WO2016168980A1 - 一种生理体征信息获取方法和系统 - Google Patents

一种生理体征信息获取方法和系统 Download PDF

Info

Publication number
WO2016168980A1
WO2016168980A1 PCT/CN2015/077026 CN2015077026W WO2016168980A1 WO 2016168980 A1 WO2016168980 A1 WO 2016168980A1 CN 2015077026 W CN2015077026 W CN 2015077026W WO 2016168980 A1 WO2016168980 A1 WO 2016168980A1
Authority
WO
WIPO (PCT)
Prior art keywords
algorithm
physiological
information
noise
result
Prior art date
Application number
PCT/CN2015/077026
Other languages
English (en)
French (fr)
Inventor
喻娇
赵纪伟
王智勇
Original Assignee
深圳市长桑技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市长桑技术有限公司 filed Critical 深圳市长桑技术有限公司
Priority to CN201580079047.4A priority Critical patent/CN107530016A/zh
Priority to US15/567,974 priority patent/US10758186B2/en
Priority to PCT/CN2015/077026 priority patent/WO2016168980A1/zh
Publication of WO2016168980A1 publication Critical patent/WO2016168980A1/zh

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A61B5/7207Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0062Arrangements for scanning
    • A61B5/0064Body surface scanning
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, 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
    • A61B5/024Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02416Detecting, measuring or recording pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, 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
    • A61B5/024Detecting, measuring or recording pulse rate or heart rate
    • A61B5/0245Detecting, measuring or recording pulse rate or heart rate by using sensing means generating electric signals, i.e. ECG signals
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • A61B5/318Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • A61B5/7246Details of waveform analysis using correlation, e.g. template matching or determination of similarity
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2560/00Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
    • A61B2560/02Operational features
    • A61B2560/0204Operational features of power management
    • A61B2560/0214Operational features of power management of power generation or supply
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/01Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, 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
    • A61B5/0205Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A61B5/02055Simultaneously evaluating both cardiovascular condition and temperature
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, 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
    • A61B5/021Measuring pressure in heart or blood vessels
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, 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
    • A61B5/024Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02405Determining heart rate variability
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/145Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A61B5/1455Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
    • A61B5/14551Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases

Definitions

  • the present invention relates to methods and systems for obtaining, processing, refining, and analyzing physiological sign information.
  • the living body produces and releases a great deal of life information all the time.
  • Life information can be summarized into two categories: chemical information (the composition of the chemical composition of the living body and its changes) and physical information (the shape, position, relative relationship of the organs of the living body, the force generated by the movement, heat, Sound, light and other related information).
  • the circulatory system of the heart and blood vessels of certain animals constitutes the blood circulation and is one of the most important organs and components of this type of animal.
  • the chemical and physical information of the cardiovascular system contains a large amount of information related to animal health.
  • one of the main techniques for diagnosing heart condition and performance is electrocardiogram (ECG).
  • ECG electrocardiogram
  • the animal body pulse system is an important part of the cardiovascular system, and is an important way for the animal to transport nutrients and transfer energy.
  • the pulse comes directly from the heart and is caused by fluctuations in the heart's contraction.
  • the left ventricle injects blood through the aortic valve into the aorta, causing pulsations in flow, pressure, and diameter on the arterial tree.
  • One of the important vital information generated by the pulse system is the pulse wave (PPG). Because the propagation characteristics of pulse wave (PPG) are closely related to the changes of mechanical parameters in the cardiovascular system, there is a large amount of animal physiological information. French 1860 Vierordt developed the first spring-loaded pulse pulsograph to obtain the pulse waveform.
  • baseline drift is known by the poor click-to-contact of the subject and the impedance change of the electrode-skin interface.
  • the frequency is usually less than 1 Hz for low-frequency interference signals; the power-frequency interference is the alternating capacitance and the magnetic field of the human body's distributed capacitance and the click electrode lead loop.
  • the interference caused by the influence is 50 Hz power frequency and its harmonics; myoelectric interference refers to interference caused by body shake and muscle tension, and its frequency range is generally large; motion/vibration interference is in the signal input process
  • the signal generator such as the transmission distance and angle of the light source, changes, thereby affecting the signal characteristics generated, causing the signal to be disturbed, distorted or submerged.
  • a system comprising: a receiving module for receiving at least one physiological information; a processing module comprising a feature extraction module, a matching operation module, and a calculation module; the feature extraction module adopting the first method and the second method Processing the physiological information separately to obtain the first type of features and the second type of features, the first method and the second method may be different; the matching operation module performs matching operations on the first type of features and the second type of features And matching the matching result; the calculation module calculates the physiological signs of the human body.
  • the processing module can include a pre-processing module.
  • the physiological information received by the receiving module includes at least one of ECG information and pulse information.
  • the first method is a peak detection algorithm
  • the second method is a PPG algorithm or an ECG algorithm.
  • the PPG algorithm and the ECG algorithm include but are not limited to one or more of a threshold method, a syntax pattern recognition, a Gaussian function decomposition method, a wavelet transform, an HTT method, a QRS wave detection algorithm, a local peak detection algorithm, and a peak detection algorithm. Ways. It should be noted that any algorithm that can obtain PPG results can be a PPG algorithm. Similarly, any algorithm that can get ECG results can be ECG. algorithm.
  • the matching operation module marks the peak result on the unmatched as a noise peak.
  • the step of determining the noise by the matching operation module includes the following steps: (1) calculating a noise ratio; (2) if the number of noise ratios is not less than 1 is greater than half of the number of algorithm result waves, or (3) If the number of noises is not less than 0.75, which is greater than 0.75 times the number of algorithm results, or (4) if the number of noises is not less than 0.5, the number of waves is greater than the number of algorithm results, then the physiological information is judged to be noisy. .
  • the algorithm result wave refers to a result wave obtained after the PPG algorithm or the ECG algorithm.
  • the calculation module calculates at least one of heart rate, blood pressure, blood oxygen saturation, body temperature, PR, and HRV values.
  • the method comprises: receiving at least one physiological information; pre-processing the physiological information.
  • the first method and the second method are respectively used to process the pre-processed physiological information to obtain a first type of feature and a second type of feature, and the first method and the second method may be different;
  • a class of features and the second type of feature perform a matching operation and mark the matching result; the noise of the physiological information is judged according to the matching result; and the physiological signs of the human body are calculated.
  • the pre-processing can include a filtering step.
  • the physiological information includes at least one of pulse information and electrocardiographic information.
  • the first method is a peak detection algorithm.
  • the second method is a PPG algorithm or an ECG algorithm.
  • the PPG algorithm and the ECG algorithm may include, but are not limited to, a threshold method, a syntax pattern recognition, a Gaussian function decomposition method, a wavelet transform, an HTT method, a QRS wave detection algorithm, a local peak detection algorithm, and a peak detection algorithm.
  • a threshold method a syntax pattern recognition
  • a Gaussian function decomposition method e.g., a wavelet transform
  • HTT method e.g., a QRS wave detection algorithm
  • a local peak detection algorithm e.g., a QRS wave detection algorithm
  • the marker matching result is to mark the peak result on the unmatch as a noise peak.
  • the step of determining noise includes the following steps: (1) calculating a noise ratio; (2) if the number of noise ratios is not less than 1 is greater than half of the number of algorithm result waves, or (3) If the number of noises is not less than 0.75, which is greater than 0.75 times the number of algorithm result waves, or (4) if the number of noises is not less than 0.5, the physiological information is judged to be noisy.
  • the noise ratio refers to a ratio of a noise peak amplitude value to a matching peak amplitude average value.
  • the algorithm result wave refers to a result wave obtained after the PPG algorithm or the ECG algorithm.
  • the physiological sign refers to at least one of heart rate, blood pressure, blood oxygen saturation, HRV, body temperature, and PR value.
  • FIG. 1 is an application scenario diagram of a physiological sign information acquisition system according to the present invention
  • FIG. 2 is a schematic view of a physiological sign information acquiring device according to the present invention.
  • FIG. 3 is a schematic diagram of a receiving module and surrounding modules in the physiological sign information acquiring device of the present invention
  • FIG. 4 is a schematic diagram of a processing module and surrounding modules in the physiological sign information acquiring device of the present invention.
  • FIG. 5 is a schematic diagram of an input/output module in a physiological sign information acquiring device according to the present invention.
  • FIG. 6 is a schematic diagram of a physiological sign information acquiring device according to the present invention.
  • FIG. 7 is a flow chart of a method for acquiring physiological sign information in the present invention.
  • FIG. 8 is a flow chart of a method for acquiring physiological sign information in the present invention.
  • FIG. 9 is a flow chart of a method for acquiring physiological sign information in the present invention.
  • FIG. 10 is a flow chart of a method for acquiring physiological sign information in the present invention.
  • Figure 11 is a timing diagram showing the relationship between the ECG signal and the PPG signal in the present invention.
  • the physiological sign information acquisition system referred to in this specification can be applied to various fields, including but not limited to: monitoring (including but not limited to elderly guardianship, middle-aged guardianship, youth and child care, etc.), medical diagnosis (including but not Limited to ECG diagnosis, pulse diagnosis, blood oxygen diagnosis, etc.), exercise monitoring (including but not limited to long-distance running, medium and short running, sprinting, cycling, rowing, archery, horse riding, swimming, climbing, etc.), hospital care (including but not Limited to critical patient monitoring, genetic disease patient monitoring, emergency patient monitoring), pet care (critical care pet care, newborn pet care, home pet care).
  • monitoring including but not limited to elderly guardianship, middle-aged guardianship, youth and child care, etc.
  • medical diagnosis including but not Limited to ECG diagnosis, pulse diagnosis, blood oxygen diagnosis, etc.
  • exercise monitoring including but not limited to long-distance running, medium and short running, sprinting, cycling, rowing, archery, horse riding, swimming, climbing, etc.
  • hospital care including but not Limited to critical patient monitoring
  • the physiological information acquisition system can acquire one or more physiological information of the living body, such as pulse, electrocardiogram, body temperature and other physical and chemical and biological information about the living body.
  • the physiological information acquisition system may have a receiving module for receiving one or more physiological information.
  • the physiological information acquisition system can have a processing module. It includes a preprocessing module, a feature extraction module, a matching operation module, and a calculation module.
  • the preprocessing module can preprocess the physiological information.
  • the feature extraction module may adopt the first method and the second method to separately process the pre-processed physiological information to obtain the first type feature and the second type feature.
  • the matching operation module may perform a matching operation on the first type of features and the second type of features and mark the matching result, and determine a noise result of the physiological information.
  • the calculation module can calculate the physiological signs of the human body.
  • Input and output modules can be used to output physiological signs.
  • the system can effectively detect the noise existing in the received physiological information data with a small amount of calculation, and perform corresponding matching and calibration.
  • the system can be easily applied to portable devices or wearable devices.
  • the system can continuously monitor the physiological information of the living body in real-time (or non-real-time) manner, and transmit the monitoring result to external devices (including but not limited to storage devices or cloud servers). For example, the system can continuously monitor the physiological signs of the user during a random period of time, such as minutes, hours, days, or months, or periodically monitor the physiological signs of the user. .
  • the system can display the physiological signs of the monitored living body in real time (also in non-real time), such as pulse, blood pressure, blood oxygen concentration and other information, and provide physiological information data to Related remote third parties, such as hospitals, nursing agencies, or related parties.
  • Related remote third parties such as hospitals, nursing agencies, or related parties.
  • users can use this system at home.
  • the physiological signs or physiological information data of the user monitored by the system can be provided to a remote hospital, a nursing institution, or a related person. Some or all of the user's physiological signs or physiological information data may also be stored to a local or remote storage device.
  • the above manner of transmitting physiological information data may be wired or wireless.
  • FIG. 1 shows an application scenario diagram of a physiological sign information acquisition system including, but not limited to, a physiological sign information acquisition device 101, a living body 102, and a transmission device 103.
  • the physiological sign information acquiring device 101 acquires, processes, refines, and/or analyzes physiological information from the living body 102.
  • the living body 102 herein includes, but is not limited to, a human body, and other living things such as animals, plants, and the like having physiological information are contained in the living body 102, and the living body 102 is not limited to a single living body.
  • Physiological information here includes, but is not limited to, body temperature, heart rate, pulse, brain waves, ultra-low frequency waves emitted by the human body, breathing, electrocardiogram, musculoskeletal state, organ morphology, organ location, organ status, fat, blood oxygen, blood sugar Physical and chemical and biological information such as blood concentration, platelet content, and the content of various components in the blood.
  • the transmission system 103 transmits the physiological information of the living body 102 to the physiological sign information acquiring device 101.
  • the signal transmitted by the transmission device 103 to the physiological sign information acquisition device 101 may be analog or digital, and may be real-time or non-real-time.
  • the transmission device 103 includes, but is not limited to, electronic, mechanical, physical, and chemical devices such as sensors, processors, single-chip microcomputers, embedded devices such as ARM, analyzers, and detectors.
  • the transmission mode of the transmission device 103 can be transmitted in a wireless manner including, but not limited to, radar, infrared, Bluetooth, etc., or can be transmitted through a wired manner including, but not limited to, a cable, an optical fiber, or the like.
  • the transmission device 103 can be directed to a specific living body, or to a plurality of specific living bodies, and can also be directed to a certain group, a class or a plurality of types of living bodies.
  • the transmission device 103 can also include a central database.
  • the physiological sign information acquiring device 101 can Collect physiological information either directly or indirectly.
  • the collected physiological information may be directly transmitted to the physiological sign information acquiring device 101 through the transmitting device 103 in real time, or may be transmitted to the physiological sign information acquiring device 101 through the transmitting device 103 in batches.
  • the physiological sign information acquiring device 101 may pass the physiological information through or not, and may also pass the physiological information through the transmitting device 103 for other purposes including, but not limited to, storage.
  • the physiological information of the living body 102 can be obtained by a heart rate collecting device, an electrocardiograph, a pulse wave detector, a brain wave detector, a vital signal detecting device, a respiratory detector, a portable monitoring device, a miniaturizing device, a non-contact monitoring device, and the like.
  • various physiological information collected from the living body 102 can be directly transmitted to the physiological sign information acquiring device 101 without passing through the transmitting device 103.
  • the physiological sign information acquiring device 101 can simultaneously acquire a plurality of different types of information directly from the plurality of living bodies 102 for comprehensive processing.
  • FIG. 2 is a schematic diagram of the physiological sign information acquiring apparatus 101.
  • the physiological sign information acquiring device 101 includes, but is not limited to, one or more components 210, one or more power sources 220, one or more external devices 230, and the like.
  • the component 210 includes, but is not limited to, a receiving module 201, a processing module 202, an input and output module 203, and the like.
  • the receiving module 201 is configured to receive the collected physiological information.
  • the receiving module 201 can receive physiological information by wire or wirelessly, or can directly collect physiological information.
  • the receiving module 201 may be distributed in the physiological sign information acquiring device 101 together with other modules, or may exist as a component separately from the physiological sign information acquiring device 101.
  • the receiving module 201 can be a local component or a remote component.
  • the receiving module 201 is not limited to the above-mentioned several ways, and the manner for obtaining physiological information should be within the scope of the claims of the present invention.
  • the processing module 202 is mainly used for calculating physiological information and main logical judgment.
  • the processing module 202 can be centralized or distributed, local or remote.
  • the input and output module 203 is for outputting or displaying physiological information.
  • the input output module 203 can include, but is not limited to, a display module (not shown) that can display combinations of symbols or symbols including, but not limited to, charts, liquid crystals, vibrations, numerical values, text, and or any particular semantics.
  • the input/output module 203 may also not include the display module, but may transmit information to other devices.
  • the transmission mode may be wired or wireless, and other devices may be local or remote.
  • Power source 220 generally refers to different embodiments that provide electrical energy.
  • the types of power sources described below are only partially applicable embodiments, and do not include all embodiments that can be applied to the physiological sign information acquisition system.
  • the power source includes, but is not limited to, an external power source, an internal battery, and a power generation device provided by the physiological sign information acquisition system.
  • External AC power is common but not limited to household or industrial AC power.
  • different countries or regions have different requirements for the voltage and frequency of household AC, such as but not limited to: 120V and 60Hz for the United States and Canada, 220V to 240V and 50Hz for European countries, and 230V for Australia and New Zealand.
  • connection between the physiological sign information acquisition system and the household alternating current may be through an internal wire connection or a standard plug connection.
  • the wire connection between the system and the household alternating current can be referred to, but not limited to, the following standards: US standards UL244A, UL514A, UL514B, UL514C, UL514D, CSA C22.2No.177, and NFPA70, European standard IEC/EN 61058-1, IEC/EN 61347-2-11 and IEC/EN 61347-1, etc., Australian Standards AS/NZS3123, AS/NZS3131, AS/NZS60320.1 and AS/NZS60320.2.2, etc., Japanese Standard JIS C 8281-2-1, etc. , Chinese standard GB16915.1, GB16915.2, GB16915.3 and EN60669.
  • the power source can also be wirelessly connected to the physiological sign information acquisition system.
  • energy can be transmitted from the power source to the information through inductive coupling. Get the system.
  • the technology can also transfer energy to the battery to supply the information acquisition system to operate.
  • the physiological sign information acquisition system may also use a battery (or a battery) as a power source, and the battery includes but is not limited to a disposable battery, and may be a rechargeable battery.
  • the types of batteries further include, but are not limited to, lead acid batteries, nickel cadmium batteries, nickel hydrogen batteries, lithium ion batteries, fuel cells, zinc manganese batteries, alkaline manganese batteries, lithium batteries, mercury batteries, and zinc mercury batteries.
  • the type of battery can also be other types. If a rechargeable battery is used, the battery can be charged through a physiological interface to extract the internal interface of the system, or the battery can be taken out and charged, or wireless charging technology can be used.
  • the external device 230 generally refers to various direct or indirect devices related to a certain device of the physiological sign information acquisition system, which may be local or remote, may be wired or wireless.
  • the external device 230 includes, but is not limited to, an external display screen, an alarm bell, a pager, a mobile phone, a computer, a tablet, a telephone, a video recorder, and the like.
  • the processing module 202 is respectively connected to the receiving module 201 and the input and output module 203, and the connection manner may be wired or wireless.
  • the receiving module 201 and the input/output module 203 may also be connected to each other, and the connection manner may be wired or wireless.
  • the receiving module 201, the processing module 202, and the input and output module 203 may have independent power sources, or may share two, two, or three or more of the same power source.
  • the receiving module 201, the processing module 202, and the input and output module 203 can be respectively connected to external devices, and a single external device can be connected to one or more modules, and the connection manner can be wired or wireless.
  • the processing module 202 may be connected to another processing module (not shown), or may be connected to a storage device (not shown) and/or a cloud server (not shown), and the connection manner may be wired. It can also be wireless.
  • the various modules and devices described above are not required, and it is possible for a person skilled in the art to understand the present principles and principles without departing from the principles and structures of the present invention.
  • Various modifications and changes in form and detail may be made in any combination, or the components may be combined with other modules, and such modifications and changes are still within the scope of the appended claims.
  • the receiving module 201 and the input and output module 203 shown in FIG. 2 may constitute a subsystem, which may be connected to an external device in a wired or wireless manner. Similar modifications are still within the scope of the claims of the present invention.
  • the receiving module 201 includes, but is not limited to, one or more receivers 301, one or more processors 302.
  • the receiving module 201 can be connected to the storage device 303 and other modules 304.
  • the storage device 303 may also be included in the receiving module 201.
  • the receiving module may be selectively connected to other one or more receiving modules 201-1, 201-2, and 201-N, or may not be connected to other receiving modules.
  • the receiving module may also be selectively connected to the other processing modules 202-1, 202-2, and 202-N, or may not be connected to the processing module.
  • the receiving module 201 can also be connected to the cloud server 305. All connections mentioned here can be wired or wireless. And the connection relationship between the receiving module 201 and the surrounding device is not limited to that shown in FIG. 3.
  • the receiving module 201 can receive physiological information according to a preset condition.
  • Physiological information may be affected by conditions such as blood vessel, blood vessel elasticity, and physical condition of the body at the time, such as when the heart rate, respiratory rate, and blood pressure of the person before and after exercise differ, before and after taking the medicine.
  • conditions such as blood vessel, blood vessel elasticity, and physical condition of the body at the time, such as when the heart rate, respiratory rate, and blood pressure of the person before and after exercise differ, before and after taking the medicine.
  • the receiving module 201 may integrate a corresponding motion compensation module to remove interference caused by motion/vibration of the living body.
  • the implementation of the motion compensation module includes but is not limited to a hardware filter, a software filter, a photoelectric sensor, and an acceleration. Sensors, shock sensors and a combination of the above. Additionally, the motion compensation module may perform a removal process on the motion/vibration noise in the pulse wave by adjusting the sensor.
  • the receiving module may be, but not limited to, an electronic or mechanical device such as a temperature sensor, a photodetector, a pressure sensor, a light emitting diode, or the like. Sensors may be affected by factors including, but not limited to, light intensity, skin color, skin roughness, skin temperature, skin moisture, ambient temperature, and environmental humidity. Therefore, it is also necessary to integrate corresponding environmental adaptation modules within the acquisition module, such as environmental factors.
  • the storage device 303 generally refers to all media that can read and/or write information, such as but not limited to random access memory (RAM) and read only memory (ROM).
  • RAM random access memory
  • ROM read only memory
  • RAM is, but not limited to, decimal counting tube, counting tube, delay line memory, Williams tube, dynamic random access memory (DRAM), static random access memory (SRAM), thyristor random access memory (T-RAM), and zero. Capacitor random access memory (Z-RAM), etc.
  • ROM has but is not limited to: bubble memory, magnetic button line memory, thin film memory, magnetic plate line memory, magnetic core memory, drum memory, optical disk drive, hard disk, magnetic tape, early NVRAM (nonvolatile memory), phase change Memory, magnetoresistive random storage memory, ferroelectric random access memory, nonvolatile SRAM, flash memory, electronic erasable rewritable read only memory, erasable programmable read only memory, programmable read only memory, shielded Heap memory, floating gate random access memory, nano random access memory, track memory, variable resistance memory, and programmable metallization cells.
  • bubble memory magnetic button line memory
  • thin film memory magnetic plate line memory
  • magnetic core memory magnetic core memory
  • drum memory optical disk drive
  • hard disk magnetic tape
  • early NVRAM nonvolatile memory
  • phase change Memory magnetoresistive random storage memory
  • ferroelectric random access memory ferroelectric random access memory
  • nonvolatile SRAM nonvolatile SRAM
  • flash memory electronic erasable rewr
  • Cloud storage is part of cloud computing. It connects one or more groups of remote servers mainly through the Internet, and realizes centralized storage and processing of data.
  • the cloud server 305 used in the physiological sign extraction system may be public, personal, or both.
  • the extracted life information, the data used by the processing module, and the corresponding parameters can be stored and calculated in the personal cloud.
  • the so-called personal cloud here needs to carry out a certain degree of identification in the process of reading and writing, and the data of some general calculation formulas or methods of vital signs can come from the public cloud.
  • the processing module 202 selects to read data in the personal cloud and the public cloud.
  • Processing module 202 includes, but is not limited to, one or more pre-processing modules 401, one or more feature extraction modules 402, one or more matching arithmetic modules 403, and one or more computing modules 404.
  • the pre-processing module 401 pre-processes the physiological sign information and transmits the pre-processed physiological information to the feature extraction module 402.
  • the feature extraction module 402 extracts the first type of features and the second type of features of the preprocessed physiological information, and passes the first type of features and the second type of features to the matching operation module 403.
  • the matching operation module 403 performs a matching operation on the first type of features and the second type of features, marks the matching result, and generates a third type of feature according to the result of the matching calculation, and transmits the third type of feature and the preprocessed vital signal to the Calculation module 404.
  • the calculation module 404 calculates the physiological signs of the human body according to the third type of characteristics of the pre-processed vital signal and/or the pre-processed vital signal.
  • Processing module 202 can be coupled to storage device 405 and other modules 406.
  • the storage device 405 can also be included in the processing module 202.
  • the processing module 202 may be selectively connected to other one or more receiving modules 201-1, 201-2, and 201-N, or may not be connected to other receiving modules.
  • the processing module 202 may also be selectively connected to the other one or more processing modules 202-1, 202-2, . . . 202-N, or may not be connected to the processing module.
  • the processing module 202 can also be connected to the cloud server 407. All connections mentioned here can be wired or wireless. And within the processing module 202, the connection relationship between the processing module 202 and the surrounding devices is not limited to that shown in FIG.
  • the processing module 202 can also receive physiological information directly from one or more modules of the storage device 405, other modules 406, the cloud server 407, the receiving module 201, and other processing modules, or the physiologically obtained after the processing is completed.
  • the vital sign information is stored in one or more modules of the storage device 405, other modules 406, the cloud server 407, the receiving module 201, and other processing modules. All such variations and modifications are within the scope of the appended claims.
  • the pre-processing module 401 performs a pre-processing step on the received physiological information, the pre-processing step including but not limited to a filtering step.
  • the pre-processing module 401 can include two or more sub-preprocessing modules simultaneously.
  • the pre-processing step may pre-process the physiological information by means of a serial connection or a cascade, or may control one or more sub-preprocessing modules to pre-process the physiological information through a control module (not shown). There may or may not be a connection between multiple sub-preprocessing modules.
  • the sub-preprocessing module can contain one or more pre-processing
  • the physiological steps can be pre-processed in a serial manner between multiple pre-processing steps, or the physiological information can be pre-processed in parallel.
  • the pre-processing step may be composed of one or more of pre-processing methods including, but not limited to, low pass filtering, band pass filtering, pass band filtering, wavelet transform filtering, morphological filtering, and Hilbert-Huang transform.
  • the pre-processing step may be a combination of time domain, frequency domain and/or time domain and frequency domain.
  • the pre-processing modules described above are not required, and those skilled in the art, after understanding the contents and principles of the present invention, may form the system without departing from the principles and structures of the present invention. And various modifications and changes in the details are intended to be included within the scope of the appended claims.
  • the pre-processing step adopts a method similar to, but not limited to, wavelet analysis to implement local conversion of time and frequency, and performs multi-scale refinement analysis on the signal, thereby extracting useful information from the physiological information.
  • the pre-processing module 401 is not necessary for the processing module 202, which may or may not participate in the process of acquiring physiological signs. Similar modifications are still within the scope of the claims of the present invention.
  • the feature extraction module 402 receives physiological information including, but not limited to, pre-processed by the pre-processing module 301. Feature extraction module 402 can also receive unprocessed physiological information, either directly or indirectly.
  • the feature extraction module 402 extracts the first type of features and the second type of features of the preprocessed physiological information.
  • the first type of feature and the second type of feature may be the same or different.
  • the first type of feature and the second type of feature may be composed of one or more characteristic values of pre-processed physiological information such as amplitude, frequency, peak, peak and valley, noise result, time information, period and envelope. .
  • the feature extraction module 402 uses the first method to extract the first type of features of the physiological information, and the second method to extract the second type of features of the physiological information.
  • the first method and the second method may be the same or different.
  • the first method and the second method may adopt threshold method, syntax pattern recognition, Gaussian function decomposition method, wavelet transform, HTT method, QRS wave detection algorithm, local peak detection algorithm, peak detection algorithm, linear discriminant analysis, and secondary discrimination.
  • the specific method may be any one of the above algorithms or a combination of any of a plurality of algorithms.
  • the various methods can be direct or indirect.
  • the feature extraction described above is not required, and it is possible for a person skilled in the art to understand the content and principles of the present invention, and the system may be implemented in a form and without departing from the principles and structures of the present invention.
  • Various modifications and changes in detail are intended to be included within the scope of the appended claims.
  • the first method described above consists of a method in which the threshold method and the wavelet transform are connected in series or in parallel.
  • the feature extraction method is replaced by other methods of amplitude, frequency, peak, valley, noise, time information, period and envelope of physiological information capable of extracting physiological information, and similar modifications are still within the scope of the claims of the present invention.
  • the feature extraction module 402 can be split into two feature extraction modules (not shown), and the two feature extraction modules use the same or different methods to extract the same type of feature values or different types of feature values of the physiological information, similar. The invention and the modifications are still within the scope of the claims of the invention.
  • the Nth type feature performs a matching operation, marks the matching result, and generates an N+1th feature according to the result of the matching calculation, and transmits the N+1th feature and the preprocessed vital signal to the calculation module 404.
  • the matching operation module 403 receives one or more kinds of information of physiological information, preprocessed physiological information, first type features or second type features, and performs matching operation on the received information.
  • Such matching operations include, but are not limited to, one or more types of matching such as range matching, value matching, time point matching, or envelope matching.
  • the matching result is then marked.
  • the tag includes, but is not limited to, marking the result on the match, marking the unmatched result, or marking the result on the match and the result on the unmatch, respectively.
  • a third type of eigenvalue of physiological information is generated based on the result of the labeling.
  • the third type of eigenvalues include, but are not limited to, one or more kinds of information such as amplitude, frequency, peak, peak and valley, noise result, time information, period and envelope of the physiological information after pre-processing.
  • the matching operations described above are not required, and those skilled in the art, after understanding the contents and principles of the present invention, may not deviate from the present invention.
  • various modifications and changes in form and detail may be made to the system, and such modifications and changes are still within the scope of the appended claims.
  • the matching operation module 403 may not generate the third type of feature value, and the module may directly use the matched result to perform the next operation, and similar modifications are still within the scope of the present invention.
  • the calculation module 404 receives one of the physiological information, the pre-processed physiological information, the first type of feature value of the physiological information, the second type of feature value of the physiological information, the third type of feature value of the physiological information, and the matching result of the mark or A variety.
  • the calculation module calculates physiological signs based on the received information.
  • the method of calculating physiological signs may employ, but is not limited to, one or more of methods such as direct calculation, intermittent calculation, continuous calculation, compensation calculation, wave velocity measurement, characteristic parameter measurement, and tension measurement. There can be links between multiple methods or no connection. You can have direct contact or indirect contact. They can be connected in parallel or in series.
  • the method based on the feature value or the matching result includes, but is not limited to, removing the feature value and the point marked by the matching result, the influence of the weakened feature value and the point marked by the matching result, the effect of the enhanced feature value and the point value marked by the matching result, One or more of the methods of ignoring the influence of the feature value and the point marked by the matching result.
  • Physiological signs include, but are not limited to, one or more of blood pressure, PR value, blood oxygen saturation, heart rate, heart murmur, bowel sounds, pH, creatinine content, transferase content, body temperature, and carcinoembryonic antigen content. .
  • the module calculates a plurality of physiological signs by a method, or calculates a physiological sign according to various methods, and the correction of the method for finally generating one or more physiological signs in the calculation module. And modifications are still within the scope of the claims of the present invention.
  • physiological signs of living organisms will change differently with different conditions.
  • the "white” phenomenon may cause a temporary increase in blood pressure.
  • Physiological signs are different when living in a home, company, mall, park, gym, leisure place, or elsewhere. In different emotions such as happiness, anger, nervousness, depression, fear There are also major differences in physical signs such as blood pressure when you are afraid, sad or anxious. In this case, a single measurement of physiological signs may not be able to truly reflect physiological characteristics. Therefore, when calculating physiological signs, it may be necessary to measure at different time periods, such as morning, noon, evening, and night. It may also be necessary to take measurements after different events, such as before and after taking the medicine, before and after the meal, before and after the exercise.
  • physiological signs may also be necessary to perform one or more measurements on physiological signs.
  • measurements include, but are not limited to, the treatment of multiple measurements of physiological signs in accordance with certain rules. For example, taking the average of multiple measurements, or obtaining physiological signs of a living body by calibration based on database-based parameter estimation and optimization such as curve fitting, artificial neural networks, and the like.
  • Various modifications and changes in form and detail may be made to the system without departing from the principles of the invention. It is still within the scope of the claims of the present invention. For example, one or more sets of physiological sign values are added to the processing module or the computing module for comparison to obtain a more realistic physiological sign value, and such modifications and variations are still within the scope of the claims of the present invention.
  • FIG. 5 is a schematic diagram of the input and output module 203.
  • Input output module 203 includes, but is not limited to, input key 501 and screen 502.
  • the input key 501 can be used as a shortcut key, and can be a function shortcut key, a return shortcut key, or a menu shortcut key.
  • the input key 503 can be a mechanical button, an electronic trigger button, or a touch button.
  • the screen 502 can have an input function, an output function, or an input/output function, and is an operation interface for the user to use the physiological sign information extraction system.
  • Input and output information types include, but are not limited to, numbers, analogs, text symbols, voice and graphic images.
  • the type of the screen 502 includes, but is not limited to, an electronic screen, a plasma screen, a resistive technology touch screen, a capacitive technology touch screen, an infrared technology touch screen, or a surface acoustic wave technology touch screen, etc., which can be selected according to specific use requirements.
  • the input and output module 203 can select input and output including but not limited to blood pressure, PR value, blood oxygen saturation, heart rate, heart murmur, bowel sound, PH value, creatinine content, transferase content, body temperature and carcinoembryonic antigen content and other physiological signs. One or more signs in the body.
  • the display content displayed on the screen can be set by the input key 501 or not by the input key 501.
  • the display content displayed on the screen can be set by default or not by the system default.
  • the input and output module 203 can also input and output local real-time weather information, weather forecast, room temperature, air humidity. And one or more of the information such as the time of each time zone in the world.
  • the input and output module 203 can also explain and further excavate the physiological sign information. For example, whether the physiological signs have abnormalities or physical signs indicated by physiological signs include, but are not limited to, the user's health index, compressive index, blood oxygen concentration, and blood lipid concentration. And whether the physical signs indicate the user's health risks and so on.
  • the input and output module 203 can transfer the content that needs to be output to the display screen display, and can also transfer the content that needs to be output to other devices, or deliver the outputted content to the storage device or the cloud server. It should be noted that the input/output module 203 may be integrated on the physiological sign information acquiring device, or may perform other modifications to the invention under the premise of implementing the input and output functions.
  • the input/output module 203 can be integrated as an input or output device on an external device, such as a watch, a wristband, a neck ring, a sphygmomanometer, a respiratory detector, a mobile phone, a laptop, a tablet, etc., and these deformations and Modifications are still within the scope of the claims of the present invention.
  • an external device such as a watch, a wristband, a neck ring, a sphygmomanometer, a respiratory detector, a mobile phone, a laptop, a tablet, etc.
  • Wired connections include, but are not limited to, the use of metal cables, optical cables, or hybrid cables of metal and optics.
  • coaxial cable, communication cable, flexible cable, spiral cable, non-metallic sheath cable, metal sheath cable, multi-core cable, twisted pair cable, ribbon cable, shielded cable, telecommunication cable, double-strand cable, Parallel twin conductors, and twisted pairs are examples described above.
  • other transmission signals such as electrical signals or optical signals.
  • Wireless connections include, but are not limited to, radio communications, free space optical communications, acoustic communications, and electromagnetic induction.
  • radio communication includes, but is not limited to, IEEE802.11 series standards, IEEE802.15 series standards (such as Bluetooth technology and Zigbee technology), first generation mobile communication technologies, second generation mobile communication technologies (such as FDMA, TDMA, SDMA).
  • CDMA, and SSMA, etc. general packet radio service technology, third-generation mobile communication technologies (such as CDMA2000, WCDMA, TD-SCDMA, and WiMAX), and fourth-generation mobile communication technologies (such as TD-LTE and FDD-LTE) Etc.), satellite communications (eg GPS technology, etc.), and other technologies operating in the ISM band (eg 2.4 GHz, etc.).
  • Free space optical communications include, but are not limited to, visible light, infrared, far infrared signals, and the like.
  • Acoustic communication includes but is not limited to sound waves, ultrasonic signals, and the like.
  • Electromagnetic induction includes but not Limited to near field communication technology. The examples described above are for convenience only, and the wirelessly connected medium may be of other types, such as Z-wave technology, other paid civilian radio bands, and military radio bands.
  • connection method may be used singly or in combination with a plurality of connection methods in the physiological sign information acquisition device. In the process of combining different connection modes, it is necessary to cooperate with the corresponding gateway device to achieve information interaction.
  • Individual modules can also be integrated to implement the functionality of more than one module from the same device. Each module may be distributed on different electronic components, or more than one module may be integrated on the same electronic component, or the same module may be divided into more than one electronic component.
  • External devices can also be integrated on the implementation device of one or more modules, and single or multiple modules can also be integrated on a single or multiple external devices.
  • Figure 6 is a specific embodiment of a physiological sign extraction system.
  • the system includes, but is not limited to, function keys 601, one or more display screens 602, one or more measurement terminals 603, one or more processing modules 604, one or more storage devices 605, and one or A plurality of power modules 606 and the like.
  • the function key 601 includes a power button, and may also include, but is not limited to, one of other function keys such as up and down adjustment, waveform display, stop, pause, return, multi-screen display, navigation key, quick measurement key, and the like. Or a variety of keys.
  • the implementation of the function keys includes, but is not limited to, a style as a mechanical button, or an inductive touch button.
  • the display screen 602 can be a liquid crystal display, or can be an electronic screen, a plasma screen, a resistive technology touch screen, a capacitive technology touch screen, an infrared technology touch screen, or a surface acoustic wave technology touch screen.
  • the display screen 602 can also implement the function of the function button 601.
  • the function button 601 can be displayed on the display screen 602 and perform its function through the display screen 602.
  • the display screen 602 can display the physiological signs such as electrocardiogram waveform, blood pressure, PR value, blood oxygen saturation, heart rate, heart murmur, bowel sound, PH value, creatinine content, transferase content, body temperature and carcinoembryonic antigen content.
  • the measuring end 603 can be measured by lead wire
  • One or more of the measurement methods such as the volume method, the chest measurement method, the leg measurement method, or the hand measurement method measure the physiological signs of the human body.
  • the processing module 604 is configured to further process the physiological information measured by the measuring end to obtain physiological signs.
  • the storage device 605 is used to store physiological sign data for a certain period of time, or can be used to store physiological volume data of a certain capacity.
  • the storage device here refers to all media that can read and/or write information.
  • the power module 606 is used to provide power, which may be a built-in power supply, or may be supplied by direct current or alternating current.
  • the built-in power supply can be in various forms such as a battery, a battery, a lithium battery, or a rechargeable battery.
  • the storage device 605 may not be limited to a local storage medium, and may also store related data in a related location that supports wireless storage, such as a cloud server or a network disk. Similar modifications and changes are still within the scope of the claims of the present invention, and there is no limitation on the size range of the storage, which can be adjusted according to actual conditions.
  • the storage time range may be more than 1 second, and the upper limit is determined according to the size of the memory, or more than 1 KB of data may be stored, and the upper limit is also determined according to the size of the memory, and the correction and change of the range size are still protected by the claims of the present invention.
  • the upper limit is determined according to the size of the memory, or more than 1 KB of data may be stored, and the upper limit is also determined according to the size of the memory, and the correction and change of the range size are still protected by the claims of the present invention.
  • FIG. 7 is a flow chart of an embodiment of an embodiment of physiological sign information noise verification and processing.
  • the pulse information of the animal body as the input physiological sign information may contain noise. First, you need to get the pulse information of the animal.
  • Step 701 Receive pulse information.
  • Step 702 Perform preprocessing on pulse information.
  • Step 703 The pre-processed pulse information obtains the PPG algorithm result and the PPG peak of the pulse wave through the PPG algorithm (step 703-1) and the peak detection algorithm (step 703-2), respectively. result;
  • Step 704 Perform matching calculation on the PPG algorithm result and the PPG peak result.
  • Step 705 If the PPG algorithm result matches the PPG peak result, the PPG peak result on the tag matching is performed;
  • Step 706 If the PPG algorithm result does not match the PPG peak result, it is determined as a PPG noise peak, the noise peak amplitude and the number are recorded, and the noise ratio is calculated according to the noise peak amplitude;
  • Step 707 Perform noise determination according to the noise ratio and the number of PPG noise peaks to obtain a PPG noise result.
  • Step 708 Calculate the physiological characteristics of the animal body according to the PPG noise result and the pulse information.
  • the pulse information is preprocessed in step 702.
  • a filtering step can be included.
  • the filter can select one or more filters such as a 1-30 Hz band pass filter, a low pass filter, a pass band filter, a wavelet transform filter, a Hilbert-Huang transform, or a morphological filter to filter the pulse wave.
  • the connection between multiple filters can be serial or parallel. It should be noted that the above pre-processing steps are not necessary.
  • step 703-1 the preprocessed pulse information is processed by using the PPG algorithm, and the PPG algorithm result is obtained.
  • the PPG algorithm described herein includes but is not limited to threshold method, syntax pattern recognition, Gaussian function decomposition method, wavelet transform, HTT method, QRS wave detection algorithm, local peak detection algorithm, peak detection algorithm, linear discriminant analysis, and secondary discrimination.
  • Step 703-2 uses the peak detection algorithm to enter the pulse information Peak detection is performed to obtain a PPG peak result.
  • an algorithm for peak detection may include the following steps:
  • the length of the window period can be set according to the situation.
  • it is not limited to 4s, and can be 1s, 2s, 3s, ⁇ Ns, and N is any positive real number.
  • the number of points to be traced forward or backward according to the current data point is not limited to 15 data points, and may be 1, 2, 3, 4, 5 ⁇ M data points. , where M is any positive integer.
  • the initial threshold setting can be calculated from the peak point of the initial window period record.
  • the first threshold is obtained by averaging all the peak point results in the initial window period and multiplying by a certain coefficient, such as 0.4.
  • a certain coefficient such as 0.4.
  • step 704 the PPG algorithm result and the PPG peak result determined in steps 703-1 and 703-2 are matched and calculated (the detailed description of the matching calculation can be seen below). And in step 705, the PPG peak result on the match is marked.
  • the PPG peak result on the unmatched in step 706 is referred to as the noise peak.
  • the noise ratio can be calculated according to the following formula:
  • Noise ratio noise peak amplitude value / matching peak amplitude average
  • the noise peak amplitude value may refer to the amplitude value of the PPG peak result on the unmatched, and the matching peak amplitude average may refer to the average of the amplitudes of the PPG peak results on the match.
  • a certain range can take, for example, 30 samples.
  • step 707 noise determination is performed.
  • the method steps for noise judgment are as follows:
  • Step a' if there is no match between the PPG algorithm result and the PPG peak result or there is no PPG algorithm result in the window period, it is judged to be noisy;
  • Step b' if the number of noises not less than 1 is greater than half of the number of waves of the PPG algorithm, it is judged to be noisy;
  • Step c' if the number of noises is not less than 0.75, which is greater than 0.75 times the number of waves of the PPG algorithm, it is judged to be noisy;
  • Step d' If the number of noises not less than 0.5 is larger than the number of waves of the PPG algorithm, it is judged to be noisy.
  • the physiological characteristics of the human body are determined based on the portion of the noise result determined in step 706.
  • the physiological signs may be calculated by one or more of the methods of removing the noise result portion determined in step 707, the noise result portion determined in step 707, or the noise result portion determined in step 707.
  • Physiological signs may include one or more of signs such as blood pressure, PR value, blood oxygen saturation, heart rate, heart murmur, HRV, bowel sounds, pH, creatinine content, transferase content, body temperature, and carcinoembryonic antigen content.
  • signs such as blood pressure, PR value, blood oxygen saturation, heart rate, heart murmur, HRV, bowel sounds, pH, creatinine content, transferase content, body temperature, and carcinoembryonic antigen content.
  • FIG 8 is a flow chart of another embodiment of the physiological sign information noise check and processing.
  • the pulse information and the electrocardiographic information of the animal body are used as physiological sign information.
  • Step 801 Receive pulse information and ECG information.
  • Step 802 Perform filter preprocessing on pulse information and ECG information.
  • Step 803 The pre-processed ECG information passes the ECG algorithm (Step 803-1), and the pulse The information is obtained by the peak detection algorithm (step 803-2), and the ECG algorithm result of the electrocardiogram information and the PPG peak result of the pulse wave (PPG) are respectively obtained;
  • Step 804 Perform a matching calculation on the ECG algorithm result and the PPG peak result.
  • Step 805 If the ECG algorithm result matches the PPG peak result, the PPG peak result on the matching is marked, and the pulse wave amplitude average value is calculated;
  • Step 806 If there is no match, it is determined as a PPG noise peak, and the noise peak amplitude and the number are recorded;
  • Step 807 Calculate a noise ratio according to a pulse wave amplitude average value and a noise peak amplitude
  • Step 808 Perform noise determination according to the noise ratio, the PPG noise peak, and the matched PPG peak result, to obtain a PPG noise result;
  • Step 809 Calculate physiological characteristics of the human body according to the PPG noise result, the pulse information and the ECG information.
  • pulse information and ECG information are pre-processed.
  • the preprocessing can include a filtering step.
  • the filter can select one or more filters such as a 1-30 Hz band pass filter, a low pass filter, a pass band filter, a wavelet transform filter, a Hilbert-Huang transform, or a morphological filter to filter the pulse wave. .
  • the connection between multiple filters can be serial or parallel. It should be noted that the above pre-processing steps are not necessary.
  • the ECG algorithm is used to process the pre-processed ECG information to obtain the ECG algorithm result.
  • the ECG algorithm described herein refers to one of methods including but not limited to threshold method, syntax pattern recognition, Gaussian function decomposition method, wavelet transform, HTT method, QRS wave detection algorithm, local peak detection algorithm and peak detection algorithm. Or a variety of methods. It should be noted that the ECG algorithm refers to any method that results in the ability to obtain an ECG, and any alternative to the ECG algorithm is within the scope of the claims of the present invention.
  • the peak detection result is obtained by performing peak detection on the pre-processed pulse information by using a peak detection algorithm. The steps of the peak detection algorithm may be the same as or different from the steps of the peak detection algorithm described in FIG. Detection algorithms for the purpose of obtaining peak results of pulse information are still within the scope of our claimed invention.
  • Step 804 performs a matching calculation on the ECG algorithm result and the PPG peak result determined in step 803 (see the following for details of the matching operation). And in step 805, the PPG peak result on the match is marked. Marking the peak results on the unmatch in step 806 is referred to as the noise peak.
  • the noise ratio in step 807 can be calculated according to the following formula:
  • Noise ratio noise peak amplitude value / matching peak amplitude average
  • the noise peak amplitude value may refer to the amplitude value of the PPG peak result on the unmatched, and the matching peak amplitude average may refer to the average of the amplitudes of the PPG peak results on the match.
  • the matching algorithm needs to delay the ECG algorithm result first because the R wave appears earlier than the PPG peak.
  • the number of points of delay may be 40, or any positive number whose absolute value is not greater than 100.
  • the matching calculation is then performed according to the matching algorithm described in FIG.
  • step 808 noise determination is performed, and the method of noise determination is as follows:
  • Step 808a If the ECG reports noise, it is determined that the PPG wave has no noise
  • Step 808b If the ECG algorithm result does not find a match, it is determined that the PPG wave is noisy;
  • Step 808c if the number of noises is not less than 1 and is greater than half of the number of waves of the ECG algorithm, it is determined that the PPG wave is noisy;
  • Step 808d if the number of noises is not less than 0.75, which is greater than 0.75 times of the number of waves of the ECG algorithm, it is determined that the PPG wave is noisy;
  • Step 808e If the number of noises not less than 0.5 is greater than the number of wave results of the ECG algorithm, it is determined that the PPG wave is noisy.
  • the physiological characteristics of the human body may be based on the noise result portion determined in step 808, and the noise result portion determined in step 808 may be removed, the noise result portion determined in step 808 may be enhanced, or the noise result portion determined in step 808 may be attenuated.
  • One or more of the methods are used to calculate physiological signs.
  • Physiological signs may include one or more of signs such as blood pressure, PR value, blood oxygen saturation, heart rate, HRV, heart murmur, bowel sounds, pH, creatinine content, transferase content, body temperature, and carcinoembryonic antigen content. kind.
  • FIG 9 is a flow chart of another embodiment of the physiological sign information noise check and processing.
  • pulse information and electrocardiographic information of the human body are used as physiological information.
  • Step 901 Receive pulse information and ECG information.
  • Step 902 Perform pre-processing on pulse information and ECG information.
  • Step 903 The pre-processed pulse information and the ECG information obtain the PPG algorithm result of the pulse wave and the ECG algorithm result of the ECG information through the PPG algorithm and the ECG algorithm, respectively, and simultaneously record the ECG noise result;
  • Step 904 Perform matching calculation on the foregoing ECG algorithm result and the PPG algorithm result.
  • Step 905 If the ECG algorithm result matches the PPG algorithm result, the PPG peak result on the tag matching is performed;
  • Step 906 If it does not match, it is determined as a PPG noise peak, and the noise peak amplitude and the number are recorded;
  • Step 907 Calculate a noise ratio according to the matched PPG algorithm result and the noise peak amplitude
  • Step 908 Perform noise determination according to the noise ratio and the PPG noise peak to obtain a PPG noise result.
  • Step 909 Calculate physiological characteristics of the human body according to the PPG noise result.
  • Step 902 when preprocessing the pulse information and the electrocardiogram information, includes at least one filtering step, and the filter may select a band pass filter of 1-30 Hz, a low pass filter, a pass band filter, a wavelet transform filter, and Hilbert- One or more filters, such as a Huang transform or a morphological filter, filter the pulse wave.
  • the relationship between the various filters can be serial or parallel.
  • step 903 the PPG algorithm is used to process the pulse information, and the PPG algorithm result is obtained.
  • ECG information is processed by ECG algorithm to obtain ECG algorithm results and ECG noise results in window period.
  • Step 904 may be the same as step 804 shown in FIG. 8, or may be different. Matching algorithms for the purpose of achieving the final PPG matching peak results are still within the scope of our claimed invention.
  • the calculation method of the noise ratio in step 907 may be the same as or different from step 807.
  • step 908 noise determination is performed, and the method steps of noise determination are as follows:
  • Step 908a If the ECG reports noise, it is determined that the PPG wave is noiseless;
  • Step 908b if the ECG algorithm result does not find a match, it is determined that the PPG wave is noisy;
  • Step 908c if the number of noises is not less than 1 is greater than half of the number of waves of the ECG algorithm, it is determined that the PPG wave is noisy;
  • Step 908d if the number of noises is not less than 0.75, which is greater than 0.75 times of the number of waves of the ECG algorithm, it is determined that the PPG wave is noisy;
  • Step 908e If the number of noise ratios not less than 0.5 is greater than the number of wave results of the ECG algorithm, it is determined that the PPG wave is noisy.
  • the physiological characteristics of the human body may be based on the noise result portion determined in step 908, and the noise result portion determined in step 908 may be removed, the noise result portion determined in step 908 may be enhanced, or the noise result portion determined in step 908 may be attenuated.
  • One or more of the methods are used to calculate physiological signs.
  • Physiological signs may include one or more of signs such as blood pressure, PR value, blood oxygen saturation, heart rate, HRV, heart murmur, bowel sounds, pH, creatinine content, transferase content, body temperature, and carcinoembryonic antigen content. kind.
  • FIG 10 is a flow chart of another embodiment of the physiological sign information noise check and processing.
  • pulse information and electrocardiographic information are used as physiological information.
  • the steps of the algorithm are as follows:
  • Step 1001 Receive pulse information and ECG information.
  • Step 1002 Calculate the noise information of the pulse information and the ECG information by using one or more algorithms of Algorithm A (Step 1002-1), Algorithm B (Step 1002-2), and Algorithm C (Step 1002-3), respectively.
  • Algorithm A, Algorithm B, and Algorithm C may be the same or different algorithms as described in Figures 7, 8, and 9.
  • Step 1003 Obtain an overall noise result according to one of the three noise results calculated in step 1002 or a plurality of noise results.
  • Step 1004 Calculate physiological signs of the human body.
  • step 1002 there may be multiple combinations, for example, only algorithm A, An algorithm in Algorithm B and Algorithm C, or a combination of any two algorithms using Algorithm A, Algorithm B, and Algorithm C, or Algorithm A, Algorithm B, and Algorithm C are used.
  • step 1003 there may be multiple combinations of modes, for example, using any one of three noise results, or a combination of any two noise results using three noise results, or using three noise results together.
  • the physiological characteristic of the human body calculated in step 1004 may be based on the noise result portion determined in 1003, and may be adopted in the method of removing the noise result portion determined in 1003, enhancing the noise result portion determined in 1003, or attenuating the noise result portion determined in 1003.
  • Physiological signs may include one or more of signs such as blood pressure, PR value, blood oxygen saturation, heart rate, HRV, heart murmur, bowel sounds, pH, creatinine content, transferase content, body temperature, and carcinoembryonic antigen content.
  • signs such as blood pressure, PR value, blood oxygen saturation, heart rate, HRV, heart murmur, bowel sounds, pH, creatinine content, transferase content, body temperature, and carcinoembryonic antigen content.
  • signs such as blood pressure, PR value, blood oxygen saturation, heart rate, HRV, heart murmur, bowel sounds, pH, creatinine content, transferase content, body temperature, and carcinoembryonic antigen content.

Abstract

本发明涉及生命体征提取方法和系统,该系统包括接收模块用于接收至少一种生理信息;特征提取模块采用第一种方法和第二种方法分别提取生理信息的第一类特征和第二类特征;处理模块对所述第一类特征和第二类特征进行匹配计算并标记匹配结果,根据匹配结果判断所述生理信息的噪声;计算模块计算人体的生理体征。

Description

一种生理体征信息获取方法和系统
说明
本申请与同一申请人于2015年4月20日提交的发明名称为“一种生命体征分析方法与系统”的PCT申请为相关申请,其全部内容以引用方式被完全包含在此。
技术领域
本发明涉及到生理体征信息的获取、处理、提炼和分析的方法和系统。
背景技术
生命体每时每刻都产生并释放着大量的生命信息。生命信息可概括成两大类:化学信息(组成生命体的化学成分构成及其变化相关的信息)和物理信息(生命体各器官的形态、位置、相对关系、运动所产生的力、热、声、光等相关信息)。某些动物的心脏和血管组成的循环系统,构成血液循环,是该类动物中最重要的器官与组成部分之一。心血管系统的化学和物理信息中包含了大量的与动物体健康有关的信息内容。其中,用于诊断心脏状况与表现的主要技术之一是心电图(ECG)。心电图将心脏跳动过程中所产生的体表电位差记录下来。1903年荷兰莱顿大学的生理学教授Einthoven采用弦线式电流计手册测出了心电图。除此之外,动物体脉搏系统是心血管系统的重要组成部分,是动物体输送养料、传递能量的重要途径。脉搏直接来自于心脏,是由心脏收缩引起的波动,左心室将血液通过主动脉瓣射入主动脉,导致动脉树上的流速、压力和直径的脉动。由此脉搏系统产生的重要生命信息之一是脉搏波(PPG)。由于脉搏波(PPG)的传播特性与心血管系统中的力学参数变化密切相关,其中蕴含着大量的动物体生理信息。1860年法国的 Vierordt研制出了第一台弹簧杠杆式脉搏描记器,用以得到脉搏波波形。
不论是脉搏波的测量还是心电图的测量,在连续检测过程中很容易受到一些噪声、伪迹和数据缺失等的干扰从而导致分析结果错误。一般情况下,所采集的信号中会存在以下几种常见的噪声干扰:基线漂移、工频干扰、肌电干扰和运动/震动干扰。其中基线漂移是因为受检者的点击接触不良及电极-皮肤界面阻抗变化所知,为低频干扰信号,其频率一般小于1Hz;工频干扰是人体分布电容和点击电极引线环路受到交流电和磁场的影响而产生的干扰,其频率为50Hz工频及其谐波;肌电干扰是指由于肌体抖动、肌肉紧张而引起的干扰,其频率范围一般较大;运动/震动干扰是在信号输入过程中,由于受检者或光源或传感器的运动或震动导致信号发生器,如光源的传输距离及角度发生变化,从而影响所产生的信号特性,导致信号被干扰、失真或淹没。
简述
本文披露了一种系统,包含以下模块:接收模块用于接收至少一种生理信息;处理模块,包含特征提取模块、匹配运算模块和计算模块;特征提取模块采取第一种方法和第二种方法分别处理生理信息,得到第一类特征和第二类特征,所述第一种方法和第二种方法可以不同;匹配运算模块对所述第一类特征和所述第二类特征进行匹配运算并标记匹配结果;计算模块计算人体的生理体征。所述处理模块可以包括一个预处理模块。
根据本申请的一个实施例,所述接收模块接收的生理信息包括心电信息和脉搏信息中的至少一种。
根据本申请的一个实施例,所述第一种方法是峰值检测算法,所述第二种方法是PPG算法或者ECG算法。所述PPG算法和ECG算法包括但不限于阈值法、句法模式识别、高斯函数分解法、小波变换、HTT方法、QRS波检测算法、局部峰值检测算法和峰值检测算法等方法中的一种或者多种方法。需要注意的是,任何能够得到PPG结果的算法都可以是PPG算法。类似地,任何能够得到ECG结果的算法都可以是ECG 算法。
根据本申请的一个实施例,所述匹配运算模块将未匹配上的峰值结果标记为噪声峰。
根据本申请的一个实施例,所述匹配运算模块判断噪声的步骤包括以下步骤:(1)计算噪声比例;(2)如果噪声比例不小于1的个数大于算法结果波个数的一半,或者(3)如果噪声比例不小于0.75的个数大于算法结果波个数的0.75倍,或者(4)如果噪声比例不小于0.5的个数大于算法结果波个数,则判断所述生理信息有噪声。
根据本申请的一个实施例,所述的算法结果波是指经过PPG算法或者ECG算法后得到的结果波。
根据本申请的一个实施例,所述计算模块计算心率、血压、血氧饱和度、体温、PR、HRV值中的至少一种。
本文还披露了一种方法。根据本申请的一个实施例,该方法包括:接收至少一种生理信息;对所述生理信息进行预处理。采用第一种方法和第二种方法分别处理预处理后的生理信息,得到第一类特征和第二类特征,所述第一种方法和所述第二种方法可以不同;对所述第一类特征和所述第二类特征进行匹配运算并标记匹配结果;根据匹配结果判断所述生理信息的噪声;计算人体的生理体征。所述预处理可以包括一个滤波步骤。
根据本申请的一个实施例,所述生理信息包括脉搏信息和心电信息中的至少一种。
根据本申请的一个实施例,所述第一种方法是峰值检测算法。所述第二种方法是PPG算法或者ECG算法。进一步的,所述PPG算法和ECG算法可以是包括但不限于阈值法、句法模式识别、高斯函数分解法、小波变换、HTT方法、QRS波检测算法、局部峰值检测算法和峰值检测算法等方法中的一种或者多种方法。需要注意的是,任何能够得到PPG结果或者ECG结果的算法都可以是PPG算法和ECG算法。
根据本申请的一个实施例,所述标记匹配结果是将未匹配上的峰值结果标记为噪声峰。
根据本申请的一个实施例,所述判断噪声的步骤包括以下步骤:(1)计算噪声比例;(2)如果噪声比例不小于1的个数大于算法结果波个数的一半,或者(3)如果噪声比例不小于0.75的个数大于算法结果波个数的0.75倍,或者(4)如果噪声比例不小于0.5的个数大于算法结果波个数,则判断所述生理信息有噪声。
根据本申请的一个实施例,所述噪声比例是指噪声峰幅度值与匹配峰幅度平均值的比值。
根据本申请的一个实施例,所述的算法结果波是指经过PPG算法或者ECG算法后得到的结果波。
根据本申请的一个实施例,所述的生理体征是指心率、血压、血氧饱和度、HRV、体温、PR值中的至少一种。
附图说明
图1为本发明中生理体征信息获取系统的应用场景图;
图2为本发明中生理体征信息获取装置的示意图;
图3为本发明中生理体征信息获取装置中接收模块及周围模块的示意图;
图4为本发明中生理体征信息获取装置中处理模块及周围模块的示意图;
图5为本发明中生理体征信息获取装置中输入输出模块的示意图;
图6为本发明中生理体征信息获取装置的一种示意图;
图7是本发明中生理体征信息获取方法的一种流程图;
图8是本发明中生理体征信息获取方法的一种流程图;
图9是本发明中生理体征信息获取方法的一种流程图;
图10是本发明中生理体征信息获取方法的一种流程图;
图11是本发明中ECG信号和PPG信号的时间关系示意图。
具体描述
为了更清楚的说明本发明实施例的技术方案,下面将对实施例描述 中所需要使用的附图做简单介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,但并不限定本发明的应用范围,对于本领域的普通技术人员来讲,在不付出创造性劳动的前提下,可以根据这些附图将本发明应用于其他类似场景。
本说明书涉及的生理体征信息获取系统可适用于多种领域,包括但不限于:监护(包括但不限于老年人监护,中年人监护,青年人及幼儿监护等)、医疗诊断(包括但不限于心电诊断,脉搏诊断,血氧诊断等)、运动监测(包括但不限于长跑,中短跑,短跑,骑车,划艇,射箭,骑马,游泳,爬山等)、医院护理(包括但不限于重症病人监测,遗传病病人监测,急诊病人监测)、宠物护理(危重症宠物护理,新生宠物护理,居家宠物护理)等。
该生理信息获取系统可以获取生命体的一种或多种生理信息,例如脉搏、心电、体温和其他有关生命体的物理和化学及生物信息。该生理信息获取系统可以有接收模块,用于接收一种或多种生理信息。该生理信息获取系统可以有处理模块。包含预处理模块、特征提取模块、匹配运算模块和计算模块。其中预处理模块可以对所述生理信息进行预处理。特征提取模块可以采取第一种方法和第二种方法分别处理预处理后的生理信息,得到第一类特征和第二类特征。匹配运算模块可以对所述第一类特征和所述第二类特征进行匹配运算并标记匹配结果,并判断生理信息的噪声结果。计算模块可以计算人体的生理体征。输入输出模块可以用于输出显示生理体征。该系统可以以较小的计算量,有效地检测出接收到的生理信息数据中存在的噪声,并做相应的匹配和标定。该系统可以方便地应用于便携设备或可穿戴设备上。该系统可以以实时(也可以非实时)的方式对生命体的生理信息进行不间断的监测,并将监测结果传输到外部设备(包括但不限于存储设备或云服务器)上。比如,该系统可以对用户在随机的一段时间内,如数分钟,数个小时,数天,或几个月内的生理体征进行连续的监测,也可以定期对用户的生理体征进行连续的监测。该系统可以实时(也可以非实时)显示所监测生命体的生理体征状况,如脉搏,血压,血氧浓度等信息,并将生理信息数据提供给 相关远程第三方,如医院,护理机构,或有关联人士等。例如,用户可以在家使用这个系统。由这个系统监测到的用户的生理体征状况或生理信息数据可以提供给远程的医院,护理机构,或有关联人士等。用户的生理体征状况或生理信息数据一部分或全部也可以存储到一个本地的或远程的存储设备。以上对生理信息数据的传送方式可以是有线,也可以是无线的。
以上对适用领域的描述仅仅是具体的示例,不应被视为是唯一可行的实施方案。显然,对于本领域的专业人员来说,在了解此种基于生理体征提取方法和系统的基本原理后,可能在不背离这一原理的情况下,对实施上述方法和系统的应用领域形式和细节上的各种修正和改变,但是这些修正和改变仍在以上描述的范围之内。
图1展示的是生理体征信息获取系统的应用场景图,该系统包括但不限于生理体征信息获取装置101,生命体102和传输装置103。其中,生理体征信息获取装置101获取、处理、提炼、和/或分析来自生命体102的生理信息。此处的生命体102包括但不限于人体,其他如动物、植物等拥有生理信息的生命皆包含在生命体102之中,且生命体102并不局限于某单个生命体。此处的生理信息包括但不局限于体温、心率、脉搏、脑电波、人体发出的超低频电波、呼吸、心电、肌肉骨骼状态、器官形态、器官位置、器官状况、脂肪、血氧、血糖、血液浓度、血小板含量以及血液中各种组分的含量等物理和化学及生物信息。传输系统103将生命体102的生理信息传输至生理体征信息获取装置101。传输装置103传递给生理体征信息获取装置101的信号可以是模拟的,也可以是数字的,可以是实时的也可以是非实时的。传输装置103包括但不限于传感器、处理器、单片机、ARM等嵌入式设备、分析仪、检测仪等电子、机械、物理、化学设备。传输装置103的传输方式可通过包括但不限于雷达、红外、蓝牙等无线方式传输,也可通过包括但不限于电缆、光纤等有线方式传输。传输装置103可以针对某一具体生命体,也可针对多个具体生命体,还可针对某一组、一类或者多类生命体。传输装置103还可以包括一个中央数据库。生理体征信息获取装置101可以 通过直接或者间接的方式来采集生理信息。所采集的生理信息可以直接实时的通过传输装置103传递给生理体征信息获取装置101,也可批量通过传输装置103传递给生理体征信息获取装置101。生理体征信息获取装置101对生理信息经过或者不经过处理,还可将生理信息通过传输装置103以做包括但不限于存储等其他用途。生命体102的生理信息可通过心率采集设备、心电图检测仪、脉搏波检测仪、脑电波检测仪、生命信号探测设备、呼吸探测仪、便携式监测设备、微型化设备、非接触式监测设备等方法获取;也可利用可穿戴的智能或非智能体温监控、腕式电子血压计、心脏检测仪、血糖仪、腕式脉搏监测器、环境污染监测口罩、智能或非智能手环、智能或非智能手表、智能或非智能颈环等方法获取。以上对生理体征信息获取系统应用场景的描述仅仅是某一具体的示例,不应被视为是唯一可行的实施方案。显然,对于本领域的专业人员来说,在了解生理体征信息获取系统的基本原理后,可能在不背离这一原理的情况下,对生理体征获取系统的应用方式进行形式或细节上的各种修正和改变,但是这些修正和改变仍在以上描述的范围之内。例如,从生命体102所采集的各种生理信息可以不通过传输装置103而直接传递给生理体征信息获取装置101。生理体征信息获取装置101也可以同时从多个生命体102直接获取多种不同类别的信息进行综合处理。这些修正和改变仍在本发明的权利要求保护范围之内。
图2所示的是生理体征信息获取装置101示意图。生理体征信息获取装置101包括但不限于一个或多个组件210、一个或多个电源220和一个或多个外部设备230等。其中组件210包括但不限于接收模块201、处理模块202和输入输出模块203等。接收模块201用于接收采集的生理信息。接收模块201可以通过有线或者无线方式接收生理信息,也可以直接采集生理信息。接收模块201可以和其他模块集中分布于生理体征信息获取装置101中,也可脱离生理体征信息获取装置101单独作为一个组件存在。接收模块201可以是本地组件也可以是远程组件。需要注意的是,接收模块201并不局限于上文所提到的几种方式,以能够获取生理信息为目的的方式都应该在本发明的权利要求保护范围以内。处 理模块202主要用于对生理信息进行计算和主要逻辑判断。处理模块202可以是集中式的也可以是分布式的、可以是本地的也可以是远程的。输入输出模块203用于输出或显示生理信息。输入输出模块203可包含但不限于显示模块(图中未显示),显示模块可显示包含但不限于图表、液晶、振动、数值、文字和或任意具有特定语义的符号或符号的组合。输入输出模块203也可不包含显示模块,而是将信息传递给其他设备,传输方式可以是有线的也可以是无线的,其他设备可以是本地的也可以是远程的。
电源220泛指能提供电能量的不同实施例。以下介绍的电源类型只是部分可以适用的实施例,并不包括所有可以适用于该生理体征信息获取系统的实施例。电源包括但不限于外接电源,内蓄电池,该生理体征信息获取系统自带的发电设备。其中外接交流电源常见但不局限于家用或工业交流电源。进一步的,不同国家或地区对家用交流电的电压和频率有不同的要求,例如但不限于:美国和加拿大基本使用120V和60Hz,欧洲各国大多使用220V至240V和50Hz的组合,澳大利亚和新西兰使用230V或240V和50Hz,阿根廷和智利使用220V和50Hz,巴西使用110V或220V和60Hz,埃及、南非、和摩洛哥大多使用220V和50Hz,沙特阿拉伯使用127V或220V和60Hz,土耳其使用230V和50Hz,日本使用100V和50Hz(东部)或60Hz(西部),中国大陆、香港特别行政区、和澳门特别行政区使用220V和50Hz,韩国使用220V和60Hz,而中国台湾使用110V和60Hz的标准。进一步的,该生理体征信息获取系统和家用交流电的连接可以是通过内部电线的连接,也可以是用标准插头进行连接。其中该系统和家用交流电之间的电线连接可以参考但不限于以下标准:美国标准UL244A、UL514A、UL514B、UL514C、UL514D、CSA C22.2No.177和NFPA70等,欧洲标准IEC/EN 61058-1、IEC/EN 61347-2-11和IEC/EN 61347-1等,澳洲标准AS/NZS3123、AS/NZS3131、AS/NZS60320.1和AS/NZS60320.2.2等,日本标准JIS C 8281-2-1等,中国标准GB16915.1、GB16915.2、GB16915.3和EN60669等。以上列举的电压、频率、家用电源标准只是为了便于说明的一部分例子,其它 类型的电压、频率、家用电源标准也可适用于生理体征信息获取系统,例如:电源也可以用无线的方式连接到生理体征信息获取系统,例如,通过电感耦合可以将能量从电源传输到该信息获取系统。该技术也可以将能量传输到电池进而供应该信息获取系统运作。
该生理体征信息获取系统也可以使用电池(或称为蓄电池)作为电源,电池包括但不限于一次性电池,也可以是可充电电池。电池的种类进一步包括但不限于铅酸电池、镍镉电池、镍氢电池、锂离子电池、燃料电池、锌锰电池、碱锰电池、锂电池、水银电池、和锌汞电池。当然电池的种类也可以是其它类型。如果使用可充电电池,对电池的充电可以通过一个生理体征提取系统内部的接口,也可以将电池取出充电,也可以使用无线充电技术等。
外部设备230泛指与生理体征信息获取系统的某个设备相关的各种直接或间接的设备,可以是本地的也可以是远程的、可以是有线的也可以是无线的。例如,外部设备230包括但不限于外接显示屏,警铃,呼叫器,手机,电脑,平板电脑,电话,录像机等。
处理模块202分别和接收模块201和输入输出模块203连接,连接的方式可以是有线的也可以是无线的。接收模块201和输入输出模块203也可以相互连接,其连接方式可以是有线的,也可以是无线的。接收模块201、处理模块202和输入输出模块203可以有各自独立的电源,也可以两两共享、三者或三者以上共享同一个电源。接收模块201、处理模块202和输入输出模块203可以分别连接外部设备,单个外部设备可以连接一个或多个模块,连接方式可以是有线的,也可以是无线的。处理模块202可以和另一个或多个处理模块(图中未体现)相连,也可以和存储设备(图中未体现)和/或云端服务器(图中未体现)相连,连接方式可以是有线的,也可以是无线的。上文所描述的各个模块和设备并不是必须的,对于本领域的专业人员来说,在了解本发明内容和原理后,都可能在不背离本发明原理、结构的情况下,对该系统进行形式和细节上的各种修正和改变,各个模块可以任意组合,或者构成子系统与其它模块连接,而这些修正和改变仍在本发明的权利要求保护范围之内。例 如图2所示的接收模块201和输入输出模块203可以构成一个子系统,该子系统可以以有线或无线的方式再与外部设备相连。类似的变形仍在本发明的权利要求保护范围之内。
图3所示的是接收模块201和周围设备的示意图。接收模块201包含但不限于一个或多个接收器301、一个或多个处理器302。接收模块201可以和存储设备303以及其他模块304相连。其中存储设备303也可以包含在接收模块201之内。另外,接收模块可以和其他一个或者多个接收模块201-1、201-2、和201-N有选择的相连,也可以不连接其他接收模块。接收模块也可以和其他一个或者多个处理模块202-1、202-2、和202-N有选择的相连,也可以不连接处理模块。接收模块201还可以和云服务器305相连。这里所提及的所有连接都可以是有线或无线的。并且接收模块201内部,接收模块201与周围设备的连接关系并不局限于图3所示。
接收模块201可以根据预先设定的条件接收生理信息。生理信息会受当时的血管、血管弹性以及身体的生理状况等条件的影响,例如当人在运动前和运动后的心率、呼吸率、血压有所不同,在吃药前和吃药后的状况也有所不同,在睡觉前和睡觉后的生理体征也存在较大的区别。因此在计算真实的生理体征时,应该考虑到生命体的外在因素和内在因素,预先设定体征参数,并将体征参数传递给后续的处理模块。例如,接受模块201内部可以集成相应的运动补偿模块,用以去除生命体运动/震动所导致的干扰,该运动补偿模块的实现形式包括但不限于硬件滤波器、软件滤波器、光电传感器、加速度传感器、震动传感器及上述几种形式的结合使用。另外地,该运动补偿模块可以通过调节传感器对脉搏波中的运动/震动噪声进行去除处理。另外,接收模块可采用但不限于温度传感器、光电检测器、压力传感器、发光二极管等电子或者机械设备。传感器会受到包括但不限于光强、肤色、皮肤粗糙度、皮肤温度、皮肤湿度、环境温度、环境湿度等因素的影响,因此也需要采集模块内部集成相应的环境适应模块,如与环境影响因素相对应的修正或者补偿模块。对本领域的专业人员来说,在了解本发明内容和原理后,都可能在 不背离本发明原理结构的情况下,对该系统进行形式和细节上的各种修正和改变,而这些修正和改变仍在本发明的权利要求保护范围以内。例如体征参数不仅可以在接收模块进行设定,还可以预存在数据库中,根据数据库中的资料进行体征参数的设定,这种修正和变形仍在本发明的权利要求保护范围之内。不光如此,上述的修正或者补偿模块亦可集成于预处理模块、处理模块或者计算模块之中,上述对生理体征系统的修正、变形或改变均应在本发明所保护的范围之内。
所有数据在经由接收模块201收集和处理后,都会有选择的存入存储设备303和云服务器305,以便进行后续处理。这里提到的存储设备303泛指所有可以读取和(或)写入信息的媒介,例如但不局限于随机存储器(RAM)和只读存储器(ROM)。其中RAM有但不限于:十进计数管、选数管、延迟线存储器、威廉姆斯管、动态随机存储器(DRAM)、静态随机存储器(SRAM)、晶闸管随机存储器(T-RAM)、和零电容随机存储器(Z-RAM)等。ROM又有但不限于:磁泡存储器、磁钮线存储器、薄膜存储器、磁镀线存储器、磁芯内存、磁鼓存储器、光盘驱动器、硬盘、磁带、早期NVRAM(非易失存储器)、相变化内存、磁阻式随机存储式内存、铁电随机存储内存、非易失SRAM、闪存、电子抹除式可复写只读存储器、可擦除可编程只读存储器、可编程只读存储器、屏蔽式堆读内存、浮动连接门随机存取存储器、纳米随机存储器、赛道内存、可变电阻式内存、和可编程金属化单元等。以上提及的存储设备只是列举了一些例子,该系统可以使用的存储设备并不局限于此。
除此以外,数据的读写还可以通过云存储的方式。云存储是云计算的一部分,主要通过互联网来连接一组或多组远端服务器,并实现数据的集中存储和处理。在生理体征提取系统中所使用的云服务器305可以是公共、个人的,或者二者并用的。例如,所提去的生命信息,处理模块所使用的数据和相应参数都可以在个人云中存储和计算。这里所谓个人云在读写过程中都需要进行一定程度的身份识别,而一些生命体征的普遍的计算公式或者方法等的数据可以来自于公共云。由处理模块202来选择读取个人云和公共云中的数据。
图4是处理模块202和周围设备连接的示意图。处理模块202包括但不限于一个或多个预处理模块401、一个或多个特征提取模块402、一个或多个匹配运算模块403以及一个或多个计算模块404。预处理模块401对生理体征信息进行预处理,并将预处理后的生理信息传递给特征提取模块402。特征提取模块402提取预处理后的生理信息的第一类特征和第二类特征,并将第一类特征和第二类特征传递给匹配运算模块403。匹配运算模块403对第一类特征和第二类特征进行匹配运算,对匹配结果进行标记,并根据匹配计算的结果产生第三类特征,将第三类特征和预处理后的生命信号传递给计算模块404。计算模块404根据预处理后的生命信号的第三类特征和/或预处理后的生命信号计算人体的生理体征。处理模块202可以和存储设备405以及其他模块406相连。其中存储设备405也可以包含在处理模块202之内。另外,处理模块202可以和其他一个或者多个接收模块201-1、201-2、和201-N有选择的相连,也可以不连接其他接收模块。处理模块202也可以和其他一个或者多个处理模块202-1、202-2···202-N有选择的相连,也可以不连接处理模块。处理模块202还可以和云服务器407相连。这里所提及的所有连接都可以是有线或无线的。并且处理模块202内部,处理模块202与周围设备的连接关系并不局限于图4所示。处理模块202还可直接从存储设备405、其他模块406、云服务器407、接收模块201、和其他处理模块等模块中的一个或者多个模块中接收生理信息,也可以将处理完成后得到的生理体征信息存储在存储设备405、其他模块406、云服务器407、接收模块201、和其他处理模块等模块中的一个或者多个模块中。类似的变形和修改都在本发明的权利要求保护范围之内。
预处理模块401对所接收到的生理信息进行预处理步骤,该预处理步骤包括但不限于一个滤波步骤。预处理模块401可同时包含两个或者两个以上的子预处理模块。该预处理步骤可通过串联或级联的方式对生理信息进行预处理,或者可以通过控制模块(图中未显示)来控制一个或者多个子预处理模块对生理信息进行预处理。多个子预处理模块之间可存在联系,也可不存在联系。子预处理模块可包含一个或者多个预处 理步骤,多个预处理步骤之间可通过串行的方式对生理信息进行预处理,也可通过并行的方式对生理信息进行预处理。预处理步骤可由包括但不限于低通滤波、带通滤波、通带滤波、小波变换滤波、形态学滤波与Hilbert-Huang变换法等预处理方法中的一个或者多个组成。预处理步骤可采用时域、频域和/或时域和频域相结合的方式。上文所描述的预处理模块并不是必须的,对于本领域的专业人员来说,在了解本发明内容和原理后,都可能在不背离本发明原理、结构的情况下,对该系统进行形式和细节上的各种修正和改变,而这些修正和改变仍在本发明的权利要求保护范围之内。例如,预处理步骤采取类似于但不限于小波分析等方法实现时间和频率的局域变换,对信号进行多尺度细化分析,从而从生理信息中提取出有用信息。还需要注意的是,预处理模块401对于处理模块202并不是必须的,该模块可以消除或者并不参与生理体征获取的过程之中。类似的变形仍在本发明的权利要求保护范围之内。
特征提取模块402接收包括但不限于预处理模块301预处理后的生理信息。特征提取模块402还可直接或间接的接收未经处理的生理信息。特征提取模块402提取预处理后的生理信息的第一类特征和第二类特征。第一类特征和第二类特征可以相同,也可以不同。第一类特征和第二类特征可以由预处理后的生理信息的幅度、频率、峰值、峰谷、噪声结果、时间信息、周期与包络性等特征中的一种或者多种特征值组成。特征提取模块402采用第一种方法提取生理信息的第一类特征,采用第二种方法提取生理信息的第二类特征。第一种方法和第二种方法可以相同,也可以不同。第一种方法和第二种方法可采取阈值法、句法模式识别、高斯函数分解法、小波变换、HTT方法、QRS波检测算法、局部峰值检测算法、峰值检测算法、线性判别分析、二次判别分析、最大熵分类器、决策树、决策表、核估计、近邻法、朴素贝叶斯分类器、神经网络、视感控器、支持向量机、基因表达式编程、分级群聚、k均值聚类、相关聚类、核主成分分析、提升方法、贝叶斯网络、马尔科夫随机场、多重线性主成分分析、卡尔曼滤波器、粒子滤波器、高斯过程回归、线性回归或拓展、独立成分分析、主成分分析、条件随即域、隐马尔科夫 模型、最大熵马尔科夫模型、递归神经网络、关联式规则、归纳逻辑编程、相似性度量学习、深度神经网络、深度信念网络、卷积神经网路、卷积深度信念网络等。所述特定的方法可为上述任意一种算法或者任意多种算法的组合。各种方法之间可以是直接联系,也可以是间接联系。上文所描述的特征提取并不是必须的,对于本领域的专业人员来说,在了解本发明内容和原理后,都可能在不背离本发明原理、结构的情况下,对该系统进行形式和细节上的各种修正和改变,而这些修正和改变仍在本发明的权利要求保护范围之内。例如,上述第一种方法由阈值法和小波变换经过串联或并联的方法组成。特征提取方法被其他能够提取生理信息的生理信息的幅度、频率、峰值、峰谷、噪声、时间信息、周期与包络性的方法替代,类似的变形仍在本发明的权利要求保护范围之内。又例如,特征提取模块402可拆分为两个特征提取模块(图中未显示),两个特征提取模块使用相同或者不同的方法提取生理信息的同一类特征值或者不同类特征值,类似的发明和变形仍在本发明的权利要求保护范围内。再例如,我们可以采取上述列举的方法提取生理信息的第一类、第二类、。。。到第N类特征,这里N为不小于2的正整数,然后再利用匹配运算模块403对第一类、第二类、。。。第N类特征进行匹配运算,对匹配结果进行标记,并根据匹配计算的结果产生第N+1类特征,将第N+1类特征和预处理后的生命信号传递给计算模块404。
匹配运算模块403接收生理信息、预处理的生理信息、第一类特征或第二类特征等信息的一种或者多种信息,并对接收到的信息进行匹配运算。该种匹配运算包括但不限于范围的匹配、数值的匹配、时间点的匹配或包络的匹配等一种或者多种的匹配。其后对匹配结果进行标记。该标记包括但不限于对匹配上的结果标记、对未匹配的结果做标记或者对匹配上的结果和未匹配上的结果分别做标记等。根据标记后的结果产生生理信息的第三类特征值。第三类特征值包括但不限于预处理后的生理信息的幅度、频率、峰值、峰谷、噪声结果、时间信息、周期与包络性等一种或者多种信息。上文描述的匹配运算并不是必须的,对本领域的专业人员来说,在了解本发明内容和原理后,都可能在不背离本发明 原理、结构的情况下,对该系统进行形式和细节上的各种修正和改变,而这些修正和改变仍在本发明的权利要求保护范围之内。例如,上述匹配运算模块403可以不产生第三类特征值,该模块可直接利用匹配后的结果来进行下一步操作,类似的变形仍在本发明的权利要求保护范围之内。
计算模块404接收生理信息、预处理后的生理信息、生理信息的第一类特征值、生理信息的第二类特征值、生理信息的第三类特征值和标记的匹配结果中的一种或者多种。计算模块基于所接收的信息计算生理体征。计算生理体征的方法可采用但不限于直接计算、间歇式计算、连续计算、补偿计算、波速测定、特征参数测定、张力测定等方法中的一种或多种方法。多种方法之间可以有联系,也可以没有联系。可以直接有联系,也可以间接有联系。可以并联,也可以串联。基于特征值或者匹配结果的方法包括但不限于去除特征值和匹配结果所标注的点、减弱特征值和匹配结果所标注的点的影响、增强特征值和匹配结果所标注的点值的影响、忽视特征值和匹配结果所标注的点的影响等方法中的一种或者多种。生理体征包括但不限于血压、PR值、血氧饱和度、心率、心脏杂音、肠鸣音、PH值、肌酐含量、转移酶含量、体温和癌胚抗原含量等体征中的一种或者多种。上文描述的计算模块中的各种方法都不是必须的,对本领域的专业人员来说,在了解本发明内容和原理后,都可能在不背离本发明原理结构的情况下,对该系统进行形式和细节上的各种修正和改变,而这些修正和改变仍在本发明的权利要求保护范围之内。例如,计算生理体征时该模块通过一种方法计算出多种生理体征,或者根据多种方法计算出一种生理体征,这种在计算模块中最后生成一种或多种生理体征的方法的修正和变形仍在本发明的权利要求保护范围之内。
值得注意的是,生命体的生理体征会随着不同的条件变化而产生不同的变化。譬如,“白衣”现象可能会引起血压的暂时性升高。当生命体在家、公司、商场、公园、健身房、休闲场所、或者在其他地方时生理体征也会不同。处于不同的情绪下例如高兴、愤怒、紧张、郁闷、恐 惧、悲伤或者焦虑时生理体征,如血压也会有较大的区别。在这种情况下,单次测量生理体征有可能不能够真实地反应生理特征状况。因而在计算生理体征时,可能需要在不同的时段,如早晨,中午,傍晚,夜晚进行测量。也可能需要在不同的事件后进行测量,如服药前后,就餐前后,运动前后进行测量。也可能需要对生理体征进行一次乃至多次测量。其中包括但不限于按照一定的规则对多次测量的生理体征进行处理。例如,取多次测量的平均值,或者根据基于数据库的参数估计和优化例如曲线拟合、人工神经网络等通过校准而获得生命体的生理体征。对本领域的专业人员来说,在了解本发明内容和原理后,都可能在不背离本发明原理结构的情况下,对该系统进行形式和细节上的各种修正和改变,而这些修正和改变仍在本发明的权利要求保护范围以内。例如在处理模块或者计算模块中加入一组或者多组生理体征值进行比较,以取得较为真实的生理体征值,这种修正和变形仍在本发明的权利要求保护范围之内。
图5是输入输出模块203的示意图。输入输出模块203包括但不限于输入键501和屏幕502。输入键501可以作为快捷键使用,可以是功能快捷键、返回快捷键或菜单快捷键等。输入键503可以是机械类按键,也可以是电子触发类按键,也可以是触摸按钮。屏幕502可具有输入功能、输出功能或者输入输出功能都有,是用户使用生理体征信息提取系统的操作界面。输入输出的信息类型包含但不限于数字、模拟量、文字符号、语音和图形图像等。屏幕502的类型包含但不限于电子屏、等离子屏、电阻技术触摸屏、电容技术触摸屏、红外线技术触摸屏或表面声波技术触摸屏等,可以根据具体使用要求进行选择。输入输出模块203可以选择输入输出包含但不限于血压、PR值、血氧饱和度、心率、心脏杂音、肠鸣音、PH值、肌酐含量、转移酶含量、体温和癌胚抗原含量等生理体征中的一种或多种体征。屏幕显示的显示内容可通过输入键501进行设置,也可不通过输入键501进行设置。屏幕显示的显示内容可以由系统默认设置,也可不通过系统默认设置。另外,输入输出模块203还可以输入输出当地的实时天气信息、天气预报、室温、空气湿度 以及世界各时区的时间等信息中的一种或多种。另外,输入输出模块203还可以对生理体征信息做出解释及进一步挖掘。例如生理体征是否有异常、生理体征指标标示的用户身体状态,包括但不限于用户的健康指数,抗压指数,血氧浓度,血脂浓度。以及生理体征指标是否代表用户的健康隐患等等。输入输出模块203可以将需要输出的内容传递给显示屏显示,还可以将需要输出的内容传递给其他设备,或者将输出的内容传递给存储设备或者云服务器。需要注意的是,输入输出模块203可以集成在生理体征信息获取装置上,也可以在实现输入输出功能的前提下,对其发明进行其他变形。例如输入输出模块203可以集成为外部设备上的输入或输出装置,如集成在手表、手环、颈环、血压计、呼吸探测仪、手机、笔记本电脑、平板电脑等等设备上,这些变形和修改依旧在本发明的权利要求保护范围之内。
生命体征获取系统各个模块之间,模块和外部设备之间的连接,以及系统与存储设备或云服务器之间的连接都可以通过有线连接或无线连接。其中有线连接包括但不限于使用金属电缆、光学电缆或者金属和光学的混合电缆。例如:同轴电缆、通信电缆、软性电缆、螺旋电缆、非金属护皮电缆、金属护皮电缆、多芯电缆、双绞线电缆、带状电缆、屏蔽电缆、电信电缆、双股电缆、平行双芯导线、和双绞线。以上描述的例子仅作为方便说明之用,有线连接的媒介还可以是其它类型。例如,其它电信号或光信号等的传输载体。无线连接包括但不限于无线电通信、自由空间光通信、声通讯、和电磁感应等。其中无线电通讯包括但不限于,IEEE802.11系列标准、IEEE802.15系列标准(例如蓝牙技术和紫蜂技术等)、第一代移动通信技术、第二代移动通信技术(例如FDMA、TDMA、SDMA、CDMA、和SSMA等)、通用分组无线服务技术、第三代移动通信技术(例如CDMA2000、WCDMA、TD-SCDMA、和WiMAX等)、第四代移动通信技术(例如TD-LTE和FDD-LTE等)、卫星通信(例如GPS技术等)、和其它运行在ISM频段(例如2.4GHz等)的技术。自由空间光通信包括但不限于可见光、红外线、远红外线讯号等。声通讯包括但不限于声波、超声波讯号等。电磁感应包括但不 限于近场通讯技术等。以上描述的例子仅作为方便说明之用,无线连接的媒介还可以是其它类型,例如,Z-wave技术、其它收费的民用无线电频段和军用无线电频段等。
生理体征提取系统中各个模块之间,模块和外部设备之间的连接,以及系统与存储设备或云服务器之间的连接并不局限于以上所列举的技术。上述的连接方式在该生理体征信息获取装置中可以单一使用,也可以多种连接方式结合使用。在不同连接方式结合使用的过程中,需要配合相应的网关设备达到信息交互。各个模块也可以集成在一起,通过同一个设备实现一个以上模块的功能。各个模块可以是分布在不同电子元件上的,也可以是一个以上的模块集成在同一个电子元件上的,还可以是同一个模块分部在一个以上电子元件上。外部设备也可以集成在一个或多个模块的实施设备上,而单个或多个模块亦可以集成在单个或多个外部设备上。
图6是生理体征提取系统的一个具体实施例。如图6所示,该系统包含但不限于功能键601,一个或多个显示屏602,一个或多个测量端603,一个或多个处理模块604、一个或多个存储设备605和一个或多个电源模块606等。其中,功能键601包含一个电源键,另外还可以包含但不限于其他类似于上下调节、波形显示、停止、暂停、返回、多屏幕显示、导航键、快速测量键等等功能键中的一种或者多种键。需要注意的是,功能键的实现包括但不限于作为机械按键的样式,也可以是感应式触摸按键。进一步地,在该系统中能够实现该功能键的功能的多种表现形式,比如光感键,电子按键,都应该包含在发明的权利要求保护范围以内。显示屏602可以是液晶显示屏,也可以是电子屏、等离子屏、电阻技术触摸屏、电容技术触摸屏、红外线技术触摸屏或表面声波技术触摸屏等等屏幕。显示屏602还可以实现功能按键601的功能。功能按键601可以在显示屏602上显示,并通过显示屏602执行其功能。显示屏602可同屏显示心电波形、血压、PR值、血氧饱和度、心率、心脏杂音、肠鸣音、PH值、肌酐含量、转移酶含量、体温和癌胚抗原含量等生理体征中的一种或者多种(如图11)。测量端603可以采用导联线测 量法、胸部测量法、腿部测量法,或者手部测量法等测量方式中一种或者多种方式对人体生理体征进行测量。处理模块604用于对测量端测量到的生理信息,做进一步处理,以得到生理体征。包括但不限于心电波形、血压、PR值、血氧饱和度、心率、心脏杂音、肠鸣音、PH值、肌酐含量、转移酶含量、体温和癌胚抗原含量等生理体征中的一种或者多种。存储设备605用于存储一定时间内的生理体征数据,或者可用于存储一定容量的生理体征数据。这里的存储设备泛指所有可以读取和(或)写入信息的媒介。电源模块606用于提供电力,其可以是内置电源供应,也可以通过直流电或者交流电供应。内置电源可以是电池、蓄电池、锂电池或者充电电池等各种表现形式。上文描述的具体实施例中的各个模块都不是必须的,对本领域的专业人员来说,在了解本发明内容和原理后,都可能在不背离本发明原理结构的情况下,对该系统进行形式和细节上的各种修正和改变,而这些和改变仍在本发明的权利要求保护范围之内。例如,所述的存储设备605,可以并不局限于在本地的存储媒介,还可以将相关数据存储于类似于云服务器、网盘等支持无线存储的相关位置。类似的修正和改变也仍在本发明的权利要求保护范围之内,并且存储的大小范围也不存在限制,可根据实际情况进行调整。存储的时间范围可以在1秒以上,上限根据存储器的大小确定,抑或是可存储1KB以上的数据,上限也根据存储器的大小确定,对范围大小的修正和改变也仍在本发明的权利要求保护范围以内。
图7是对生理体征信息噪声检验及处理的一个实施例算法流程图。在这个实施例中,动物体的脉搏信息作为输入的生理体征信息,可能包含有噪声。首先需获得动物体的脉搏信息。
如图7所示,该算法的处理步骤如下所示:
步骤701:接收脉搏信息;
步骤702:对脉搏信息进行预处理;
步骤703:预处理后的脉搏信息分别通过PPG算法(步骤703-1)和峰值检测算法(步骤703-2)获得脉搏波的PPG算法结果和PPG峰值 结果;
步骤704:对上述PPG算法结果和PPG峰值结果做匹配计算;
步骤705:如果PPG算法结果和PPG峰值结果相匹配,则标记匹配上的PPG峰值结果;
步骤706:如果PPG算法结果和PPG峰值结果不匹配,则判定为PPG噪声峰,记录噪声峰幅度和个数,并根据噪声峰幅度计算噪声比例;
步骤707:根据噪声比例和PPG噪声峰个数进行噪声判断,得到PPG噪声结果;
步骤708:根据PPG噪声结果和脉搏信息计算动物体生理特征。
下面对上述步骤进行详细说明:
步骤702中对脉搏信息进行预处理。可以包含一个滤波步骤。滤波器可选择1-30Hz的带通滤波器、低通滤波器、通带滤波器、小波变换滤波器、Hilbert-Huang变换或者形态学滤波器等一种或者多种滤波器对脉搏波进行滤波,多种滤波器之间的联系方式可以是串行的,也可以是并行的。需要说明的是,以上预处理步骤并非是必要的。
步骤703-1中采用PPG算法对经过预处理后的脉搏信息进行处理,得到PPG算法结果。此处所述的PPG算法包括但不限于阈值法、句法模式识别、高斯函数分解法、小波变换、HTT方法、QRS波检测算法、局部峰值检测算法、峰值检测算法、线性判别分析、二次判别分析、最大熵分类器、决策树、决策表、核估计、近邻法、朴素贝叶斯分类器、神经网络、视感控器、支持向量机、基因表达式编程、分级群聚、k均值聚类、相关聚类、核主成分分析、提升方法、贝叶斯网络、马尔科夫随机场、多重线性主成分分析、卡尔曼滤波器、粒子滤波器、高斯过程回归、线性回归或拓展、独立成分分析、主成分分析、条件随即域、隐马尔科夫模型、最大熵马尔科夫模型、递归神经网络、关联式规则、归纳逻辑编程、相似性度量学习、深度神经网络、深度信念网络、卷积神经网路、卷积深度信念网络等所述任意一种算法或者任意多种算法的组合中的一种或者多种方法。步骤703-2采用峰值检测算法对脉搏信息进 行峰值检测,得到PPG峰值结果。作为一个实施例,峰值检测的一种算法可以包括如下步骤:
首先取得脉搏信息当前窗口期,例如4秒(4s),的数据,对每一个数据点按照以下步骤进行判断:
步骤a):根据当前数据点往前追溯15个数据点,找到该范围内的数据最大值max1;
步骤b):根据当前数据点往后追溯15个数据点,找到该范围内的数据最大值max2;
步骤c):若当前数据点数值大于max1和max2,则判定当前数据点为一个峰值点,若不是,则忽略;
步骤d):步骤703c判定的峰值点与阈值作比较,如果大于阈值,则判定该峰值为合格峰并做标记,若不是,则忽略。
在峰值检测算法的过程中,窗口期的长度可以按照情况具体设定,这里并不局限于4s,可以是1s,2s,3s,···Ns,N为任意正实数。
步骤a)和步骤b)中,根据当前数据点往前或往后追溯点的个数并不局限于15个数据点,可以是1,2,3,4,5···M个数据点,其中M为任意正整数。
在步骤d)中,初始阈值的设定可以由初始窗口期记录的峰值点计算得到。例如将初始窗口期内所有的峰值点结果取平均值并乘以某个系数,如0.4,即可得到首次阈值。在后续窗口期的计算中,需要迭代更新阈值,例如当窗口期内的合格峰值点取平均值后,乘以上述系数,如0.4,与当前阈值平均即可得到新的阈值。
步骤704中对步骤703-1及703-2中判定的PPG算法结果和PPG峰值结果进行匹配计算(匹配计算的具体描述可见下文)。并在步骤705标记匹配上的PPG峰值结果。步骤706中未匹配上的PPG峰值结果称为噪声峰。噪声比例可以按照以下公式计算:
噪声比例=噪声峰幅度值/匹配峰幅度平均值
其中噪声峰幅度值可以指未匹配上的PPG峰值结果的幅度值,匹配峰幅度平均值可以指匹配上的PPG峰值结果的幅度的平均值。
在进行匹配计算时,如果PPG算法结果和PPG峰值结果的特性参数之一,例如波的波峰所在位置,其距离相差在一定的范围以内,都可认为两者匹配。其中一定的范围可采取例如30个样点。
步骤707中进行噪声判断。噪声判断的方法步骤如下所示:
步骤a’):如果PPG算法结果和PPG峰值结果无匹配或者窗口期内没有PPG算法结果,则判断有噪声;
步骤b’):如果噪声比例不小于1的个数大于PPG算法结果波个数的一半,则判断有噪声;
步骤c’):如果噪声比例不小于0.75的个数大于PPG算法结果波个数的0.75倍,则判断有噪声;
步骤d’):如果噪声比例不小于0.5的个数大于PPG算法结果波个数,则判断有噪声。
其中,在步骤a’)-d’)中,所列步骤之间并不存在先后顺序,该判断的步骤可以任意排列,对步骤的顺序之间的修正或者改变依旧在本发明的权利要求保护范围以内。
步骤708中,人体的生理特征判明可基于步骤706中判定的噪声结果部分。可以采用去除步骤707中判定的噪声结果部分、加强步骤707中判定的噪声结果部分或者减弱步骤707中判定的噪声结果部分等方法中的一种或者多种方式来计算生理体征。生理体征可以包含例如血压、PR值、血氧饱和度、心率、心脏杂音、HRV、肠鸣音、PH值、肌酐含量、转移酶含量、体温和癌胚抗原含量等体征中的一种或者多种。
图8是生理体征信息噪声检验及处理的又一个实施例算法流程图。在这个实施例中,动物体的脉搏信息和心电信息作为生理体征信息。首先需获得动物体的脉搏信息和心电信息。
如图8所示,该算法的处理步骤如下所示:
步骤801:接收脉搏信息和心电信息;
步骤802:对脉搏信息和心电信息进行滤波预处理;
步骤803:预处理后的心电信息通过ECG算法(步骤803-1),脉搏 信息通过峰值检测算法(步骤803-2),分别获得心电信息的ECG算法结果和脉搏波(PPG)的PPG峰值结果;
步骤804:对上述ECG算法结果和PPG峰值结果做匹配计算;
步骤805:如果ECG算法结果和PPG峰值结果相匹配,则标记匹配上的PPG峰值结果,并计算脉搏波幅度平均值;
步骤806:如果不匹配,则判定为PPG噪声峰,记录噪声峰幅度和个数;
步骤807:根据脉搏波幅度平均值和噪声峰幅度计算噪声比例;
步骤808:根据噪声比例、PPG噪声峰和匹配的PPG峰值结果进行噪声判断,得到PPG噪声结果;
步骤809:根据PPG噪声结果,脉搏信息和心电信息计算人体生理特征。
下面对上述步骤进行详细说明:
步骤802中对脉搏信息和心电信息进行预处理。预处理可以包含一个滤波步骤。滤波器可选择1-30Hz的带通滤波器、低通滤波器、通带滤波器、小波变换滤波器、Hilbert-Huang变换或者形态学滤波器等一种或者多种滤波器对脉搏波进行滤波。多种滤波器之间的联系方式可以是串行的,也可以是并行的。需要说明的是,以上预处理步骤并非是必要的。
步骤803中采用ECG算法对经过预处理后的心电信息进行处理,得到ECG算法结果。此处所述的ECG算法是指包括但不限于阈值法、句法模式识别、高斯函数分解法、小波变换、HTT方法、QRS波检测算法、局部峰值检测算法和峰值检测算法等方法中的一种或者多种方法。需要注意的是,ECG算法是指以能够得到ECG为结果的任何方法,对于本领域的专业人员来说,任何对于ECG算法的替代都在本发明的权利要求保护范围以内。采用峰值检测算法对经过预处理后的脉搏信息进行峰值检测,可以得到峰值结果。其中峰值检测算法的步骤与图7中所述的峰值检测算法的步骤可以相同也可以不同。以能够取得脉搏信息的峰值结果为目的的检测算法都仍在我们发明的权利要求保护范围以内。
步骤804对步骤803中判定的ECG算法结果和PPG峰值结果进行匹配计算(匹配运算具体细节见下文)。并在步骤805中标记匹配上的PPG峰值结果。在步骤806中标记未匹配上的峰值结果称为噪声峰。在步骤807中噪声比例可以按照以下公式计算:
噪声比例=噪声峰幅度值/匹配峰幅度平均值
其中噪声峰幅度值可以指未匹配上的PPG峰值结果的幅度值,匹配峰幅度平均值可以指匹配上的PPG峰值结果的幅度的平均值。
其中匹配算法需先将ECG算法结果进行延迟处理,因为R波比PPG波峰出现的更早。例如,延迟的点数可以为40,或者任何绝对值不大于100的正数。然后再根据图7中所述的匹配算法进行匹配计算。
步骤808中进行噪声判断,噪声判断的方法步骤如下所示:
步骤808a:ECG如果报噪声,则判断PPG波无噪声;
步骤808b:如果ECG算法结果未找到匹配,则判断PPG波有噪声;
步骤808c:如果噪声比例不小于1的个数大于ECG算法结果波个数的一半,则判断PPG波有噪声;
步骤808d:如果噪声比例不小于0.75的个数大于ECG算法结果波个数的0.75倍,则判断PPG波有噪声;
步骤808e:如果噪声比例不小于0.5的个数大于ECG算法结果波个数,则判断PPG波有噪声。
步骤809中,人体的生理特征可基于步骤808中判定的噪声结果部分,可以采用去除步骤808中判定的噪声结果部分、加强步骤808中判定的噪声结果部分或者减弱步骤808中判定的噪声结果部分等方法中的一种或者多种方式来计算生理体征。生理体征可以包含例如血压、PR值、血氧饱和度、心率、HRV、心脏杂音、肠鸣音、PH值、肌酐含量、转移酶含量、体温和癌胚抗原含量等体征中的一种或者多种。
图9是生理体征信息噪声检验及处理的又一个实施例算法流程图。在这个实施例中,采用人体的脉搏信息和心电信息作为生理信息。首先需获得人体的脉搏信息和心电信息。
如图9所示,该算法的处理步骤如下所示:
步骤901:接收脉搏信息和心电信息;
步骤902:对脉搏信息和心电信息进行预处理;
步骤903:预处理后的脉搏信息和心电信息分别通过PPG算法和ECG算法获得脉搏波的PPG算法结果和心电信息的ECG算法结果,并且同时记录ECG噪声结果;
步骤904:对上述ECG算法结果和PPG算法结果做匹配计算;
步骤905:如果ECG算法结果和PPG算法结果相匹配,则标记匹配上的PPG峰值结果;
步骤906:如果不匹配则判定为PPG噪声峰,记录噪声峰幅度以及个数;
步骤907:根据匹配的PPG算法结果和噪声峰幅度计算噪声比例;
步骤908:根据噪声比例和PPG噪声峰进行噪声判断,得到PPG噪声结果;
步骤909:根据PPG噪声结果计算人体生理特征。
下面对上述步骤进行详细说明:
步骤902对脉搏信息和心电信息进行预处理时,至少包含一个滤波步骤,滤波器可选择1-30Hz的带通滤波器、低通滤波器、通带滤波器、小波变换滤波器、Hilbert-Huang变换或者形态学滤波器等一种或者多种滤波器对脉搏波进行滤波,多种滤波器之间的联系方式可以是串行的,也可以是并行的。
步骤903中采用PPG算法对脉搏信息进行处理,得到PPG算法结果。采用ECG算法对心电信息进行处理,得到ECG算法结果和窗口期内ECG噪声结果。
步骤904与图8所示的步骤804可以相同,也可以不同。以能够取得最终PPG匹配峰值结果为目的的匹配算法都仍在我们发明的权利要求保护范围以内。
步骤907中对噪声比例的计算方式可以与步骤807相同,也可以不同。
步骤908中进行噪声判断,噪声判断的方法步骤如下所示:
步骤908a:ECG如果报噪声,则判断PPG波无噪声;
步骤908b:如果ECG算法结果未找到匹配,则判断PPG波有噪声;
步骤908c:如果噪声比例不小于1的个数大于ECG算法结果波个数的一半,则判断PPG波有噪声;
步骤908d:如果噪声比例不小于0.75的个数大于ECG算法结果波个数的0.75倍,则判断PPG波有噪声;
步骤908e:如果噪声比例不小于0.5的个数大于ECG算法结果波个数,则判断PPG波有噪声。
步骤909中,人体的生理特征可基于步骤908中判定的噪声结果部分,可以采用去除步骤908中判定的噪声结果部分、加强步骤908中判定的噪声结果部分或者减弱步骤908中判定的噪声结果部分等方法中的一种或者多种方式来计算生理体征。生理体征可以包含例如血压、PR值、血氧饱和度、心率、HRV、心脏杂音、肠鸣音、PH值、肌酐含量、转移酶含量、体温和癌胚抗原含量等体征中的一种或者多种。
图10是生理体征信息噪声检验及处理的又一个实施例算法流程图。在这个实施例中,采用脉搏信息和心电信息作为生理信息。如图10所示,该算法的步骤如下:
步骤1001:接收脉搏信息和心电信息。
步骤1002:利用算法A(步骤1002-1),算法B(步骤1002-2),算法C(步骤1002-3)中的一种或者多种算法分别计算出脉搏信息和心电信息的噪声结果。这里算法A,算法B,算法C可以是图7,8,9中所述的相同或者不同算法。
步骤1003:根据步骤1002计算出的三种噪声结果中的一种噪声结果或多种噪声结果得到整体的噪声结果。
步骤1004:计算人体的生理体征。
其中,步骤1002中,可以有多种组合模式,比如,只使用算法A、 算法B和算法C中的一种算法,或者使用算法A、算法B和算法C的任意两种算法组合,或者算法A、算法B和算法C都被使用。
步骤1003中,也可以有多种组合模式,例如,使用三种噪声结果的任意一种噪声结果,或者使用三种噪声结果的任意两种噪声结果的组合,或者共同使用三种噪声结果。
步骤1004中计算人体的生理特征可基于1003中判定的噪声结果部分,可以采用去除1003中判定的噪声结果部分、加强1003中判定的噪声结果部分或者减弱1003中判定的噪声结果部分等方法中的一种或者多种方式来计算生理体征。生理体征可以包含例如血压、PR值、血氧饱和度、心率、HRV、心脏杂音、肠鸣音、PH值、肌酐含量、转移酶含量、体温和癌胚抗原含量等体征中的一种或者多种。
应注意,本文所示的各种步骤、操作或功能可以按所示的顺序执行、并行执行,或在一些情况下略去。类似地,处理的顺序不是实现本文中所述的示例实施例的特征和优点所必须的,而是为便于演示和说明而提供。取决于所使用的具体策略,可以重复执行所示步骤、功能或操作中的一个或多个。此外,所述操作、功能和/或步骤可以在图像上表示变成到控制系统中的计算机可读存储介质中的代码。
还应理解,在本文中公开的结构和配置本质上是示例性的,且这些具体实施例不应被视为具有限制意义,因为大量的变体是可能的。本文中公开的主题包括在本文中公开的各种结构和配置,及其他特征、功能,和/或属性的所有新颖和非显而易见的组合及子组合。
本申请的权利要求特别指出视为新颖和非显而易见的特定组合及子组合。这些权利要求可能引用“一个”元素或者“第一”元素或其等价。这样的权利要求应被理解为包括对一个或一个以上这样的元素的结合,而不是要求或排除两个或两个以上这样的元素。所公开的特征、功能、元素和/或属性的其他组合及子组合可以通过修改本申请的权利要求或通过在本申请或相关申请中提出新的权利要求来请求保护。这样的权利要求,无论是在范围上比原始权利要求更宽、更窄、等价或不同,都应被视为包括在发明的主题之内。

Claims (20)

  1. 一种系统,包含:
    接收模块,用于接收至少一种生理信息;
    处理模块,包含特征提取模块、匹配运算模块和计算模块,其中特征提取模块采取第一种方法和第二种方法分别处理所述生理信息,得到第一类特征和第二类特征,所述第一种方法和第二种方法不同;匹配运算模块对所述第一类特征和所述第二类特征进行匹配运算并标记匹配结果;计算模块计算人体的生理体征。
  2. 根据权利要求1所述的系统,所述接收模块接收的生理信息包括心电信息和脉搏信息中的至少一种。
  3. 根据权利要求1所述的系统,所述第一种方法是峰值检测算法,所述第二种方法是PPG算法或者ECG算法。
  4. 根据权利要求1所述的系统,所述第一种方法是PPG算法,所述第二种方法是ECG算法。
  5. 根据权利要求1所述的系统,所述匹配运算模块进行的匹配运算包括将未匹配上的峰值结果标记为噪声峰。
  6. 根据权利要求1所述的系统,所述系统包括输入输出模块用于输出显示所述生理体征。
  7. 根据权利要求1所述的系统,所述匹配运算模块进一步判断所述生理信息的噪声结果。
  8. 根据权利要求7所述的系统,所述匹配运算模块判断噪声的步骤包括以下步骤:(1)计算噪声比例;(2)如果噪声比例不小于1的个数大于算法结果波个数的一半,或者(3)如果噪声比例不小于0.75的个数大于算法结果波个数的0.75倍,或者(4)如果噪声比例不小于0.5的个数大于算法结果波个数,则判断所述生理信息有噪声。
  9. 根据权利要求8所述的系统,所述噪声比例是指噪声峰幅度值和匹配峰幅度平均值的比值。
  10. 根据权利要求8所述的系统,所述的算法结果波是指经过PPG算法或者ECG算法后得到的结果波。
  11. 根据权利要求1所述的系统,所述计算模块计算心率、血压、血氧饱和度、体温、HRV、PR值中的至少一种生理体征。
  12. 一种方法,包括:
    接收至少一种生理信息;
    采用第一种方法和第二种方法分别处理生理信息,得到第一类特征和第二类特征,所述第一种方法和所述第二种方法不同;
    对所述第一类特征和所述第二类特征进行匹配运算并标记匹配结果;
    根据匹配结果判断所述生理信息的噪声;
    计算人体的生理体征。
  13. 根据权利要求12所述的方法,所述生理信息包括脉搏信息和心电信息中的至少一种。
  14. 根据权利要求12所述的方法,所述第一种方法是峰值检测算法。所述第二种方法是PPG算法或者ECG算法。
  15. 根据权利要求12所述的方法,所述第一种方法是PPG算法,所述第二种方法是ECG算法。
  16. 根据权利要求12所述的方法,所述标记匹配结果是将未匹配上的峰值结果标记为噪声峰。
  17. 根据权利要求12所述的方法,所述判断噪声的步骤包括以下步骤:(1)计算噪声比例;(2)如果噪声比例不小于1的个数大于算法结果波个数的一半,或者(3)如果噪声比例不小于0.75的个数大于算法结果波个数的0.75倍,或者(4)如果噪声比例不小于0.5的个数大于算法结果波个数,则判断所述生理信息有噪声。
  18. 根据权利要求12所述的方法,所述噪声比例是指噪声峰幅度值和匹配峰幅度平均值的比值。
  19. 根据权利要求12所述的方法,所述的算法结果波是指经过PPG算法或者ECG算法后得到的结果波。
  20. 根据权利要求12所述的方法,所述生理体征是指心率、血压、血氧饱和度、体温、HRV、PR值中的至少一种。
PCT/CN2015/077026 2015-04-20 2015-04-20 一种生理体征信息获取方法和系统 WO2016168980A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201580079047.4A CN107530016A (zh) 2015-04-20 2015-04-20 一种生理体征信息获取方法和系统
US15/567,974 US10758186B2 (en) 2015-04-20 2015-04-20 Physiological sign information acquisition method and system
PCT/CN2015/077026 WO2016168980A1 (zh) 2015-04-20 2015-04-20 一种生理体征信息获取方法和系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/077026 WO2016168980A1 (zh) 2015-04-20 2015-04-20 一种生理体征信息获取方法和系统

Publications (1)

Publication Number Publication Date
WO2016168980A1 true WO2016168980A1 (zh) 2016-10-27

Family

ID=57144383

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/077026 WO2016168980A1 (zh) 2015-04-20 2015-04-20 一种生理体征信息获取方法和系统

Country Status (3)

Country Link
US (1) US10758186B2 (zh)
CN (1) CN107530016A (zh)
WO (1) WO2016168980A1 (zh)

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN204515353U (zh) 2015-03-31 2015-07-29 深圳市长桑技术有限公司 一种智能手表
EP3576626A4 (en) * 2017-02-01 2020-12-09 Cerebian Inc. SYSTEM AND METHOD FOR MEASURING PERCEPTIONAL EXPERIENCE
CN109243597A (zh) * 2017-06-29 2019-01-18 京东方科技集团股份有限公司 远程医疗设备、信息获取设备以及远程医疗系统及方法
WO2019036908A1 (zh) * 2017-08-22 2019-02-28 深圳市汇顶科技股份有限公司 心率检测方法及装置、电子终端
US11850087B2 (en) * 2018-05-08 2023-12-26 Cardiac Pacemakers, Inc. Heart sound sensing headgear
EP3608918A1 (en) 2018-08-08 2020-02-12 Tata Consultancy Services Limited Parallel implementation of deep neural networks for classifying heart sound signals
US11260888B2 (en) * 2018-11-16 2022-03-01 Alstom Transport Technologies Method and system for health assessment of a track circuit and/or of a track section
WO2020157989A1 (ja) * 2019-02-01 2020-08-06 日本電気株式会社 覚醒度推定装置、覚醒度推定方法、及びコンピュータ読み取り可能な記録媒体
CN110287805B (zh) * 2019-05-31 2021-02-09 东南大学 基于三流卷积神经网络的微表情识别方法及系统
CN110742593B (zh) * 2019-09-17 2022-02-11 东南大学 一种基于线谱跟踪的生命信号特征提取方法
US11617528B2 (en) * 2019-10-08 2023-04-04 GE Precision Healthcare LLC Systems and methods for reduced lead electrocardiogram diagnosis using deep neural networks and rule-based systems
CN111107478B (zh) * 2019-12-11 2021-04-09 江苏爱谛科技研究院有限公司 一种声音增强方法及声音增强系统
CN110811638A (zh) * 2019-12-11 2020-02-21 齐鲁工业大学 一种用于监测睡眠的svm分类器构建方法、系统及方法
US11550360B1 (en) * 2020-08-28 2023-01-10 Securus Technologies, Llc Controlled-environment facility resident wearables and systems and methods for use
CN112187318B (zh) * 2020-08-31 2022-02-18 南京理工大学 基于深度学习的脉冲噪声削减方法
CN112450920A (zh) * 2020-11-23 2021-03-09 青岛歌尔智能传感器有限公司 血氧状态检测装置、设备及存储介质
CN113017613B (zh) * 2021-03-03 2022-05-06 四川大学华西医院 基于人工智能的心冲击波信号处理方法及计算机设备
CN114239649B (zh) * 2021-07-15 2023-04-07 电子科技大学 面向可穿戴设备光电容积脉搏波信号发现和识别新用户的身份识别方法
CN113662520B (zh) * 2021-08-26 2022-10-14 电子科技大学 一种基于不确定性量化策略的可穿戴连续血压测量系统
CN116889395B (zh) * 2023-08-24 2024-02-13 迈德医疗科技(深圳)有限公司 一种基于catpca的无创血糖膳食分类方法及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101953682A (zh) * 2010-10-15 2011-01-26 张辉 基于袖带装置的心率检测方法
CN102988041A (zh) * 2012-11-16 2013-03-27 中国科学院上海微系统与信息技术研究所 心磁信号噪声抑制中的信号选择性平均方法
CN104102915A (zh) * 2014-07-01 2014-10-15 清华大学深圳研究生院 一种心电异常状态下基于ecg多模板匹配的身份识别方法

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101683260B (zh) * 2008-09-28 2012-05-30 深圳迈瑞生物医疗电子股份有限公司 一种节律性生理信号的优化处理方法及装置
US8632465B1 (en) * 2009-11-03 2014-01-21 Vivaquant Llc Physiological signal denoising
US10413251B2 (en) * 2012-10-07 2019-09-17 Rhythm Diagnostic Systems, Inc. Wearable cardiac monitor
CN103860162B (zh) 2012-12-11 2018-02-23 深圳迈瑞生物医疗电子股份有限公司 一种起搏信号检测方法、系统和心电检测设备
CN103083013B (zh) 2013-01-18 2015-05-13 哈尔滨工业大学深圳研究生院 基于形态学与小波变换的心电信号qrs复波检测方法
CN104182625A (zh) 2014-08-15 2014-12-03 重庆邮电大学 基于形态学与emd类小波阈值的心电信号去噪方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101953682A (zh) * 2010-10-15 2011-01-26 张辉 基于袖带装置的心率检测方法
CN102988041A (zh) * 2012-11-16 2013-03-27 中国科学院上海微系统与信息技术研究所 心磁信号噪声抑制中的信号选择性平均方法
CN104102915A (zh) * 2014-07-01 2014-10-15 清华大学深圳研究生院 一种心电异常状态下基于ecg多模板匹配的身份识别方法

Also Published As

Publication number Publication date
CN107530016A (zh) 2018-01-02
US10758186B2 (en) 2020-09-01
US20180116597A1 (en) 2018-05-03

Similar Documents

Publication Publication Date Title
WO2016168980A1 (zh) 一种生理体征信息获取方法和系统
Mahmud et al. A wireless health monitoring system using mobile phone accessories
Villarroel et al. Non-contact physiological monitoring of preterm infants in the neonatal intensive care unit
Xiao et al. Wearable heart rate monitoring intelligent sports bracelet based on Internet of things
CN110944577B (zh) 一种血氧饱和度的检测方法与系统
Khusainov et al. Real-time human ambulation, activity, and physiological monitoring: Taxonomy of issues, techniques, applications, challenges and limitations
US20170249445A1 (en) Portable devices and methods for measuring nutritional intake
CN102917661B (zh) 基于多变量残差的用于人体健康监视的健康指数
Sung et al. Evidence-based multi-sensor information fusion for remote health care systems
CN107530015B (zh) 一种生命体征分析方法与系统
EP3602572A1 (en) Learning sleep stages from radio signals
Lan et al. Traditional Chinese medicine pulse diagnosis on a smartphone using skin impedance at acupoints: a feasibility study
Li et al. Design of a wireless sensor system with the algorithms of heart rate and agility index for athlete evaluation
Guo et al. Smart healthcare system based on cloud-internet of things and deep learning
Alim et al. Wearable sensors for the monitoring of maternal health—A systematic review
Zhou et al. Wearable continuous blood pressure monitoring devices based on pulse wave transit time and pulse arrival time: A review
He et al. A new approach for daily life Blood-Pressure estimation using smart watch
Chen et al. A data-driven model with feedback calibration embedded blood pressure estimator using reflective photoplethysmography
Sundaravadivel et al. i-sad: An edge-intelligent iot-based wearable for substance abuse detection
WO2019084802A1 (zh) 一种生命体征信号噪声的检测方法与系统
Zabihi et al. Bp-net: Cuff-less and non-invasive blood pressure estimation via a generic deep convolutional architecture
Dissanayake et al. CompRate: Power efficient heart rate and heart rate variability monitoring on smart wearables
CN110428893A (zh) 一种远程医疗生命体征数据采集装置
Ma et al. PPG-based continuous BP waveform estimation using polarized attention-guided conditional adversarial learning model
Kher et al. A comprehensive review on wearable health monitoring systems

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15889469

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15567974

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 11.04.2018)

122 Ep: pct application non-entry in european phase

Ref document number: 15889469

Country of ref document: EP

Kind code of ref document: A1