US2016007910A1PendingUtilityA1
Avoidance of cognitive impairment events
Est. expiryJul 10, 2034(~8 yrs left)· nominal 20-yr term from priority
A61B 5/486A61B 5/725A61B 5/7282A61B 5/4064A61B 5/746A61B 5/7246A61B 5/6803A61B 5/11A61B 5/749A61B 5/7225A61B 5/7275A61B 5/7264A61B 5/0022A61B 5/742G16Z 99/00G16H 40/67A61B 5/02055A61B 5/112A61B 2560/0242A61B 5/4803A61B 5/165
53
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
A method guides evasive actions to avoid effects of a cognitive impairment state. A first buffer, which is communicatively coupled to at least one sensor on a wearable sensor device, is loaded with a first set of sensor readings. The wearable sensor device receives a first cognitive impairment state signal based on an observer of a wearer of the wearable sensor device observing an impairment to a cognitive state of the wearer of the wearable sensor device. Subsequently, a second buffer on the wearable sensor device initiates loading of a second set of sensor readings, and the first buffer and the second buffer are compared. In response to sensors readings from the first and second buffers matching, an alert is issued to the wearer of the wearable sensor device, thus prompting the wearer to take evasive steps to avoid a recurrence of the impairment.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A method of guiding evasive actions to avoid effects of an impaired cognitive state, the method comprising:
loading a first buffer on a wearable sensor device with a first set of time-dependent sensor readings, wherein the first buffer is communicatively coupled to at least one sensor on the wearable sensor device; receiving, by the wearable sensor device, a first cognitive impairment state signal, wherein an observer of a wearer of the wearable sensor device sends the first cognitive impairment state signal in response to observing an impairment to a cognitive state of the wearer of the wearable sensor device; inserting a cognitive impairment state marker at a predefined position in the first buffer in response to the wearable sensor device receiving the first cognitive impairment state signal; initiating loading of a second buffer on the wearable sensor device with a second set of time-dependent sensor readings from said at least one sensor on the wearable sensor device; comparing time-dependent sensor readings from the first buffer up to the predefined position with time-dependent sensor readings from the second buffer; and in response to a partial match of the first set of time-dependent sensors readings up to the predefined position and the second set of time-dependent sensors readings sensor readings reaching a predefined match level, issuing an alert to the wearer of the wearable sensor device.
2 . The method of claim 1 , wherein the alert advises the wearer of the wearable sensor device to take an action that has been predetermined to avoid receiving a second cognitive impairment state signal from the observer.
3 . The method of claim 2 , further comprising:
loading the alert into the second buffer as a member of the second set of time-dependent sensor readings.
4 . The method of claim 1 , wherein the alert advises the wearer of the wearable sensor device to take an action that has been predetermined to avoid experiencing an impairment to the cognitive state of the wearer.
5 . The method of claim 1 , further comprising:
identifying a cause of the impairment to the cognitive state of the wearer by analyzing, by one or more processors, the first set of time-dependent sensor readings.
6 . The method of claim 1 , wherein the first buffer and the second buffer are both continuous circular buffers, wherein each of the continuous circular buffers stores data from a different sensor in the wearable sensor device, and wherein the method further comprises:
predicting a cause of the impairment to the cognitive state of the wearer based on a probability formula:
P
(
M
|
E
)
=
P
(
E
|
M
)
∑
mP
(
E
|
Mm
)
P
(
Mm
)
*
P
(
M
)
where:
P(M|E) is a probability that the impairment to the cognitive state will occur (M) given that (|) data from the continuous circular buffers falls within a predefined Push Triggered Average (PTA) of previously pushed data from the continuous circular buffers (E);
P(E|M) is a probability that data from the continuous circular buffers falls within the predefined PTA of previously pushed data from the continuous circular buffers (E) given that (|) the impairment to the cognitive state of the wearer is actually occurring (M);
P(M) is a probability that the impairment to the cognitive state of the wearer will occur regardless of any other information; and
Σm is a sum of all occurrences m, for the probability P(E|M) times the probability P(M).
7 . The method of claim 1 , further comprising:
predicting whether the impairment to the cognitive state of the wearer of the wearable sensor device will occur based on a statistical analysis of the second set of time-dependent sensor readings compared to the first set of time-dependent sensor readings, wherein a match within a predefined statistical range between the second set of time-dependent sensor readings and the first set of time-dependent sensor readings leads to a prediction of the impairment to the cognitive state of the wearer of the wearable sensor device.
8 . The method of claim 1 , wherein the wearable sensor device is a protective sports helmet, wherein said at least one sensor comprises a physiological sensor and an accelerometer sensor, wherein the physiological sensor detects a biological state of the wearer of the wearable sensor device, wherein the accelerometer sensor detects a change in velocity of the protective sports helmet, and wherein the method further comprises:
loading the first buffer and the second buffer with sensor readings from a combination of the physiological sensor and the accelerometer sensor.
9 . The method of claim 8 , further comprising:
detecting a download of the first set of time-dependent sensor readings from the first buffer; and in response to detecting the download of the first set of time-dependent sensor readings from the first buffer, generating the first cognitive impairment state signal.
10 . The method of claim 1 , wherein the predefined position in the first buffer at which the cognitive impairment state marker is inserted is at an end of the first set of time-dependent sensor readings, and wherein the method further comprises:
determining that sensor readings stored prior to the end of the first set of time-dependent sensor readings are precursors to the impairment to the cognitive state of the wearer of the wearable sensor device.
11 . The method of claim 1 , wherein the first set of time-dependent sensor readings comprise a first subset of time-dependent sensor readings and a second subset of time-dependent sensor readings, wherein the first subset of time-dependent sensor readings record event states that occur before event states that are represented by the second subset of time-dependent sensor readings, wherein the second set of time-dependent sensor readings comprise a third subset of time-dependent sensor readings and a fourth subset of time-dependent sensor readings, wherein the third subset of time-dependent sensor readings record event states that occur before event states that are represented by the fourth subset of time-dependent sensor readings, and wherein the method further comprises:
defining the partial match as a match of sensor readings from the first subset and the third subset of time-dependent sensor readings.
12 . The method of claim 1 , wherein the said at least one sensor are multiple sensors that detect physiological states of the user, musculoskeletal bodily acts of the user, keywords spoken by the user, a quality of a voice pattern from the user, and ambient environmental conditions around the user.
13 . A method of enabling a guidance of evasive actions to avoid an impaired cognitive state, the method comprising:
receiving a first set of time-dependent sensor readings from a first buffer on a wearable sensor device, wherein the first buffer is communicatively coupled to at least one sensor on the wearable sensor device; transmitting, to the wearable sensor device, a first cognitive impairment state signal, wherein an observer of a wearer of the wearable sensor device sends the first cognitive impairment state signal in response to observing an impairment to a cognitive state of the wearer of the wearable sensor device; transmitting a cognitive impairment state marker to the wearable sensor device, wherein the cognitive impairment state marker is inserted at a predefined position in the first buffer in response to the wearable sensor device receiving the first cognitive impairment state signal; detecting an initiation of loading of a second buffer on the wearable sensor device with a second set of time-dependent sensor readings from said at least one sensor on the wearable sensor device; comparing time-dependent sensor readings from the first buffer up to the predefined position with time-dependent sensor readings from the second buffer; and in response to a partial match of the first set of time-dependent sensors readings up to the predefined position and the second set of time-dependent sensors readings sensor readings reaching a predefined match level, issuing an alert to the wearer of the wearable sensor device.
14 . The method of claim 13 , wherein the alert advises the wearer of the wearable sensor device to take an evasive action that has been predetermined to avoid experiencing an impairment to the cognitive state of the wearer.
15 . The method of claim 13 , wherein the observer of the wearer of the wearable sensor device sends multiple cognitive impairment state signals in response to observing multiple instances of the impairment to the cognitive state of the wearer of the wearable sensor device, wherein the multiple cognitive impairment state signals are generated in response to the observer making multiple observations of the impairment to the cognitive state of the wearer of the wearable sensor device, and wherein the method further comprises:
applying, by one or more processors, a Kalman filter to the multiple observations of the impairment to the cognitive state of the wearer of the wearable sensor device, wherein the Kalman filter uses a linear quadratic estimation to recursively remove anomalous observations from the multiple observations to generate an observation of the impairment to the cognitive state of the wearer of the wearable sensor device using an algorithm:
x k =F k x k-1 +B k u k +w k
where x k is the observation of the impairment to the cognitive state of the wearer of the wearable sensor device,
F k is a predefined state transition model that is applied to a previous state x k-1 of observed impairments to the cognitive state of the wearer of the wearable sensor device,
B k is a predefined control-input model that is applied to a control vector u k , and
w k is erroneous observation noises that are drawn from a multivariate normal distribution Q k , wherein w k is approximately equal to the set of numbers N from zero to Q k (N(0, Q k )).
16 . The method of claim 13 , wherein the first buffer and the second buffer are both continuous circular buffers, wherein each of the continuous circular buffers stores data from a different sensor in the wearable sensor device, and wherein the method further comprises:
predicting a cause of the impairment to the cognitive state of the wearer based on a probability formula:
P
(
M
|
E
)
=
P
(
E
|
M
)
∑
mP
(
E
|
Mm
)
P
(
Mm
)
*
P
(
M
)
where:
P(M|E) is a probability that the impairment to the cognitive state will occur (M) given that (|) data from the continuous circular buffers falls within a predefined Push Triggered Average (PTA) of previously pushed data from the continuous circular buffers (E);
P(E|M) is a probability that data from the continuous circular buffers falls within the predefined PTA of previously pushed data from the continuous circular buffers (E) given that (|) the impairment to the cognitive state of the wearer is actually occurring (M);
P(M) is a probability that the impairment to the cognitive state of the wearer will occur regardless of any other information; and
Σm is a sum of all occurrences m, for the probability P(E|M) times the probability P(M).
17 . The method of claim 13 , wherein the first set of time-dependent sensor readings comprise a first subset of time-dependent sensor readings and a second subset of time-dependent sensor readings, wherein the first subset of time-dependent sensor readings record event states that occur before event states that are represented by the second subset of time-dependent sensor readings, wherein the second set of time-dependent sensor readings comprise a third subset of time-dependent sensor readings and a fourth subset of time-dependent sensor readings, wherein the third subset of time-dependent sensor readings record event states that occur before event states that are represented by the fourth subset of time-dependent sensor readings, and wherein the method further comprises:
defining the partial match as a match of sensor readings from the first subset and the third subset of time-dependent sensor readings.
18 . A sports helmet, wherein a wearable sensor device is integrated into the sports helmet, and wherein the wearable sensor device comprises:
a physiological sensor, wherein the physiological sensor detects a biological state of the wearer of the sports helmet; an accelerometer sensor, wherein the accelerometer sensor detects a change in velocity of the protective sports helmet; a first buffer for storing a first set of time-dependent sensor readings, wherein the first buffer is communicatively coupled to the physiological sensor and the accelerometer sensor; a receiver for receiving a first cognitive impairment state signal, wherein an observer of a wearer of the wearable sensor device sends the first cognitive impairment state signal in response to the observer subjectively observing an impairment to a cognitive state of the wearer of the wearable sensor device; a data insertion logic for inserting a cognitive impairment state marker at a predefined position in the first buffer in response to the wearable sensor device receiving the first cognitive impairment state signal; a second buffer, wherein the second buffer initiates loading of a second set of time-dependent sensor readings from the physiological sensor and the accelerometer sensor; a hardware comparator for comparing time-dependent sensor readings from the first buffer up to the predefined position with time-dependent sensor readings from the second buffer; and an alert generator that issues an alert to the wearer of the wearable sensor device in response to a partial match of the first set of time-dependent sensors readings up to the predefined position and the second set of time-dependent sensors readings sensor readings reaching a predefined match level.
19 . The sport helmet of claim 18 , wherein the alert advises the wearer of the wearable sensor device to take an action that has been predetermined to avoid receiving a second cognitive impairment state signal from the observer.
20 . The sports helmet of claim 18 , wherein the alert advises the wearer of the wearable sensor device to take an action that has been predetermined to avoid experiencing an impairment to the cognitive state of the wearer.Join the waitlist — get patent alerts
Track US2016007910A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.