KR101664323B1 - Health Parameter Estimating System and Health Parameter Estimating Method - Google Patents
Health Parameter Estimating System and Health Parameter Estimating Method Download PDFInfo
- Publication number
- KR101664323B1 KR101664323B1 KR1020160022882A KR20160022882A KR101664323B1 KR 101664323 B1 KR101664323 B1 KR 101664323B1 KR 1020160022882 A KR1020160022882 A KR 1020160022882A KR 20160022882 A KR20160022882 A KR 20160022882A KR 101664323 B1 KR101664323 B1 KR 101664323B1
- Authority
- KR
- South Korea
- Prior art keywords
- signal
- bio
- reliability
- health parameter
- estimated
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000007635 classification algorithm Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000012706 support-vector machine Methods 0.000 claims description 11
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000012417 linear regression Methods 0.000 claims description 5
- 206010003119 arrhythmia Diseases 0.000 claims description 4
- 230000006793 arrhythmia Effects 0.000 claims description 4
- 230000036760 body temperature Effects 0.000 claims description 4
- 230000000747 cardiac effect Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 239000011800 void material Substances 0.000 claims 1
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000017531 blood circulation Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000035882 stress Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7221—Determining signal validity, reliability or quality
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02416—Detecting, measuring or recording pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
-
- A61B5/0402—
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1102—Ballistocardiography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/22—Social work or social welfare, e.g. community support activities or counselling services
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
- A61B2562/02—Details of sensors specially adapted for in-vivo measurements
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Physiology (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Cardiology (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Economics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Child & Adolescent Psychology (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Dentistry (AREA)
- Human Resources & Organizations (AREA)
- Fuzzy Systems (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
Description
The present invention relates to a health parameter estimation system and a health parameter estimation method for estimating a health parameter using a bio-signal, and more particularly, to a health parameter estimation system and a health parameter estimation method for estimating a health parameter of a bio- To a health parameter estimation system and a health parameter estimation method for estimating a health parameter using only a health parameter.
2. Description of the Related Art In recent years, research and development on a bio-signal measurement embedded system that collects information from a bio-signal sensor provided in an automobile seat, a wheelchair, a bed, etc., and estimates a health parameter of a user,
Electrocardiogram (ECG), ballistocardiogram (BCG), and photoplethysmogram (PPG) are examples of representative bio-signals applied to such a system. Electrocardiogram (ECG) is the transmission of electrical signals from the heart's SA node to the outside of the body. BCG is the measurement of vibrations caused by heartbeats outside the body. In addition, the optical pulse wave PPG utilizes the fact that the blood flow rate of the blood vessel changes periodically as the heart rate is shifted. The amount of reflected light is measured by using the amount of light reflected from the outside of the human body varies depending on the blood flow amount To estimate the heart rate.
Various health parameters such as heartbeat, arrhythmia, body temperature, and stress level can be estimated through the features extracted from the bio-signal.
In the meantime, such a bio-signal is measured in a non-contact state in a non-constrained state or in a non-subjective state. Since the bio-signal is accompanied by a dynamic state in which the body moves, a large motion artifact occurs, It is very difficult and therefore difficult to estimate accurate health parameters.
In order to solve such a problem, a method of increasing a signal-to-noise ratio (SNR) using a signal processing technique such as filtering is mainly used.
However, there is a problem in that a sensor for measuring a bio-signal does not directly contact the skin, the information loss is very large while the body is moving, and the amount of motion noise relatively higher than the bio- Since the absolute bio-signal information can not be increased, there is a limit to increase the SNR.
SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and it is an object of the present invention to improve the accuracy of health parameter estimation by estimating health parameters using only reliable biometric signals by judging the reliability of each bio- A health parameter estimation system and a health parameter estimation method.
A health parameter estimation system according to the present invention comprises: a plurality of sensors for measuring a bio-signal; A bio-signal discrimination unit for determining the reliability of each bio-signal measured from the plurality of sensors and selecting the bio-signal of the highest reliability as an effective bio-signal; And a health parameter estimator for estimating a health parameter using the valid bio-signal.
The health parameter estimation system according to the present invention is characterized in that the bio-signal discrimination unit extracts signal characteristics of the respective bio-signals, classifies the extracted signal characteristics by a classification algorithm, and determines reliability of each bio- can do.
In the health parameter estimation system according to the present invention, the signal characteristics include power at 5 to 15 Hz, power at 0 to 1 Hz, purity of the signal, power at 0 to 5 Hz, kurtosis of the signal, skewness of the signal, a high frequency mask, and an entropy of the signal.
In the health parameter estimation system according to the present invention, the classification algorithm may be a support vector machine (SVM), an artificial neural network (ANN), a linear discriminant analysis (LDA) And may be any one of multiple linear regression analysis (MLRA) algorithms.
In the health parameter estimation system according to the present invention, the biological signal discriminator can select an effective biological signal only when the reliability of the biological signal having the highest reliability is equal to or higher than a predetermined value.
The health parameter estimation system according to the present invention is characterized in that when the reliability of the bio-signal judged to be the highest by the bio-signal discrimination unit is less than a predetermined value, the bio- The bio-signal determination unit may determine the reliability of the estimated bio-signal and may select the estimated bio-signal as an effective bio-signal when the reliability of the estimated bio-signal is more than a predetermined value.
In the health parameter estimation system according to the present invention, the bio-signal estimator may generate an estimated bio-signal using a Kalman filter.
In the health parameter estimation system according to the present invention, the plurality of sensors may be a non-contact type sensor for measuring a living body signal without binding.
In the health parameter estimation system according to the present invention, the biological signal may be any one of an electrocardiogram (ECG), cardiac trajectory (BCG), and optical pulse wave (PPG).
A method for estimating a health parameter according to the present invention includes: inputting a bio-signal from a plurality of channels; A bio-signal discrimination step of selecting a bio-signal having the highest reliability among the inputted bio-signals; And a health parameter estimation step of estimating a health parameter using the selected bio-signal.
In the method for estimating a health parameter according to the present invention, the bio-signal discrimination step may include: extracting a signal characteristic of each bio-signal; A reliability determination step of classifying the signal characteristics by a classification algorithm and determining reliability of each of the bio-signals; And a bio-signal selection step of selecting a bio-signal having the highest reliability.
In the method of estimating the health parameters according to the present invention, the signal characteristics may include power at 5 to 15 Hz, power at 0 to 1 Hz, purity of the signal, power at 0 to 5 Hz, kurtosis of the signal, skewness of the signal, a high frequency mask, and an entropy of the signal.
In the method of estimating a health parameter according to the present invention, the classification algorithm may be a support vector machine (SVM), an artificial neural network (ANN), a linear discriminant analysis (LDA) And may be any one of multiple linear regression analysis (MLRA) algorithms.
In the method for estimating a health parameter according to the present invention, the bio-signal discrimination step is valid when the reliability of the bio-signal selected in the bio-signal selection step is at least a predetermined value, and invalid when the reliability of the selected bio-signal is less than a predetermined value Wherein the health parameter estimating step estimates the health parameter only when it is determined to be valid in the validity determination step.
The method for estimating a health parameter according to the present invention may further comprise: an estimated bio-signal generation step of generating an estimated bio-signal by combining all of the bio-signals when it is determined to be invalid in the bio-signal validity determination step; Further comprising a step of determining reliability of the estimated bio-signal to determine that the reliability of the estimated bio-signal is valid if the reliability of the estimated bio-signal is greater than or equal to a predetermined value, Can estimate the health parameter using the estimated living body signal when the estimated living body signal is valid.
In the method for estimating a health parameter according to the present invention, the estimated bio-signal generation step may generate an estimated bio-signal using a Kalman filter.
In the method for estimating a health parameter according to the present invention, the bio-signal can be measured in a non-contact manner in a non-binding situation.
In the method for estimating a health parameter according to the present invention, the bio-signal may be any one of an electrocardiogram (ECG), cardiac trajectory (BCG), and optical pulse wave (PPG).
According to the present invention, the accuracy of health parameter estimation can be improved by estimating the health parameters using only the highly reliable bio-signals by determining the reliability of each bio-signal input from a plurality of channels.
According to the present invention, when the reliability of all the bio-signals input from a plurality of channels is equal to or lower than a certain level, the bio-signals are estimated by combining the bio-signals input from the plurality of channels, The time when the parameter can not be estimated can be minimized.
1 is a conceptual diagram of a health parameter estimation system according to an embodiment of the present invention;
FIG. 2 is a graph showing the power at 5 to 15 Hz extracted from an ECG signal, power at 0 to 1 Hz, purity of the signal, power at 0 to 5 Hz, kurtosis of the signal, skewness of the signal, A graph plotting the entropy of a signal over time.
3 is a flowchart of a health parameter estimation method according to an embodiment of the present invention.
Hereinafter, specific embodiments of the present invention will be described in detail with reference to the drawings. It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the inventive concept. Other embodiments falling within the scope of the inventive concept may be easily suggested, but are also included within the scope of the invention.
In the following description, the same reference numerals are used to designate the same components in the same reference numerals in the drawings.
1 is a conceptual diagram of a health
1, a health
The plurality of
The plurality of
The
At this time, the signal characteristics include power at 5 to 15 Hz, power at 0 to 1 Hz, purity of the signal, power at 0 to 5 Hz, kurtosis of the signal, skewness of the signal, high frequency mask of the signal, And may include at least one.
Here, the classification algorithm may be a support vector machine (SVM), an artificial neural network (ANN), a linear discriminant analysis (LDA), and a multiple linear regression Analysis, MLRA).
More specifically, by classifying the above eight signal characteristics by any one of SVM, LDA, and ANN, a discontinuous reliability class or reliability value can be given to each bio-signal. In addition, the eight signal characteristics described above can be classified by any one of the ANN or MLRA algorithms, and a continuous reliability value can be given to each bio-signal.
At this time, the biological
For example, if the reliability level of the bio-signal measured by the
On the other hand, a plurality of biological signals having the highest reliability can be used. In this case, an arbitrary biological signal can be selected as an effective biological signal. That is, when the reliability of the bio-signals measured by the
FIG. 2 is a graph showing the power at 5 to 15 Hz extracted from an ECG signal, power at 0 to 1 Hz, purity of the signal, power at 0 to 5 Hz, kurtosis of the signal, skewness of the signal, , And the entropy of the signal over time. Referring to FIG. 2, it can be seen that the eight signal characteristics described above rapidly increase or decrease in a similar section. Thus, it is confirmed that the interval in which the signal characteristic value changes abruptly is the interval in which the reliability of the signal is low. Referring to this, it can be seen that the reliability of the bio-signal can be determined using the eight signal characteristics described above.
On the other hand, the biological
The
At this time, the
In other words, when the valid bio-signal is not selected by the
At this time, the
That is, the
The
As described above, the health
Hereinafter, a health parameter estimation method (S100) according to an embodiment of the present invention will be described in detail.
FIG. 3 is a flowchart of a health parameter estimation method (S100) according to an embodiment of the present invention.
Referring to FIG. 3, a health parameter estimation method S100 according to an exemplary embodiment of the present invention includes a biological signal input step S110, a biological signal discrimination step S120, a biological signal estimation step S130, An invalidation determination step (S140), and a health parameter estimation step (S150).
The biological signal input step (S110) may be a step of receiving biological signals from a plurality of channels. At this time, the bio-signal can be measured in a non-contact manner in a non-restricting state, and can be any one of ECG, heart trajectory (BCG), and optical pulse wave (PPG). In other words, the bio-electrical signals can be measured by ECG, BCG, PPG, etc., which are measured in a non-contact manner in a non-restraint situation in which the subject is unaware of the subject, such as clothes, automobile seats, wheel chairs, .
The bio-signal discrimination step S120 may be a step of selecting a bio-signal having the highest reliability among the bio-signals input from the plurality of channels. At this time, the bio-signal discrimination step S120 may include a signal characteristic extraction step S121, a reliability determination step S122, a bio-signal selection step S123, Step S124.
The signal characteristic extraction step S121 may be a step of extracting signal characteristics of each of the bio-signals input from the plurality of channels. At this time, the signal characteristics include power at 5 to 15 Hz, power at 0 to 1 Hz, purity of the signal, power at 0 to 5 Hz, kurtosis of the signal, skewness of the signal, high frequency mask of the signal, And entropy.
The reliability determination step S122 may be a step of determining reliability for each bio-signal by classifying the signal characteristics extracted in the signal characteristic extraction step S121 using a classification algorithm.
The biological signal selection step (S123) may be a step of selecting the biological signal with the highest reliability.
If the reliability of the bio-signal selected in the bio-signal selection step S123 is not less than a predetermined value, the bio-signal validity determination step S124 may be determined to be invalid if the reliability of the bio-signal is less than a predetermined value.
In other words, the bio-signal discrimination step S120 is a step of discriminating the reliability of each bio-signal input from a plurality of channels and selecting a bio-signal having the highest reliability, only when the reliability of the selected bio- It can be judged as valid.
The estimated biomedical signal generation step (S130) may be a step of generating an estimated biomedical signal by combining all of the biomedical signals input from the plurality of channels, and if the biomedical signal selected in the biomedical signal validity determination step is determined to be invalid It may be a step that is performed only when it is performed.
In other words, when there is no valid living body signal among the living body signals input from the plurality of channels, it may be a step for estimating an effective living body signal.
The estimated bio-signal determination step S140 may be a step of determining the reliability of the estimated bio-signal generated in the estimated bio-signal generation step S130. In other words, in the estimated bio-signal determination step (S140), the reliability of the estimated bio-signal can be determined by extracting the signal characteristics of the estimated bio-signal and classifying it through a classification algorithm. If the reliability of the estimated bio- And if it is less than the predetermined value, it can be determined as invalid.
The signal characteristics used at this time are also the power at 5 ~ 15Hz, power at 0 ~ 1Hz, purity of the signal, power at 0 ~ 5Hz, kurtosis of signal, skewness of signal, high frequency mask of signal, Or the like.
The health parameter estimation step S150 may be a step of estimating a health parameter using a bio-signal. At this time, the bio-signal used for health parameter estimation may be a bio-signal selected in the bio-signal discrimination step S120. In other words, the health parameter estimation step (S150) uses the most reliable biomedical signal among the bio-signals input from the plurality of channels, and only when the bio-signal is judged to be valid in the bio-signal validity determination step (S124) . ≪ / RTI >
If the bio-signal having the highest reliability is determined to be invalid in the bio-signal validity determination step S124, the health parameter is estimated using the estimated bio-signal generated in the estimated bio-signal generation step S130 . At this time as well, the health parameter can be estimated only when the estimated bio-signal validity is determined to be valid in the estimated bio-signal validity determination step (S140).
Meanwhile, the health parameter estimation method (S100) according to an embodiment of the present invention includes the steps of inputting a bio-signal (S110), determining a bio-signal (S120), calculating an estimated bio-signal (S130) The invalidation determination step S140, and the health parameter estimation step S150 may be repeated at predetermined time intervals, thereby enabling health parameter estimation in real time.
As described above, the health parameter estimation method (S100) according to an embodiment of the present invention estimates a health parameter by selecting a bio-signal having the highest reliability among bio-signals input from a plurality of channels, Estimates the health parameters only when the selected biometric signal has a reliability lower than a predetermined value, combines all the inputted biometric signals to generate an estimated biometric signal, determines the validity of the estimated biometric signal, The estimation of the health parameter using the estimated bio-signal can improve the accuracy of the health parameter estimation and minimize the time during which the health parameter can not be estimated.
While the invention has been shown and described with reference to certain embodiments thereof, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims. It will be obvious to those of ordinary skill in the art.
100: a health parameter estimation system according to an embodiment of the present invention
110: a plurality of sensors
110a: first sensor
110b: second sensor
110c: third sensor
120: biological signal discrimination unit
130: Biometric signal estimator
140: health parameter estimating unit
S100: According to one embodiment of the present invention,
S110: Biological signal input step
S120: Bio-signal discrimination step
S121: Signal characteristic extraction step
S122: Reliability determination step
S123: Biological signal selection step
S124: Biometric signal uselessness determination step
S130: Estimated biological signal generation step
S140: Estimation of Inferred Biological Signal Invalidation Step
S150: Health parameter estimation step
Claims (18)
Wherein the reliability of each of the bio-signals measured from the plurality of sensors is determined, and only one bio-signal having the highest reliability among the reliability of the determined bio-signals is selected. When the reliability of the selected bio- A bio-signal discrimination unit for selecting an effective bio-signal for health parameter estimation only; And
And a health parameter estimator for estimating the health parameter using the selected valid bio-signal,
Wherein the biological signal is any one of an electrocardiogram (ECG), cardiac trajectory (BCG), and optical pulse wave (PPG), and the health parameter includes at least one of arrhythmia, heartbeat, body temperature, and stress level.
Wherein the bio-signal determination unit extracts signal characteristics of the respective bio-signals and classifies the extracted signal characteristics by a classification algorithm to determine reliability of the bio-signals.
The signal characteristics include at least one of power at 5 to 15 Hz, power at 0 to 1 Hz, purity of the signal, power at 0 to 5 Hz, kurtosis of the signal, skewness of the signal, high frequency mask of the signal, Wherein the health parameter estimating system comprises one.
The classification algorithm may be a support vector machine (SVM), an artificial neural network (ANN), a linear discriminant analysis (LDA), and a multiple linear regression analysis (MLRA) ). ≪ / RTI >
And a bio-signal estimator for generating an estimated bio-signal by combining the bio-signals when the reliability of the selected bio-signal is not equal to or more than a predetermined value,
Wherein the bio-signal discrimination unit judges the reliability of the estimated bio-signal and selects the estimated bio-signal as an effective bio-signal only when the reliability of the estimated bio-signal is at least a predetermined value.
Wherein the bio-signal estimating unit generates the estimated bio-signal by a Kalman filter.
Wherein the plurality of sensors is a non-contact type sensor that measures a living body signal without binding.
The reliability of each of the input bio-signals is determined, and one bio-signal having the highest reliability among the reliability of the bio-signals is selected, and the health parameter estimation is performed only when the reliability of the selected bio- A bio-signal discrimination step of selecting a valid bio-signal for the bio-signal; And
And a health parameter estimating step of estimating the health parameter using the selected valid bio-signal,
Wherein the bio-signal is any one of an electrocardiogram (ECG), cardiac trajectory (BCG), and optical pulse wave (PPG), and the health parameter includes at least one of arrhythmia, heartbeat, body temperature, and stress level.
Wherein the bio-signal discrimination step comprises:
Extracting a signal characteristic of each of the bio-signals;
A reliability determination step of classifying each of the extracted signal characteristics by a classification algorithm and determining reliability of each of the biological signals;
A bio-signal selecting step of selecting one bio-signal having the highest reliability among the reliability of each bio-signal judged; And
Determining whether the selected bio-signal is valid if the reliability of the selected bio-signal is equal to or greater than a predetermined value, and invalidating the bio-signal if the reliability of the selected bio-signal is less than a predetermined value.
The signal characteristics include at least one of power at 5 to 15 Hz, power at 0 to 1 Hz, purity of the signal, power at 0 to 5 Hz, kurtosis of the signal, skewness of the signal, high frequency mask of the signal, Lt; / RTI >
The classification algorithm may be a support vector machine (SVM), an artificial neural network (ANN), a linear discriminant analysis (LDA), and a multiple linear regression analysis (MLRA) ) ≪ / RTI >
An estimated bio-signal generation step of generating an estimated bio-signal by combining all the bio-signals when it is judged to be invalid in the bio-signal void determination step;
Further comprising a step of determining reliability of the estimated bio-signal to determine that the reliability of the estimated bio-signal is valid if the reliability of the estimated bio-signal is not less than a predetermined value,
Wherein the health parameter estimating step estimates a health parameter using the estimated living body signal when the estimated living body signal is valid.
Wherein the estimated bio-signal generation step generates the estimated bio-signal using a Kalman filter.
Wherein the bio-signal is measured in a non-contact manner in a non-binding state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160022882A KR101664323B1 (en) | 2016-02-25 | 2016-02-25 | Health Parameter Estimating System and Health Parameter Estimating Method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160022882A KR101664323B1 (en) | 2016-02-25 | 2016-02-25 | Health Parameter Estimating System and Health Parameter Estimating Method |
Publications (1)
Publication Number | Publication Date |
---|---|
KR101664323B1 true KR101664323B1 (en) | 2016-10-10 |
Family
ID=57146164
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020160022882A KR101664323B1 (en) | 2016-02-25 | 2016-02-25 | Health Parameter Estimating System and Health Parameter Estimating Method |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101664323B1 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101998114B1 (en) * | 2018-03-15 | 2019-07-10 | 한국과학기술연구원 | Method of monitoring stress using heart rate variability parameter selection in daily life |
WO2019143196A1 (en) * | 2018-01-19 | 2019-07-25 | 울산대학교 산학협력단 | Apparatus for generating artificial neural network and apparatus for predicting ventricular arrhythmia |
KR102033499B1 (en) | 2018-07-12 | 2019-10-18 | 동국대학교 산학협력단 | Apparatus and method for judging drowsiness |
US11317840B2 (en) | 2018-08-16 | 2022-05-03 | Korea Institute Of Science And Technology | Method for real time analyzing stress using deep neural network algorithm |
KR20230009182A (en) * | 2021-07-08 | 2023-01-17 | 강남대학교 산학협력단 | Non-invasive glucose sensor and method for measuring glucose |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20030063640A (en) * | 2002-01-23 | 2003-07-31 | 삼성전자주식회사 | Apparatus and method for recognizing user emotional status using short-time monitoring of physiological signals |
US20080200774A1 (en) | 2007-02-16 | 2008-08-21 | Hongyue Luo | Wearable Mini-size Intelligent Healthcare System |
JP2013085702A (en) * | 2011-10-18 | 2013-05-13 | Toyota Central R&D Labs Inc | Device and program for estimation of biosignals |
-
2016
- 2016-02-25 KR KR1020160022882A patent/KR101664323B1/en active IP Right Grant
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20030063640A (en) * | 2002-01-23 | 2003-07-31 | 삼성전자주식회사 | Apparatus and method for recognizing user emotional status using short-time monitoring of physiological signals |
US20080200774A1 (en) | 2007-02-16 | 2008-08-21 | Hongyue Luo | Wearable Mini-size Intelligent Healthcare System |
JP2013085702A (en) * | 2011-10-18 | 2013-05-13 | Toyota Central R&D Labs Inc | Device and program for estimation of biosignals |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019143196A1 (en) * | 2018-01-19 | 2019-07-25 | 울산대학교 산학협력단 | Apparatus for generating artificial neural network and apparatus for predicting ventricular arrhythmia |
KR101998114B1 (en) * | 2018-03-15 | 2019-07-10 | 한국과학기술연구원 | Method of monitoring stress using heart rate variability parameter selection in daily life |
KR102033499B1 (en) | 2018-07-12 | 2019-10-18 | 동국대학교 산학협력단 | Apparatus and method for judging drowsiness |
US11317840B2 (en) | 2018-08-16 | 2022-05-03 | Korea Institute Of Science And Technology | Method for real time analyzing stress using deep neural network algorithm |
KR20230009182A (en) * | 2021-07-08 | 2023-01-17 | 강남대학교 산학협력단 | Non-invasive glucose sensor and method for measuring glucose |
KR102535505B1 (en) * | 2021-07-08 | 2023-05-26 | 강남대학교 산학협력단 | Non-invasive glucose sensor and method for measuring glucose |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101664323B1 (en) | Health Parameter Estimating System and Health Parameter Estimating Method | |
Biswas et al. | Heart rate estimation from wrist-worn photoplethysmography: A review | |
CN108042108B (en) | Sleep quality monitoring method and system based on body vibration signals | |
JP6208372B2 (en) | Depression state determination method and depression state determination device | |
US20160038061A1 (en) | Method for detecting falls and a fall detector | |
JP5760351B2 (en) | Sleep evaluation apparatus, sleep evaluation system, and program | |
WO2018030380A1 (en) | Blood pressure state measurement device | |
JP6079824B2 (en) | Sleep evaluation apparatus and program | |
KR102202029B1 (en) | Method for estimating continuous blood pressure using recurrent neural network and apparatus thereof | |
Xie et al. | A personalized beat-to-beat heart rate detection system from ballistocardiogram for smart home applications | |
EP3643227B1 (en) | Minimum heart rate value approximation | |
JP2019513433A (en) | System and method for evaluating changes in heart rate of a subject | |
CN109310351A (en) | For characterizing the assessment system and method for the heart rate of object | |
Johnson et al. | Performance measures on blood pressure and heart rate measurement from PPG signal for biomedical applications | |
Alivar et al. | Motion detection in bed-based ballistocardiogram to quantify sleep quality | |
KR20180089118A (en) | Apparatus for monitoring of seismocardiography(scg) using accelerometer sensor and gyroscope sensor and method thereof | |
KR101659798B1 (en) | Noncontact heart rate monitoring system based on accelerometer attached on a chair and thereof method | |
JP5637583B2 (en) | Age estimation device, age estimation method and age estimation program by non-contact biological information collection | |
JP2018033795A (en) | Depressive state determination method and depressive state determination device | |
TWI629049B (en) | A method for analyzing a heart shock signal for calculating a short-term heart rate value | |
US20150313481A1 (en) | Cardiovascular screening diagnostic and monitoring system and method | |
NL2019604A (en) | System for estimation of pulse transit time and blood pressure | |
JP6557489B2 (en) | Biological state estimation device and computer program | |
Schumm et al. | Automatic signal appraisal for unobtrusive ECG measurements | |
Schumm et al. | ECG monitoring in an airplane seat: Appraising the signal quality |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GRNT | Written decision to grant |