CN112386765B - Intelligent infusion monitoring system based on 5G - Google Patents
Intelligent infusion monitoring system based on 5G Download PDFInfo
- Publication number
- CN112386765B CN112386765B CN202011155242.XA CN202011155242A CN112386765B CN 112386765 B CN112386765 B CN 112386765B CN 202011155242 A CN202011155242 A CN 202011155242A CN 112386765 B CN112386765 B CN 112386765B
- Authority
- CN
- China
- Prior art keywords
- infusion
- pixel
- pixels
- unit
- alarm
- 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
- 238000001802 infusion Methods 0.000 title claims abstract description 232
- 238000012544 monitoring process Methods 0.000 title claims description 48
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000005540 biological transmission Effects 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims description 45
- 239000007788 liquid Substances 0.000 claims description 38
- 239000003814 drug Substances 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 21
- 230000010365 information processing Effects 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000005303 weighing Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 2
- 101100006960 Caenorhabditis elegans let-2 gene Proteins 0.000 claims 1
- 230000002708 enhancing effect Effects 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000003709 image segmentation Methods 0.000 description 4
- 101100001674 Emericella variicolor andI gene Proteins 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000001990 intravenous administration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
- A61M5/14—Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
- A61M5/168—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body
- A61M5/16831—Monitoring, detecting, signalling or eliminating infusion flow anomalies
- A61M5/1684—Monitoring, detecting, signalling or eliminating infusion flow anomalies by detecting the amount of infusate remaining, e.g. signalling end of infusion
- A61M5/16845—Monitoring, detecting, signalling or eliminating infusion flow anomalies by detecting the amount of infusate remaining, e.g. signalling end of infusion by weight
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
- A61M5/14—Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
- A61M5/168—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body
- A61M5/16804—Flow controllers
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2205/00—General characteristics of the apparatus
- A61M2205/33—Controlling, regulating or measuring
- A61M2205/3306—Optical measuring means
Landscapes
- Health & Medical Sciences (AREA)
- Vascular Medicine (AREA)
- Engineering & Computer Science (AREA)
- Anesthesiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Hematology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Image Processing (AREA)
Abstract
The utility model provides an intelligence infusion monitored control system based on 5G, includes infusion monitor module, information transmission module and infusion monitor terminal, infusion monitor module is used for gathering the image of infusion signal and transfusion system to transmit to infusion monitor terminal through information transmission module, infusion monitor terminal is used for acquireing patient's infusion state, shows patient's infusion information, provides infusion alarm function, and statistics patient's infusion details and the log information of reporting to the police provide infusion details and the inquiry function of the log information of reporting to the police. The invention has the beneficial effects that: make medical personnel can directly acquire the state information and the image information that the patient infused at infusion monitor terminal to improve the security of infusion process, alleviateed medical personnel's the amount of labour, data and image use in the control process, when further having improved the security of infusion process, make medical personnel can more audio-visual grasp the real-time condition of infusion.
Description
Technical Field
The invention relates to the field of intelligent monitoring, in particular to an intelligent infusion monitoring system based on 5G.
Background
Intravenous infusion is the most common and important means for assisting in treating diseases in clinical medical work, and infusion needs to be hung on an infusion support or above a puncture site of a patient, liquid medicine is infused into the body of the patient by utilizing potential difference, a nurse observes liquid drops in the infusion tube by naked eyes and estimates infusion dropping speed, and the infusion speed is controlled by manually adjusting pulleys on the infusion set according to experience. The nurse needs to continuously patrol and examine in the infusion process, and the patient or the accompanying person observes the residual liquid medicine amount, and when the liquid medicine amount is about to be infused or the dripping speed is abnormal, the nurse on duty is timely informed to come and handle. Therefore, the labor intensity of medical staff is increased, the error rate is greatly increased, the rest of a patient is not facilitated, and the treatment quality is influenced. If the nurse fails to timely find and handle the patient due to the fact that the liquid medicine is completely infused or the infusion tube is blocked, blood return or other dangers may occur, pain may be caused to the patient, and even medical accidents may be caused.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a 5G-based intelligent infusion monitoring system.
The purpose of the invention is realized by the following technical scheme:
an intelligent transfusion monitoring system based on 5G comprises a transfusion monitoring module, an information transmission module and a transfusion monitoring terminal, wherein the transfusion monitoring module comprises an infrared detection unit, a transfusion weighing unit and a transfusion visual monitoring unit, the infrared detection unit is used for collecting a dropping speed signal of a liquid medicine, the transfusion weighing unit is used for collecting weight change data of a transfusion device, the transfusion visual monitoring unit is used for collecting images of the transfusion device, the transfusion monitoring module transmits the collected dropping speed signal of the liquid medicine, the weight change data of the transfusion device and the images of the transfusion device to the transfusion monitoring terminal through the information transmission module, the transfusion monitoring terminal comprises a system configuration module, a transfusion information processing module, a transfusion information display module, a transfusion detail inquiry and statistics module, a transfusion intelligent alarm module and an alarm information inquiry and statistics module, the system configuration module comprises a patient management unit and a bed management unit, medical staff inputs basic information of a patient and basic information of infusion through the patient management unit, the bed management unit is used for binding an infusion monitoring module and a bed number, the infusion information processing module comprises an infusion information processing unit and an infusion image processing unit, the infusion information processing unit is used for calculating the infusion state of the patient according to the basic information of the infusion of the patient, a received dropping speed signal of liquid medicine and weight change data of an infusion apparatus, the infusion image processing unit is used for processing the received infusion apparatus image, the infusion information display module is used for displaying the infusion state of the patient and the processed infusion apparatus image, the infusion detail inquiry and statistics module comprises an infusion detail statistics unit and an infusion detail inquiry unit, the infusion detail counting unit is used for counting the infusion details of the patient from the system configuration module and the infusion information processing module, and calculating the percentage of the infusion progress of the patient and a change trend chart of the infusion speed of the patient according to the infusion details of the patient; medical personnel can inquire the percentage of patient's infusion details, patient's infusion progress and the change trend chart of the speed of dripping of patient's infusion through infusion details inquiry unit, infusion intelligent alarm module is used for comparing patient's infusion state and predetermined alert value to judge whether report to the police, alarm information inquiry statistics module includes alarm information statistical unit and alarm information inquiry unit, alarm information statistical unit is used for counting the log information of reporting to the police when infusion intelligent alarm module reports to the police, and medical personnel can inquire the log information of reporting to the police through alarm information inquiry unit.
Preferably, the information transmission module transmits information by using a 5G communication technology.
Preferably, the infrared detection unit includes an infrared emission module and an infrared receiving module, the infrared emission module is configured to emit infrared light, and the infrared receiving module is configured to receive infrared light.
Preferably, the basic information of the patient includes the ward, the bed number and the name of the patient; the basic information of the infusion includes infusion start time, estimated infusion end time, and the amount of liquid medicine to be infused.
Preferably, the transfusion state of the patient includes the remaining amount of the liquid medicine, the remaining transfusion time, and the transfusion dripping speed.
Preferably, the infusion details of the patient include a ward, a bed number, a name, an infusion start time, a predicted infusion end time, a liquid medicine amount to be infused, a remaining liquid medicine amount, a remaining infusion time, and an infusion drop rate.
Preferably, infusion intelligent alarm module is used for comparing patient's infusion state and predetermined alert value to whether the judgement is reported to the police, including remaining liquid volume reminding unit, drip speed reminding unit and remaining time reminding unit, remaining liquid volume reminding unit is used for reporting to the police when remaining liquid volume of medicine is less than predetermined alert value, drip speed reminding unit is used for reporting to the police when dripping speed and surpassing predetermined alert value, remaining time reminding unit is used for reporting to the police when remaining infusion time is less than predetermined alert value.
Preferably, the log information of the alarm comprises a ward, a bed number, alarm time and alarm types, wherein the alarm types comprise residual liquid volume alarm, dripping speed alarm and residual time alarm.
Preferably, the infusion set image processing unit is configured to process the received infusion set image, and includes an image optimization unit and a target segmentation unit, where the image optimization unit is configured to perform filtering processing on the received infusion set image and enhance the filtered infusion set image, and the target segmentation unit is configured to perform target segmentation on the optimized infusion set image and remove a background region in the infusion set image.
Preferably, the image optimization unit is configured to perform filtering processing on the received infusion apparatus image, where I is assumed to represent the infusion apparatus image to be processed, I (x, y) is assumed to represent a pixel at a coordinate (x, y) in the infusion apparatus image I, and the filtering processing is performed on the pixel I (x, y), specifically:
let U (x, y) denote a local area of (2o +1) × (2o +1) centered on a pixel I (x, y), where o is a given positive integer, and
m and K are respectively the length and the width of the infusion apparatus image I, H (x, y) is set to represent a neighborhood pixel set of the pixel I (x, y), and pixels in the set H (x, y) are selected from pixels in a local area U (x, y) in the following mode:
let u (x, y) denote a 3 x 3 local neighborhood centered on the pixel I (x, y),
representing the mean of the grey values of the pixels in the local neighborhood U (x, y), I (I, j) representing the pixel at coordinate (I, j) in the local area U (x, y), f (I, j) representing the grey value of the pixel I (I, j), given a grey threshold value f (h), when the pixel I (I, j) satisfies
Then the pixel I (I, j) is added to the set H (x, y) when the pixel I (I, j) satisfies
If so, not adding the pixel I (I, j) into the set H (x, y), and according to the method, completing the selection of the pixels in the local area U (x, y);
definition eta1(x, y) denotes a first pixel corresponding to a pixel in the set H (x, y)Coefficient of attribute detection, η2(x, y) represents a second attribute detection coefficient corresponding to a pixel in the set H (x, y), and η1(x, y) and η2The values of (x, y) are:
where I (a, b) represents the pixel at coordinate (a, b) in the set H (x, y), f (a, b) represents the grayscale value of the pixel I (a, b), I (M, n) represents the pixel at coordinate (M, n) in the set H (x, y), f (M, n) represents the grayscale value of the pixel I (M, n), M (x, y) represents the number of pixels in the set H (x, y),
representing the mean of the gray values of the pixels in the set H (x, y);
determine a set of neighboring pixels of the pixel I (x, y), given the attribute threshold η (H), and
wherein f ismid(x, y) represents the median of the gray values of the pixels in the set H (x, y), when |. eta1(x，y)-η2When the (x, y) | is less than or equal to eta (H), selecting the set H (x, y) as the adjacent pixel set of the pixel I (x, y), and enabling the set H (x, y) to be adjacent to the pixel I (x, y)
Where ρ (a, b) represents a distribution detection coefficient of the pixel I (a, b) in the set H (x, y), and
when eta1(x，y)-η2(x，y)If | η (H), then the set of neighboring pixels for pixel I (x, y) is determined as follows:
screening the pixels in the set H (x, y) when the pixels I (a, b) satisfy
When the pixel I (a, b) is satisfied, the pixel I (a, b) is retained in the set H (x, y)
Then, deleting the pixel I (a, b) in the set H (x, y) until the screening of all the pixels in the set H (x, y) is completed according to the method, wherein rhomid(x, y) represents a median value of distribution detection coefficients of pixels in the set H (x, y), ρmax(x, y) represents the maximum value of the distribution detection coefficients of the pixels in the set H (x, y);
let H ' (x, y) denote a set of pixels remaining after the pixels in the set H (x, y) have been screened, and the pixels in the set H ' (x, y) are classified, let H '1(x, y) represents a first subset, H ', of the set H ' (x, y) into which the pixels are classified '2(x, y) represents a second subset obtained by classifying pixels in the set H ' (x, y), a pixel having the smallest distribution detection coefficient in the set H (x, y) of the pixels in the set H ' (x, y) is selected as a classification reference pixel, I (C, D) represents a pixel at a coordinate (C, D) in the set H ' (x, y), and I (C, D) is argminI(c，d)∈H′(x，y)ρ (C, D), where I (C, D) represents the pixel at coordinate (C, D) in the set H '(x, y), ρ (C, D) represents the distribution detection coefficient of the pixel I (C, D) in the set H (x, y), the selected classification reference pixel I (C, D) is first added to the first subset H'1(x, y), then classifying other pixels in the set H ' (x, y), and adding the pixel I (C, D) to the first subset H ' when | f (C, D) -f (C, D) | ≦ f (H) '1(x, y) when | f (C, D) -f (C, D) | > f (H), then pixel I (C, D) is added to the second subset H'2(x, y), where f (C, D) represents the number of classified reference pixels I (C,D) f (c, d) represents the gray value of the pixel I (c, d);
determine a set of neighboring pixels of the pixel I (x, y)
Denotes a first subset H'1The mean of the gray values of the pixels in (x, y),
denotes a second subset H'2Mean of the gray values of the pixels in (x, y) when the pixel I (x, y) satisfies
Then, selecting a first subset H'1(x, y) is a set of neighboring pixels of pixel I (x, y), such that
Wherein, I (c)1，d1) Denotes a first subset H'1Coordinate (c) in (x, y)1，d1) Pixel of (d), f (c)1，d1) Represents a pixel I (c)1，d1) Is a gray value of p1(c1，d1) Represents a pixel I (c)1，d1) In a first subset H'1The distribution in (x, y) is detected as a coefficient, and
I(a1，b1) Denotes a first subset H'1Coordinate (a) in (x, y)1，b1) Pixel of (d), f (a)1，b1) Represents a pixel I (a)1，b1) Gray value of (D), M1(x, y) denotes a first subset H'1The number of pixels in (x, y); when the pixel I (x, y) satisfies
Then, selecting a second subset H'2(x, y) is a set of neighboring pixels of the pixel I (x, y), and f (x, y) is defined as
Wherein, I (c)2，d2) Denotes a second subset H'2Coordinate (c) in (x, y)2，d2) Pixel of (d), f (c)2，d2) Represents a pixel I (c)2，d2) Is a gray value of p2(c2，d2) Represents a pixel I (c)2，d2) In a second subset H'2The distribution in (x, y) is detected as a coefficient, and
wherein, I (a)2，b2) Denotes a second subset H'2Coordinate (a) in (x, y)2，b2) Pixel of (d), f (a)2，b2) Represents a pixel I (a)2，b2) Gray value of (D), M2(x, y) denotes a second subset H'2The number of pixels in (x, y); when in use
Then, select local neighborhood u (x, y) as the neighboring pixel set of pixel I (x, y), and let
Preferably, the image segmentation unit segments the optimized infusion set image by using a maximum inter-class variance method, and determines an optimal threshold of the maximum inter-class variance method used in the image segmentation unit by using a particle swarm algorithm.
The beneficial effects created by the invention are as follows:
the infusion monitoring module in the system collects the signal of the dropping speed and the process of infusion through the infrared detection unit and the infusion weighing unit, the image of the infusion apparatus is collected through the visual monitoring unit of infusion, so that medical personnel can directly obtain the state information and the image information of patient infusion at an infusion monitoring terminal, thereby improving the safety of the infusion process, the labor capacity of the medical personnel is reduced, the data and the image are used in the monitoring process, the safety of the infusion process is further improved, and the medical personnel can more intuitively master the real-time condition of infusion.
Drawings
The invention is further described with the aid of the accompanying drawings, in which, however, the embodiments do not constitute any limitation to the invention, and for a person skilled in the art, without inventive effort, further drawings may be derived from the following figures.
FIG. 1 is a schematic diagram of the present invention.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the intelligent infusion monitoring system based on 5G of the embodiment comprises an infusion monitoring module, an information transmission module and an infusion monitoring terminal, wherein the infusion monitoring module comprises an infrared detection unit, an infusion weighing unit and an infusion visual monitoring unit, the infrared detection unit is used for collecting a dropping speed signal of a liquid medicine, the infusion weighing unit is used for collecting weight change data of an infusion apparatus, the infusion visual monitoring unit is used for collecting images of the infusion apparatus, the infusion monitoring module transmits the collected dropping speed signal of the liquid medicine, the collected weight change data of the infusion apparatus and the collected images of the infusion apparatus to the infusion monitoring terminal through the information transmission module, the infusion monitoring terminal comprises a system configuration module, an infusion information processing module, an infusion information display module, an infusion detail query and statistics module, an infusion intelligent alarm module and an alarm information query and statistics module, the system configuration module comprises a patient management unit and a bed management unit, medical staff inputs basic information of a patient and basic information of infusion through the patient management unit, the bed management unit is used for binding an infusion monitoring module and a bed number, the infusion information processing module comprises an infusion information processing unit and an infusion image processing unit, the infusion information processing unit is used for calculating the infusion state of the patient according to the basic information of the infusion of the patient, a received dropping speed signal of liquid medicine and weight change data of an infusion apparatus, the infusion image processing unit is used for processing the received infusion apparatus image, the infusion information display module is used for displaying the infusion state of the patient and the processed infusion apparatus image, the infusion detail inquiry and statistics module comprises an infusion detail statistics unit and an infusion detail inquiry unit, the infusion detail counting unit is used for counting the infusion details of the patient from the system configuration module and the infusion information processing module, and calculating the percentage of the infusion progress of the patient and a change trend chart of the infusion speed of the patient according to the infusion details of the patient; medical personnel can inquire the percentage of patient's infusion details, patient's infusion progress and the change trend chart of the speed of dripping of patient's infusion through infusion details inquiry unit, infusion intelligent alarm module is used for comparing patient's infusion state and predetermined alert value to judge whether report to the police, alarm information inquiry statistics module includes alarm information statistical unit and alarm information inquiry unit, alarm information statistical unit is used for counting the log information of reporting to the police when infusion intelligent alarm module reports to the police, and medical personnel can inquire the log information of reporting to the police through alarm information inquiry unit.
Preferably, the information transmission module transmits information by using a 5G communication technology.
Preferably, the infrared detection unit includes an infrared emission module and an infrared receiving module, the infrared emission module is configured to emit infrared light, and the infrared receiving module is configured to receive infrared light.
Preferably, the basic information of the patient includes the ward, the bed number and the name of the patient; the basic information of the infusion includes infusion start time, estimated infusion end time, and the amount of liquid medicine to be infused.
Preferably, the transfusion state of the patient includes the remaining amount of the liquid medicine, the remaining transfusion time, and the transfusion dripping speed.
Preferably, the infusion details of the patient include a ward, a bed number, a name, an infusion start time, a predicted infusion end time, a liquid medicine amount to be infused, a remaining liquid medicine amount, a remaining infusion time, and an infusion drop rate.
Preferably, infusion intelligent alarm module is used for comparing patient's infusion state and predetermined alert value to whether the judgement is reported to the police, including remaining liquid volume reminding unit, drip speed reminding unit and remaining time reminding unit, remaining liquid volume reminding unit is used for reporting to the police when remaining liquid volume of medicine is less than predetermined alert value, drip speed reminding unit is used for reporting to the police when dripping speed and surpassing predetermined alert value, remaining time reminding unit is used for reporting to the police when remaining infusion time is less than predetermined alert value.
Preferably, the log information of the alarm comprises a ward, a bed number, alarm time and alarm types, wherein the alarm types comprise residual liquid volume alarm, dripping speed alarm and residual time alarm.
This preferred embodiment provides an intelligent infusion monitored control system based on 5G, infusion monitoring module in the system passes through infrared detecting element and the signal of the speed of dripping and the process of infusion weighing unit collection, the image of transfusion system is gathered through the visual monitoring unit of infusion, make medical personnel can directly acquire patient's infusion state information and image information at infusion monitor terminal, thereby the security of infusion process has been improved, medical personnel's the amount of labour has been alleviateed, data and image use in the control process, when further having improved the security of infusion process, make medical personnel can more audio-visually master the real-time condition of infusion.
Preferably, the infusion set image processing unit is configured to process the received infusion set image, and includes an image optimization unit and a target segmentation unit, where the image optimization unit is configured to perform filtering processing on the infusion set image and enhance the filtered infusion set image, and the target segmentation unit is configured to perform target segmentation on the optimized infusion set image and remove a background region in the infusion set image.
Preferably, the image optimization unit is configured to perform filtering processing on the received infusion apparatus image, where I is assumed to represent the infusion apparatus image to be processed, I (x, y) is assumed to represent a pixel at a coordinate (x, y) in the infusion apparatus image I, and the filtering processing is performed on the pixel I (x, y), specifically:
let U (x, y) denote a local area of (2o +1) × (2o +1) centered on a pixel I (x, y), where o is a given positive integer, and
m and K are respectively the length and the width of the infusion apparatus image I, H (x, y) is set to represent a neighborhood pixel set of the pixel I (x, y), and pixels in the set H (x, y) are selected from pixels in a local area U (x, y) in the following mode:
let u (x, y) denote a 3 x 3 local neighborhood centered on the pixel I (x, y),
representing the mean of the grey values of the pixels in the local neighborhood U (x, y), I (I, j) representing the pixel at coordinate (I, j) in the local area U (x, y), f (I, j) representing the grey value of the pixel I (I, j), given a grey threshold value f (h), the value of f (h) may take 10, when the pixel I (I, j) satisfies
Then the pixel I (I, j) is added to the set H (x, y) when the pixel I (I, j) satisfies
If so, not adding the pixel I (I, j) into the set H (x, y), and according to the method, completing the selection of the pixels in the local area U (x, y);
definition eta1(x, y) denotes a first attribute detection coefficient corresponding to a pixel in the set H (x, y), η2(x, y) represents a second attribute detection coefficient corresponding to a pixel in the set H (x, y), and η1(x, y) and η2The values of (x, y) are:
where I (a, b) represents the pixel at coordinate (a, b) in the set H (x, y), f (a, b) represents the grayscale value of the pixel I (a, b), I (M, n) represents the pixel at coordinate (M, n) in the set H (x, y), f (M, n) represents the grayscale value of the pixel I (M, n), M (x, y) represents the number of pixels in the set H (x, y),
representing the mean of the gray values of the pixels in the set H (x, y);
determine a set of neighboring pixels of the pixel I (x, y), given the attribute threshold η (H), and
wherein f ismid(x, y) represents the median of the gray values of the pixels in the set H (x, y), when |. eta1(x，y)-η2When the (x, y) | is less than or equal to eta (H), selecting the set H (x, y) as the adjacent pixel set of the pixel I (x, y), and enabling the set H (x, y) to be adjacent to the pixel I (x, y)
Where ρ (a, b) represents a distribution detection coefficient of the pixel I (a, b) in the set H (x, y), and
when eta1(x，y)-η2(x, y) | > η (H), then the set of neighboring pixels for pixel I (x, y) is determined as follows:
screening the pixels in the set H (x, y) when the pixels I (a, b) satisfy
Then, in the set H (x,y) remaining in the pixel I (a, b) when the pixel I (a, b) satisfies
Then, deleting the pixel I (a, b) in the set H (x, y) until the screening of all the pixels in the set H (x, y) is completed according to the method, wherein rhomid(x, y) represents a median value of distribution detection coefficients of pixels in the set H (x, y), ρmax(x, y) represents the maximum value of the distribution detection coefficients of the pixels in the set H (x, y);
let H ' (x, y) denote a set of pixels remaining after the pixels in the set H (x, y) have been screened, and the pixels in the set H ' (x, y) are classified, let H '1(x, y) represents a first subset, H ', of the set H ' (x, y) into which the pixels are classified '2(x, y) represents a second subset obtained by classifying pixels in the set H ' (x, y), a pixel having the smallest distribution detection coefficient in the set H (x, y) of the pixels in the set H ' (x, y) is selected as a classification reference pixel, I (C, D) represents a pixel at a coordinate (C, D) in the set H ' (x, y), and I (C, D) is argminI(c，d)∈H′(x，y)ρ (C, D), where I (C, D) represents the pixel at coordinate (C, D) in the set H '(x, y), ρ (C, D) represents the distribution detection coefficient of the pixel I (C, D) in the set H (x, y), the selected classification reference pixel I (C, D) is first added to the first subset H'1(x, y), then classifying other pixels in the set H ' (x, y), and adding the pixel I (C, D) to the first subset H ' when | f (C, D) -f (C, D) | ≦ f (H) '1(x, y) when | f (c, D) -f (c, D) | > f (H), then pixel I (c, D) is added to the second subset H'2(x, y), wherein f (C, D) represents a gray value of the classification reference pixel I (C, D), and f (C, D) represents a gray value of the pixel I (C, D);
determine a set of neighboring pixels of the pixel I (x, y)
Denotes a first subset H'1Grey scale value of pixel in (x, y)The average value of the average value is calculated,
denotes a second subset H'2Mean of the gray values of the pixels in (x, y) when the pixel I (x, y) satisfies
Then, selecting a first subset H'1(x, y) is a set of neighboring pixels of pixel I (x, y), such that
Wherein, I (c)1，d1) Denotes a first subset H'1Coordinate (c) in (x, y)1，d1) Pixel of (d), f (c)1，d1) Represents a pixel I (c)1，d1) Is a gray value of p1(c1，d1) Represents a pixel I (c)1，d1) In a first subset H'1The distribution in (x, y) is detected as a coefficient, and
I(a1，b1) Denotes a first subset H'1Coordinate (a) in (x, y)1，b1) Pixel of (d), f (a)1，b1) Represents a pixel I (a)1，b1) Gray value of (D), M1(x, y) denotes a first subset H'1The number of pixels in (x, y); when the pixel I (x, y) satisfies
Then, selecting a second subset H'2(x, y) is a set of neighboring pixels of pixel I (x, y), such that
Wherein, I (c)2，d2) Denotes a second subset H'2Coordinate (c) in (x, y)2，d2) Pixel of (d), f (c)2，d2) Represents a pixel I (c)2，d2) Is a gray value of p2(c2，d2) Represents a pixel I (c)2，d2) In a second subset H'2The distribution in (x, y) is detected as a coefficient, and
wherein, I (a)2，b2) Denotes a second subset H'2Coordinate (a) in (x, y)2，b2) Pixel of (d), f (a)2，b2) Represents a pixel I (a)2，b2) Gray value of (D), M2(x, y) denotes a second subset H'2The number of pixels in (x, y); when in use
Then, select local neighborhood u (x, y) as the neighboring pixel set of pixel I (x, y), and let
The preferred embodiment is used for filtering the infusion set image, and the weighted gray-scale value mean of the pixels in the local area of the pixel to be filtered is generally used as the gray-scale value of the pixel to be filtered in the prior art, however, this filtering method is easily affected by the noise pixels in the local neighborhood, and the structure information of the image is easy to blur, aiming at the defects, the preferred embodiment selects a part of pixels in the local area of the pixel to be filtered to form an adjacent pixel set of the pixel to be filtered, the pixels in the selected adjacent pixel set and the pixel to be filtered have higher gray scale similarity and structure similarity, therefore, the weighted gray value mean value of the pixels in the adjacent pixel set is used as the filtering mode of the gray value of the pixel to be filtered, so that the accuracy of the filtering result is improved, and meanwhile, the structural information in the infusion apparatus image can be effectively protected; when selecting the neighboring pixel set of the pixel to be filtered, the preferred embodiment uses a local neighborhood of 3 × 3 of the pixel to be filtered as a reference, selects a pixel in a local area of the pixel to be filtered within a certain range of the gray value of the local neighborhood as a neighboring pixel of the pixel to be filtered, thereby ensuring that the pixels in the selected neighboring pixel set and the local neighborhood of the pixel to be filtered have high similarity of gray values, selects the neighboring pixel set of the pixel to be filtered from the neighboring pixels, defines a first attribute detection coefficient and a second attribute detection coefficient to detect the selected neighboring pixels, wherein the first attribute detection coefficient measures the distribution characteristics of the pixels in the neighboring pixel set by calculating the difference between the neighboring pixels and the mean value thereof, and the second attribute detection coefficient measures the distribution characteristics of the pixels in the neighboring pixel set by calculating the difference between two different neighboring pixels, when the difference between the first attribute detection coefficient and the second attribute detection coefficient is small, the region where the pixel to be filtered is located is a flat region, namely the pixels in the neighborhood pixel set are relatively uniform, at the moment, the neighborhood pixel set is selected as a neighboring pixel set of the pixel to be filtered, when the difference between the first attribute detection coefficient and the second attribute detection coefficient is large, the pixel to be filtered is located in an edge region, namely the neighborhood pixel set only has part of pixels and the pixel to be filtered is located in a similar structural region, at the moment, the pixels in the neighborhood pixel set are screened by defining the distribution detection coefficient, the neighborhood pixels with high possibility of being noise in the neighborhood pixel set are removed, thereby reducing the influence of the noise pixels on the accuracy of a next classification result and classifying the remaining neighborhood pixels after screening, the neighborhood pixels with the minimum distribution detection coefficients have the maximum probability of being normal pixels, so that the neighborhood pixels with the minimum distribution detection coefficients are selected as classification reference pixels, the remaining neighborhood pixels after screening are divided into two types with larger gray value difference, and then the subsets with higher similarity to the pixels to be filtered are selected to be the adjacent pixel sets of the pixels to be filtered, so that the pixels in the selected adjacent pixel sets and the pixels to be filtered have higher gray value similarity and structural similarity; after the selection of the adjacent pixel set is completed, determining the gray value of the pixel to be filtered according to the weighted gray value mean value of the pixels in the adjacent pixel set, in the process of weighted averaging, determining the weight of the adjacent pixel through a defined distribution detection coefficient, wherein the distribution detection coefficient measures the abnormality of the adjacent pixel by calculating the similarity between the adjacent pixel and other pixels in the adjacent pixel set, when the value of the distribution detection coefficient of the adjacent pixel in the adjacent pixel set is smaller, the higher the similarity between the adjacent pixel and the pixels in the adjacent pixel set is indicated, at this time, the higher the weight of the adjacent pixel is, conversely, the larger the difference is, the higher the abnormality of the adjacent pixel in the adjacent pixel set is indicated, at this time, the smaller the weight of the adjacent pixel is, thereby ensuring that the noise in the infusion set is effectively filtered, and protecting the structural information in the infusion apparatus image.
Preferably, the image segmentation unit segments the optimized infusion set image by using a maximum inter-class variance method, and determines an optimal threshold of the maximum inter-class variance method used in the image segmentation unit by using a particle swarm algorithm.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (8)
1. The utility model provides a 5G-based intelligent transfusion monitoring system, which is characterized by comprising a transfusion monitoring module, an information transmission module and a transfusion monitoring terminal, wherein the transfusion monitoring module comprises an infrared detection unit, a transfusion weighing unit and a transfusion visual monitoring unit, the infrared detection unit is used for collecting a dropping speed signal of a liquid medicine, the transfusion weighing unit is used for collecting weight change data of a transfusion device, the transfusion visual monitoring unit is used for collecting images of the transfusion device, the transfusion monitoring module transmits the collected dropping speed signal of the liquid medicine, the collected weight change data of the transfusion device and the collected images of the transfusion device to the transfusion monitoring terminal through the information transmission module, the transfusion monitoring terminal comprises a system configuration module, a transfusion information processing module, a transfusion information display module, a transfusion detail inquiry and statistics module, a transfusion intelligent alarm module and an alarm information inquiry and statistics module, the system configuration module comprises a patient management unit and a bed management unit, medical staff inputs basic information of a patient and basic information of infusion through the patient management unit, the bed management unit is used for binding an infusion monitoring module and a bed number, the infusion information processing module comprises an infusion information processing unit and an infusion image processing unit, the infusion information processing unit is used for calculating the infusion state of the patient according to the basic information of the infusion of the patient, a received dropping speed signal of liquid medicine and weight change data of an infusion apparatus, the infusion image processing unit is used for processing the received infusion apparatus image, the infusion information display module is used for displaying the infusion state of the patient and the processed infusion apparatus image, the infusion detail inquiry and statistics module comprises an infusion detail statistics unit and an infusion detail inquiry unit, the infusion detail counting unit is used for counting the infusion details of the patient from the system configuration module and the infusion information processing module, and calculating the percentage of the infusion progress of the patient and a change trend chart of the infusion speed of the patient according to the infusion details of the patient; the intelligent infusion alarm system comprises an infusion detail query unit, an alarm information query and statistics module, an alarm information statistics unit and an alarm information query unit, wherein medical staff can query infusion details of a patient, the percentage of infusion progress of the patient and a change trend graph of the infusion speed of the patient through the infusion detail query unit, the infusion intelligent alarm module is used for comparing the infusion state of the patient with a preset alarm value so as to judge whether to give an alarm or not, the alarm information query and statistics module comprises the alarm information statistics unit and the alarm information query unit, the alarm information statistics unit is used for counting alarm log information when the infusion intelligent alarm module gives an alarm, and the medical staff can query the alarm log information through the alarm information query unit;
the infusion set image processing unit is used for processing the received infusion set image and comprises an image optimization unit and a target segmentation unit, the image optimization unit is used for filtering the received infusion set image and enhancing the filtered infusion set image, and the target segmentation unit is used for performing target segmentation on the optimized infusion set image and removing a background area in the infusion set image;
the image optimization unit is used for performing filtering processing on the received infusion apparatus image, setting I to represent the infusion apparatus image to be processed, and I (x, y) to represent a pixel at a coordinate (x, y) in the infusion apparatus image I, and performing filtering processing on the pixel I (x, y), specifically:
let U (x, y) denote a local area of (2o +1) × (2o +1) centered on a pixel I (x, y), where o is a given positive integer, and
m and K are respectively the length and the width of the infusion apparatus image I, H (x, y) is set to represent a neighborhood pixel set of the pixel I (x, y), and pixels in the set H (x, y) are selected from pixels in a local area U (x, y) in the following mode:
let u (x, y) denote a 3 x 3 local neighborhood centered on the pixel I (x, y),
representing the mean of the grey values of the pixels in the local neighborhood U (x, y), I (I, j) representing the pixel at coordinate (I, j) in the local area U (x, y), f (I, j) representing the grey value of the pixel I (I, j), given a grey threshold value f (h), when the pixel I (I, j) satisfies
Then the pixel I (I, j) is added to the set H (x, y) when the pixel I (I, j) satisfies
If so, not adding the pixel I (I, j) into the set H (x, y), and according to the method, completing the selection of the pixels in the local area U (x, y);
definition eta1(x, y) denotes a first attribute detection coefficient corresponding to a pixel in the set H (x, y), η2(x, y) represents a second attribute detection coefficient corresponding to a pixel in the set H (x, y), and η1(x, y) and η2The values of (x, y) are:
where I (a, b) represents the pixel at coordinate (a, b) in the set H (x, y), f (a, b) represents the grayscale value of the pixel I (a, b), I (M, n) represents the pixel at coordinate (M, n) in the set H (x, y), f (M, n) represents the grayscale value of the pixel I (M, n), M (x, y) represents the number of pixels in the set H (x, y),
representing the mean of the gray values of the pixels in the set H (x, y);
determine a set of neighboring pixels of the pixel I (x, y), given the attribute threshold η (H), and
wherein f ismid(x, y) represents the median of the gray values of the pixels in the set H (x, y), when |. eta1(x，y)-η2When the (x, y) | is less than or equal to eta (H), selecting the set H (x, y) as the adjacent pixel set of the pixel I (x, y), and enabling the set H (x, y) to be adjacent to the pixel I (x, y)
Where ρ (a, b) represents a distribution detection coefficient of the pixel I (a, b) in the set H (x, y), and
when eta1(x，y)-η2(x, y) | > η (H), then the set of neighboring pixels for pixel I (x, y) is determined as follows:
screening the pixels in the set H (x, y) when the pixels I (a, b) satisfy
When the pixel I (a, b) is satisfied, the pixel I (a, b) is retained in the set H (x, y)
Then, deleting the pixel I (a, b) in the set H (x, y) until the screening of all the pixels in the set H (x, y) is completed according to the method, wherein rhomid(x, y) represents a median value of distribution detection coefficients of pixels in the set H (x, y), ρmax(x, y) represents the maximum value of the distribution detection coefficients of the pixels in the set H (x, y);
let H ' (x, y) denote a set of pixels remaining after the pixels in the set H (x, y) have been screened, and the pixels in the set H ' (x, y) are classified, let H '1(x, y) represents a first subset, H ', of the set H ' (x, y) into which the pixels are classified '2(x, y) represents a second subset obtained by classifying the pixels in the set H ' (x, y), the pixel with the minimum distribution detection coefficient in the set H (x, y) in the pixels in the set H ' (x, y) is selected as a classification reference pixel, I (C, D) represents the pixel at the coordinate (C, D) in the set H ' (x, y), and
wherein I (C, D) represents the pixel at coordinate (C, D) in the set H '(x, y), ρ (C, D) represents the distribution detection coefficient of the pixel I (C, D) in the set H (x, y), the selected classification reference pixel I (C, D) is first added to the first subset H' 1(x, y), then the other pixels in the set H '(x, y) are classified, and when | f (C, D) -f (C, D) | ≦ f (H), the pixel I (C, D) is added to the first subset H'1(x, y) when | f (C, D) -f (C, D) | > f (H), then pixel I (C, D) is added to the second subset H'2In (x, y), f (C, D) represents the gradation value of the classification reference pixel I (C, D), and f (C, D) represents the gradation value of the pixel I (C, D);
determine a set of neighboring pixels of the pixel I (x, y)
Denotes a first subset H'1The mean of the gray values of the pixels in (x, y),
denotes a second subset H'2Mean of the gray values of the pixels in (x, y) when the pixel I (x, y) satisfies
Then, selecting a first subset H'1(x, y) is a set of neighboring pixels of pixel I (x, y), such that
Wherein, I (c)1，d1) Denotes a first subset H'1In (x, y)Coordinate (c)1，d1) Pixel of (d), f (c)1，d1) Represents a pixel I (c)1，d1) Is a gray value of p1(c1，d1) Represents a pixel I (c)1，d1) In a first subset H'1The distribution in (x, y) is detected as a coefficient, and
I(a1，b1) Denotes a first subset H'1Coordinate (a) in (x, y)1，b1) Pixel of (d), f (a)1，b1) Represents a pixel I (a)1，b1) Gray value of (D), M1(x, y) denotes a first subset H'1The number of pixels in (x, y); when the pixel I (x, y) satisfies
Then, selecting a second subset H'2(x, y) is a set of neighboring pixels of pixel I (x, y), such that
Wherein, I (c)2，d2) Denotes a second subset H'2Coordinate (c) in (x, y)2，d2) Pixel of (d), f (c)2，d2) Represents a pixel I (c)2，d2) Is a gray value of p2(c2，d2) Represents a pixel I (c)2，d2) In a second subset H'2The distribution in (x, y) is detected as a coefficient, and
wherein, I (a)2，b2) Denotes a second subset H'2Coordinate (a) in (x, y)2，b2) Pixel of (d), f (a)2，b2) Represents a pixel I (a)2，b2) Gray value of (D), M2(x, y) denotes a second subset H'2The number of pixels in (x, y); when in use
Then, select local neighborhood u (x, y) as the neighboring pixel set of pixel I (x, y), and let
2. The intelligent infusion monitoring system based on 5G as claimed in claim 1, wherein the information transmission module adopts 5G communication technology for information transmission.
3. The intelligent infusion monitoring system based on 5G as claimed in claim 2, wherein the infrared detection unit comprises an infrared emission module and an infrared receiving module, the infrared emission module is used for emitting infrared light, and the infrared receiving module is used for receiving infrared light.
4. The intelligent infusion monitoring system based on 5G as claimed in claim 1, wherein the basic information of the patient comprises the ward, the bed number and the name of the patient; the basic information of the infusion includes infusion start time, estimated infusion end time, and the amount of liquid medicine to be infused.
5. The intelligent infusion monitoring system based on 5G as claimed in claim 4, wherein the infusion state of the patient comprises the remaining amount of liquid medicine, the remaining infusion time and the infusion dropping speed.
6. The intelligent transfusion monitoring system based on 5G as claimed in claim 5, wherein the transfusion details of the patient include a ward, a bed number, a name, a transfusion start time, a predicted transfusion end time, a liquid medicine amount to be transfused, a remaining liquid medicine amount, a remaining transfusion time and a transfusion dripping speed.
7. The intelligent infusion monitoring system based on 5G as claimed in claim 6, wherein the intelligent infusion alarm module is used for comparing the infusion state of the patient with a preset alarm value so as to determine whether to alarm or not, and comprises a residual liquid reminding unit, a dripping speed reminding unit and a residual time reminding unit, wherein the residual liquid reminding unit is used for alarming when the residual liquid amount is lower than the preset alarm value, the dripping speed reminding unit is used for alarming when the dripping speed exceeds the preset alarm value, and the residual time reminding unit is used for alarming when the residual infusion time is lower than the preset alarm value.
8. The intelligent infusion monitoring system based on 5G as claimed in claim 7, wherein the log information of alarm includes ward, bed number, alarm time and alarm type, and the alarm type includes remaining liquid volume alarm, dripping speed alarm and remaining time alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011155242.XA CN112386765B (en) | 2020-10-26 | 2020-10-26 | Intelligent infusion monitoring system based on 5G |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011155242.XA CN112386765B (en) | 2020-10-26 | 2020-10-26 | Intelligent infusion monitoring system based on 5G |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112386765A CN112386765A (en) | 2021-02-23 |
| CN112386765B true CN112386765B (en) | 2021-07-27 |
Family
ID=74596170
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011155242.XA Active CN112386765B (en) | 2020-10-26 | 2020-10-26 | Intelligent infusion monitoring system based on 5G |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112386765B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113486702A (en) * | 2021-05-13 | 2021-10-08 | 北京旷视科技有限公司 | Infusion monitoring method and device, electronic equipment and computer storage medium |
| CN113450550A (en) * | 2021-06-24 | 2021-09-28 | 张�杰 | Alarming method and device in blood transfusion process |
| CN113591953B (en) * | 2021-07-20 | 2022-06-28 | 深圳市德邦物流有限公司 | An effective information extraction algorithm for dynamic logistics big data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104307070A (en) * | 2014-11-13 | 2015-01-28 | 杨茂林 | Transfusion monitor and transfusion monitoring system based on cloud service |
| CN109259727A (en) * | 2018-08-28 | 2019-01-25 | 苏州德品医疗科技股份有限公司 | A kind of intelligent nursing system based on Mobile nursing |
| CN110368552A (en) * | 2019-07-24 | 2019-10-25 | 江苏开放大学（江苏城市职业学院） | One kind remotely combining unattended medical infusion monitoring system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7645258B2 (en) * | 1999-12-01 | 2010-01-12 | B. Braun Medical, Inc. | Patient medication IV delivery pump with wireless communication to a hospital information management system |
| WO2017069246A1 (en) * | 2015-10-21 | 2017-04-27 | 株式会社アイム | Infusion injection system |
-
2020
- 2020-10-26 CN CN202011155242.XA patent/CN112386765B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104307070A (en) * | 2014-11-13 | 2015-01-28 | 杨茂林 | Transfusion monitor and transfusion monitoring system based on cloud service |
| CN109259727A (en) * | 2018-08-28 | 2019-01-25 | 苏州德品医疗科技股份有限公司 | A kind of intelligent nursing system based on Mobile nursing |
| CN110368552A (en) * | 2019-07-24 | 2019-10-25 | 江苏开放大学（江苏城市职业学院） | One kind remotely combining unattended medical infusion monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112386765A (en) | 2021-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112386765B (en) | Intelligent infusion monitoring system based on 5G | |
| CN113842118B (en) | Epileptic seizure real-time detection monitoring system for epileptic video electroencephalogram examination | |
| EP2281506B1 (en) | Method and system for determining an individual's state of attention | |
| US8374687B2 (en) | Rapid serial visual presentation triage prioritization based on user state assessment | |
| Yu et al. | Epileptic seizure prediction based on local mean decomposition and deep convolutional neural network. | |
| CN111951949A (en) | An intelligent nursing interactive system for smart wards | |
| US12169788B2 (en) | Analysis of neurological conditions, including prediction of future seizure events and/or detection of current seizure events, based on analysis of blepharometric data | |
| CN104068868A (en) | Method and device for monitoring driver fatigue on basis of machine vision | |
| Picot et al. | Drowsiness detection based on visual signs: blinking analysis based on high frame rate video | |
| CN110781873A (en) | Driver fatigue grade identification method based on bimodal feature fusion | |
| CN110334592A (en) | A driver abnormal behavior monitoring and safety assurance system and method thereof | |
| Alagarsamy et al. | Prediction of road accidents using machine learning technique | |
| CN111179551A (en) | A real-time monitoring method for drivers of hazardous chemicals transport | |
| CN106104539A (en) | Use the optimization that the alarm for alarm consulting of alarm regeneration is arranged | |
| CN118280576A (en) | Patient care grade intelligent evaluation system based on high-dimensional tumor data | |
| CN117017301A (en) | Wearable electrocardiograph monitoring alarm system and method | |
| CN110097012B (en) | Fatigue detection method for monitoring eye movement parameters based on N-range image processing algorithm | |
| Yan et al. | A novel deep learning method for red lesions detection using hybrid feature | |
| CN105894003A (en) | Large-field fruit tree disease monitoring early-warning system based on machine vision | |
| CN118629644A (en) | A fall risk assessment method and system | |
| CN109649166A (en) | Vehicle drive method for managing and monitoring, device and system | |
| Xie et al. | Revolutionizing road safety: YOLOv8-powered driver fatigue detection | |
| Singh et al. | Enhanced Driver Drowsiness Detection using Deep Learning | |
| Devi et al. | Texture based feature extraction and classification of retinal fundus image for glaucoma detection | |
| Mašanović et al. | Driver monitoring using the in-vehicle camera |
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 | ||
| CP03 | Change of name, title or address |
Address after: 518000, Block BC, B901-B908, B801-B808, Huizhi R&D Center, Longteng Community, Xixiang Street, Bao'an District, Shenzhen City, Guangdong Province Patentee after: Guangdong deao smart Medical Technology Co.,Ltd. Country or region after: China Address before: Room 501, Room 502, room 503, room 504, room 505, floor 5, building 10, Industrialization Center, No.19 Alishan Road, Songshanhu high tech Industrial Development Zone, Dongguan City, Guangdong Province 523000 Patentee before: Guangdong deao smart Medical Technology Co.,Ltd. Country or region before: China |
|
| CP03 | Change of name, title or address |