CN108333126B - Artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system - Google Patents
Artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system Download PDFInfo
- Publication number
- CN108333126B CN108333126B CN201810042375.2A CN201810042375A CN108333126B CN 108333126 B CN108333126 B CN 108333126B CN 201810042375 A CN201810042375 A CN 201810042375A CN 108333126 B CN108333126 B CN 108333126B
- Authority
- CN
- China
- Prior art keywords
- cerebrospinal fluid
- fluid container
- light
- light source
- embedded groove
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses an artificial intelligent real-time dynamic spectrum cerebrospinal fluid monitoring system, which comprises a computer, a light source, a cerebrospinal fluid container, a light frequency converter, a display screen and a wireless communication module, the light frequency converter, the display screen and the wireless communication module are electrically connected with a computer, the cerebrospinal fluid container is arranged in a dish shape, a light reflecting cover is covered on the cerebrospinal fluid container, the light reflecting cover is in threaded connection with the cerebrospinal fluid container, the cerebrospinal fluid container is arranged in a transparent way, the light source is positioned on the inner wall of the cerebrospinal fluid container, an embedded groove is arranged on the inner wall of the cerebrospinal fluid container, the light source is embedded into the embedded groove and is detachably connected with the groove bottom of the embedded groove, the light source and the embedded groove are both arranged in an annular shape, the light frequency converter is positioned in the middle of the bottom surface of the cerebrospinal fluid container, and the light frequency converter is embedded in the cerebrospinal fluid container; the artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system can meet the requirements of modern medicine.
Description
Technical Field
The invention relates to the technical field of medical instruments, in particular to an artificial intelligent real-time dynamic spectrum cerebrospinal fluid monitoring system.
Background
Cerebrospinal Fluid (CSF) is a colorless and transparent liquid that fills the ventricles of the brain, the subarachnoid space, and the central Spinal canal. Cerebrospinal fluid is produced by the choroid plexus in the ventricles, and is somewhat viscous, similar in nature to plasma and lymphatic fluid. The cerebrospinal fluid of a normal adult is about 100-150 ml, has a specific gravity of 1, is weakly alkaline, does not contain erythrocytes, but contains about 5 lymphocytes per cubic millimeter. Normal cerebrospinal fluid has certain chemical components and pressure, and plays an important role in maintaining the relative stability of cranial pressure. When the central nervous system diseases are suffered, the lumbar puncture is often required to suck cerebrospinal fluid for examination so as to assist diagnosis. The character and pressure of cerebrospinal fluid are influenced by various factors, and if the central nervous system is diseased, the character and components of cerebrospinal fluid are changed due to metabolic disturbance of nerve cells; if the circulation path of cerebrospinal fluid is blocked, the intracranial pressure will increase. Therefore, when the central nervous system is damaged, cerebrospinal fluid detection becomes one of the important auxiliary diagnostic tools.
Traditionally, cerebrospinal fluid is visually distinguished based on the color and transparency of cerebrospinal fluid. This traditional approach is very unscientific and has not met the needs of modern medicine.
Disclosure of Invention
The invention aims to provide an artificial intelligent real-time dynamic spectrum cerebrospinal fluid monitoring system which can meet the requirements of modern medicine.
In order to solve the problems, the invention adopts the following technical scheme:
an artificial intelligent real-time dynamic spectrum cerebrospinal fluid monitoring system comprises a computer, a light source, a cerebrospinal fluid container, a light frequency converter, a display screen and a wireless communication module, the light frequency converter, the display screen and the wireless communication module are electrically connected with a computer, the cerebrospinal fluid container is arranged in a dish shape, a light reflecting cover is covered on the cerebrospinal fluid container, the light reflecting cover is in threaded connection with the cerebrospinal fluid container, the cerebrospinal fluid container is arranged in a transparent way, the light source is positioned on the inner wall of the cerebrospinal fluid container, an embedded groove is arranged on the inner wall of the cerebrospinal fluid container, the light source is embedded into the embedded groove and is detachably connected with the groove bottom of the embedded groove, the light source and the embedded groove are both arranged in an annular mode, the light frequency converter is located in the middle of the bottom face of the cerebrospinal fluid container, and the light frequency converter is embedded into the cerebrospinal fluid container.
Preferably, the light frequency converter is an RGB color light/frequency converter, and even a color with a slight difference in background color can be detected, so that the processing speed is high. The wavelength is automatically adapted, and small differences in gray values can be detected.
Preferably, be provided with the tenon on the tank bottom of embedded groove, the tenon bonds with the tank bottom of embedded groove, be provided with on the light source with tenon matched with mortise, the light source passes through tenon and mortise releasable connection with the tank bottom of embedded groove, the light source stability is good in the embedded groove, light source easy dismounting moreover.
Preferably, the light source is an LED lamp strip, the LED lamp strip is long in service life, and the LED lamp strip is energy-saving and environment-friendly.
Preferably, the wireless communication module is a zigbee module, and the zigbee module has low power consumption, low cost and low complexity, and is beneficial to popularization and application of equipment.
The invention also provides a detection method of the artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system, which comprises the following steps:
1) establishing a diagnosis model according to the general character data of the cerebrospinal fluid, and training the diagnosis model;
2) detecting the properties of cerebrospinal fluid by using a light-frequency converter, and inputting the properties into a diagnosis model for diagnosis;
3) and outputting the result.
Further, the training of step 1) is to analyze and grasp the potential rules between the input data and the output data corresponding to each other through 1600-2700 data provided in advance.
Further, the general properties of the cerebrospinal fluid comprise a color property and a transparency property.
Further, the diagnostic model is a diagnostic model of a neural network.
The principle is as follows:
the invention adopts a digital photoelectric sensor. The digital photoelectric sensor can directly output digital quantity, simplifies the circuit and prevents signal distortion. The digital photoelectric sensor has three groups of photoelectric receiving tubes, red (R), green (G) and blue (B). And covering the full spectrum. The color and transparency of cerebrospinal fluid will be displayed in digital quantities of RGB as it passes through. The digital quantities of RGB here are the raw data set. After the normalized transformation, its magnitude will be in the (0, 1) interval. It can be processed by a computer as an input to a neural network. The color of an object that we usually see is actually the reaction of the surface of the object to absorb a portion of the colored components of white light (sunlight) impinging on it and reflect another portion of the colored light in the human eye. White is formed by mixing visible light with various frequencies, that is, white light includes colored light of various colors (such as red R, yellow Y, green G, cyan V, blue B, and violet P). According to the theory of the three primary colors of helmholtz (helmholtz), the germany physicist knows that each color is formed by mixing three primary colors (red, green and blue) in different proportions. As can be seen from the above three primary color sensing principle, if the values of the three primary colors constituting the respective colors are known, the color of the object under test can be known.
The present invention uses a digitized color light/frequency sensor that integrates red, green and blue filters on a single chip, and can achieve a resolution of more than 10 bits per color channel without the need for an ADC. The chip contains an array of cross-connected 8 x 8 photodiodes, each 16 of which provides a color pattern of four types, red, blue, green and clear of all optical information, to minimize non-uniformity of incident light radiation. All the 16 photodiodes of the same color are connected in parallel. When a color filter is selected, it only allows a certain primary color to pass through, and blocks the other primary colors from passing through. For example: when the red filter is selected, only red light in the incident light can pass through, and blue light and green light are blocked, so that the light intensity of red light can be obtained; similarly, the intensity of blue light and green light can be obtained by selecting other filters. From these three values, the color of the light projected onto the sensor can be analyzed. Similarly, the transparency of the digitized color light/frequency sensor is unique, and the transparency and the opacity cannot be clearly distinguished by the naked eye, and can only be described approximately, while the transparency and the opacity of the digitized light/frequency sensor can be quantified digitally. The resolution from transparency to turbidity can be classified into a plurality of grades, and then the resolution problem of transparency and turbidity which cannot be finished by naked eyes can be easily finished through an artificial neural network.
And processing the massive RGB values by adopting a neural network model. Artificial intelligence is a branch of computer science and is a theory related to building a machine. The research on artificial intelligence includes two methods for realizing functional simulation and physiological structure simulation, the former is generally called Artificial Intelligence (AI), the latter is Artificial Neural Network (ANN) which has self-learning and self-adapting capabilities, potential laws between the two can be analyzed and mastered through a set of input-output data which are provided in advance and correspond to each other, and finally, the output result is calculated by using new input data according to the laws, and the process of learning and analysis is called as 'training'.
Similar to biological nervous system, artificial neural network is also composed of artificial neurons as basic units. The artificial neuron is a mathematical model simulating a biological neuron, is a basic material unit of an artificial neural network, and is also a multi-input/single-output nonlinear element.
As shown in FIG. 3, each input connection of a neuron has a synaptic connection strength, represented by a connection weight, by which the signal to be generated is amplified, and each input quantity (Pi) has an associated weight (Wi). The processing unit quantizes the weighted inputs, adds the weighted inputs to obtain the sum of the weighted values, and calculates a unique output quantity, wherein the output quantity (a) is a function of the weighted sum, and the function is generally called a transfer function. This process can be formulated as:
where a represents the transfer function employed by this neuron.
Where Pi is the RGB value we get.
The neural network is composed of processing units arranged in layers, a neuron layer for receiving input signals is called an input layer, a neuron layer for outputting signals is called an output layer, and a neuron layer which is not directly related with input/output is called an intermediate layer or a hidden layer.
After the model structure of the neural network is determined, learning and training are followed.
The invention adopts a supervised learning algorithm. That is, the network gives both the input and the correct output, and the network adjusts the network according to the difference between the current output and the required target output, so that the network reacts correctly. Supervised learning algorithms require a large amount of standard data. A standard sample library is created. The cerebrospinal fluid data standard sample library is still blank at present, and the data obtained by the spectrometry and clinical performance need to be established into the standard sample library. And (3) entering the relationship established by the obtained RGB value, clinical performance inspection data and the like into a network database.
The invention has the beneficial effects that: through having adopted digital photoelectric sensor to gather the spectrum real time kinematic digitization of cerebrospinal fluid, obtain quantitative cerebrospinal fluid spectral data, then cooperate the computer to carry out the analysis with the data of cerebrospinal fluid again to reach the result, can effectually alleviate staff's work burden, in addition, light frequency converter is RGB colorama frequency converter, even the background color has the colour of slight difference to also can detect, and the processing speed is fast. The wavelength is automatically adapted, and small differences in gray values can be detected. The embedded groove is characterized in that a tenon is arranged on the groove bottom of the embedded groove, the tenon is adhered to the groove bottom of the embedded groove, a mortise matched with the tenon is arranged on the light source, the light source is detachably connected with the groove bottom of the embedded groove through the tenon and the mortise, the light source is good in stability in the embedded groove, and the light source is convenient to disassemble and assemble. The light source is an LED lamp strip which is long in service life, energy-saving and environment-friendly. The wireless communication module is a zigbee module, and the zigbee module has low power consumption, low cost and low complexity, and can be beneficial to popularization and application of equipment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic diagram of the overall structure of an artificial intelligence real-time dynamic spectroscopy cerebrospinal fluid monitoring system according to the present invention;
fig. 2 is a schematic diagram of an RGB color light/frequency converter of an artificial intelligence real-time dynamic spectroscopy cerebrospinal fluid monitoring system according to the present invention.
FIG. 3 is an artificial neuron model.
FIG. 4 is a partial cross-sectional view of a cerebrospinal fluid container of an artificial intelligence real-time dynamic spectroscopic cerebrospinal fluid monitoring system of the present invention.
In the figure:
1. a computer; 2. a light source; 3. a cerebrospinal fluid container; 4. a light frequency converter; 5. a display screen; 6. A wireless communication module; 7. a light reflecting cover; 8. a groove is embedded; 9. a tenon.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
Example 1
As shown in fig. 1 and 4, an artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system comprises a computer 1, a light source 2, a cerebrospinal fluid container 3, a light frequency converter 4, a display screen 5 and a wireless communication module 6, wherein the light frequency converter 4, the display screen 5 and the wireless communication module 6 are all electrically connected with the computer 1, the cerebrospinal fluid container 3 is in a dish-shaped arrangement, the cerebrospinal fluid container 3 is covered with a light reflecting cover 7, the light reflecting cover 7 is in threaded connection with the cerebrospinal fluid container 3, the cerebrospinal fluid container 3 is in a transparent arrangement, the light source 2 is located on the inner wall of the cerebrospinal fluid container 3, an embedded groove 8 is formed in the inner wall of the cerebrospinal fluid container 3, the light source 2 is embedded in the embedded groove 8, the light source 2 is detachably connected with the bottom of the embedded groove 8, the light source 2 and the embedded groove 8 are both in an annular arrangement, the light frequency converter 4 is located in the middle of the bottom of the cerebrospinal, the light frequency converter 4 is embedded in the cerebrospinal fluid container 3. The spectrum of cerebrospinal fluid is collected in a real-time dynamic digital mode through the digital photoelectric sensor, quantized cerebrospinal fluid spectrum data are obtained, and then the data of the cerebrospinal fluid are analyzed in a matched mode through the computer, so that a result is obtained, and the workload of workers can be effectively relieved.
The beneficial effect of this embodiment does: the spectrum of cerebrospinal fluid is collected in a real-time dynamic digital mode through the digital photoelectric sensor, quantized cerebrospinal fluid spectrum data are obtained, and then the data of the cerebrospinal fluid are analyzed in a matched mode through the computer, so that a result is obtained, and the workload of workers can be effectively relieved.
Example 2
As shown in fig. 1 and 4, an artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system comprises a computer 1, a light source 2, a cerebrospinal fluid container 3, a light frequency converter 4, a display screen 5 and a wireless communication module 6, wherein the light frequency converter 4, the display screen 5 and the wireless communication module 6 are all electrically connected with the computer 1, the cerebrospinal fluid container 3 is in a dish-shaped arrangement, the cerebrospinal fluid container 3 is covered with a light reflecting cover 7, the light reflecting cover 7 is in threaded connection with the cerebrospinal fluid container 3, the cerebrospinal fluid container 3 is in a transparent arrangement, the light source 2 is located on the inner wall of the cerebrospinal fluid container 3, an embedded groove 8 is formed in the inner wall of the cerebrospinal fluid container 3, the light source 2 is embedded in the embedded groove 8, the light source 2 is detachably connected with the bottom of the embedded groove 8, the light source 2 and the embedded groove 8 are both in an annular arrangement, the light frequency converter 4 is located in the middle of the bottom of the cerebrospinal, the light frequency converter 4 is embedded in the cerebrospinal fluid container 3. The light frequency converter 4 is an RGB color light/frequency converter, and can detect even a color with a slight difference in background color, and the processing speed is high. The wavelength is automatically adapted, and small differences in gray values can be detected. Be provided with tenon 9 on embedded groove 8's the tank bottom, tenon 9 bonds with embedded groove 8's tank bottom, be provided with on the light source 2 with tenon 9 assorted mortise (not shown), light source 2 passes through tenon and mortise releasable connection with embedded groove 8's tank bottom, and light source 2 is good at embedded groove 8 internal stability, light source easy dismounting moreover. The light source 2 is an LED lamp strip which is long in service life, energy-saving and environment-friendly.
The beneficial effect of this embodiment does: through having adopted digital photoelectric sensor to gather the spectrum real time kinematic digitization of cerebrospinal fluid, obtain quantitative cerebrospinal fluid spectral data, then cooperate the computer to carry out the analysis with the data of cerebrospinal fluid again to reach the result, can effectually alleviate staff's work burden, in addition, light frequency converter is RGB colorama frequency converter, even the background color has the colour of slight difference to also can detect, and the processing speed is fast. The wavelength is automatically adapted, and small differences in gray values can be detected. The embedded groove is characterized in that a tenon is arranged on the groove bottom of the embedded groove, the tenon is adhered to the groove bottom of the embedded groove, a mortise matched with the tenon is arranged on the light source, the light source is detachably connected with the groove bottom of the embedded groove through the tenon and the mortise, the light source is good in stability in the embedded groove, and the light source is convenient to disassemble and assemble. The light source is an LED lamp strip which is long in service life, energy-saving and environment-friendly.
Example 3
As shown in fig. 1 and 4, an artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system comprises a computer 1, a light source 2, a cerebrospinal fluid container 3, a light frequency converter 4, a display screen 5 and a wireless communication module 6, wherein the light frequency converter 4, the display screen 5 and the wireless communication module 6 are all electrically connected with the computer 1, the cerebrospinal fluid container 3 is in a dish-shaped arrangement, the cerebrospinal fluid container 3 is covered with a light reflecting cover 7, the light reflecting cover 7 is in threaded connection with the cerebrospinal fluid container 3, the cerebrospinal fluid container 3 is in a transparent arrangement, the light source 2 is located on the inner wall of the cerebrospinal fluid container 3, an embedded groove 8 is formed in the inner wall of the cerebrospinal fluid container 3, the light source 2 is embedded in the embedded groove 8, the light source 2 is detachably connected with the bottom of the embedded groove 8, the light source 2 and the embedded groove 8 are both in an annular arrangement, the light frequency converter 4 is located in the middle of the bottom of the cerebrospinal, the light frequency converter 4 is embedded in the cerebrospinal fluid container 3. The spectrum of cerebrospinal fluid is collected in a real-time dynamic digital mode through the digital photoelectric sensor, quantized cerebrospinal fluid spectrum data are obtained, and then the data of the cerebrospinal fluid are analyzed in a matched mode through the computer, so that a result is obtained, and the workload of workers can be effectively relieved.
The light frequency converter 4 is an RGB color light/frequency converter, and can detect even a color with a slight difference in background color, and the processing speed is high. The wavelength is automatically adapted, and small differences in gray values can be detected.
Be provided with tenon 9 on embedded groove 8's the tank bottom, tenon 9 bonds with embedded groove 8's tank bottom, be provided with on the light source 2 with tenon 9 assorted mortise (not shown), light source 2 passes through tenon and mortise releasable connection with embedded groove 8's tank bottom, and light source 2 is good at embedded groove 8 internal stability, light source easy dismounting moreover.
The light source 2 is an LED lamp strip which is long in service life, energy-saving and environment-friendly.
The wireless communication module 6 is a zigbee module, which has low power consumption, low cost and low complexity, and is beneficial to popularization and application of equipment.
The beneficial effect of this embodiment does: through having adopted digital photoelectric sensor to gather the spectrum real time kinematic digitization of cerebrospinal fluid, obtain quantitative cerebrospinal fluid spectral data, then cooperate the computer to carry out the analysis with the data of cerebrospinal fluid again to reach the result, can effectually alleviate staff's work burden, in addition, light frequency converter is RGB colorama frequency converter, even the background color has the colour of slight difference to also can detect, and the processing speed is fast. The wavelength is automatically adapted, and small differences in gray values can be detected. The embedded groove is characterized in that a tenon is arranged on the groove bottom of the embedded groove, the tenon is adhered to the groove bottom of the embedded groove, a mortise matched with the tenon is arranged on the light source, the light source is detachably connected with the groove bottom of the embedded groove through the tenon and the mortise, the light source is good in stability in the embedded groove, and the light source is convenient to disassemble and assemble. The light source is an LED lamp strip which is long in service life, energy-saving and environment-friendly. The wireless communication module is a zigbee module, and the zigbee module has low power consumption, low cost and low complexity, and can be beneficial to popularization and application of equipment.
The invention also provides a detection method of the artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system, which comprises the following steps:
1) establishing a diagnosis model according to the general character data of the cerebrospinal fluid, and training the diagnosis model;
2) detecting the properties of cerebrospinal fluid by using a light-frequency converter, and inputting the properties into a diagnosis model for diagnosis;
3) and outputting the result.
Further, the training of step 1) is to analyze and grasp potential laws between the input data and the output data corresponding to each other through a pre-provided 2700.
Further, the general properties of the cerebrospinal fluid comprise a color property and a transparency property.
Color:
normal cerebrospinal fluid is a colorless, transparent fluid. In pathological conditions, cerebrospinal fluid may present different color changes.
Red: many red blood cells appear in cerebrospinal fluid due to various bleeding, mainly due to puncture injury bleeding and subarachnoid hemorrhage.
② yellow: it can be caused by hemorrhage, obstruction, stasis, jaundice, etc.
③ white or off-white: it is usually caused by increase of leukocytes and usually seen in suppurative meningitis.
(iv) brown or black: it is common in meningeal melanoma.
Transparency:
the normal cerebrospinal fluid should be clear and transparent.
The cerebrospinal fluid of viral encephalitis, neurosyphilis and other diseases can also be transparent in appearance. Leukocytes in cerebrospinal fluid can become turbid when they exceed 300X 106/L; the protein content is increased or the protein contains a large amount of bacteria, fungi and the like to make the protein turbid; tuberculous meningitis often appears as a ground glass-like micro-mix; purulent meningitis usually presents with obvious turbidity.
Further, the diagnostic model is a diagnostic model of a neural network.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (1)
1. The utility model provides a real-time dynamic spectrum cerebrospinal fluid monitoring system of artificial intelligence which characterized in that: including computer (1), light source (2), cerebrospinal fluid container (3), light frequency converter (4), display screen (5) and wireless communication module (6) all with computer (1) electric connection, cerebrospinal fluid container (3) are the dish form setting, be stamped reflection of light lid (7) on cerebrospinal fluid container (3), reflection of light lid (7) and cerebrospinal fluid container (3) threaded connection, cerebrospinal fluid container (3) is transparent setting, light source (2) are located the inner wall of cerebrospinal fluid container (3), it has embedded groove (8) to open on the inner wall of cerebrospinal fluid container (3), light source (2) are embedded into and set up in embedded groove (8), light source (2) can be dismantled with the tank bottom of embedded groove (8) and be connected, light source (2) and embedded groove (8) all are the annular setting, the light frequency converter (4) is positioned in the middle of the bottom surface of the cerebrospinal fluid container (3), and the light frequency converter (4) is embedded in the cerebrospinal fluid container (3);
wherein the light frequency converter (4) is an RGB color light/frequency converter;
the computer is used for detecting cerebrospinal fluid in real time and dynamically to obtain a detection result and sending the detection result to the display screen, wherein the detection result is realized by the following steps:
1) establishing a diagnosis model by using the general character data of the cerebrospinal fluid, and training the diagnosis model;
2) detecting the properties of cerebrospinal fluid by using a light-frequency converter, and inputting the properties into a diagnosis model for diagnosis;
3) outputting a result;
wherein, the training of step 1) is to analyze and master the potential rule between the input data and the output data corresponding to each other through 1600-2700 data provided in advance;
the general character data of the cerebrospinal fluid comprises a color character and a transparency character;
the diagnosis model is a diagnosis model of a neural network;
a tenon (9) is arranged on the bottom of the embedded groove (8), the tenon (9) is adhered to the bottom of the embedded groove (8), a mortise matched with the tenon (9) is arranged on the light source (2), and the light source (2) is detachably connected with the bottom of the embedded groove (8) through the tenon (9) and the mortise;
the light source (2) is an LED lamp strip;
the wireless communication module (6) is a zigbee module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810042375.2A CN108333126B (en) | 2018-01-17 | 2018-01-17 | Artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810042375.2A CN108333126B (en) | 2018-01-17 | 2018-01-17 | Artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108333126A CN108333126A (en) | 2018-07-27 |
| CN108333126B true CN108333126B (en) | 2020-12-01 |
Family
ID=62925137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810042375.2A Expired - Fee Related CN108333126B (en) | 2018-01-17 | 2018-01-17 | Artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108333126B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ATE197511T1 (en) * | 1995-07-25 | 2000-11-11 | Horus Therapeutics Inc | COMPUTER-ASSISTED METHOD AND ARRANGEMENT FOR DIAGNOSING DISEASES |
| JP2000105192A (en) * | 1998-09-29 | 2000-04-11 | Kett Electric Laboratory | Grain-discriminating device by neural net work utilizing bolonoi division |
| WO2008092114A2 (en) * | 2007-01-26 | 2008-07-31 | O.I. Corporation D/B/A O.I. Analytical | Non-dispersive electromagnetic radiation detector |
| CN101055206B (en) * | 2007-05-25 | 2010-06-02 | 南开大学 | Interference-free color sampling device of machine vision system |
| CN201063021Y (en) * | 2007-08-08 | 2008-05-21 | 天地科技股份有限公司 | Infrared multi-gas detecting sensor for double light sources and double sense organs |
| CN102680095A (en) * | 2011-03-08 | 2012-09-19 | 致茂电子(苏州)有限公司 | Light source with uniform chroma and brightness and color sensor with light source |
| CN103424382A (en) * | 2013-08-26 | 2013-12-04 | 沈玉红 | Intelligent gastric lavage dynamic-monitoring method and device used for same |
| CN203782154U (en) * | 2014-01-26 | 2014-08-20 | 湖南鸿鹰生物科技有限公司 | Multifunctional microorganism colony counter |
| CN103822893B (en) * | 2014-02-28 | 2016-07-06 | 江苏物联网研究发展中心 | A kind of NDIR gas sensor |
-
2018
- 2018-01-17 CN CN201810042375.2A patent/CN108333126B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN108333126A (en) | 2018-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Backhaus et al. | Color distance derived from a receptor model of color vision in the honeybee | |
| CN105205984B (en) | A kind of logging for UHV transmission line | |
| EP0650591B1 (en) | Non-invasive testing | |
| CN102334422B (en) | Machine vision based real-time diagnosis method and system of vegetable leaf diseases | |
| CN106388781A (en) | Method for detecting skin colors and pigmentation situation of skin | |
| CN107133960A (en) | Image crack dividing method based on depth convolutional neural networks | |
| CN112464863A (en) | Learning attention detection and prejudgment device under variable light environment | |
| CN106805985B (en) | Concentration detection, training system and method based on functional near-infrared spectrum technique | |
| CN103565419A (en) | Color measurement device and color information skin color mapping image obtained through the color measurement device | |
| AU764447B2 (en) | Fiber color grading system | |
| CN105606543A (en) | Portable banana maturity detector | |
| CN111742055A (en) | Method for identifying microorganisms using spectroscopic techniques | |
| CN108333126B (en) | Artificial intelligence real-time dynamic spectrum cerebrospinal fluid monitoring system | |
| CN109342378A (en) | Bacterium colony growth conditions detection device and method based on multi-modality imaging technology | |
| CN112022108A (en) | Jaundice detection device and auxiliary decision system | |
| Azmi et al. | Conceptual determination and assessment of cyanosis | |
| Macnab et al. | Evaluation of cortical neuroexcitation in urinary urgency using simultaneous near infrared spectroscopy of the brain and bladder with quantification of sensation | |
| Sudki et al. | Fungal identification in peanuts seeds through multispectral images: Technological advances to enhance sanitary quality | |
| CN205484016U (en) | Portable banana maturity detector | |
| Várkonyi-Kóczy et al. | Intelligent Space: New challenges in research and education | |
| CN107205732A (en) | Near-infrared Brain functional measurement device and measuring method | |
| CN213364593U (en) | Urine detection system | |
| CN117116474B (en) | Health condition intelligent monitoring system based on human fingertip data | |
| Evgenievich et al. | Using the colorimetric method to control biological objects | |
| Evgenievich et al. | Color Measurement Using Electronic Colorimeter |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201201 Termination date: 20220117 |