Abstract: According to an aspect, there is provided a computer-implemented method of determining a fall risk of a subject, the method including receiving a first data set indicative of movement of the subject; receiving a second data set indicative of context information of the subject; selecting a part of the first data set based on the second data set; and determining a fall risk based on the selected part of the first data set.

Abstract: A method and system for training a fall detection classifier using subject-specific movement data. Movement data responsive to a subject's movements during everyday activities are obtained over a predetermined data collection period. For each detected event in the movement data, values for one or more parameters that may (together or individually) indicate a fall are obtained. The obtained values are used to generate a subject-specific probability distribution for non-fall events. A fall event probability distribution is obtained using the non-fall event probability distribution. This fall event probability distribution can then be subsequently processed, with reference to a threshold value, to distinguish fall events from non-fall events.

Abstract: According to an aspect, there is provided a computer-implemented method of determining a fall risk of a subject, the method comprising receiving a first data set indicative of movement of the subject; receiving a second data set indicative of context information of the subject; selecting a part of the first data set based on the second data set; and determining a fall risk based on the selected part of the first data set.

Abstract: Proposed are concepts for distinguishing between fall events and non-fall-events for different sub-groups within a monitored group (i.e., monitored population) of subjects. It is proposed that an entire/group population of monitored subjects may be portioned into sub-groups, each sub-group consisting of a plurality of members (i.e., subjects) having a certain property value or characteristic unique to that group. A respective decision value may be determine for each sub-group, wherein the decision value for a sub-group takes account of a previously obtained false fall detection rate for that sub-group.

Abstract: According to an aspect, there is provided a fall detection apparatus for detecting a fall by a user, the fall detection apparatus comprising a processing unit configured to: receive measurements of movements of the user over time from a first movement sensor that is to be worn or carried by the user, determine if any of one or more objects are being carried or used by the user, and determine whether the user has fallen by processing the received measurements of the movements of the user and measurements of movements of any object that is being carried or used by the user.

Abstract: A method and system for training a fall detection classifier using subject-specific movement data. A subject sets a preferred non-fall detection rate. Movement data responsive to a subject's movements during everyday activities are obtained over a predetermined data collection period. For each detected event in the movement data, values for one or more parameters that may (together or individually) indicate a fall are obtained. The obtained values are used to generate a subject-specific non-fall detection rate function. This non-fall detection rate function is used to derive a threshold value, in reference to the subject-set preferred non-fall detection rate, to distinguish fall events from non-fall events.

Abstract: A personal help button and the administrator part of a personal emergency response system are provided, in which verbal audio is converted into a low bandwidth format signal. A conversation algorithm is used which comprises a trained neural network. The low bandwidth format has a bandwidth below 500 bits/second.

Abstract: A method includes obtaining first measurements of movement of a user, processing the first measurements of movement to determine whether the user has fallen, and initiating a revocation period to determine if the user stands up in response to determining that the user has fallen. During the revocation period, the method also includes obtaining second measurements of movement of the user and processing the second measurements of movement to determine whether the user stands up before the revocation period expires. The first and second measurements of movement are measured by a movement sensor of the device. In response to determining that the user has not stood up before the revocation period expired, the method also includes automatically sending a fall alert to an emergency service. The fall alert includes data that provides an indication that the user has fallen.

Abstract: A method and system for training a fall detection classifier using subject-specific movement data. A subject sets a preferred non-fall detection rate. Movement data responsive to a subject's movements during everyday activities are obtained over a predetermined data collection period. For each detected event in the movement data, values for one or more parameters that may (together or individually) indicate a fall are obtained. The obtained values are used to generate a subject-specific non-fall detection rate function. This non-fall detection rate function is used to derive a threshold value, in reference to the subject-set preferred non-fall detection rate, to distinguish fall events from non-fall events.

Abstract: According to an aspect, there is provided a computer-implemented method for evaluating movement of a subject. The method includes obtaining a first signal from a first sensor; processing the first signal to determine a value of a quality measure for the first signal; and determining a configuration for a movement evaluation algorithm. The configuration of the movement evaluation algorithm is dependent on the determined value of the quality measure for the first signal such that either or both of a decision threshold of the movement evaluation algorithm is determined based on the determined value of the quality measure; and one or more weightings used in the movement evaluation algorithm for the one or more first features that are to be derived from a signal from the first sensor are determined based on the determined value of the quality measure. A corresponding apparatus and computer program product are also provided.

Abstract: Proposed are concepts for distinguishing between fall events and non-fall-events for different sub-groups within a monitored group (i.e., monitored population) of subjects. It is proposed that an entire/group population of monitored subjects may be portioned into sub-groups, each sub-group consisting of a plurality of members (i.e., subjects) having a certain property value or characteristic unique to that group. A respective decision value may be determine for each sub-group, wherein the decision value for a sub-group takes account of a previously obtained false fall detection rate for that sub-group.

Abstract: According to an aspect, there is provided a computer-implemented method for evaluating movement of a subject. The method comprises obtaining a first signal from a first sensor; processing the first signal to determine a value of a quality measure for the first signal; and determining a configuration for a movement evaluation algorithm. The configuration of the movement evaluation algorithm is dependent on the determined value of the quality measure for the first signal such that either or both of a decision threshold of the movement evaluation algorithm is determined based on the determined value of the quality measure; and one or more weightings used in the movement evaluation algorithm for the one or more first features that are to be derived from a signal from the first sensor are determined based on the determined value of the quality measure. A corresponding apparatus and computer program product are also provided.

Abstract: Proposed are concepts for distinguishing between fall events and non-fall-events for different sub-groups of subjects within a monitored group (i.e. monitored population) of subjects. It is proposed that an entire group/population of monitored subjects may be partitioned into sub-groups, each sub-group consisting of a plurality of members (i.e. subjects) having a certain property value or characteristic unique to that group. A respective decision value may be determined for each sub-group, wherein the decision value for a sub-group takes account of a previously obtained false fall detection rate for that sub-group.

Abstract: A method for detecting cognitive decline of a user includes receiving speech data corresponding to one or more utterances spoken by the user and processing the received speech data to determine if the speech data is sufficient to perform a cognitive decline analysis of the user. When the speech data is insufficient to perform the cognitive decline analysis, the method also includes initiating a follow-up interaction with the user to collect additional speech data from the user, receiving the additional speech data from the user, and processing the received speech data and the additional speech data to determine a cognitive decline score for the user. The additional speech data corresponds to one or more additional utterances spoken by the user. The method also includes performing an action based on the cognitive decline score of the user.

Abstract: According to an aspect, there is provided a fall detection apparatus for detecting a fall by a user, the fall detection apparatus comprising a processing unit configured to: receive measurements of movements of the user over time from a first movement sensor that is to be worn or carried by the user, determine if any of one or more objects are being carried or used by the user, and determine whether the user has fallen by processing the received measurements of the movements of the user and measurements of movements of any object that is being carried or used by the user.

Abstract: A lanyard device (10) having a flexible neck cord (12) and at least one strain sensor (30) arranged for sensing strain in the flexible neck cord; and a personal lanyard monitoring system including the lanyard device (10). A position recognition unit (52) is configured for comparing strain data obtained from the at least one strain sensor (30) to predetermined strain data, and recognizing a position of the flexible neck cord (12) in dependence on a result of the comparison.

Abstract: A method includes obtaining first measurements of movement of a user, processing the first measurements of movement to determine whether the user has fallen, and initiating a revocation period to determine if the user stands up in response to determining that the user has fallen. During the revocation period, the method also includes obtaining second measurements of movement of the user and processing the second measurements of movement to determine whether the user stands up before the revocation period expires. The first and second measurements of movement are measured by a movement sensor of the device. In response to determining that the user has not stood up before the revocation period expired, the method also includes automatically sending a fall alert to an emergency service. The fall alert includes data that provides an indication that the user has fallen.

Abstract: According to an aspect, there is provided a fall detection apparatus for detecting a fall by a user, the fall detection apparatus comprising a processing unit configured to: receive measurements of movements of the user over time from a first movement sensor that is to be worn or carried by the user; determine if any of one or more objects are being carried or used by the user; and determine whether the user has fallen by processing the received measurements of the movements of the user and measurements of movements of any object that is being carried or used by the user.

Abstract: The present system is configured to track informal observations by multiple caregivers about a care recipient and provide actionable feedback to the multiple caregivers for managing health of the care recipient based on the informal observations. Informal caregivers are constantly observing the health and/or wellness of care recipients they provide care for. Within families for example, multiple informal caregivers coordinate the care they provide for a care recipient amongst each other to balance the workload. These caregivers observe the same care recipient often on different occasions, from different perspectives, and with varying levels of subjectivity. Keeping an eye out for abnormal behavior by the care recipient, changes in capabilities of the care recipient, and/or potential disease progression, for example, are pieces of data caregivers commonly observe in an informal, rarely structured way.

Abstract: According to an aspect, there is provided a computer-implemented method of monitoring a subject. The method comprises, following detection of a first fall by the subject and a revocation of a fall alert for the first fall due to detecting the subject has stood up after the first fall, obtaining first measurements of movement of the subject; determining a first value of at least one mobility characteristic of the subject from the obtained first movement measurements; determining if the mobility of the subject has degraded after the first fall based on the first value of the at least one mobility characteristic and a second value of the at least one mobility characteristic, wherein the second value is determined from second movement measurements obtained prior to the first fall; and in response to determining that the mobility of the subject has degraded after the first fall, performing a fall alert action in respect of the first fall. A corresponding apparatus and a computer program product are also provided.