection apparatus of claim 1 , wherein the stroke detection apparatus is configured to generate one or more user tests once a threshold for the probability of the user stroke has been exceeded, wherein the one or more user tests comprises at least one of a reaction time test, an arithmetic test, a reading test, a comprehension test, a memory test, or a user response test.

3 . The stroke detection apparatus of claim 2 , wherein the stroke detection apparatus is configured to generate a stroke escalation signal where the user fails the one or more of the user tests.

4 . The stroke detection apparatus according to claim 1 , wherein the stroke detection apparatus is configured to operate in the first mode wherein the processed movement data is limited to a single dimension, and

wherein the stroke detection apparatus is configured to

operate in the second mode wherein the processed movement data is 3-dimensional, and

determine the probability of the user stroke in dependence on the processed movement data according to the first mode and determine a user gesture in dependence on the processed movement data according to the second mode.

5 . The stroke detection apparatus according to claim 1 , wherein the stroke detection apparatus is configured to operate in a third mode when the stroke detection apparatus is monitoring the user for a specific movement.

6 . The stroke detection apparatus according to claim 5 , wherein the stroke detection apparatus is configured to operate in the third mode when the stroke detection apparatus has prompted the user to perform the specific movement in order to pass a test.

7 . The stroke detection apparatus according to claim 5 , wherein the movement data of the user from the at least one wearable sensor is stored at a third fidelity in the third mode, wherein the third fidelity is higher than a first fidelity and a second fidelity.

8 . 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.

Assignments (1)

Priority Claims (2)

Continuity (1)

References Cited (128)