Systems and methods for remote monitoring care using wireless sensing technologies
System and methods of a mobile application to remotely monitor residents with device-free sensing of human motion over Wi-Fi is provided. A detailed behavioral analysis of various functions related to the sleep and activity of the subject has been provided. The Remote Care Application (RCA) is a mobile application on several platforms that displays the results of all the analysis and behavioral patterns obtained from the motion from the subject. The system relies on existing wireless communication signals and machine learning techniques in order to automatically detect the motion of the subject, sleep analysis of the subject, activity analysis of the subject.
1 . A method comprising:
acquiring data relating to wireless signals exchanged between a plurality of wireless devices within an environment;
processing the acquired data with one or more processing modules of a plurality of processing modules to establish one or more characteristics relating to one or more users within the environment; and
generating one or more summaries of a plurality of summaries in dependence upon the outputs of the plurality of processing modules;
wherein each summary of the plurality of summaries employs outputs of a predetermined subset of the plurality of processing modules;
wherein processing the acquired data with one or more processing modules of a plurality of processing modules to establish one or more characteristics relating to one or more users within the environment comprises:
continuously applying pre-processing one or more pre-processing filters to remove noise within the acquired data and to remove anomalous packets within the acquired data,
continuously applying one or more algorithms to the pre-processed acquired data to establish a series of numerical values, each numerical value relating to an intensity of motion of a subject within a sensing area established by the plurality of wireless devices,
continuously establishing a series of raw activity levels of the subject by applying one or more processes to predetermined subsets of the series of numerical values, each process relating to the application of one of a mathematical process, a neural network, and a classifier, and
establishing a consecutive series of activity levels, each activity level established for a predetermined time base in dependence upon applying further processing to a predetermined subset of the series of raw activity levels associated with an activity level of the consecutive series of activity levels;
wherein applying the further processing comprises:
buffering the predetermined subset of the series of raw activity levels associated with the activity level of the consecutive series of activity level to generate a buffered set of raw activity levels,
adjusting and correcting the baselines of the buffered set of raw activity levels to establish a set of baseline corrected activity levels,
segmenting the set of baseline corrected activity levels into a set of chunks,
analysing each chunk of the set of chunks with a sub-process comprising a series of layers to establish a set of summaries, and
establishing value of a binary flag in dependence upon the set of summaries;
wherein each layer of the sub-process applies statistical estimations and thresholds and the series of layers form a tree topological network of layers; and
wherein the values of the binary flags are the consecutive series of activity levels.
2 . A method comprising:
acquiring data relating to wireless signals exchanged between a plurality of wireless devices within an environment;
processing the acquired data with one or more processing modules of a plurality of processing modules to establish one or more characteristics relating to one or more users within the environment; and
generating a series of sets of activity level summaries, each set of activity level summaries being a consecutive series of activity level summary data for a predetermined time duration of a set of predetermined time durations;
wherein each item of activity level summary data for a predetermined time duration within a consecutive series of activity level summary data for the predetermined time duration is established in dependence upon applying further processing to a predetermined subset of a previous set of activity level summaries for another predetermined time duration of the set of predetermined time durations;
wherein each subsequent set of activity level summaries summarises over a longer predetermined time period of the set of predetermined time durations than the preceding set of activity level summaries; and
wherein processing the acquired data with one or more processing modules of a plurality of processing modules to establish one or more characteristics relating to one or more users within the environment comprises:
continuously applying pre-processing one or more pre-processing filters to remove noise within the acquired data and to remove anomalous packets within the acquired data,
continuously applying one or more algorithms to the pre-processed acquired data to establish a series of numerical values, each numerical value relating to an intensity of motion of a subject within a sensing area established by the plurality of wireless devices,
continuously establishing a series of raw activity levels of the subject by applying one or more processes to predetermined subsets of the series of numerical values, each process relating to the application of one of a mathematical process, a neural network, and a classifier, and
establishing a consecutive series of activity levels, each activity level established for a predetermined time base in dependence upon applying further processing to a predetermined subset of the series of raw activity levels associated with an activity level of the consecutive series of activity levels.
3 . A method comprising:
processing upon a system comprising one or more microprocessors acquired data with one or more processing modules of a plurality of processing modules to establish one or more characteristics relating to one or more users within the environment, by:
continuously applying pre-processing via one or more pre-processing filters to remove noise within the acquired data and to remove anomalous packets within the acquired data,
continuously applying one or more algorithms to the pre-processed acquired data to establish a series of numerical values, each numerical value relating to an intensity of motion of a subject within a sensing area established by the plurality of wireless devices,
continuously establishing a series of raw activity levels of the subject by applying one or more processes to predetermined subsets of the series of numerical values, each process relating to the application of one of a mathematical process, a neural network, and a classifier, and
establishing a consecutive series of activity levels, each activity level established for a predetermined time base in dependence upon applying further processing to a predetermined subset of the series of raw activity levels associated with an activity level of the consecutive series of activity levels;
wherein each layer of the sub-process applies statistical estimations and thresholds and the series of layers form a tree topological network of layers;
wherein applying the further processing comprises:
buffering the predetermined subset of the series of raw activity levels associated with the activity level of the consecutive series of activity level to generate a buffered set of raw activity levels,
adjusting and correcting the baselines of the buffered set of raw activity levels to establish a set of baseline corrected activity levels,
segmenting the set of baseline corrected activity levels into a set of chunks,
analysing each chunk of the set of chunks with a sub-process comprising a series of layers to establish a set of summaries, and
establishing value of a binary flag in dependence upon the set of summaries; and
wherein the values of the binary flags are the consecutive series of activity levels.
4 . A method comprising:
acquiring data relating to wireless signals exchanged between a plurality of wireless devices within an environment;
processing the acquired data with one or more processing modules of a plurality of processing modules to establish one or more characteristics relating to one or more users within the environment;
generating one or more summaries of a plurality of summaries in dependence upon the outputs of the plurality of processing modules; and
generating a series of sets of activity level summaries, each set of activity level summaries being a consecutive series of activity level summary data for a predetermined time duration of a set of predetermined time durations;
wherein each summary of the plurality of summaries employs outputs of a predetermined subset of the plurality of processing modules;
wherein each subsequent set of activity level summaries summarises over a longer predetermined time period of the set of predetermined time durations than the preceding set of activity level summaries;
wherein each item of activity level summary data for a predetermined time duration within a consecutive series of activity level summary data for the predetermined time duration is established in dependence upon applying further processing to a predetermined subset of a previous set of activity level summaries for another predetermined time duration of the set of predetermined time durations; and
wherein processing the acquired data with one or more processing modules of a plurality of processing modules to establish one or more characteristics relating to one or more users within the environment comprises:
continuously applying pre-processing one or more pre-processing filters to remove noise within the acquired data and to remove anomalous packets within the acquired data,
continuously applying one or more algorithms to the pre-processed acquired data to establish a series of numerical values, each numerical value relating to an intensity of motion of a subject within a sensing area established by the plurality of wireless devices,
continuously establishing a series of raw activity levels of the subject by applying one or more processes to predetermined subsets of the series of numerical values, each process relating to the application of one of a mathematical process, a neural network, and a classifier, and
establishing a consecutive series of activity levels, each activity level established for a predetermined time base in dependence upon applying further processing to a predetermined subset of the series of raw activity levels associated with an activity level of the consecutive series of activity levels.
5 . A method comprising:
processing upon a system comprising one or more microprocessors acquired data with one or more processing modules of a plurality of processing modules to establish one or more characteristics relating to one or more users within the environment, by:
continuously applying pre-processing via one or more pre-processing filters to remove noise within the acquired data and to remove anomalous packets within the acquired data,
continuously applying one or more algorithms to the pre-processed acquired data to establish a series of numerical values, each numerical value relating to an intensity of motion of a subject within a sensing area established by the plurality of wireless devices,
continuously establishing a series of raw activity levels of the subject by applying one or more processes to predetermined subsets of the series of numerical values, each process relating to the application of one of a mathematical process, a neural network, and a classifier, and
establishing a consecutive series of activity levels, each activity level established for a predetermined time base in dependence upon applying further processing to a predetermined subset of the series of raw activity levels associated with an activity level of the consecutive series of activity levels; and
generating one or more summaries of a plurality of summaries in dependence upon the outputs of the plurality of processing modules;
wherein each layer of the sub-process applies statistical estimations and thresholds and the series of layers form a tree topological network of layers;
wherein each summary of the plurality of summaries employs outputs of a predetermined subset of the plurality of processing modules; and
wherein the acquired data relates to wireless signals exchanged between a plurality of wireless devices within an environment and each summary of the plurality of summaries relates to an activity of a user within the environment.
6 . A method comprising:
processing upon a system comprising one or more microprocessors acquired data with one or more processing modules of a plurality of processing modules to establish one or more characteristics relating to one or more users within the environment, by:
continuously applying pre-processing via one or more pre-processing filters to remove noise within the acquired data and to remove anomalous packets within the acquired data,
continuously applying one or more algorithms to the pre-processed acquired data to establish a series of numerical values, each numerical value relating to an intensity of motion of a subject within a sensing area established by the plurality of wireless devices,
continuously establishing a series of raw activity levels of the subject by applying one or more processes to predetermined subsets of the series of numerical values, each process relating to the application of one of a mathematical process, a neural network, and a classifier, and
establishing a consecutive series of activity levels, each activity level established for a predetermined time base in dependence upon applying further processing to a predetermined subset of the series of raw activity levels associated with an activity level of the consecutive series of activity levels;
generating one or more summaries of a plurality of summaries in dependence upon the outputs of the plurality of processing modules; and
establishing a consecutive series of other activity levels, each other activity level established for a predetermined other time base in dependence upon applying other processing to a predetermined subset of the consecutive series of activity levels;
wherein each layer of the sub-process applies statistical estimations and thresholds and the series of layers form a tree topological network of layers; and
wherein each summary of the plurality of summaries employs outputs of a predetermined subset of the plurality of processing modules.
7 . The method according to claim 6 ,
wherein the other processing comprises:
buffering the predetermined subset of the series of activity levels associated with the activity level of the consecutive series of activity level to generate a buffered set of activity levels,
adjusting and correcting the baselines of the buffered set of activity levels to establish a set of baseline corrected activity levels,
segmenting the set of baseline corrected activity levels into a set of other chunks,
analysing each other chunk of the set of other chunks with a sub-process comprising a series of layers to establish a set of summaries where each layer of the sub-process applies statistical estimations and thresholds and the series of layers form a tree topological network of layers, and
establishing a binary flag in dependence upon the set of summaries;
wherein the values of the binary flags are the consecutive series of activity levels; and
wherein the values of the other binary flags are the consecutive series of other activity levels.