CN111803032B - Large-area observation method and system for suspected infection of Xinguan pneumonia - Google Patents
Large-area observation method and system for suspected infection of Xinguan pneumonia Download PDFInfo
- Publication number
- CN111803032B CN111803032B CN202010632445.7A CN202010632445A CN111803032B CN 111803032 B CN111803032 B CN 111803032B CN 202010632445 A CN202010632445 A CN 202010632445A CN 111803032 B CN111803032 B CN 111803032B
- Authority
- CN
- China
- Prior art keywords
- detected person
- calculation module
- degree
- acquiring
- data
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/021—Measuring pressure in heart or blood vessels
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1103—Detecting eye twinkling
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/117—Identification of persons
- A61B5/1171—Identification of persons based on the shapes or appearances of their bodies or parts thereof
- A61B5/1176—Recognition of faces
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7282—Event detection, e.g. detecting unique waveforms indicative of a medical condition
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Cardiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Ophthalmology & Optometry (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Optics & Photonics (AREA)
- Evolutionary Computation (AREA)
- Vascular Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to a large-area observation method and a system for suspected infection of new coronary pneumonia, wherein the observation method comprises the following steps: acquiring physiological characteristics, namely directly acquiring or indirectly calculating the physiological characteristics of a detected person through a sensor assembly; establishing a risk assessment model, acquiring symptoms and clinical sign data of a patient with confirmed diagnosis of new coronary pneumonia as training samples, and training by a statistical learning method, a machine learning method or a deep learning method to generate a suspected infection risk assessment model of new coronary pneumonia; and performing suspected judgment, namely inputting the physiological characteristics of the detected person into the suspected infection risk evaluation model of the new coronary pneumonia, and outputting the suspected infection risk degree of the new coronary pneumonia of the detected person.
Description
Technical Field
The invention relates to a large-area observation method and a system for suspected infection of new coronary pneumonia, and relates to the technical field of medical monitoring.
Background
At present, new coronary pneumonia epidemic situations are popularized worldwide. In order to inhibit the spread of new coronary pneumonia virus, in a place where people gather, the body temperature of a human body is often required to be detected and screened, and whether the detected people are suspected to be infected with new coronary pneumonia or not is judged. However, the detection screening method is simply to judge according to a single physiological index of the body temperature of the human body, so that the detection result is not accurate enough, and the missed detection and the false detection of suspected infected persons of new coronary pneumonia can be caused.
In fact, besides the physiological characteristic index of body temperature, the physiological characteristic indexes of dry cough, respiratory rate, blood oxygen saturation, heart rate variability, blood pressure, nasal obstruction, shivering, physical fatigue, human face complexion and the like are closely related to the suspected infection of new coronary pneumonia.
Disclosure of Invention
The invention aims to overcome the defect that the screening of the existing single body temperature index is not accurate enough, and provides a method and a system for observing suspected infection of new coronary pneumonia, which are accurate in detection and suitable for large-area deployment.
The technical scheme of the invention is as follows:
the first technical scheme is as follows:
a large-area observation method for suspected infection of Xinguan pneumonia comprises the following steps:
acquiring physiological characteristics, namely directly acquiring or indirectly calculating the physiological characteristics of a detected person through a sensor assembly;
establishing a risk assessment model, acquiring symptoms and clinical sign data of a patient with confirmed diagnosis of new coronary pneumonia as training samples, and training by a statistical learning method, a machine learning method or a deep learning method to generate a suspected infection risk assessment model of new coronary pneumonia;
and performing suspected judgment, namely inputting the physiological characteristics of the detected person into the suspected infection risk evaluation model of the new coronary pneumonia, and outputting the suspected infection risk degree of the new coronary pneumonia of the detected person.
Further, before the physiological characteristic obtaining step, an identity verification step is further included, wherein the identity verification step specifically comprises the following steps:
acquiring the identity of the detected person, judging whether the detected person is the person or not by verifying the identity, executing the physiological characteristic acquisition step if the verification is passed, and ending if the verification is not passed;
wherein the identification is face data, voice data, fingerprint data, heart rate data, vein data or iris data.
Further, the sensor assembly includes an optical sensor, a sound sensor, and an infrared sensor.
Further, the physiological characteristics comprise main judgment indexes and auxiliary judgment indexes, wherein the main judgment indexes comprise the body temperature of the human face, the dry cough degree and the respiratory rate; the auxiliary judgment indexes comprise blood oxygen saturation, heart rate variation rate, blood pressure, blink rate, nasal obstruction degree, shivering degree, fatigue degree and human face complexion;
acquiring optical change data of the blood flow of the face of the detected person, facial action data and the color and texture of each part of the face through the optical sensor;
acquiring a time domain waveform and/or a frequency domain waveform of the heartbeat of the detected person according to the facial blood flow optical change data, and calculating the heart rate and the heart rate variation rate of the detected person based on the time domain waveform and/or the frequency domain waveform of the heartbeat;
acquiring the arrival time difference of heartbeat wave peaks and/or the arrival time difference of heartbeat wave troughs and/or the heartbeat frequency spectrum characteristics of different parts of the face of the detected person according to the optical change data of the facial blood flow, and calculating the blood pressure of the detected person according to the arrival time difference of heartbeat wave peaks and/or the arrival time difference of heartbeat wave troughs and/or the heartbeat frequency spectrum characteristics of different parts of the face;
acquiring the light intensity variation ratio of red light and infrared light of the face of the detected person according to the optical variation data of the facial blood flow, and calculating the blood oxygen saturation of the detected person according to the light intensity variation ratio of the red light and the infrared light of the face;
acquiring a time domain waveform and/or a frequency domain waveform of the respiration of the detected person according to the facial motion data, and calculating the respiration rate of the detected person based on the time domain waveform and/or the frequency domain waveform of the respiration;
acquiring the number of spontaneous blinks of the detected person according to the facial motion data, and calculating the blink rate of the detected person based on the number of spontaneous blinks and the detection time;
acquiring micro-movement of the nose part of the detected person according to the facial movement data, and calculating the nasal obstruction times and the nasal obstruction degree of the detected person by combining the characteristics and the strength of the instantaneous micro-movement of the nose part;
acquiring periodic shaking motion of the head of the detected person according to the facial motion data, and calculating the shaking degree of the head of the detected person according to the shaking frequency of the head in the vertical direction and/or the horizontal direction;
acquiring the blink time length, the eye opening degree, the continuous eye closing time length and the yawning degree of the detected person according to the facial motion data, and calculating the psychological and/or physical fatigue degree of the detected person through the blink rate, the heart rate, the respiration rate, the heart rate variation rate, the blink time length, the eye opening degree, the continuous eye closing time length and the yawning degree;
calculating the face color of the detected person according to the color and the texture of each part of the face;
acquiring the voiceprint characteristics of the detected person through the sound sensor, judging the frequency of the sound emitted by the detected person as cough sound according to the voiceprint characteristics of the detected person, and calculating the dry cough degree of the detected person according to the amplitude, the frequency and the duration of the voiceprint characteristics of the cough sound emitted by the detected person;
and acquiring temperature data of a plurality of parts of the human face through the infrared sensor, and calculating the body temperature of the human face.
Further, the method also comprises an evaluation result feedback and uploading step, which comprises the following specific steps:
acquiring personal basic information of the detected person according to the identity authentication identifier of the detected person;
sending the suspected infection risk degree of the new coronary pneumonia of the detected person to the detected person and/or the detected person guardian and/or the new coronary pneumonia related manager;
and uploading and storing the acquired physiological characteristic indexes of the detected person, the suspected infection risk degree of the new coronary pneumonia of the detected person and the personal basic information of the detected person in a database.
The second technical scheme is as follows:
a large-area observation system for suspected infection of new coronary pneumonia comprises: the system comprises a physiological characteristic acquisition module, a risk evaluation module and a judgment module;
the physiological characteristic acquisition module is used for directly acquiring or indirectly calculating the physiological characteristics of the detected person through the sensor assembly;
the risk assessment module is used for acquiring symptoms and clinical sign data of a patient with confirmed diagnosis of new coronary pneumonia as training samples, and training the training samples by a statistical learning method, a machine learning method or a deep learning method to generate a suspected infection risk assessment model of the new coronary pneumonia;
the judgment module is used for inputting the physiological characteristics of the detected person into the suspected infection risk evaluation model of the new coronary pneumonia and outputting the suspected infection risk degree of the new coronary pneumonia of the detected person.
The system further comprises an identity authentication module, wherein the identity authentication module is used for acquiring an identity of the detected person and judging whether the detected person is the person or not by verifying the identity; the identification is face data, voice data, fingerprint data, heart rate data, vein data or iris data.
Further, the physiological characteristic acquisition module comprises an optical sensor, a sound sensor and an infrared sensor.
Further, the optical sensor is used for acquiring the optical change data of the blood flow of the face of the detected person, the facial action data and the color and texture of each part of the face; the sound sensor is used for acquiring the voiceprint characteristics of the detected person; the infrared sensor is used for acquiring temperature data of one or more parts of the human face;
the physiological characteristic acquisition module further comprises a human face body temperature calculation module, a dry cough degree calculation module, a respiratory rate calculation module, a blood oxygen saturation degree calculation module, a heart rate variability rate calculation module, a blood pressure calculation module, a blink rate calculation module, a nasal obstruction degree calculation module, a shivering degree calculation module, a fatigue degree calculation module and a human face gas color calculation module;
the heart rate calculation module is used for acquiring a time domain waveform and/or a frequency domain waveform of the heartbeat of the detected person according to the optical change data of the facial blood flow, and calculating the heart rate of the detected person based on the time domain waveform and/or the frequency domain waveform of the heartbeat;
the heart rate variation rate calculation module is used for calculating the heart rate variation rate of the detected person according to the time intervals between the continuous peaks or troughs of the time domain waveform of the heartbeat and/or the frequency spectrum characteristics of the frequency domain waveform of the heartbeat;
the blood pressure calculation module is used for acquiring the arrival time difference of heartbeat wave peaks and/or the arrival time difference of heartbeat wave troughs and/or the heartbeat frequency spectrum characteristics of different parts of the face of the detected person according to the optical change data of the facial blood flow, and calculating the blood pressure of the detected person according to the arrival time difference of heartbeat wave peaks and/or the arrival time difference of heartbeat wave troughs and/or the heartbeat frequency spectrum characteristics of different parts of the face;
the blood oxygen saturation calculation module is used for acquiring the ratio of the light intensity variation of the red light and the infrared light of the face of the detected person and calculating the blood oxygen saturation of the detected person according to the ratio of the light intensity variation of the red light and the infrared light of the face;
the respiration rate calculation module is used for acquiring a time domain waveform and/or a frequency domain waveform of the respiration of the detected person according to the facial motion data, and calculating the respiration rate of the detected person based on the time domain waveform and/or the frequency domain waveform of the respiration;
the blink rate calculation module is used for acquiring the spontaneous blink frequency of the detected person according to the face motion data and calculating the blink rate of the detected person according to the spontaneous blink frequency and the detection time;
the nasal obstruction degree calculating module is used for acquiring micro-movement of the nose part of the detected person according to the facial action data, and calculating the nasal obstruction times and the nasal obstruction degree of the detected person by combining the characteristics and the strength of the instantaneous micro-movement of the nose part;
the shake degree calculation module is used for acquiring the periodic shake motion of the head of the detected person according to the facial action data and calculating the shake degree of the head of the detected person according to the shake frequency of the head in the vertical direction and/or the horizontal direction;
the tiredness degree calculation module is used for acquiring the blink time length, the eye opening degree, the continuous eye closing time length and the yawning degree of the detected person according to the facial motion data, and calculating the psychological and/or physical tiredness degree of the detected person according to the blink rate, the heart rate, the respiration rate, the heart rate variation rate, the blink time length, the eye opening degree, the continuous eye closing time length and the yawning degree;
the human face gas color calculation module is used for calculating the human face gas color of the detected person according to the color and the texture of each part of the face;
the dry cough degree calculation module is used for judging the frequency of the sound emitted by the detected person as cough sound according to the vocal print characteristics of the detected person, and calculating the dry cough degree of the detected person according to the amplitude, the frequency and the duration of the vocal print characteristics of the cough sound emitted by the detected person;
the human face body temperature calculation module is used for calculating the human face body temperature according to the temperature data of the plurality of parts of the human face.
Further, the system also comprises a final physical examination result feedback module and a physical examination data remote automatic reporting module; the final physical examination result feedback module is used for sending the risk evaluation result of suspected infection of the new coronary pneumonia of the detected person to the detected person and/or the detected person guardian and/or the new coronary pneumonia related manager; the physical examination data remote automatic reporting module automatically uploads the acquired physiological characteristic indexes of the detected person, the risk assessment result of suspected infection of new coronary pneumonia of the detected person and the personal basic information of the detected person to a database.
The invention has the following beneficial effects:
1. according to the invention, by one or a combination of two or more of a statistical learning method, a machine learning method and a deep learning method, the symptoms and clinical sign data of a patient with confirmed diagnosis of new coronary pneumonia are trained to generate a risk assessment model of suspected infection of new coronary pneumonia, so that large-area suspected infection screening of new coronary pneumonia can be carried out, and subjective judgment errors caused by artificial observation are reduced.
2. The invention is provided with the identity verification module to ensure that the person to be detected is the person and then the person is detected, thereby avoiding the phenomena of misreport and misreport.
3. On the basis of the existing single body temperature index screening, multiple physiological indexes such as dry cough, respiratory rate, blood oxygen saturation, heart rate variability rate, nasal obstruction, blood pressure, blink rate, shivering degree, fatigue degree, face complexion and the like closely related to the new coronary pneumonia infection are additionally added, and the accuracy and robustness of the new coronary pneumonia suspected infection observation judgment result are greatly improved.
4. All the physiological indexes to be collected can be automatically and remotely collected and reported in a non-contact mode, so that the infection risk of the medical staff for field physical examination is avoided.
Drawings
FIG. 1 is a flow chart of a first embodiment of the present invention;
FIG. 2 is a flowchart of a second embodiment of the present invention;
FIG. 3 is a system diagram of a third embodiment of the present invention;
FIG. 4 is a schematic diagram of a third embodiment of the present invention;
fig. 5 is a system interface schematic diagram of a physiological index display module according to a fourth embodiment of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and the specific embodiments.
The first embodiment is as follows:
referring to fig. 1, a large-area observation method for suspected infection of new coronary pneumonia includes the following steps:
acquiring physiological characteristics, namely directly acquiring or indirectly calculating the physiological characteristics of a detected person through a sensor assembly;
establishing a risk assessment model, acquiring symptom and clinical sign data of a patient with confirmed diagnosis of new coronary pneumonia as training samples, training by one or a combination of two or more of a statistical learning method, a machine learning method and a deep learning method, and generating the risk assessment model suspected of infecting the new coronary pneumonia, wherein the statistical learning method, the machine learning method and the deep learning method comprise various statistical analysis methods, a support vector machine, a neural network, a genetic algorithm and the like;
performing suspected judgment, namely inputting the physiological characteristics of the detected person into the suspected infection risk evaluation model of the new coronary pneumonia, and outputting a suspected infection risk value of the new coronary pneumonia of the detected person; presetting at least one risk threshold, comparing the risk value of the suspected infection of the new coronary pneumonia of the detected person with the risk threshold, and outputting the suspected infection risk degree of the new coronary pneumonia of the detected person.
According to the method, one or a combination of two or more of a statistical learning method, a machine learning method and a deep learning method is used for training the symptoms and clinical sign data of the patient with confirmed diagnosis of new coronary pneumonia to generate a risk assessment model of suspected infection of new coronary pneumonia, so that large-area suspected infection screening of new coronary pneumonia can be performed, and subjective judgment errors caused by artificial observation are reduced.
The second embodiment:
further, referring to fig. 2, in this embodiment, the suspected infection risk of coronary pneumonia of the subject is determined by the following steps:
step S100: the sensor assembly comprises an optical sensor, a sound sensor and an infrared sensor; the method comprises the steps that human face video data of a detected person are obtained through an optical sensor, wherein the optical sensor can adopt a common color camera, an infrared night vision camera, a high-speed camera, an optical camera with one or more optical filters, a network camera, an IP (Internet protocol) camera, a laser camera and the like; the sound sensor can be a microphone built in a common notebook computer, a microphone built in a mobile phone, a microphone built in a camera, a microphone external to a desktop computer, an omnidirectional stereo microphone or a microphone array and the like; the infrared sensor can be an infrared single-point temperature sensor, an infrared dot matrix temperature sensor, an infrared thermal imaging camera, an infrared thermometer and the like;
step S200: verifying the identity of the detected person, judging whether the identity is the detected person, if not, executing the step S200 again, and if so, executing the step S300; the identification can be face data, voice data, fingerprint data, rhythm of the heart data, vein data and iris data, and in this embodiment, identification adopts face data.
Step S300: calculating main judgment indexes and auxiliary judgment indexes of a detected person based on physiological characteristic data, wherein the main judgment indexes comprise human face body temperature, dry cough degree and respiration rate; the auxiliary judgment indexes comprise blood oxygen saturation, heart rate variation rate, blood pressure, blink rate, nasal obstruction degree, shivering degree, fatigue degree and human face complexion; the specific calculation method of various physiological indexes is as follows:
firstly, performing optical compensation to maintain the stability of light brightness in a recorded face video; and selecting the area with better human face detection effect as follows: the forehead and the cheek are used as characteristic areas; the RGB three-dimensional vector (pixel values of RED, GREEN and BLUE) of each pixel point in the characteristic region is obtained through an optical sensor, obtaining green light value, ratio of green light to blue light and three components of light intensity value of each pixel point through RGB three-dimensional vector, amplifying green light value, ratio of green light to blue light and light intensity value through Euler color amplification technology, filtering after amplification, analyzing the filtered green light value, the ratio of green light to blue light and the light intensity value by a principal component analysis method, outputting principal components and filtering, calculating a time domain waveform and/or a frequency domain waveform of the heartbeat of the detected person according to the peak-valley value of the filtered principal component value changing along with the time, and calculating the heart rate of the detected person based on the time domain waveform and/or the frequency domain waveform of the heartbeat; acquiring time intervals between continuous peaks and/or troughs through a time domain waveform of the heartbeat, counting time interval characteristics between a plurality of continuous peaks and/or troughs, acquiring frequency spectrum characteristics of the heartbeat through a frequency domain waveform of the heartbeat, and calculating the heart rate variation rate of the detected person according to the time interval characteristics of the peaks and troughs of the heartbeat and/or the frequency spectrum characteristics of the heartbeat; amplifying the facial movement of a detected person in the face video data by an Euler movement amplification technology, counting micro movement information of characteristic points related to the face and the respiration of the detected person, calculating the respiration rate of the detected person, capturing a plurality of characteristic points related to the respiration of the face, such as nostrils and nasal wings, and amplifying the characteristic points to calculate the respiration rate of the person, wherein the characteristic points are related to the respiration of the face and move along with the person when the person breathes; calculating the blink rate of a detected person by acquiring the time interval between spontaneous blinks of a human body, wherein the spontaneous blinks refer to eye closing actions within the time of 0.3-0.4 s, and if the eye closing time of the detected person exceeds the time interval of the spontaneous blinks, the current blink is not counted into the number of the spontaneous blinks; calculating the blood oxygen saturation of the detected person by acquiring the light intensity variation ratio of the red light and the infrared light of the human face; the method comprises the steps of obtaining the arrival time difference of heartbeat wave peaks and/or the arrival time difference of heartbeat wave troughs at different parts of a human face and/or the heartbeat frequency spectrum characteristics of different parts of the face to calculate the blood pressure information of a detected person, wherein the lengths of blood vessels reaching different parts are different when the heart pumps blood, so that the blood pressure data can be calculated according to the arrival time difference of the heartbeat wave peaks and/or the arrival time difference of the heartbeat wave troughs at different parts of the human face and/or the heartbeat frequency spectrum characteristics of different parts of the face, the Euler color amplification technology can know when different parts are in the state of the arrival of the heartbeat wave peaks and the arrival of the wave troughs, and the frame extraction processing can be carried out on the face video data to obtain the arrival time difference of the heartbeat wave peaks and the arrival of the wave troughs between different parts; when a person is in nasal obstruction, the person is difficult to inhale, micro-movement of multiple parts of the face can be caused, if the nasal wing can contract and the nose head can rise, the micro-movement of the nose part of the face can be obtained through an edge detection algorithm, the nasal obstruction degree information of the detected person can be calculated by combining the instantaneous movement of the nose part and the micro-movement characteristics of the mouth caused by the inhaling action of the nasal obstruction, if the nasal obstruction degree information of the detected person is detected, if the nasal wing contracts for a long time, the nose head rises, the nose head folds and the mouth upper lip lifts, the person is judged to be seriously nasal obstruction, and if the nasal wing contracts for a short time, the nose head rises slightly and the mouth does not have obvious change, the person is judged to be lightly nasal obstruction; when a person is ill, the person can have a cold shivering condition, so the shivering degree can also be used as a physiological characteristic for evaluating whether the person is suffered from new coronary pneumonia, the periodic shivering motion of the head of the person to be detected is obtained according to the facial action data, and the shivering degrees of the head of the person to be detected, such as spontaneous nodding, shaking head and the like caused by vestibular reflection, of the head of the person to be detected are calculated according to the shivering frequency in the vertical direction and/or the horizontal direction of the head; according to the facial motion data, acquiring the blink time length, the eye opening degree, the continuous eye closing time length and the yawning degree of the detected person, calculating the psychological and/or physical fatigue degree of the detected person through the combination of one or two or more of the blink rate, the heart rate, the respiration rate, the heart rate variation rate, the blink time length, the eye opening degree, the continuous eye closing time length and the yawning degree, and determining whether the person is sick or not according to the human fatigue degree, wherein the human fatigue degree also reflects whether the person is sick or not and can be used as a physiological characteristic for evaluating whether the person is suffered from new coronary pneumonia or not; calculating the face complexion of the detected person according to the color and the texture of each part of the face, estimating the predicted age of the face according to the information such as the face complexion, the face muscle loss, the face wrinkle distribution, the face contour and the like by judging the face complexion, calculating the face complexion information of the detected person according to the difference between the predicted age and the actual age, and calculating the face complexion according to the colors and the characteristics of the iris and the eyeball of the detected person, wherein if the eye has a plurality of blood streak, the iris is yellow and the white eyeball is yellow, the face complexion of one person belongs to a bad state, the face complexion can be calculated according to the colors and the texture of tongue fur, the colors and the texture of the lip and other characteristics of different parts of the face, and the face complexion of the detected person can reflect the health state of the detected person;
step S400: acquiring sound data of a detected person through a sound sensor, judging whether the sound sent by the detected person is cough sound or not based on a voiceprint feature matching technology, and calculating information such as cough times, cough intensity, cough type and the like of the detected person by analyzing information such as amplitude, frequency, duration and the like of the voiceprint feature of the cough;
step S500: detecting one or a combination of two or more of the highest body temperature of the forehead of the human face, the lowest body temperature of the forehead of the human face, the average body temperature of the forehead of the human face, the highest body temperature of the face, the lowest body temperature of the face and the average body temperature of the face by an infrared sensor, wherein the infrared sensor adopts an infrared dot matrix sensor; fusing the infrared body temperature face contour acquired by the infrared dot matrix sensor with the face video information, and accurately extracting the highest body temperature, the lowest body temperature and the average body temperature of the forehead part of the face;
step S600: judging whether the physical examination duration of the detected person reaches a preset value, if not, repeatedly executing the step S200; if the preset value has been reached, executing step S700; the preset value of the physical examination duration can be flexibly set according to the severity of the new coronary pneumonia epidemic situation and the limitation of the detection site, for example, the preset value of the physical examination duration can be 10 seconds, 30 seconds, 1 minute, 2 minutes, 3 minutes, 5 minutes and the like;
step S700: calculating statistical characteristic information of physiological indexes such as heart rate, heart rate variation rate, respiration rate, blink rate, blood oxygen saturation, blood pressure, nasal obstruction degree, dry cough degree, human face temperature, shivering degree, fatigue degree, human face complexion and the like, such as calculating the minimum value, the maximum value, the average value, the standard deviation and the like of various physiological indexes;
step S800: acquiring symptoms and clinical sign data of a new coronary pneumonia confirmed patient as a training sample, and training by one or a combination of two or more of a statistical learning method, a machine learning method and a deep learning method to generate a new coronary pneumonia suspected infection risk assessment model, wherein the statistical learning method, the machine learning method and the deep learning method comprise various statistical analysis methods, a support vector machine, a neural network, a genetic algorithm and the like;
inputting the acquired physiological characteristics of the detected person into a trained suspected infection risk assessment model of the new coronary pneumonia for prediction and analysis, and outputting the suspected infection risk degree of the new coronary pneumonia of the detected person;
for example: after data mining and deep learning, the obtained new suspected coronary pneumonia infection risk assessment model adopts three main judgment indexes of human face body temperature, dry cough degree and respiratory rate and three auxiliary judgment indexes of blood oxygen saturation, heart rate and blood pressure as assessment indexes; the suspected infection risk assessment model of the new coronary pneumonia carries out risk grading scoring according to the similarity between each physiological characteristic value and a patient with confirmed diagnosis of the new coronary pneumonia, wherein the body temperature of a human face is less than or equal to 35 ℃ for 3 minutes, the body temperature of the human face is less than or equal to 1 minute at 35.1-36 ℃, the body temperature of the human face is 0 minute at 36.1-38 ℃, the body temperature of the human face is 1 minute at 38.1-39 ℃, and the body temperature of the human face is more than or equal to 2 minutes at 39.1 ℃; the respiratory rate is less than or equal to 8 times/min and is scored as 3 points, the respiratory rate is scored as 1 point for 9-11 times/min, the respiratory rate is 0 point for 12-20 times/min, the respiratory rate is 2 points for 21-24 times/min, and the respiratory rate is 3 points for 25 times/min or more; the dry cough degree is 0 score when no dry cough symptom exists, 1 score when mild dry cough exists, 2 score when moderate dry cough exists, and 3 score when severe dry cough exists; the blood oxygen saturation is less than or equal to 91 percent for 3 minutes, 92 percent to 93 percent for 2 minutes, 94 percent to 95 percent for 1 minute, and more than or equal to 96 percent for 0 minute; the heart rate is less than or equal to 40 times/min for 3 min, 41-50 times/min for 1 min, 51-90 times/min for 0 min, 91-110 times/min for 1 min, 111-130 times/min for 2 min, and more than or equal to 131 times/min for 3 min; the systolic pressure is 3 minutes for less than 90 mmHg, 2 minutes for 91-100mmHg, 1 minute for 101-219 mmHg, 0 minute for 111-219 mmHg and 3 minutes for more than 220 mmHg; through deep learning, different weights are respectively given to the human face body temperature, the respiratory rate, the dry cough degree, the blood oxygen saturation, the heart rate and the blood pressure, the human face body temperature is 0.25, the respiratory rate is 0.25, the dry cough degree is 0.20, the blood oxygen saturation is 0.10, the heart rate is 0.10 and the blood pressure is 0.10, and a linear equation model for calculating the suspected infection risk assessment of the new coronary pneumonia is obtained; the preset risk threshold values are 2.6, 1.8, 1.2 and 0.6, when the risk evaluation value is greater than or equal to 2.6, the suspected infection risk degree of the new coronary pneumonia of the detected person is considered to be extremely high, when the risk evaluation value is greater than or equal to 1.8 and less than 2.6, the suspected infection risk degree of the new coronary pneumonia of the detected person is considered to be high, when the risk evaluation value is greater than or equal to 1.2 and less than 1.8, the suspected infection risk degree of the new coronary pneumonia of the detected person is considered to be medium, when the risk evaluation value is greater than or equal to 0.6 and less than 1.2, the suspected infection risk degree of the new coronary pneumonia of the detected person is considered to be low, and when the risk evaluation value is less than 0.6, the suspected infection risk degree of the new coronary pneumonia of the detected person is considered to be extremely low; for example, when plum is subjected to physical examination, if the face body temperature of plum is 37.2 ℃, the respiratory rate is 15 times/minute, the dry cough degree is no dry cough symptom, the blood oxygen saturation is 97%, the heart rate is 92 times/minute, and the systolic pressure is 103mmHg, then the risk scores of various physiological characteristics of plum are respectively 0, 1, and the risk evaluation value of plum is 0.25 + 0.20 + 0.10 + 1 + 0.10 = 0.2 and less than 0.6, so the suspected risk degree of infection of certain new coronary pneumonia of plum is considered to be extremely low;
step S900: acquiring pre-recorded personal basic information of the detected person through an identity authentication identifier of the detected person, and automatically and remotely reporting the personal basic information of the detected person, the acquired physiological characteristic index information and the calculated risk degree information of suspected infection of the new coronary pneumonia to a database for a new coronary pneumonia epidemic situation management department to use; the personal basic information of the detected person comprises a name, an identification card number, gender, age, a unit, a living address, a mobile phone number, an electronic mail box and the like;
on the basis of the existing single body temperature index screening, multiple physiological indexes such as dry cough, respiratory rate, blood oxygen saturation, heart rate variability, nasal obstruction, blood pressure, blink rate, shivering degree, fatigue degree and face complexion closely related to the new coronary pneumonia infection are additionally added, and the accuracy and robustness of the new coronary pneumonia suspected infection observation judgment result are greatly improved; and all the physiological indexes can be automatically and remotely acquired and reported in a non-contact mode, so that the infection risk of the medical staff for field physical examination is avoided.
Example three:
referring to fig. 3, a large-area observation system for suspected infection of new coronary pneumonia comprises: the system comprises a physiological characteristic acquisition module, a risk evaluation module and a judgment module;
the physiological characteristic acquisition module is used for directly acquiring or indirectly calculating the physiological characteristics of the detected person through the sensor assembly;
the risk assessment module is used for acquiring symptoms and clinical sign data of a patient with confirmed diagnosis of new coronary pneumonia as a training sample, and training the patient by one or a combination of two or more of a statistical learning method, a machine learning method and a deep learning method to generate a suspected infection risk assessment model of the new coronary pneumonia;
the judgment module is used for inputting the physiological characteristics of the detected person into the suspected new coronary pneumonia infection risk evaluation model and outputting the suspected new coronary pneumonia infection risk degree of the detected person.
Referring to fig. 4, in the present embodiment, the modules are integrated into a desktop computer, and the subject can start to perform the risk assessment of suspected infection of new coronary pneumonia by sitting right in front of the desktop computer.
According to the embodiment, the accuracy of the observation and judgment result of the suspected infection of the new coronary pneumonia is improved by acquiring various physiological characteristics of a detected person as screening characteristics; the risk degree of suspected new coronary pneumonia infection of a detected person is calculated by the judging module by combining symptoms and clinical sign data of a patient confirmed with new coronary pneumonia, and subjective judgment errors caused by artificial observation are reduced.
Example four:
the identity authentication module is used for acquiring the identity of the detected person and judging whether the detected person is the person or not by verifying the identity; the identity identification comprises face data, voice data, fingerprint data, heart rate data, vein data and iris data.
Further, the physiological characteristic acquisition module comprises an optical sensor, a sound sensor and an infrared sensor; the optical sensor can adopt a common color camera, an infrared night vision camera, a high-speed camera, an optical camera with one or more optical filters, a network camera, an IP camera, a laser camera and the like; the sound sensor can be a microphone built in a common notebook computer, a microphone built in a mobile phone, a microphone built in a camera, a microphone external to a desktop computer, an omnidirectional stereo microphone or a microphone array and the like; the infrared sensor can be an infrared single-point temperature sensor, an infrared dot matrix temperature sensor, an infrared thermal imaging camera, an infrared thermometer and the like.
Further, the optical sensor is used for acquiring the optical change data of the blood flow of the face of the detected person, the facial action data and the color and texture of each part of the face; the sound sensor is used for acquiring the voiceprint characteristics of the detected person; the infrared sensor is used for acquiring temperature data of one or more parts of the human face;
the physiological characteristic acquisition module also comprises a human face body temperature calculation module, a dry cough degree calculation module, a respiratory rate calculation module, a blood oxygen saturation degree calculation module, a heart rate variation rate calculation module, a blood pressure calculation module, a blink rate calculation module, a nasal obstruction degree calculation module, a shivering degree calculation module, a fatigue degree calculation module and a human face gas color calculation module;
the heart rate calculation module firstly performs optical compensation to maintain the stability of the brightness in the recorded human face video; and selecting the area with better human face detection effect as follows: the forehead and the cheek are taken as characteristic areas; the RGB three-dimensional vector (pixel values of RED, GREEN and BLUE) of each pixel point in the characteristic region is obtained through an optical sensor, obtaining green light value, ratio of green light to blue light and three components of light intensity value of each pixel point through RGB three-dimensional vector, amplifying green light value, ratio of green light to blue light and light intensity value through Euler color amplification technology, filtering after amplification, analyzing the filtered green light value, the ratio of green light to blue light and the light intensity value by a principal component analysis method, outputting principal components and filtering, calculating a time domain waveform and/or a frequency domain waveform of the heartbeat of the detected person according to the peak-to-valley value of the filtered principal component value changing along with the time, and calculating the heart rate of the detected person based on the time domain waveform and/or the frequency domain waveform of the heartbeat;
the heart rate variation rate calculation module is used for acquiring time intervals between continuous peaks and/or troughs through the time domain waveform of heartbeat, counting time interval characteristics between a plurality of continuous peaks and/or troughs, acquiring frequency spectrum characteristics of the heartbeat through the frequency domain waveform of the heartbeat, and calculating the heart rate variation rate of the detected person according to the time interval characteristics of the peaks and the troughs of the heartbeat and/or the frequency spectrum characteristics of the heartbeat;
the blood pressure calculation module is used for obtaining the arrival time difference of heartbeat wave peaks and/or the arrival time difference of heartbeat wave troughs at different parts of a human face and/or the heartbeat frequency spectrum characteristics of different parts of the face to calculate the blood pressure information of a detected person, because the lengths of blood vessels reaching different parts are different when the heart pumps blood, blood pressure data can be calculated according to the arrival time difference of the heartbeat wave peaks and/or the arrival time difference of the heartbeat wave troughs at different parts of the human face and/or the heartbeat frequency spectrum characteristics of different parts of the face, the arrival states of the heartbeat wave peaks and the wave troughs at different parts can be known through the Euler color amplification technology, and the arrival time difference of the heartbeat wave peaks and the wave troughs between different parts can be obtained by carrying out frame extraction processing on the face video data;
the blood oxygen saturation calculation module is used for calculating the blood oxygen saturation of the detected person by acquiring the light intensity variation ratio of the red light and the infrared light of the human face;
the respiratory rate calculation module is used for amplifying the facial motion of a detected person in the human face video data through an Euler motion amplification technology, counting micro-motion information of feature points related to the face and the breath of the detected person to calculate the respiratory rate of the detected person, when the person breathes, a plurality of feature parts related to the breath on the face move along with the person, such as nostrils and nasal wings, and capturing the feature points to perform Euler motion amplification to calculate the respiratory rate of the person;
the blink rate calculation module is used for calculating the blink rate of the detected person by acquiring the time interval between spontaneous blinks of the human body, wherein the spontaneous blinks refer to eye closing actions with the time of 0.3 s-0.4 s, and if the eye closing time of the detected person exceeds the time interval of the spontaneous blinks, the current blink is not counted into the number of spontaneous blink;
the nasal obstruction degree calculating module is used for acquiring micro-movement of a nose part of a human face through an edge detection algorithm, calculating nasal obstruction degree information of a detected person by combining instantaneous nose part movement and micro-movement mouth characteristics caused by nasal obstruction inspiration movement, judging to be serious nasal obstruction if detecting that the nasal wings contract for a long time, the nose rises, the nose folds and the upper lip of the mouth rise, and judging to be slight nasal obstruction if detecting that the nasal wings contract for a short time, the nose rises slightly and the mouth does not change obviously;
the shake degree calculation module is used for acquiring the periodic shake motion of the head of the detected person according to the facial action data, and calculating the shake degrees of the head of the detected person, such as spontaneous nodding, shaking head and the like caused by vestibular reflection through the shake frequency of the head in the vertical direction and/or the horizontal direction;
the tiredness degree calculation module is used for acquiring the blink time length, the eye opening degree, the continuous eye closing time length and the yawning degree of the detected person according to the facial motion data, and calculating the psychological and/or physical tiredness degree of the detected person through one or the combination of two or more of the blink rate, the heart rate, the respiration rate, the heart rate variation rate, the blink time length, the eye opening degree, the continuous eye closing time length and the yawning degree;
the human face complexion calculation module is used for calculating the human face complexion of the detected person according to the color and the texture of each part of the face, the predicted age of the human face can be estimated through the information of the human face complexion, the facial muscle loss, the facial wrinkle distribution, the human face contour and the like according to the judgment of the human face complexion, the human face complexion information of the detected person can be calculated through the difference between the predicted age and the actual age, the human face complexion can be calculated through the color and the characteristic of the iris and the eyeball of the detected person, if the eye has a lot of blood streak, the iris is yellow and the white eyeball is yellow, the human face complexion of one person belongs to a bad state, and the human face complexion can be calculated through the color and the texture of tongue coating, the color and the texture of the lip and other characteristics of different parts of the face;
the dry cough degree calculation module is used for judging the frequency of the sound emitted by the detected person as cough sound according to the voiceprint characteristics of the detected person and calculating the dry cough degree of the detected person according to the amplitude, the frequency and the duration of the voiceprint characteristics of the cough sound emitted by the detected person;
the human face body temperature calculation module is used for detecting one or a combination of two or more of human face forehead highest body temperature, human face forehead lowest body temperature, human face forehead average body temperature, face highest body temperature, face lowest body temperature and face average body temperature through an infrared sensor, wherein the infrared sensor is an infrared dot matrix sensor; and fusing the infrared body temperature face outline acquired by the infrared dot matrix sensor with the face video information, and accurately extracting the highest body temperature, the lowest body temperature and the average body temperature of the forehead part of the face.
Referring to fig. 5, the device further comprises a physiological index display module, wherein the physiological index display module is used for displaying one or two or more detection results of heart rate waveforms, heart rate variation rate, respiration rate, blink rate, blood oxygen saturation, blood pressure, nasal obstruction degree, dry cough degree, human face temperature, shivering degree, fatigue degree and human face complexion.
Further, the system also comprises a final physical examination result feedback module and a physical examination data remote automatic reporting module; the final physical examination result feedback module is used for informing the final physical examination result to the detected person and/or the detected person guardian and/or the new coronary pneumonia related manager in the forms of characters, images, sounds and the like through a projector, a notebook computer screen, a desktop computer display, a mobile phone screen, a mobile phone short message, an e-mail, a voice broadcast and the like; the physical examination data remote automatic reporting module automatically uploads the acquired physiological characteristic indexes of the detected person, the risk evaluation result of suspected new coronary pneumonia infection of the detected person and the personal basic information of the detected person to a database for use by new coronary pneumonia epidemic situation managers or departments.
On the basis of the existing single body temperature index screening, multiple physiological characteristic indexes such as dry cough, respiratory rate, blood oxygen saturation, heart rate variation rate, nasal obstruction, blood pressure, blink rate, shivering degree, fatigue degree and face complexion closely related to the new coronary pneumonia infection are additionally added, so that the accuracy and robustness of the suspected infection observation judgment result of the new coronary pneumonia are greatly improved; and all the physiological characteristic indexes can be automatically and remotely acquired and reported in a non-contact mode, so that the infection risk of the medical staff for field physical examination is avoided.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (3)
1. A large-area observation system for suspected infection of new coronary pneumonia is characterized by comprising: the system comprises a physiological characteristic acquisition module, a risk evaluation module and a judgment module;
the physiological characteristic acquisition module is used for directly acquiring or indirectly calculating the physiological characteristics of the detected person through the sensor assembly;
the risk assessment module is used for acquiring symptoms and clinical sign data of a patient with confirmed diagnosis of new coronary pneumonia as training samples, and training the training samples by a statistical learning method, a machine learning method or a deep learning method to generate a suspected infection risk assessment model of the new coronary pneumonia;
the judgment module is used for inputting the physiological characteristics of the detected person into the suspected new coronary pneumonia infection risk evaluation model and outputting the suspected new coronary pneumonia infection risk degree of the detected person;
the physiological characteristic acquisition module comprises an optical sensor, a sound sensor and an infrared sensor;
the optical sensor is used for acquiring the optical change data of the blood flow of the face of the detected person, the facial action data and the color and texture of each part of the face; the sound sensor is used for acquiring the voiceprint characteristics of the detected person; the infrared sensor is used for acquiring temperature data of one or more parts of the human face;
the physiological characteristic acquisition module further comprises a human face body temperature calculation module, a dry cough degree calculation module, a respiratory rate calculation module, a blood oxygen saturation degree calculation module, a heart rate variability rate calculation module, a blood pressure calculation module, a blink rate calculation module, a nasal obstruction degree calculation module, a shivering degree calculation module, a fatigue degree calculation module and a human face gas color calculation module;
the heart rate calculation module is used for acquiring a time domain waveform and/or a frequency domain waveform of heartbeat of the detected person according to the facial blood flow optical change data, and calculating the heart rate of the detected person based on the time domain waveform and/or the frequency domain waveform of the heartbeat;
the heart rate variation rate calculation module is used for calculating the heart rate variation rate of the detected person according to the time intervals between the continuous peaks or troughs of the time domain waveform of the heartbeat and/or the frequency spectrum characteristics of the frequency domain waveform of the heartbeat;
the blood pressure calculation module is used for acquiring the arrival time difference of heartbeat wave peaks and/or the arrival time difference of heartbeat wave troughs and/or the heartbeat frequency spectrum characteristics of different parts of the face of the detected person according to the optical change data of the facial blood flow, and calculating the blood pressure of the detected person according to the arrival time difference of heartbeat wave peaks and/or the arrival time difference of heartbeat wave troughs and/or the heartbeat frequency spectrum characteristics of different parts of the face;
the blood oxygen saturation calculation module is used for acquiring the light intensity variation ratio of red light and infrared light on the face of the detected person and calculating the blood oxygen saturation of the detected person according to the light intensity variation ratio of the red light and the infrared light on the face;
the breathing rate calculation module is used for acquiring a time domain waveform and/or a frequency domain waveform of the breath of the detected person according to the facial motion data, and calculating the breathing rate of the detected person based on the time domain waveform and/or the frequency domain waveform of the breath;
the blink rate calculation module is used for acquiring the number of spontaneous blinks of the detected person according to the face motion data and calculating the blink rate of the detected person according to the number of spontaneous blinks and the detection time;
the nasal obstruction degree calculating module is used for acquiring micro-movement of the nose part of the detected person according to the facial action data, and calculating the nasal obstruction times and the nasal obstruction degree of the detected person by combining the characteristics and the strength of the instantaneous micro-movement of the nose part;
the shake degree calculation module is used for acquiring the periodic shake motion of the head of the detected person according to the facial action data and calculating the shake degree of the head of the detected person according to the shake frequency of the head in the vertical direction and/or the horizontal direction;
the tiredness degree calculation module is used for acquiring the blink time length, the eye opening degree, the continuous eye closing time length and the yawning degree of the detected person according to the facial motion data, and calculating the psychological and/or physical tiredness degree of the detected person according to the blink rate, the heart rate, the respiration rate, the heart rate variation rate, the blink time length, the eye opening degree, the continuous eye closing time length and the yawning degree;
the human face gas color calculation module is used for calculating the human face gas color of the detected person according to the color and the texture of each part of the face;
the dry cough degree calculation module is used for judging the frequency of the sound emitted by the detected person as cough sound according to the vocal print characteristics of the detected person, and calculating the dry cough degree of the detected person according to the amplitude, the frequency and the duration of the vocal print characteristics of the cough sound emitted by the detected person;
the human face body temperature calculation module is used for calculating the human face body temperature according to the temperature data of the plurality of parts of the human face.
2. The system according to claim 1, wherein the system is used for observing suspected infection of new coronary pneumonia in large area, and comprises: the identity authentication module is used for acquiring the identity of the detected person and judging whether the detected person is the person or not by verifying the identity; the identification is face data, voice data, fingerprint data, heart rate data, vein data or iris data.
3. The system according to claim 1, wherein the system is used for observing suspected infection of new coronary pneumonia in large area, and comprises: the system also comprises a final physical examination result feedback module and a physical examination data remote automatic reporting module; the final physical examination result feedback module is used for sending a risk evaluation result of suspected infection of the detected person with the new coronary pneumonia to the detected person and/or the detected person guardian and/or a new coronary pneumonia related manager; the physical examination data remote automatic reporting module automatically uploads the acquired physiological characteristic indexes of the detected person, the risk assessment result of suspected infection of new coronary pneumonia of the detected person and the personal basic information of the detected person to a database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010632445.7A CN111803032B (en) | 2020-07-03 | 2020-07-03 | Large-area observation method and system for suspected infection of Xinguan pneumonia |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010632445.7A CN111803032B (en) | 2020-07-03 | 2020-07-03 | Large-area observation method and system for suspected infection of Xinguan pneumonia |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111803032A CN111803032A (en) | 2020-10-23 |
| CN111803032B true CN111803032B (en) | 2022-08-19 |
Family
ID=72855273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010632445.7A Active CN111803032B (en) | 2020-07-03 | 2020-07-03 | Large-area observation method and system for suspected infection of Xinguan pneumonia |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111803032B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112494032A (en) * | 2021-02-03 | 2021-03-16 | 中南大学湘雅二医院 | Respiratory disease monitoring and early warning system based on acoustic characteristics |
| CN113208575A (en) * | 2021-05-06 | 2021-08-06 | 成都安瑞健康科技有限公司 | Method and system for detecting coronavirus infection by using wearable device of Internet of things |
| WO2022243137A1 (en) * | 2021-05-21 | 2022-11-24 | Femtec Health, Inc. | System and method for pre-symptomatic and/or asymptomatic detection of a human viral or bacterial infection |
| CN116074033A (en) * | 2021-11-04 | 2023-05-05 | 中兴通讯股份有限公司 | Information verification method, server and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355035A (en) * | 2016-09-28 | 2017-01-25 | 湖南老码信息科技有限责任公司 | Pneumonia prediction method and prediction system based on incremental neural network model |
| WO2018096335A1 (en) * | 2016-11-24 | 2018-05-31 | Ucl Business Plc | Apparatus comprising a nasal airflow sensing device and a computing system |
| CN110584618A (en) * | 2019-08-15 | 2019-12-20 | 济南市疾病预防控制中心 | Infectious disease machine recognition system based on artificial intelligence |
| CN110891486A (en) * | 2017-03-10 | 2020-03-17 | 梅西莫股份有限公司 | Pneumonia screening instrument |
| CN111110269A (en) * | 2020-01-07 | 2020-05-08 | 湖南大学 | Infant pneumonia rapid intelligent diagnosis method based on mixed deep learning model |
-
2020
- 2020-07-03 CN CN202010632445.7A patent/CN111803032B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355035A (en) * | 2016-09-28 | 2017-01-25 | 湖南老码信息科技有限责任公司 | Pneumonia prediction method and prediction system based on incremental neural network model |
| WO2018096335A1 (en) * | 2016-11-24 | 2018-05-31 | Ucl Business Plc | Apparatus comprising a nasal airflow sensing device and a computing system |
| CN110891486A (en) * | 2017-03-10 | 2020-03-17 | 梅西莫股份有限公司 | Pneumonia screening instrument |
| CN110584618A (en) * | 2019-08-15 | 2019-12-20 | 济南市疾病预防控制中心 | Infectious disease machine recognition system based on artificial intelligence |
| CN111110269A (en) * | 2020-01-07 | 2020-05-08 | 湖南大学 | Infant pneumonia rapid intelligent diagnosis method based on mixed deep learning model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111803032A (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111803032B (en) | Large-area observation method and system for suspected infection of Xinguan pneumonia | |
| JP4401079B2 (en) | Subject behavior analysis | |
| CN108697386B (en) | System and method for detecting physiological state | |
| EP2748743B1 (en) | Data administration system and method | |
| JP5977255B2 (en) | Dysphagia detection device and operation method thereof | |
| CN107809951B (en) | Psychophysiological detection (lie detection) method and apparatus for distortion using video-based detection of physiological signals | |
| CN103841888B (en) | The apnea and hypopnea identified using breathing pattern is detected | |
| CN111839489B (en) | Non-contact physiological and psychological health detection system | |
| US20090216092A1 (en) | System for analyzing eye responses to accurately detect deception | |
| KR101270954B1 (en) | Biometric system using ecg signal and fingerprint identification | |
| KR101738278B1 (en) | Emotion recognition method based on image | |
| CN112233516A (en) | Grading method and system for physician CPR examination training and examination | |
| CN108597621B (en) | Health state monitoring device, system and method based on traditional Chinese medicine theory | |
| WO2022039559A1 (en) | Method and system for breathing measurement and management using an electronic device | |
| US20220338757A1 (en) | System and method for non-face-to-face health status measurement through camera-based vital sign data extraction and electronic questionnaire | |
| CN111803031A (en) | Non-contact type drug addict relapse monitoring method and system | |
| CN112233515A (en) | Unmanned examination and intelligent scoring method applied to physician CPR examination | |
| KR102442425B1 (en) | Method for Classifying Mental State, Server for Classifying Mental State and Computing Device | |
| CN113040773A (en) | Data acquisition and processing method | |
| RU2549314C2 (en) | Method of controlling cardio-pulmonary resuscitation and device for its realisation | |
| WO2020203015A1 (en) | Illness aggravation estimation system | |
| Tatulli et al. | Respiratory Inductance Plethysmography for Automated Swallowing Detection | |
| JP2019198531A (en) | Biological information measurement device and biological information measurement method | |
| KR20150101323A (en) | Apparatus for analyzing physiological signals based on image processing and method thereof | |
| Hanawa et al. | Nasal cavity detection in facial thermal image for non-contact measurement of breathing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |