# US 11,998,360 B2 · Device and method for sequential posture identification and autonomic function information acquisition

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,998,360 B2
- Document ID: US11998360B2
- Status: Granted
- Kind: B2
- Application number: 17/352,499
- Filed: 2021-06-21
- Published: 2021-10-07
- Granted: 2024-06-04
- Earliest claimed: 2015-02-17
- Assignees: Nippon Telegraph and Telephone Corporation
- Applicants: Nippon Telegraph and Telephone Corporation
- Inventors: Keitaro Horikawa; Yoshitaka Nakamura; Masato Sawada; Akihiro Yamanaka; Shingo Tsukada; Toshiya Yamada
- Web page: https://patentgrep.com/patent/US11998360B2

## CPC

- A61B 5/721: {using a separate sensor to detect motion or using motion information derived from signals other than the physiological signal to be measured}
- A61B 5/024: Measuring pulse rate or heart rate
- A61B 5/02405: {Determining heart rate variability}
- A61B 5/1116: {Determining posture transitions}
- A61B 5/1118: {Determining activity level}
- A61B 5/1123: {Discriminating type of movement, e.g. walking or running (A61B5/1116, A61B5/112 take precedence)}
- A61B 5/16: Devices for psychotechnics (using teaching or educational appliances G09B1/00 - G09B7/00); Testing reaction times {; Devices for evaluating the psychological state}
- A61B 5/4035: {Evaluating the autonomic nervous system}
- A61B 5/7267: {involving training the classification device}
- A61B 5/7282: {Event detection, e.g. detecting unique waveforms indicative of a medical condition (cough events A61B5/0823; seizures A61B5/4094; sleep apnoea A61B5/4818)}
- G16H 20/30: relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- A61B 5/021: Measuring pressure in heart or blood vessels
- A61B 5/352: Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
- A61B 5/6804: {Garments; Clothes}
- A61B 2503/10: Athletes
- A61B 2503/12: Healthy persons not otherwise provided for, e.g. subjects of a marketing survey
- A61B 2505/09: Rehabilitation or training
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A wearable device attached to a subject includes an accelerometer that measures acceleration information, and a biological sensor that measures biological signal information of the subject. From the measured acceleration information and biological signal information, first feature data corresponding to a first predetermined period and second feature data corresponding to a second predetermined period are extracted. By machine learning based on the first feature data, a dynamic/static activity identification model, a dynamic-activity identification model, and a static-activity identification model, for the subject, are generated. By combination of results of determination based on each of the identification models, a posture and an activity of the subject are identified and correspondence information, which associates the identified posture and activity with the biological signal information of the subject, is generated.

## Claims

### Claim 1

An autonomic function information acquisition device, comprising:
a wearable device that has a shirt shape and is configured to be attached to a trunk of a subject;
an acceleration sensor that is provided in the wearable device, and measures acceleration information of motion of the subject whom the wearable device is attached to;
a biological signal information sensing device that is provided in the wearable device, and measures biological signal information of the subject; and
processing circuitry configured to
identify, by executing sequential machine learning for the acceleration information and the biological signal information in a first predetermined period, a posture and an activity of the subject in a second predetermined period;
extract biological signal information corresponding to a combination of the same posture and activity identified; and
calculate a parameter of autonomic function evaluation from the biological signal information extracted and corresponding to the combination of the same posture and activity.

### Claim 2 (depends on 1)

The autonomic function information acquisition device according to claim 1, wherein
the biological signal information sensing device measures, as the biological signal information, heart rate data of the subject, and
the processing circuitry
extracts heart rate data corresponding to the combination of the same posture and activity, and
calculates, as the parameter, at least one of an average value, a variance value, and a median point, of the heart rate data extracted by the processing circuitry.

### Claim 3 (depends on 2)

The autonomic function information acquisition device according to claim 2,
wherein the processing circuitry connects together the extracted heart rate data corresponding to the combination of the same posture and activity, into a group of data, wherein
when a difference between values of connected portions of the connected heart rate data is less than a predetermined threshold, the processing circuitry statistically calculates an estimated value that corrects the difference, and connects together the heart rate data that have been corrected by the estimated value.

### Claim 4 (depends on 2)

The autonomic function information acquisition device according to claim 2,
wherein the processing circuitry connects together the extracted heart rate data corresponding to the combination of the same posture and activity, into a group of data, wherein
when a difference between values of connected portions of the connected heart rate data is equal to or larger than a predetermined threshold, the processing circuitry deletes a value exceeding the predetermined threshold and connects the heart rate data together.

### Claim 5 (depends on 1)

The autonomic function information acquisition device according to claim 1, wherein
the biological signal information sensing device measures, as the biological signal information, heart rate data of the subject, and
the processing circuitry
extracts plural sets of heart rate data corresponding to periods corresponding to the same consecutive changes in posture and activity, and
synchronously adds together the plural sets of heart rate data by synchronizing starting time points or ending time points of a change in the posture or activity in the plural sets of heart rate data extracted by the processing circuitry, and calculates the parameter from the synchronously added data.

### Claim 6 (depends on 5)

The autonomic function information acquisition device according to claim 5, wherein
the processing circuitry
extracts the plural sets of heart rate data corresponding to the periods corresponding to the same consecutive changes in posture and activity, each of the periods being a period, in which the subject changes a posture, and in which a body of the subject is static before and after a time point of the change of the posture, and
calculates, as the parameter, at least one of a difference between average heartbeat intervals before and after the time point of the change of the posture; a maximum inclination of heartbeat intervals in an initial response; and a maximum inclination of heartbeat intervals in a late response.

### Claim 7 (depends on 5)

The autonomic function information acquisition device according to claim 5, wherein
the processing circuitry
extracts the plural sets of heart rate data corresponding to the periods corresponding to the same consecutive changes in posture and activity, each of the periods being a period, in which the subject changes from a static state to a dynamic state and thereafter returns to the static state again, and during which a posture of the subject does not change, and
synchronously adds together the plural sets of heart rate data by synchronizing starting time points of the dynamic state, and calculates, as the parameter, at least one of: a maximum inclination of a rising phase of heart rate; an average heart rate after the rise; and a difference between average heart rates or average heartbeat intervals before start of the dynamic state and during the dynamic state.

### Claim 8 (depends on 5)

The autonomic function information acquisition device according to claim 5, wherein
the processing circuitry
extracts plural sets of heart rate data corresponding to the periods corresponding to the same consecutive changes in posture and activity, each of the periods being a period, in which the subject changes from a static state to a dynamic state and thereafter returns to a static state again, and during which the posture of the subject does not change, and
synchronously adds together the plural sets of heart rate data by synchronizing ending time points of the dynamic state, and calculates, as the parameter, at least one of: a maximum inclination of a heart rate falling phase; an average heart rate after the fall; and a difference between average heart rates or average heartbeat intervals during the dynamic state and after ending of the dynamic state.

### Claim 9 (depends on 1)

The autonomic function information acquisition device according to claim 1, wherein the processing circuitry
executes machine learning based on correspondence between the posture and activity identified by the processing circuitry and the biological signal information; and
detects, based on a result of the machine learning, an abnormality in the subject from the acceleration information and the biological signal information measured by the acceleration sensor and the biological signal information sensing device.

### Claim 10 (depends on 1)

The autonomic function information acquisition device according to claim 1, wherein the first predetermined period and the second predetermined period overlap each other at least partially.

### Claim 11

An autonomic function information acquisition method, comprising:
a reception step of receiving respectively, from an acceleration sensor and a biological signal information sensing device that are provided in a wearable device that has a shirt shape and is configured to be attached to a trunk of a subject, acceleration information on motion of a subject whom the wearable device is attached to, and biological signal information of the subject;
an identification step of identifying, by executing sequential machine learning for the acceleration information and the biological signal information in a first predetermined period, a posture and a motion of the subject in a second predetermined period;
an extraction step of extracting biological signal information corresponding to a combination of the same posture and activity identified in the identification step; and
a calculation step of calculating a parameter of autonomic function evaluation from the biological signal information extracted in the extraction step and corresponding to the combination of the same posture and activity.

### Claim 12

A non-transitory computer-readable recording medium having stored therein an autonomic function information acquisition program that causes a computer to execute:
a reception process of receiving respectively, from an acceleration sensor and a biological signal information sensing device that are provided in a wearable device that has a shirt shape and is configured to be attached to a trunk of a subject, acceleration information on motion of a subject whom the wearable device is attached to, and biological signal information of the subject;
an identification process of identifying, by executing sequential machine learning for the acceleration information and the biological signal information in a first predetermined period, a posture and an activity of the subject in a second predetermined period;
an extraction process of extracting biological signal information corresponding to a combination of the same posture and activity identified in the identification process; and
a calculation process of calculating a parameter of autonomic function evaluation from the biological signal information extracted in the extraction process and corresponding to the combination of the same posture and activity.