CN108399946A - A kind of nursing work load distribution assistance system - Google Patents
A kind of nursing work load distribution assistance system Download PDFInfo
- Publication number
- CN108399946A CN108399946A CN201810179793.6A CN201810179793A CN108399946A CN 108399946 A CN108399946 A CN 108399946A CN 201810179793 A CN201810179793 A CN 201810179793A CN 108399946 A CN108399946 A CN 108399946A
- Authority
- CN
- China
- Prior art keywords
- nursing
- module
- pixel
- image
- work load
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to nursing work load distribution technique fields, a kind of nursing work load distribution assistance system is disclosed, patient information acquisition module, video monitoring module, main control module, nursing distribution module, nursing record module, cloud service module, Workload Account module are provided with.The present invention determines the quantized value of every nursing items workload by Workload Account module first, then input currently needs the nursing items counted, then according to the current total nursing work load of quantization Data-Statistics of the nursing items that need to currently carry out and corresponding every nursing items workload, to realize the statistics to nursing module and the workload for nursing monomer, desk work amount is assessed for Nursing management, the management method that science distributes nurse, effectively control nursing quality provides science；Nursing work load statistics, dispensing rate can be greatly improved by cloud service module simultaneously, improve allocative efficiency, ensure that patient is nursed in time.
Description
Technical field
The invention belongs to nursing work load distribution technique fields more particularly to a kind of nursing work load to distribute assistance system.
Background technology
Currently, the prior art commonly used in the trade is such：
Nursing is the reaction of diagnosis and the processing mankind to existing or potential health problem.To losing self care ability
Patient provide personal hygiene treatment and help.The purpose of patient's hygiene care is：Remove slough, micro- life
Object, secretion and other dirts；Blood circulation is stimulated, relaxs one's muscles, patient is made to feel comfortable, help to regain one's vigor；Change disease
The sickly look of people eliminates bad smell；Pre- counteracting bedsores and cross-infection；Convenient for observing the state of an illness.However, existing nursery work lacks standard
True quantitative statistics cause nursing work load larger difference occur with actual care situation；Nursing work load is counted simultaneously, is divided
When with workload, data processing speed is slow, influences allocative efficiency, causes patient that cannot be nursed in time, influences patient's treatment.
Currently, nursery work how the quantitative statistics research contents that be head nurses extremely pay close attention to.Traditional measurement
Method is counting statistics method or processing time matrix method, and counting method is exactly to record the quantity of care operation, and man-hour method is record nursing behaviour
Make nursing time used, counting method confidence level is poor, and man-hour method is practically carrying out certain difficulty, can not in clinical position
The time of operation can be accurately recorded item by item.There is researcher to select more than ten nursing items with general character as workload recently
Statistical indicator according to the complexity of each index, takes time how much to assign score values, passes through computer statistics each indexs
Then divided by nurse's number of the lesion score value calculates workload per capita, according to the scoring of workload, periodically to each lesion
Nursing number is adjusted.Fraction nursery work is only included in this research, is not covered by most Direct Nursing work, as
It is not scientific and reasonable enough according to allotment nursing human resource.Studies have reported that, nursed again from the interior acquisitions of HIS (hospital information system)
Project is calculated with man-hour method and completes each nursing items required time and assign weight, counts the total hours worked of each lesion,
The nursing staff of each lesion is adjusted according to the height of score value, but this research does not account for nursing item in nursing items assignment
Purpose technical difficulty and risk, in addition the nursing items in HIS be also not covered by all Direct Nursing work, as according to tune
It is Shortcomings with nursing human resource foundation.So up to the present the country is there is not yet more comprehensive, scientifical, accurate culvert
The quantitative statistics method of lid Direct Nursing work.
The stingy diagram technology of interactive mode takes the foreground of image in the case where limited user interacts, and is widely used in image and regards
In the fields such as frequency editor, three-dimensional reconstruction, there is high application value.In stingy diagram technology in recent years, Laplace matrix provides alpha
Linear relationship on figure between pixel plays important function to the estimation of alpha figures.The stingy figure of interactive mode is handed in limited user
Under mutually, the alpha figures of foreground are calculated, to separate foreground from background.The input for scratching figure problem is original image I and use
Three components that family provides, output are alpha figures and foreground F, background B, therefore are typical ill-conditioning problems, need to introduce and assume item
Part solves alpha figures.Stingy nomography can be divided into three classes：Method based on sampling, the method based on propagation, sampling and propagation combine
Method.
The stingy figure matrix of Laplace that the prior art is derived provides the linear relationship between the alpha value of neighborhood territory pixel, extensive
Apply scratch nomography in；Laplace, which scratches figure matrix, has its limitation, Laplace to scratch figure matrix and indicate in spatial neighborhood between pixel
Relationship, but the relationship between non-neighborhood between pixel cannot be embodied；Laplace is scratched figure matrix and is established on the basis of space is continuously assumed,
The region of certain foreground and background component mutation, Laplace scratch figure matrix and are difficult to obtain ideal effect.
In conclusion problem of the existing technology is：
Due to lacking accurate quantitative statistics to nursery work, reasonable disposition nursing human resource is caused to become existing nursing
One of difficulties of management, because existing nursing establishment is calculated with the ratio between bed shield mostly, due to there are rate of utilization of hospital beds,
Patient populations, the dynamic change of nurse's rate of attendance and conditions of patients severity difference, cause between nursing unit and nurse
Workload in unit and there is also differences for workload per capita, and then can frequently result in hospital and some section office's human ltcs occur
Inadequate resource and situation that other section office personnel are left unused, there are no a kind of unification, generally acknowledged scientific methods so far to solve
Certainly this problem.
Existing nursery work lacks accurate quantitative statistics, causes nursing work load to occur with actual care situation larger
Difference；When counting nursing work load, Amount of work simultaneously, data processing speed is slow, influences allocative efficiency, causes patient cannot
It is nursed in time, influences patient's treatment.
The relationship of the existing technology derived between Laplace matrix cannot embody non-neighborhood between pixel；In certain foregrounds and
The region of background component mutation, Laplace matrix are difficult to obtain ideal effect.
In the prior art, picture noise filter out it is existing be unfavorable for automatic noise detection, adaptive ability is poor, noise remove
There are contradictions with filtering performance.
Invention content
In view of the problems of the existing technology, the present invention provides a kind of nursing work loads to distribute assistance system.
The invention is realized in this way a kind of nursing work load distributes assistance system, including：
Patient information acquisition module, connect with main control module, when for acquiring personal patient information, treatment information, being hospitalized
Between information；It specifically includes：For personal information, treatment information, the information signal of hospital stays, according to the following equation to acquisition
Information signal in each frame signal carry out noise tracking, obtain the noise spectrum N (w, n) of each frame signal：
Wherein, X (w, n) indicates personal patient information or treats the Fourier in short-term of information or the information signal of hospital stays
Transformation；α u, α d are predetermined coefficient and 0<αd<αu<1；W indicates the frequency point serial number on frequency domain；N indicates the frame number in time domain；
According to the following equation to the Short Time Fourier Transform of each frame signal carry out binary conversion treatment obtain two-value spectrum Xb (w,
n)：
Tb is preset first threshold value；
Between the corresponding Ka two-value spectrum of wherein frame signal Kb two-value spectrum corresponding with another frame signal is carried out two-by-two
Coherence match to obtain first matching result, first matching result includes the highest one group of two-value spectrum pair of matching degree
The matching position and matching degree answered, Ka, Kb are positive integer；
For each frame signal, calculate according to the following equation each frame signal in the voice signal power spectrum P (w,
n)：
P (w, n)=αpP (w, n-1)+(1- αp) | X (w, n) |2
Wherein, X (w, n) indicates personal patient information or treats the Fourier in short-term of information or the information signal of hospital stays
Transformation；
α p are predetermined coefficient and 0 ＜ α p ＜ 1；W indicates the frequency point serial number on frequency domain；N indicates the frame number in time domain；
The Spectral correlation DP (w, n) of the power spectrum of each frame signal is calculated according to the following equation：
DP (w, n)=| P (w+1, n)-P (w, n) |
Noise tracking is carried out to the Spectral correlation DP (w, n) according to the following equation, obtains the noise of each frame signal
The Spectral correlation NDP (w, n) of power spectrum：
Wherein, β u, β d are predetermined coefficient and 0 ＜ β d ＜ β u ＜ 1；
Video monitoring module is connect with main control module, for carrying out video monitoring to patient by camera；Video monitoring
When the integrated image processing module construction of module scratches Tu Lashi matrixes, substitutes least square method using Moving Least and obtain
Linear relationship on alpha figures is detected using Pulse-coupled Neural Network Model centering alpha images；Image is by close
The smaller impulsive noise pollution of degree is handled by adaptive weighted filter；Image is polluted by the larger impulsive noise of density to be used
The introducing binode constitutive element mathematical morphology of edge detail information is kept to carry out secondary filtering；
Moving Least Squares scratch figure method include：
In gray level image, window wiNeighborhood in alpha value meet local linear condition, use Moving Least
Local linear relationship is solved, is indicated as follows：
Weights ω, ω in formula (1)iIt is neighborhood wkIn weights；Formula (1) is expressed as the form of following matrix:
For each neighborhood wk,GkIt is defined as ‖ wkThe matrixes of ‖ × 2；GkOften row includes vector (Ii, 1), WkIt is every row vector pair
The weights ω answerediThe vector of composition, Gk' it is GkWkWeighting, it is corresponding to be expressed as (W per row vectork.Ii,Wk),It is in neighborhood
The vector of the corresponding alpha value composition of all pixels；
Coefficient ak,bkIt solves as follows：
It enablesJ (α) is expressed as following formula：
δi,jIt is Kronecker delta functions, μkAnd σ2It is wicket w respectivelykIt is interior based on WkWeighted mean and side
Difference, ‖ wk‖ is the number of pixel in window, and L is that mobile Laplace scratches figure matrix；
Main control module is connect with patient information acquisition module, video monitoring module, nursing distribution module, for dispatching letter
Cease acquisition module, video monitoring module, nursing distribution module normal work；
Distribution module is nursed, is connect with main control module, for distributing nursery work task to nurse.
Further, the nursing work load distribution assistance system further includes：Nursing record module, connect with main control module,
Nursery work content progress is completed for recording nurse.
The nursing work load distributes assistance system：Cloud service module, connect with main control module, for passing through cloud
Server centered big data computing resource handles the distribution of nursery work task.
The nursing work load distributes assistance system：Workload Account module, connect with main control module, for uniting
Meter calculates nursery work task amount.
Further, the Workload Account module statistical method is as follows：
First, the quantized value of every nursing items workload is predefined；
Then, input currently needs the nursing items counted；
Finally, worked as according to the quantization Data-Statistics of the nursing items that need to currently carry out and corresponding every nursing items workload
Preceding nursing work load.
Further, in image processing module image procossing, weights ω is introducedi, color model is applied to, under color model
Moving Least Squares scratch drawing method：
The linear relationship of each interchannel of coloured image is indicated with following formula：
C is the port number of coloured image, and after considering each channel information, formula (1) is converted into following formula:
After carrying out abbreviation to formula (2), solves mobile Laplace matrix under color model and be shown below：
J (α)=α L αT；
In (3) formula, I is the matrix that all pixels correspond to 3*1 color vectors composition in small neighbourhood, μkFor the W of IkWeighting is flat
, ΣkIt is I in WkCovariance matrix under weighting；
Moving Least Squares scratch big core method for solving in figure：Alpha value is solved using conjugate gradient method；
For equation Lx=b, the key of conjugate gradient method is to construct conjugate vector p, and seeks corresponding residual error；Conjugation ladder
Degree method is solved with alternative manner, and in each iterative process, new conjugate vector is solved by following formula：
The coefficient of conjugate direction is solved by following formula：
New x values are solved with residual error with following formula：
The corresponding element q of Lp vectors midpoint i are solved with following formulai：
WkIt is the corresponding neighborhoods of pixel k, ‖ wk‖ is the size of neighborhood, and i is to surround pixel k neighborhoods WkIn a pixel, qi
For i-th of element of q vectors, IiFor corresponding 3 dimensional vectors of pixel i, R, tri- channels G, B, p are indicatediFor pixel in conjugate vector
The corresponding elements of i, μkIt is 3 dimensional vectors, is neighborhood WkMiddle IiThe mean value of vector,For neighborhood WkThe corresponding conjugate vector of middle element i
piMean value,It is corresponding 3 dimensional vector of pixel k,For the corresponding scalars of pixel k.
Further, Pulse-coupled Neural Network Model：
Fij[n]=Sij；
Uij[n]=Fij[n](1+βij[n]Lij[n])；
θij[n]=θ0e-αθ(n-1)；
Wherein, βij[n] is adaptive link strength factor；
Sij、Fij[n]、Lij[n]、Uij[n]、θij[n] is respectively received image signal, feed back input, link input, inside
Active entry and dynamic threshold, NwFor the sum of all pixels in selected pending window W, Δ is adjustment factor, chooses 1~3；
When Pulse-coupled Neural Network Model is detected image, gray scale is set to be S using network characteristicijmaxPixel
Fire activation, then second of Pulse Coupled Neural Network iterative processing is carried out, between [Sijmax/1+βijLij,Sijmax] between pixel
Capture activation, makes the corresponding Y of the pixel activated twiceijOutput is 1；Then processing is highlighted to former image polluted by noise, then right
Treated image SijIt is iterated processing by aforementioned, and makes corresponding output Yij=1, utilize picture noise pixel and surrounding
Pixel interdependence is small, the big characteristic of gray scale difference, when the excitation of a neuron does not cause most of nerves near region
When the excitation of member, just illustrate that the neuron respective pixel may be noise spot；
Tentatively screen out Yij=0 corresponding pixel is the signaling point of microimage of Chinese medical herb, is protected；To YijIt is defeated
Go out and is counted within the scope of 3*3 templates B to export Y for 1 pixelijThe number N that neighborhood element value is 1 centered on=1YDifferentiation is returned
Class：1≤NY≤ 8, it is noise spot, works as NY=9, it is determined as image slices vegetarian refreshments；
The method of image adaptive weighting filter noise filtering includes：
When pulse exports Yij=1 and NY=1~8, NYIt is to choose filter window M when being 1 number in 3*3 templates B, it is right
Image polluted by noise fijAdaptive-filtering, filtering equations are：
In formula, xrsIt is the coefficient of respective pixel in filter window, SrsFor the gray value of respective pixel in filter window, fij
To correspond to the output valve of window center position after filtering：
D in formulaijFor pixel grey scale intermediate value in box filter window M, ΩijEach pixel of filter window and center gray scale difference are exhausted
To mean value, max is maximizing symbol；
Further, the method for binode constitutive element mathematical morphology progress secondary filtering includes：
The image of residual impulse noise is f, and E is structural element SE, then expansion has following relational expression：
In formulaIt is accorded with for dilation operation, F and G are the domain of f and E respectively, and x-z is displacement parameter；
Above formula extension relationship is all to be merged into all background dots contacted with object in object, and boundary is made to be expanded to outside
Process, fill up the hole in object；
Above formula Θ accords with for erosion operation, and corrosion is to eliminate boundary point, and boundary is internally shunk, while in the base of corrosion expansion
On plinth, in conjunction with morphologic opening and closing operation：
Another object of the present invention is to provide a kind of letters distributing assistance system equipped with the nursing work load
Cease processing terminal.
Advantages of the present invention and good effect are：
The present invention determines that the quantized value of every nursing items workload, then input are worked as by Workload Account module first
It is preceding to need the nursing items that count, then according to the nursing items that need to currently carry out and corresponding every nursing items workload
Quantify the current total nursing work load of Data-Statistics, to realize the statistics to nursing module and the workload for nursing monomer, for nursing
Administrative staff assess desk work amount, science distribution nurse, effectively control the management method that nursing quality provides science；Lead to simultaneously
Nursing work load statistics, dispensing rate can be greatly improved by crossing cloud service module, improve allocative efficiency, ensure that patient obtains in time
Nursing.
The information data accuracy of patient information acquisition module acquisition of the present invention improves nearly 6 percentages compared with the prior art
Point.
The present invention scratches figure matrix method using the Laplce of Moving Least, there is complicated foreground and foreground zone
Domain and the region of foreground and background COMPLEX MIXED, can obtain preferable effect.It is substituted using moving least square method minimum
Square law derives mobile Laplace matrix；Relative to least square method, linear conditions that Moving Least solves more subject to
Really；KNN neighborhoods are used to substitute spatial neighborhood so that Laplace matrix can reflect the relationship of the alpha value of pixel between non-neighborhood.This
The Laplce using Moving Least of invention scratches figure matrix method, is schemed according to Matrix Solving alpha, so as to right
Image under complex background carries out foreground FIG pull handle, more effective compared to pervious method, can solve more accurate
Alpha schemes, and in figure preceding background complexity region, especially in foreground and background color-mixed areas, and can locally go out
The region in existing cavity, the region changed greatly can obtain good effect, can accurately be monitored to patient, and it is accurate to obtain
The image data to be nursed.
The present invention is the research that Image Information Processing technology carries out traditional medicine modern measure identifies image application technology,
It is combined with " modern times " analysis detection for image in the information age " tradition " and completely new technical thought and method is provided, to modern doctor
It learns image detection analysis and carries out beneficial exploration, improve picture quality detection for next step, basis early period is established in identification；
2) in image impulse noise detection-phase, the present invention provides characteristic using the lock-out pulse of Pulse Coupled Neural Network
Position pulse noise spot and signal pixels point position are distinguished, it is relatively traditional that intermediate value detection side is improved based on intermediate value detection or correlation
Method has higher noise detection performance, relative to other threshold value noise detection methods；The present invention makes an uproar without setting detection threshold value
Sound fallout ratio and omission factor are low, and noise measuring precision is higher；Meanwhile relative to other noise iteration detection methods；Side of the present invention
Method detection time is short, and automaticity is strong；
There is presently no any impulse noise correction methods to apply in the detection of medical image impulsive noise；
3) in the Filtering image impulse noise stage, the present invention is first according to the above-mentioned noise detected and signaling point, to figure
As pixel carries out classification processing；Only the noise spot of detection is filtered when using first order adaptive weighted filter,
Signaling point information is protected while effectively filtering out noise relative to the methods of other medium filterings, Wiener filtering；Second
It is to carry out supplement auxiliary to the related noise missed in prime filtering to filter out when grade mathematical morphology filter, while denoising not
But noise jamming can be effectively filtered out, and the information such as image edge detailss can be protected well；
The present invention has stronger subjective vision effect and objective evaluation index, and noise removal capability is strong, signal-to-noise ratio is high and adapts to
Property is good, especially to the image by serious noise pollution, it is shown that the filtering superiority of bigger.
Description of the drawings
Fig. 1 is that system structure diagram is assisted in nursing work load distribution provided in an embodiment of the present invention.
In figure：1, patient information acquisition module；2, video monitoring module；3, main control module；4, distribution module is nursed；5, it protects
Manage logging modle；6, cloud service module；7, Workload Account module.
Specific implementation mode
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and coordinate attached drawing
Detailed description are as follows.
The structure of the present invention is explained in detail below in conjunction with the accompanying drawings.
As shown in Figure 1, nursing work load distribution assistance system provided by the invention includes：Patient information acquisition module 1 regards
Frequency monitoring module 2, main control module 3, nursing distribution module 4, nursing record module 5, cloud service module 6, Workload Account module
7。
Patient information acquisition module 1 is connect with main control module 3, for acquiring personal patient information, treatment information, being hospitalized
The information such as time；
Video monitoring module 2 is connect with main control module 3, for carrying out video monitoring to patient by camera；
Main control module 3, with patient information acquisition module 1, video monitoring module 2, nursing distribution module 4, nursing record mould
Block 5, cloud service module 6, Workload Account module 7 connect, for dispatching modules normal work；
Distribution module 4 is nursed, is connect with main control module 3, for distributing nursery work task to nurse；
Nursing record module 5 is connect with main control module 3, and nursery work content progress is completed for recording nurse；
Cloud service module 6 is connect with main control module 3, for concentrating big data computing resource to nursing by Cloud Server
Task distribution is handled；
Workload Account module 7 is connect with main control module 3, and nursery work task amount is calculated for counting.
7 statistical method of Workload Account module provided by the invention is as follows：
First, the quantized value of every nursing items workload is predefined；
Then, input currently needs the nursing items counted；
Finally, worked as according to the quantization Data-Statistics of the nursing items that need to currently carry out and corresponding every nursing items workload
Preceding nursing work load.
When the present invention works, personal patient information, treatment information, hospital stays are acquired by patient information acquisition module 1
Etc. information；Video monitoring is carried out to patient by video monitoring module 2；The scheduling nursing distribution module 4 of main control module 3 is to nurse point
With nursery work task；Nurse records nurse in carrying out nursing process, by nursing record module 5 and completes nursery work content
Progress；Big data computing resource is concentrated to handle the distribution of nursery work task by cloud service module 6；It is united by workload
It counts the statistics of module 7 and calculates nursery work task amount.
With reference to concrete analysis, the invention will be further described.
Patient information acquisition module in nursing work load distribution assistance system provided in an embodiment of the present invention, with master control mould
Block connects, for acquiring personal patient information, treatment information, the information of hospital stays；It specifically includes：For personal information, control
Information, the information signal of hospital stays are treated, noise is carried out to each frame signal in the information signal of acquisition according to the following equation
Tracking, obtains the noise spectrum N (w, n) of each frame signal：
Wherein, X (w, n) indicates personal patient information or treats the Fourier in short-term of information or the information signal of hospital stays
Transformation；α u, α d are predetermined coefficient and 0<αd<αu<1；W indicates the frequency point serial number on frequency domain；N indicates the frame number in time domain；
According to the following equation to the Short Time Fourier Transform of each frame signal carry out binary conversion treatment obtain two-value spectrum Xb (w,
n)：
Tb is preset first threshold value；
Between the corresponding Ka two-value spectrum of wherein frame signal Kb two-value spectrum corresponding with another frame signal is carried out two-by-two
Coherence match to obtain first matching result, first matching result includes the highest one group of two-value spectrum pair of matching degree
The matching position and matching degree answered, Ka, Kb are positive integer；
For each frame signal, calculate according to the following equation each frame signal in the voice signal power spectrum P (w,
n)：
P (w, n)=αpP (w, n-1)+(1- αp) | X (w, n) |2
Wherein, X (w, n) indicates personal patient information or treats the Fourier in short-term of information or the information signal of hospital stays
Transformation；
α p are predetermined coefficient and 0 ＜ α p ＜ 1；W indicates the frequency point serial number on frequency domain；N indicates the frame number in time domain；
The Spectral correlation DP (w, n) of the power spectrum of each frame signal is calculated according to the following equation：
DP (w, n)=| P (w+1, n)-P (w, n) |
Noise tracking is carried out to the Spectral correlation DP (w, n) according to the following equation, obtains the noise of each frame signal
The Spectral correlation NDP (w, n) of power spectrum：
Wherein, β u, β d are predetermined coefficient and 0 ＜ β d ＜ β u ＜ 1；
Video monitoring module is connect with main control module, for carrying out video monitoring to patient by camera；Video monitoring
When the integrated image processing module construction of module scratches Tu Lashi matrixes, substitutes least square method using Moving Least and obtain
Linear relationship on alpha figures is detected using Pulse-coupled Neural Network Model centering alpha images；Image is by close
The smaller impulsive noise pollution of degree is handled by adaptive weighted filter；Image is polluted by the larger impulsive noise of density to be used
The introducing binode constitutive element mathematical morphology of edge detail information is kept to carry out secondary filtering；
Moving Least Squares scratch figure method include：
In gray level image, window wiNeighborhood in alpha value meet local linear condition, use Moving Least
Local linear relationship is solved, is indicated as follows：
Weights ω, ω in formula (1)iIt is neighborhood wkIn weights；Formula (1) is expressed as the form of following matrix:
For each neighborhood wk,GkIt is defined as ‖ wkThe matrixes of ‖ × 2；GkOften row includes vector (Ii, 1), WkIt is every row vector pair
The weights ω answerediThe vector of composition, Gk' it is GkWkWeighting, it is corresponding to be expressed as (W per row vectork.Ii,Wk),It is in neighborhood
The vector of the corresponding alpha value composition of all pixels；
Coefficient ak,bkIt solves as follows：
It enablesJ (α) is expressed as following formula：
δi,jIt is Kronecker delta functions, μkAnd σ2It is wicket w respectivelykIt is interior based on WkWeighted mean and side
Difference, ‖ wk‖ is the number of pixel in window, and L is that mobile Laplace scratches figure matrix；
In image processing module image procossing, weights ω is introducedi, it is applied to color model, the movement under color model is most
Small two multiply stingy drawing method：
The linear relationship of each interchannel of coloured image is indicated with following formula：
C is the port number of coloured image, and after considering each channel information, formula (1) is converted into following formula:
After carrying out abbreviation to formula (2), solves mobile Laplace matrix under color model and be shown below：
J (α)=α L αT；
In (3) formula, I is the matrix that all pixels correspond to 3*1 color vectors composition in small neighbourhood, μkFor the W of IkWeighting is flat
, ΣkIt is I in WkCovariance matrix under weighting；
Moving Least Squares scratch big core method for solving in figure：Alpha value is solved using conjugate gradient method；
For equation Lx=b, the key of conjugate gradient method is to construct conjugate vector p, and seeks corresponding residual error；Conjugation ladder
Degree method is solved with alternative manner, and in each iterative process, new conjugate vector is solved by following formula：
The coefficient of conjugate direction is solved by following formula：
New x values are solved with residual error with following formula：
The corresponding element q of Lp vectors midpoint i are solved with following formulai：
WkIt is the corresponding neighborhoods of pixel k, ‖ wk‖ is the size of neighborhood, and i is to surround pixel k neighborhoods WkIn a pixel, qi
For i-th of element of q vectors, IiFor corresponding 3 dimensional vectors of pixel i, R, tri- channels G, B, p are indicatediFor pixel in conjugate vector
The corresponding elements of i, μkIt is 3 dimensional vectors, is neighborhood WkMiddle IiThe mean value of vector,For neighborhood WkThe corresponding conjugate vector of middle element i
piMean value,It is corresponding 3 dimensional vector of pixel k,For the corresponding scalars of pixel k.
Pulse-coupled Neural Network Model：
Fij[n]=Sij；
Uij[n]=Fij[n](1+βij[n]Lij[n])；
θij[n]=θ0e-αθ(n-1)；
Wherein, βij[n] is adaptive link strength factor；
Sij、Fij[n]、Lij[n]、Uij[n]、θij[n] is respectively received image signal, feed back input, link input, inside
Active entry and dynamic threshold, NwFor the sum of all pixels in selected pending window W, Δ is adjustment factor, chooses 1~3；
When Pulse-coupled Neural Network Model is detected image, gray scale is set to be S using network characteristicijmaxPixel
Fire activation, then second of Pulse Coupled Neural Network iterative processing is carried out, between [Sijmax/1+βijLij,Sijmax] between pixel
Capture activation, makes the corresponding Y of the pixel activated twiceijOutput is 1；Then processing is highlighted to former image polluted by noise, then right
Treated image SijIt is iterated processing by aforementioned, and makes corresponding output Yij=1, utilize picture noise pixel and surrounding
Pixel interdependence is small, the big characteristic of gray scale difference, when the excitation of a neuron does not cause most of nerves near region
When the excitation of member, just illustrate that the neuron respective pixel may be noise spot；
Tentatively screen out Yij=0 corresponding pixel is the signaling point of microimage of Chinese medical herb, is protected；To YijIt is defeated
Go out and is counted within the scope of 3*3 templates B to export Y for 1 pixelijThe number N that neighborhood element value is 1 centered on=1YDifferentiation is returned
Class：1≤NY≤ 8, it is noise spot, works as NY=9, it is determined as image slices vegetarian refreshments；
The method of image adaptive weighting filter noise filtering includes：
When pulse exports Yij=1 and NY=1~8, NYIt is to choose filter window M when being 1 number in 3*3 templates B, it is right
Image polluted by noise fijAdaptive-filtering, filtering equations are：
In formula, xrsIt is the coefficient of respective pixel in filter window, SrsFor the gray value of respective pixel in filter window, fij
To correspond to the output valve of window center position after filtering：
D in formulaijFor pixel grey scale intermediate value in box filter window M, ΩijEach pixel of filter window and center gray scale difference are exhausted
To mean value, max is maximizing symbol；
Binode constitutive element mathematical morphology carry out secondary filtering method include：
The image of residual impulse noise is f, and E is structural element SE, then expansion has following relational expression：
In formulaIt is accorded with for dilation operation, F and G are the domain of f and E respectively, and x-z is displacement parameter；
Above formula extension relationship is all to be merged into all background dots contacted with object in object, and boundary is made to be expanded to outside
Process, fill up the hole in object；
Above formula Θ accords with for erosion operation, and corrosion is to eliminate boundary point, and boundary is internally shunk, while in the base of corrosion expansion
On plinth, in conjunction with morphologic opening and closing operation：
With reference to the prior art, the invention will be further described with comparison of the invention.
The prior art：1. a kind of nursing work load distributes assistance system, which is characterized in that the system comprises：
Input unit, before being set to each sick bed, to the nursing items for inputting each nurse in real time and each nursing item
Purpose nurses number；
Central processing unit is connected with the input unit, and the data from input unit are handled to real-time reception, real
When obtain the nursing work load of each nurse；
Display device is connected with the central processing unit, nursing items, Mei Gehu to each nurse of real-time display
The nursing number and nursing work load of reason project.
2. nursing work load according to claim 1 distributes assistance system, it is characterised in that：The input unit packet
It includes：
Touch display screen clicks the nursing items and nursing number that input will operate to nurse；
Storage unit is set to inside the touch display screen, record input unit place sick bed has been automatically stored
Nursing items, nursing number, operation nurse and the operating time done.
3. nursing work load according to claim 1 distributes assistance system, it is characterised in that：The center processing dress
Set including：
Database server, to store the unit score value of every nursing items；
First processing module is connected with the touch display screen and database server respectively, each to calculate in real time
The nursing work load of nurse；
Memory, to store the nursing items for recording each sick bed and having done, nursing number, operation nurse and operation
Time.
4. nursing work load according to claim 3 distributes assistance system, which is characterized in that the system also includes
One distributor, the distributor include：
Second processing module is connected with the first processing module, to the nursing work load of more each nurse, respectively
It obtains workload difference, then judges whether the workload difference reaches setting value, start broadcast mould if reaching setting value
Block；
Broadcast module is connected with the Second processing module, reaches setting value to broadcast notice workload difference automatically
And the few nurse of workload goes to the big nursing sector of nursing work load.
The prior art not only has the image acquiring method and collecting method of the present invention；Do not have the positive of the present invention
Effect；The present invention has：
The information data accuracy of patient information acquisition module acquisition of the present invention improves nearly 6 percentages compared with the prior art
Point.
The present invention scratches figure matrix method using the Laplce of Moving Least, there is complicated foreground and foreground zone
Domain and the region of foreground and background COMPLEX MIXED, can obtain preferable effect.It is substituted using moving least square method minimum
Square law derives mobile Laplace matrix；Relative to least square method, linear conditions that Moving Least solves more subject to
Really；KNN neighborhoods are used to substitute spatial neighborhood so that Laplace matrix can reflect the relationship of the alpha value of pixel between non-neighborhood.This
The Laplce using Moving Least of invention scratches figure matrix method, is schemed according to Matrix Solving alpha, so as to right
Image under complex background carries out foreground FIG pull handle, more effective compared to pervious method, can solve more accurate
Alpha schemes, and in figure preceding background complexity region, especially in foreground and background color-mixed areas, and can locally go out
The region in existing cavity, the region changed greatly can obtain good effect, can accurately be monitored to patient, and it is accurate to obtain
The image data to be nursed.
The present invention is the research that Image Information Processing technology carries out traditional medicine modern measure identifies image application technology,
It is combined with " modern times " analysis detection for image in the information age " tradition " and completely new technical thought and method is provided, to modern doctor
It learns image detection analysis and carries out beneficial exploration, improve picture quality detection for next step, basis early period is established in identification；
2) in image impulse noise detection-phase, the present invention provides characteristic using the lock-out pulse of Pulse Coupled Neural Network
Position pulse noise spot and signal pixels point position are distinguished, it is relatively traditional that intermediate value detection side is improved based on intermediate value detection or correlation
Method has higher noise detection performance, relative to other threshold value noise detection methods；The present invention makes an uproar without setting detection threshold value
Sound fallout ratio and omission factor are low, and noise measuring precision is higher；Meanwhile relative to other noise iteration detection methods；Side of the present invention
Method detection time is short, and automaticity is strong；
There is presently no any impulse noise correction methods to apply in the detection of medical image impulsive noise；
3) in the Filtering image impulse noise stage, the present invention is first according to the above-mentioned noise detected and signaling point, to figure
As pixel carries out classification processing；Only the noise spot of detection is filtered when using first order adaptive weighted filter,
Signaling point information is protected while effectively filtering out noise relative to the methods of other medium filterings, Wiener filtering；Second
It is to carry out supplement auxiliary to the related noise missed in prime filtering to filter out when grade mathematical morphology filter, while denoising not
But noise jamming can be effectively filtered out, and the information such as image edge detailss can be protected well；
The present invention has stronger subjective vision effect and objective evaluation index, and noise removal capability is strong, signal-to-noise ratio is high and adapts to
Property is good, especially to the image by serious noise pollution, it is shown that the filtering superiority of bigger.
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Every any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (9)
1. a kind of nursing work load distributes assistance system, which is characterized in that the nursing work load distributes assistance system and includes：
Patient information acquisition module, connect with main control module, for acquiring personal patient information, treatment information, hospital stays
Information；It specifically includes：For personal information, treatment information, the information signal of hospital stays, according to the following equation to the letter of acquisition
Each frame signal in information signal carries out noise tracking, obtains the noise spectrum N (w, n) of each frame signal：
Wherein, X (w, n) indicates personal patient information or treats the change of Fourier in short-term of information or the information signal of hospital stays
It changes；α u, α d are predetermined coefficient and 0<αd<αu<1；W indicates the frequency point serial number on frequency domain；N indicates the frame number in time domain；
Binary conversion treatment is carried out to the Short Time Fourier Transform of each frame signal according to the following equation and obtains two-value spectrum Xb (w, n)：
Tb is preset first threshold value；
The corresponding Ka two-value of a wherein frame signal is composed into the phase between Kb two-value spectrum progress two-by-two corresponding with another frame signal
Dryness matches to obtain first matching result, and first matching result includes that the highest one group of two-value spectrum of matching degree is corresponding
Matching position and matching degree, Ka, Kb are positive integer；
For each frame signal, the power spectrum P (w, n) of each frame signal in the voice signal is calculated according to the following equation：
P (w, n)=αpP(w,n-1)+(1-αp)|X(w,n)|2
Wherein, X (w, n) indicates personal patient information or treats the change of Fourier in short-term of information or the information signal of hospital stays
It changes；
α p are predetermined coefficient and 0 ＜ α p ＜ 1；W indicates the frequency point serial number on frequency domain；N indicates the frame number in time domain；
The Spectral correlation DP (w, n) of the power spectrum of each frame signal is calculated according to the following equation：
DP (w, n)=| P (w+1, n)-P (w, n) |
Noise tracking is carried out to the Spectral correlation DP (w, n) according to the following equation, obtains the noise power of each frame signal
The Spectral correlation NDP (w, n) of spectrum：
Wherein, β u, β d are predetermined coefficient and 0 ＜ β d ＜ β u ＜ 1；
Video monitoring module is connect with main control module, for carrying out video monitoring to patient by camera；Video monitoring module
When integrated image processing module construction scratches Tu Lashi matrixes, substitutes least square method using Moving Least and obtain
Linear relationship on alpha figures is detected using Pulse-coupled Neural Network Model centering alpha images；Image is by close
The smaller impulsive noise pollution of degree is handled by adaptive weighted filter；Image is polluted by the larger impulsive noise of density to be used
The introducing binode constitutive element mathematical morphology of edge detail information is kept to carry out secondary filtering；
Moving Least Squares scratch figure method include：
In gray level image, window wiNeighborhood in alpha value meet local linear condition, solved using Moving Least
Local linear relationship indicates as follows：
Weights ω, ω in formula (1)iIt is neighborhood wkIn weights；Formula (1) is expressed as the form of following matrix:
For each neighborhood wk,GkIt is defined as ‖ wkThe matrixes of ‖ × 2；GkOften row includes vector (Ii, 1), WkIt is that every row vector is corresponding
Weights ωiThe vector of composition, Gk' it is GkWkWeighting, it is corresponding to be expressed as (W per row vectork.Ii,Wk),It is to own in neighborhood
The vector of the corresponding alpha value composition of pixel；
Coefficient ak,bkIt solves as follows：
Gk'=Wk.Gk
It enablesJ (α) is expressed as following formula：
δi,jIt is Kronecker delta functions, μkAnd σ2It is wicket w respectivelykIt is interior based on WkWeighted mean and variance, ‖
wk‖ is the number of pixel in window, and L is that mobile Laplace scratches figure matrix；
Main control module connect with patient information acquisition module, video monitoring module, nursing distribution module, is adopted for scheduling information
Collect module, video monitoring module, nursing distribution module normal work；
Distribution module is nursed, is connect with main control module, for distributing nursery work task to nurse.
2. nursing work load as described in claim 1 distributes assistance system, which is characterized in that the nursing work load distribution is assisted
System further includes：Nursing record module, connect with main control module, and nursery work content progress is completed for recording nurse.
3. nursing work load as described in claim 1 distributes assistance system, which is characterized in that the nursing work load distribution is assisted
System further includes：Cloud service module, connect with main control module, for concentrating big data computing resource to nursing by Cloud Server
Task distribution is handled.
4. nursing work load as described in claim 1 distributes assistance system, which is characterized in that the nursing work load distribution is assisted
System further includes：Workload Account module, connect with main control module, and nursery work task amount is calculated for counting.
5. nursing work load as described in claim 1 distributes assistance system, which is characterized in that the Workload Account module statistics
Method is as follows：
First, the quantized value of every nursing items workload is predefined；
Then, input currently needs the nursing items counted；
Finally, current according to the quantization Data-Statistics of the nursing items that need to currently carry out and corresponding every nursing items workload
Nursing work load.
6. nursing work load as described in claim 1 distributes assistance system, which is characterized in that image processing module image procossing
In, introduce weights ωi, it is applied to color model, the Moving Least Squares under color model scratch drawing method：
The linear relationship of each interchannel of coloured image is indicated with following formula：
C is the port number of coloured image, and after considering each channel information, formula (1) is converted into following formula:
After carrying out abbreviation to formula (2), solves mobile Laplace matrix under color model and be shown below：
J (α)=α L αT；
In (3) formula, I is the matrix that all pixels correspond to 3*1 color vectors composition in small neighbourhood, μkFor the W of IkWeighted average,
ΣkIt is I in WkCovariance matrix under weighting；
Moving Least Squares scratch big core method for solving in figure：Alpha value is solved using conjugate gradient method；
For equation Lx=b, the key of conjugate gradient method is to construct conjugate vector p, and seeks corresponding residual error；Conjugate gradient method
It is solved with alternative manner, in each iterative process, new conjugate vector is solved by following formula：
The coefficient of conjugate direction is solved by following formula：
New x values are solved with residual error with following formula：
The corresponding element q of Lp vectors midpoint i are solved with following formulai：
WkIt is the corresponding neighborhoods of pixel k, ‖ wk‖ is the size of neighborhood, and i is to surround pixel k neighborhoods WkIn a pixel, qiFor q to
I-th of element of amount, IiFor corresponding 3 dimensional vectors of pixel i, R, tri- channels G, B, p are indicatediIt is corresponded to for pixel i in conjugate vector
Element, μkIt is 3 dimensional vectors, is neighborhood WkMiddle IiThe mean value of vector,For neighborhood WkThe corresponding conjugate vector p of middle element ii's
Mean value,It is corresponding 3 dimensional vector of pixel k,For the corresponding scalars of pixel k.
7. nursing work load as described in claim 1 distributes assistance system, which is characterized in that Pulse-coupled Neural Network Model：
Fij[n]=Sij；
Uij[n]=Fij[n](1+βij[n]Lij[n])；
Wherein, βij[n] is adaptive link strength factor；
Sij、Fij[n]、Lij[n]、Uij[n]、θij[n] is respectively received image signal, feed back input, link input, internal activity
Item and dynamic threshold, NwFor the sum of all pixels in selected pending window W, Δ is adjustment factor, chooses 1~3；
When Pulse-coupled Neural Network Model is detected image, gray scale is set to be S using network characteristicijmaxPixel igniting swash
It is living, then second of Pulse Coupled Neural Network iterative processing is carried out, between [Sijmax/1+βijLij,Sijmax] between pixel capture
Activation, makes the corresponding Y of the pixel activated twiceijOutput is 1；Then processing is highlighted to former image polluted by noise, then to processing
Image S afterwardsijIt is iterated processing by aforementioned, and makes corresponding output Yij=1, utilize picture noise pixel and surrounding pixel
Correlation is small, the big characteristic of gray scale difference, when the excitation of a neuron does not cause most of neurons near region
When excitation, just illustrate that the neuron respective pixel may be noise spot；
Tentatively screen out Yij=0 corresponding pixel is the signaling point of microimage of Chinese medical herb, is protected；To YijOutput is 1
Pixel counted within the scope of 3*3 templates B to export YijThe number N that neighborhood element value is 1 centered on=1YDifferentiate and sorts out：1
≤NY≤ 8, it is noise spot, works as NY=9, it is determined as image slices vegetarian refreshments；
The method of image adaptive weighting filter noise filtering includes：
When pulse exports Yij=1 and NY=1~8, NYIt is to work as in 3*3 templates B for 1 number, filter window M is chosen, to noise dirt
Contaminate image fijAdaptive-filtering, filtering equations are：
In formula, xrsIt is the coefficient of respective pixel in filter window, SrsFor the gray value of respective pixel in filter window, fijFor filter
The output valve of window center position is corresponded to after wave：
D in formulaijFor pixel grey scale intermediate value in box filter window M, ΩijEach pixel of filter window and center gray scale difference are absolutely equal
Value, max are maximizing symbol；
8. nursing work load as described in claim 1 distributes assistance system, which is characterized in that binode constitutive element mathematical morphology into
The method of row secondary filtering includes：
The image of residual impulse noise is f, and E is structural element SE, then expansion has following relational expression：
In formulaIt is accorded with for dilation operation, F and G are the domain of f and E respectively, and x-z is displacement parameter；
Above formula extension relationship is all to be merged into all background dots contacted with object in object, makes boundary to the mistake of outside expansion
Journey fills up the hole in object；
Above formula Θ accords with for erosion operation, and corrosion is to eliminate boundary point, and boundary is internally shunk, while on the basis of corrosion expansion
On, in conjunction with morphologic opening and closing operation：
9. a kind of information processing terminal distributing assistance system equipped with nursing work load described in claim 1-8 any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810179793.6A CN108399946A (en) | 2018-03-05 | 2018-03-05 | A kind of nursing work load distribution assistance system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810179793.6A CN108399946A (en) | 2018-03-05 | 2018-03-05 | A kind of nursing work load distribution assistance system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108399946A true CN108399946A (en) | 2018-08-14 |
Family
ID=63092383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810179793.6A Pending CN108399946A (en) | 2018-03-05 | 2018-03-05 | A kind of nursing work load distribution assistance system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108399946A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792986A (en) * | 2021-08-23 | 2021-12-14 | 东风柳州汽车有限公司 | Human resource plan generation method, device, equipment and storage medium |
| US11386995B2 (en) * | 2019-02-08 | 2022-07-12 | GE Precision Healthcare LLC | Method and system for centralized patient monitoring management |
| CN115034273A (en) * | 2021-12-27 | 2022-09-09 | 驻马店市中心医院 | Myoelectricity biofeedback equipment and system based on pattern recognition |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101154277A (en) * | 2006-09-29 | 2008-04-02 | 上海市第十人民医院 | Statistical method for nursing work load |
| CN201681421U (en) * | 2010-04-28 | 2010-12-22 | 同济大学附属第十人民医院 | Nursing workload distribution and assisting system |
| CN104700842A (en) * | 2015-02-13 | 2015-06-10 | 广州市百果园网络科技有限公司 | Sound signal time delay estimation method and device |
| CN104732500A (en) * | 2015-04-10 | 2015-06-24 | 天水师范学院 | Traditional Chinese medicinal material microscopic image noise filtering system and method adopting pulse coupling neural network |
| CN105096326A (en) * | 2015-08-13 | 2015-11-25 | 丽水学院 | Laplace cutout matrix method by using moving least square method |
| CN105825460A (en) * | 2016-04-30 | 2016-08-03 | 安徽硕尼信息科技有限公司 | Hospital nursing system based on Internet of Things |
| CN107545265A (en) * | 2017-07-17 | 2018-01-05 | 浙江智神数码科技有限公司 | A kind of intelligent vehicle license plate recognition system |
-
2018
- 2018-03-05 CN CN201810179793.6A patent/CN108399946A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101154277A (en) * | 2006-09-29 | 2008-04-02 | 上海市第十人民医院 | Statistical method for nursing work load |
| CN201681421U (en) * | 2010-04-28 | 2010-12-22 | 同济大学附属第十人民医院 | Nursing workload distribution and assisting system |
| CN104700842A (en) * | 2015-02-13 | 2015-06-10 | 广州市百果园网络科技有限公司 | Sound signal time delay estimation method and device |
| CN104732500A (en) * | 2015-04-10 | 2015-06-24 | 天水师范学院 | Traditional Chinese medicinal material microscopic image noise filtering system and method adopting pulse coupling neural network |
| CN105096326A (en) * | 2015-08-13 | 2015-11-25 | 丽水学院 | Laplace cutout matrix method by using moving least square method |
| CN105825460A (en) * | 2016-04-30 | 2016-08-03 | 安徽硕尼信息科技有限公司 | Hospital nursing system based on Internet of Things |
| CN107545265A (en) * | 2017-07-17 | 2018-01-05 | 浙江智神数码科技有限公司 | A kind of intelligent vehicle license plate recognition system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11386995B2 (en) * | 2019-02-08 | 2022-07-12 | GE Precision Healthcare LLC | Method and system for centralized patient monitoring management |
| CN113792986A (en) * | 2021-08-23 | 2021-12-14 | 东风柳州汽车有限公司 | Human resource plan generation method, device, equipment and storage medium |
| CN113792986B (en) * | 2021-08-23 | 2024-03-26 | 东风柳州汽车有限公司 | Human resource plan generation method, device, equipment and storage medium |
| CN115034273A (en) * | 2021-12-27 | 2022-09-09 | 驻马店市中心医院 | Myoelectricity biofeedback equipment and system based on pattern recognition |
| CN115034273B (en) * | 2021-12-27 | 2023-09-01 | 驻马店市中心医院 | Myoelectricity biofeedback equipment and system based on pattern recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110522448B (en) | Brain network classification method based on atlas neural network | |
| Fabiani et al. | Conversion of EEG activity into cursor movement by a brain-computer interface (BCI) | |
| CN110491480A (en) | A kind of medical image processing method, device, electromedical equipment and storage medium | |
| CN107066814A (en) | A kind of traditional Chinese medical science intelligent auxiliary diagnosis system cooperateed with based on the four methods of diagnosis | |
| CN107767935A (en) | Medical image specification processing system and method based on artificial intelligence | |
| CN108399946A (en) | A kind of nursing work load distribution assistance system | |
| CN110070935A (en) | Medical image synthetic method, classification method and device based on confrontation neural network | |
| CN111297349A (en) | Machine learning-based heart rhythm classification system | |
| CN107169998A (en) | A kind of real-time tracking and quantitative analysis method based on hepatic ultrasound contrast enhancement image | |
| CN106170246A (en) | For four-dimensional (4D) stream equipment of nuclear magnetic resonance, method and product | |
| CN105595990A (en) | Intelligent terminal device for evaluating and distinguishing quality of electrocardiosignal | |
| CN113990494B (en) | Tic disorder auxiliary screening system based on video data | |
| CN109509552A (en) | A kind of mental disease automatic distinguishing method of the multi-level features fusion based on function connects network | |
| CN105678058A (en) | Traditional Chinese medicine auxiliary diagnosis and treatment device and system | |
| CN108710890A (en) | Preoperative grading of cerebral glioma method, apparatus, equipment and storage medium | |
| CN111523617B (en) | Epilepsy detection system based on white matter fusion characteristic diagram and residual error attention network | |
| CN106202861A (en) | Nervous system image interactive system | |
| CN110728666A (en) | Typing method and system for chronic nasosinusitis based on digital pathological slide | |
| CN111968108A (en) | CT intelligent imaging method, device and system based on intelligent scanning protocol | |
| CN114241240A (en) | Method and device for classifying brain images, electronic equipment and storage medium | |
| CN117612710A (en) | Medical diagnosis auxiliary system based on electroencephalogram signals and artificial intelligence classification | |
| Cheng et al. | Quantitative evaluation of liver fibrosis based on ultrasound radio frequency signals: An animal experimental study | |
| CN117095813A (en) | Method, system, equipment and medium for constructing sarcopenia automatic diagnosis model | |
| WO2023184598A1 (en) | Artificial intelligence-based heart simulator data correction system and method | |
| CN114847933A (en) | Myoelectric signal gesture recognition method and system based on full convolution residual error network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180814 |