CN116451145A - Cooling device and method for stem cell transportation - Google Patents
Cooling device and method for stem cell transportation Download PDFInfo
- Publication number
- CN116451145A CN116451145A CN202310202516.3A CN202310202516A CN116451145A CN 116451145 A CN116451145 A CN 116451145A CN 202310202516 A CN202310202516 A CN 202310202516A CN 116451145 A CN116451145 A CN 116451145A
- Authority
- CN
- China
- Prior art keywords
- feature vector
- temperature
- power
- vector
- time sequence
- 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.)
- Withdrawn
Links
- 238000001816 cooling Methods 0.000 title claims abstract description 130
- 210000000130 stem cell Anatomy 0.000 title claims abstract description 113
- 238000000034 method Methods 0.000 title claims description 19
- 238000000605 extraction Methods 0.000 claims abstract description 38
- 239000013598 vector Substances 0.000 claims description 390
- 239000011159 matrix material Substances 0.000 claims description 79
- 230000004927 fusion Effects 0.000 claims description 28
- 230000003247 decreasing effect Effects 0.000 claims description 12
- 230000004656 cell transport Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 238000011217 control strategy Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims 1
- 230000008859 change Effects 0.000 abstract description 26
- 238000013135 deep learning Methods 0.000 abstract description 14
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 230000000694 effects Effects 0.000 description 8
- 238000013507 mapping Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 6
- 210000004027 cell Anatomy 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000001788 irregular Effects 0.000 description 4
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 238000007710 freezing Methods 0.000 description 2
- 230000008014 freezing Effects 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 241000124008 Mammalia Species 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000001464 adherent effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 239000002158 endotoxin Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000010076 replication Effects 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
- F25D29/005—Mounting of control devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0832—Special goods or special handling procedures, e.g. handling of hazardous or fragile goods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Mechanical Engineering (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Combustion & Propulsion (AREA)
- Thermal Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Control Of Temperature (AREA)
Abstract
The application relates to the technical field of stem cell transportation, and particularly discloses a cooling device and a cooling method for stem cell transportation, which adopt an artificial intelligent detection technology based on deep learning to excavate time sequence change mode characteristics of a temperature value of stem cells and a power value of the cooling device through a multi-scale neighborhood characteristic extraction module and extract time sequence change cooperative characteristics between the temperature value and the power value of the cooling device so as to carry out classification treatment. Like this, the time sequence change cooperation condition between the temperature value of stem cell and the power value of heat sink carries out self-adaptation control to the power value of heat sink, and then makes the temperature of heat sink can adapt to the real-time temperature change condition of current stem cell under the power drive of current heat sink.
Description
Technical Field
The present application relates to the field of stem cell transportation technology, and more particularly, to a cooling device and method for stem cell transportation.
Background
Stem cells are the origin cells, have proliferation and differentiation potential, have self-renewing and replication capacity, and are functional cells capable of generating high differentiation.
Since cells derived from mammals need to be preserved at a constant temperature of 37 ℃ and under appropriate conditions of humidity, oxygen and carbon dioxide concentration, the cells gradually lose activity when exposed to inappropriate culture conditions for a long time, and transportation and preservation of stem cells are particularly important. In order to solve the problems, chinese patent CN113881622a provides a method for preserving and transporting stem cells, which includes resuspending stem cells, freezing treatment, transportation and recovery treatment, and the cells treated by the preserving and transporting method have high activity, high proportion of adherent cells after recovery, and less bacterial endotoxin. However, in the process of actually performing the freezing treatment, the actual temperature of the stem cells is affected by factors such as the external environment and the like and fluctuates within a certain period of time, so that the temperature control of the cooling device needs to be performed in real time and adaptively based on the actual temperature of the stem cells.
Therefore, a cooling device and method for stem cell transport is desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems. The embodiment of the application provides a cooling device and a cooling method for stem cell transportation, which adopt an artificial intelligent detection technology based on deep learning to excavate time sequence change mode characteristics of a temperature value of stem cells and a power value of the cooling device through a multi-scale neighborhood characteristic extraction module and extract time sequence change cooperative characteristics between the temperature value and the power value of the cooling device so as to carry out classification processing. Like this, the time sequence change cooperation condition between the temperature value of stem cell and the power value of heat sink carries out self-adaptation control to the power value of heat sink, and then makes the temperature of heat sink can adapt to the real-time temperature change condition of current stem cell under the power drive of current heat sink.
Accordingly, according to one aspect of the present application, there is provided a cooling device for stem cell transport, comprising:
the monitoring module is used for acquiring power values of the cooling device at a plurality of preset time points in a preset time period and temperature values of the stem cells at the preset time points acquired by the temperature sensor;
the data structuring module is used for respectively arranging the power values of the cooling devices at the plurality of preset time points and the temperature values of the stem cells at the plurality of preset time points into a power input vector and a temperature input vector according to the time dimension;
the time sequence feature extraction module is used for respectively passing the power input vector and the temperature input vector through the multi-scale neighborhood feature extraction module to obtain a power time sequence feature vector and a temperature time sequence feature vector;
the fusion module is used for fusing the power time sequence feature vector and the temperature time sequence feature vector based on a Gaussian density chart to obtain a collaborative correlation matrix; and
and the regulation and control strategy generation module is used for enabling the collaborative correlation matrix to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the power value of the cooling device at the current time point should be increased or decreased.
In the above cooling device for stem cell transportation, the multi-scale neighborhood feature extraction module includes: the system comprises a first convolution layer, a second convolution layer and a multi-scale fusion layer connected with the first convolution layer and the second convolution layer, wherein the first convolution layer and the second convolution layer are parallel to each other, and one-dimensional convolution kernels with different scales are respectively used for the first convolution layer and the second convolution layer.
In the above cooling device for stem cell transportation, the time sequence feature extraction module is further configured to: using a first convolution layer of the multi-scale neighborhood feature extraction module to perform one-dimensional convolution coding on the power input vector and the temperature input vector respectively according to the following formula to obtain a first-scale power feature vector and a first-scale temperature feature vector; wherein, the formula is:
wherein a is the width of the first convolution kernel in the x direction,For the first convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, w is the size of the first convolution kernel, X represents the power input vector or the temperature input vector, +.>Representing one-dimensional convolutional encoding of the power input vector or the temperature input vector; using a second convolution layer of the multi-scale neighborhood feature extraction module to perform one-dimensional convolution coding on the power input vector and the temperature input vector respectively according to the following formula to obtain a second-scale power feature vector and a second-scale temperature feature vector; wherein, the formula is:
Wherein b is the width of the second convolution kernel in the x direction,For a second convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, m is the size of the second convolution kernel, X represents the power input vector or the temperature input vector, +.>Representing one-dimensional convolutional encoding of the power input vector or the temperature input vector; and cascading the first scale power feature vector and the second scale power feature vector by using a multi-scale fusion layer of the multi-scale neighborhood feature extraction module to obtain the power time sequence feature vector, and cascading the first scale temperature feature vector and the second scale temperature feature vector to obtain the temperature time sequence feature vector.
In the above cooling device for stem cell transportation, the fusion module includes: a joint gaussian density map construction unit, configured to construct a joint gaussian density map of the power timing feature vector and the temperature timing feature vector, where a mean vector of the joint gaussian density map is a per-position mean vector between the power timing feature vector and the temperature timing feature vector, and a value of each position in a covariance matrix of the joint gaussian density map is a per-position variance of the power timing feature vector and the temperature timing feature vector; the Gaussian probability density distribution distance index calculation unit is used for calculating the Gaussian probability density distribution distance indexes of the power time sequence feature vector and the temperature time sequence feature vector relative to the joint Gaussian density map respectively to obtain a first Gaussian probability density distribution distance index and a second Gaussian probability density distribution distance index; the weighting correction unit is used for weighting the power time sequence feature vector and the temperature time sequence feature vector by taking the first Gaussian probability density distribution distance index and the second Gaussian probability density distribution distance index as weights so as to obtain a weighted power time sequence feature vector and a weighted temperature time sequence feature vector; and a collaborative fusion unit, configured to calculate a collaborative correlation matrix between the weighted power timing characteristic vector and the weighted temperature timing characteristic vector.
In the above cooling device for stem cell transportation, the combined gaussian density map construction unit is further configured to: constructing a joint gaussian density map of the power timing feature vector and the temperature timing feature vector in the following formula; wherein, the formula is:
wherein,,representing a per-position mean vector between the power timing feature vector and the temperature timing feature vector, and +.>A covariance matrix formed by position variances representing the power timing eigenvector and the temperature timing eigenvector,>representing the joint gaussian density map.
In the above cooling device for stem cell transportation, the gaussian probability density distribution distance index calculating unit is further configured to: calculating Gaussian probability density distribution distance indexes of the power time sequence feature vector and the temperature time sequence feature vector relative to the joint Gaussian density map respectively according to the following formula to obtain a first Gaussian probability density distribution distance index and a second Gaussian probability density distribution distance index; wherein, the formula is:
wherein,,and->The power timing feature vector and the temperature timing feature vector, +. >And->Is the mean vector and covariance matrix of the joint Gaussian density map, i.e. +.>A mean value vector representing the power timing characteristic vector and the temperature timing characteristic vector, and +.>A covariance matrix formed by position variances and representing the power time sequence characteristic vector and the temperature time sequence characteristic vector, wherein the vectors are column vectors,>representing difference in position->Representing matrix multiplication +.>Representing an exponential function operation with e as the base, < ->And->The first gaussian probability density distribution distance index and the second gaussian probability density distribution distance index are respectively.
In the above cooling device for stem cell transportation, the synergistic fusion unit is further configured to: calculating the collaborative correlation matrix between the weighted power timing feature vector and the weighted temperature timing feature vector by the formula; wherein, the formula is:
=/>
wherein the method comprises the steps ofA transpose vector representing the weighted power timing feature vector,>representing the weighted temperature timing feature vector, < >>Representing the collaborative correlation matrix,/->Representing matrix multiplication.
In the above cooling device for stem cell transportation, the regulation strategy generation module includes: the unfolding unit is used for unfolding the collaborative correlation matrix into a classification characteristic vector according to a row vector or a column vector; the probability unit is used for inputting the classification feature vector into a Softmax classification function of the classifier to obtain a probability value of the classification feature vector belonging to each classification label; and the classification result generation unit is used for determining the classification label corresponding to the maximum probability value as the classification result.
According to another aspect of the present application, there is also provided a method of cooling a device for stem cell transportation, comprising:
acquiring power values of a cooling device at a plurality of preset time points in a preset time period and temperature values of stem cells at the plurality of preset time points acquired by a temperature sensor;
arranging the power values of the cooling devices at the preset time points and the temperature values of the stem cells at the preset time points into a power input vector and a temperature input vector according to the time dimension respectively;
respectively passing the power input vector and the temperature input vector through a multi-scale neighborhood feature extraction module to obtain a power time sequence feature vector and a temperature time sequence feature vector;
fusing the power time sequence feature vector and the temperature time sequence feature vector based on a Gaussian density chart to obtain a collaborative correlation matrix; and
and the collaborative correlation matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the power value of the cooling device at the current time point should be increased or decreased.
Compared with the prior art, the cooling device and the cooling method for stem cell transportation, which are provided by the application, adopt an artificial intelligent detection technology based on deep learning, so as to excavate time sequence change mode characteristics of the temperature value of the stem cells and the power value of the cooling device through the multi-scale neighborhood characteristic extraction module, extract time sequence change cooperative characteristics between the temperature value and the power value of the cooling device, and conduct classification processing. Like this, the time sequence change cooperation condition between the temperature value of stem cell and the power value of heat sink carries out self-adaptation control to the power value of heat sink, and then makes the temperature of heat sink can adapt to the real-time temperature change condition of current stem cell under the power drive of current heat sink.
Drawings
The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is an application scenario diagram of a cooling device for stem cell transportation according to an embodiment of the present application.
Fig. 2 is a block diagram of a cooling device for stem cell transport according to an embodiment of the present application.
Fig. 3 is a schematic diagram of a cooling device for stem cell transportation according to an embodiment of the present application.
Fig. 4 is a block diagram of a fusion module in a cooling device for stem cell transport according to an embodiment of the present application.
Fig. 5 is a flow chart of a method of a cooling device for stem cell transportation according to an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Summary of the application
Accordingly, in the technical scheme of the application, self-adaptive control is expected to be performed on the power value of the cooling device based on the time sequence variation coordination condition between the temperature value of the stem cells and the power value of the cooling device, and then the temperature of the cooling device can be adapted to the real-time temperature variation condition of the current stem cells under the power driving of the current cooling device. However, since the temperature of the stem cells is in different change states in each time period, the power value of the cooling device is dynamically changed due to the adjustment of the temperature control strategy, so that a complex nonlinear mapping relationship exists between the temperature change of the stem cells and the power value of the cooling device.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
Deep learning and development of the neural network provide new solutions and schemes for excavating complex mapping relations between temperature changes of stem cells and power values of cooling devices. Those of ordinary skill in the art will appreciate that deep learning based deep neural network models can be tuned by appropriate training strategies, such as by gradient descent back-propagation algorithms, to enable complex nonlinear correlations between things to be simulated, which is obviously suitable for simulating and establishing complex mappings between temperature changes of stem cells and power values of cooling devices.
Specifically, in the technical solution of the present application, first, and acquiring power values of the cooling device at a plurality of preset time points in a preset time period and temperature values of the stem cells at the preset time points acquired by the temperature sensor. The power value of the cooling device can be obtained by a power sensor arranged on the cooling device.
And then, arranging the power values of the cooling devices at the preset time points and the temperature values of the stem cells at the preset time points into a power input vector and a temperature input vector according to the time dimension respectively. That is, the time-series discrete distribution of the power values and the time-series discrete distribution of the temperature values are structured as the structured power input vector and the temperature input vector.
It should be understood that, since the power value of the cooling device and the temperature value of the stem cells may present different mode states in different time periods within the predetermined time period, in order to accurately extract the dynamic change implicit characteristics of the power value of the cooling device and the temperature value of the stem cells, the power input vector and the temperature input vector are further respectively passed through a multi-scale neighborhood feature extraction module to obtain a power time sequence feature vector and a temperature time sequence feature vector. Here, the multi-scale neighborhood feature extraction module includes: the system comprises a first convolution layer, a second convolution layer and a multi-scale fusion layer connected with the first convolution layer and the second convolution layer, wherein the first convolution layer and the second convolution layer are parallel to each other, and one-dimensional convolution kernels with different scales are respectively used for the first convolution layer and the second convolution layer. In the technical scheme of the application, the power input vector and the temperature input vector are respectively subjected to one-dimensional convolution coding by using the convolution layers (namely the first convolution layer and the second convolution layer) of the multi-scale neighborhood feature extraction module, wherein the one-dimensional convolution kernels are provided with different scales, and then the obtained feature vectors corresponding to the two one-dimensional convolution kernels with different scales are cascaded to respectively obtain the power time sequence feature vector and the temperature time sequence feature vector. In particular, the multi-scale neighborhood feature extraction module can extract multi-scale neighborhood associated features of the power value of the cooling device and the temperature value of the stem cells under different time spans so as to represent multi-scale neighborhood dynamic change feature information of the power value of the cooling device and the temperature value of the stem cells in a time dimension, meanwhile, the output features comprise the smoothed features, the original input features are saved so as to avoid information loss, and further the accuracy of subsequent classification is improved.
In order to mine the mapping relation between the power time sequence feature vector and the temperature time sequence feature vector, the power time sequence feature vector and the temperature time sequence feature vector are expected to be fused to map time sequence dynamic change mode features expressed by the temperature time sequence feature vector and related to the temperature of stem cells into the power time sequence feature vector, so that a cooperative correlation matrix is obtained. The collaborative correlation matrix contains time-series correlation characteristic information about temperature changes of stem cells and power changes of the cooling device.
In particular, in the technical solution of the present application, considering that the power timing feature vector and the temperature timing feature vector correspond to one feature distribution manifold in a high-dimensional feature space, and these feature distribution manifolds are due to their irregular shapes and scattering positions, if the power timing feature vector and the temperature timing feature vector are simply cascaded, it would be quite simple to stack these feature distribution manifolds according to the original positions and shapes, so that the boundaries of the newly obtained feature distribution manifolds become very irregular and complex.
Based on this, the applicant of the present application considered that gaussian density maps are widely used in deep learning for a priori based estimation of the objective posterior and can therefore be used to correct the data distribution, thus achieving the above objective. Specifically, in the technical scheme of the application, the power time sequence feature vector and the temperature time sequence feature vector are fused based on a Gaussian density chart to obtain a collaborative correlation matrix. Specifically, firstly, constructing a fused Gaussian density map of the power time sequence feature vector and the temperature time sequence feature vector, wherein the mean value vector of the fused Gaussian density map is a per-position mean value vector between the power time sequence feature vector and the temperature time sequence feature vector, and the value of each position in a covariance matrix of the fused Gaussian density map is a variance between feature values of corresponding positions between the power time sequence feature vector and the temperature time sequence feature vector. And further, performing Gaussian discretization on the Gaussian distribution of each position in the fused Gaussian density map to obtain a collaborative correlation matrix.
After the collaborative correlation matrix is obtained, the collaborative correlation matrix is passed through a classifier to obtain a classification result, and the power value of the classification result for the cooling device at the current time point is increased or decreased. That is, in the technical solution of the present application, the labels of the classifier include that the power value of the cooling device at the current time point should be increased (first label), and that the power value of the cooling device at the current time point should be decreased (second label), wherein the classifier determines to which classification label the classification feature vector belongs through a soft maximum function. It should be understood that, in the technical scheme of the present application, the classification label of the classifier is a power value control policy label of the cooling device, so after the classification result is obtained, the power value of the cooling device can be adaptively adjusted based on the classification result, and then the temperature of the cooling device can be adapted to the real-time temperature change condition of the current stem cells under the power driving of the current cooling device.
Here, when the power time sequence feature vector and the temperature time sequence feature vector are fused based on the gaussian density map to obtain the collaborative correlation matrix, the problem that the consistency and the correlation are poor in the fusion target dimension of the gaussian density map is caused by the fact that the correspondence between source data cannot be completely consistent along the time sequence although the power time sequence feature vector and the temperature time sequence feature vector both follow the multi-scale time sequence neighborhood distribution is considered, so that the fusion effect of the collaborative correlation matrix obtained based on the gaussian density map is affected, and the accuracy of the classification result obtained by the collaborative correlation matrix through the classifier is reduced.
Therefore, when calculating the joint gaussian density map of the power timing feature vector and the temperature timing feature vector, a gaussian probability density distribution distance index of the power timing feature vector and the temperature timing feature vector and the joint gaussian density map is further calculated, expressed as:
wherein,,and->The power timing characteristic vector and the temperature timing characteristic vector are respectively>And->Is the mean vector and covariance matrix of the joint Gaussian density map, i.e. +.>A mean value vector representing the power timing characteristic vector and the temperature timing characteristic vector, and +.>And the covariance matrix formed by the position variances of the power time sequence feature vector and the temperature time sequence feature vector is represented, wherein the vectors are all in column vector form.
Therefore, by calculating the Gaussian probability density distribution distance indexes of the power time sequence feature vector and the temperature time sequence feature vector and the corresponding combined Gaussian density map respectively, the feature distribution distance of the feature distribution of the target feature vector relative to the feature distribution distance of the combined Gaussian probability density distribution can be represented, and by weighting the power time sequence feature vector and the temperature time sequence feature vector respectively, the compatibility of the probability density combined distribution relative migration of the target feature vector to the Gaussian probability density on the target domain can be improved, so that the consistency and the correlation of the Gaussian probability density distribution on the fusion target dimension of the Gaussian density map are improved, the fusion effect of the collaborative feature matrix is improved, and the accuracy of the classification result obtained by the collaborative correlation matrix through the classifier is improved.
Fig. 1 is an application scenario diagram of a cooling device for stem cell transportation according to an embodiment of the present application. As shown in fig. 1, in this application scenario, first, power values of a cooling device (e.g., D as illustrated in fig. 1) at a plurality of predetermined time points within a predetermined period of time acquired by a power sensor (e.g., se1 as illustrated in fig. 1) and temperature values of stem cells (e.g., C as illustrated in fig. 1) at the plurality of predetermined time points acquired by a temperature sensor (e.g., se2 as illustrated in fig. 1) are acquired. Further, the power values of the cooling device at the plurality of predetermined time points and the temperature values of the stem cells at the plurality of predetermined time points are input into a data processor (e.g., P as illustrated in fig. 1) of the cooling device for stem cell transportation, wherein the data processor is capable of processing the power values of the cooling device at the plurality of predetermined time points and the temperature values of the stem cells at the plurality of predetermined time points based on a predetermined algorithm to obtain a classification result for indicating whether the power value of the cooling device at the current time point should be increased or decreased.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Exemplary System
Fig. 2 is a block diagram of a cooling device for stem cell transport according to an embodiment of the present application. As shown in fig. 2, a cooling device 100 for stem cell transportation according to an embodiment of the present application includes: the monitoring module 110 is configured to obtain power values of the cooling device at a plurality of predetermined time points within a predetermined time period and temperature values of the stem cells at the plurality of predetermined time points acquired by the temperature sensor; the data structuring module 120 is configured to arrange the power values of the cooling devices at the plurality of predetermined time points and the temperature values of the stem cells at the plurality of predetermined time points into a power input vector and a temperature input vector according to a time dimension, respectively; the time sequence feature extraction module 130 is configured to pass the power input vector and the temperature input vector through a multi-scale neighborhood feature extraction module to obtain a power time sequence feature vector and a temperature time sequence feature vector; a fusion module 140, configured to fuse the power timing feature vector and the temperature timing feature vector based on a gaussian density map to obtain a collaborative correlation matrix; and a regulation and control strategy generation module 150, configured to pass the collaborative correlation matrix through a classifier to obtain a classification result, where the classification result is used to indicate that the power value of the cooling device at the current time point should be increased or decreased.
Fig. 3 is a schematic diagram of a cooling device for stem cell transportation according to an embodiment of the present application. As shown in fig. 3, first, power values of a cooling device at a plurality of predetermined time points within a predetermined period of time and temperature values of stem cells at the plurality of predetermined time points acquired by a temperature sensor are acquired; then, arranging the power values of the cooling devices at the preset time points and the temperature values of the stem cells at the preset time points into a power input vector and a temperature input vector according to the time dimension respectively; then, the power input vector and the temperature input vector are respectively passed through a multi-scale neighborhood feature extraction module to obtain a power time sequence feature vector and a temperature time sequence feature vector; then, fusing the power time sequence feature vector and the temperature time sequence feature vector based on a Gaussian density map to obtain a collaborative correlation matrix; and finally, the collaborative correlation matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the power value of the cooling device at the current time point should be increased or decreased.
Accordingly, in the technical scheme of the application, self-adaptive control is expected to be performed on the power value of the cooling device based on the time sequence variation coordination condition between the temperature value of the stem cells and the power value of the cooling device, and then the temperature of the cooling device can be adapted to the real-time temperature variation condition of the current stem cells under the power driving of the current cooling device. However, since the temperature of the stem cells is in different change states in each time period, the power value of the cooling device is dynamically changed due to the adjustment of the temperature control strategy, so that a complex nonlinear mapping relationship exists between the temperature change of the stem cells and the power value of the cooling device.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
Deep learning and development of the neural network provide new solutions and schemes for excavating complex mapping relations between temperature changes of stem cells and power values of cooling devices. Those of ordinary skill in the art will appreciate that deep learning based deep neural network models can be tuned by appropriate training strategies, such as by gradient descent back-propagation algorithms, to enable complex nonlinear correlations between things to be simulated, which is obviously suitable for simulating and establishing complex mappings between temperature changes of stem cells and power values of cooling devices.
In the cooling device 100 for stem cell transportation, the monitoring module 110 is configured to obtain power values of the cooling device at a plurality of predetermined time points within a predetermined period of time and temperature values of the stem cells at the plurality of predetermined time points acquired by the temperature sensor. The power value of the cooling device can be obtained by a power sensor arranged on the cooling device.
In the cooling device 100 for stem cell transportation, the data structuring module 120 is configured to arrange the power values of the cooling device at the plurality of predetermined time points and the temperature values of the stem cells at the plurality of predetermined time points into a power input vector and a temperature input vector according to a time dimension, respectively. That is, the time-series discrete distribution of the power values and the time-series discrete distribution of the temperature values are structured as the structured power input vector and the temperature input vector.
In the cooling device 100 for stem cell transportation, the time sequence feature extraction module 130 is configured to pass the power input vector and the temperature input vector through the multi-scale neighborhood feature extraction module to obtain a power time sequence feature vector and a temperature time sequence feature vector. It should be understood that, since the power value of the cooling device and the temperature value of the stem cells may present different mode states in different time periods within the predetermined time period, in order to accurately extract the dynamic change implicit characteristics of the power value of the cooling device and the temperature value of the stem cells, the power input vector and the temperature input vector are further respectively passed through a multi-scale neighborhood feature extraction module to obtain a power time sequence feature vector and a temperature time sequence feature vector.
Here, the multi-scale neighborhood feature extraction module includes: the system comprises a first convolution layer, a second convolution layer and a multi-scale fusion layer connected with the first convolution layer and the second convolution layer, wherein the first convolution layer and the second convolution layer are parallel to each other, and one-dimensional convolution kernels with different scales are respectively used for the first convolution layer and the second convolution layer. In the technical scheme of the application, the power input vector and the temperature input vector are respectively subjected to one-dimensional convolution coding by using the convolution layers (namely the first convolution layer and the second convolution layer) of the multi-scale neighborhood feature extraction module, wherein the one-dimensional convolution kernels are provided with different scales, and then the obtained feature vectors corresponding to the two one-dimensional convolution kernels with different scales are cascaded to respectively obtain the power time sequence feature vector and the temperature time sequence feature vector. In particular, the multi-scale neighborhood feature extraction module can extract multi-scale neighborhood associated features of the power value of the cooling device and the temperature value of the stem cells under different time spans so as to represent multi-scale neighborhood dynamic change feature information of the power value of the cooling device and the temperature value of the stem cells in a time dimension, meanwhile, the output features comprise the smoothed features, the original input features are saved so as to avoid information loss, and further the accuracy of subsequent classification is improved.
Specifically, in the embodiment of the present application, the timing feature extraction module 130 is further configured to: using a first convolution layer of the multi-scale neighborhood feature extraction module to perform one-dimensional convolution coding on the power input vector and the temperature input vector respectively according to the following formula to obtain a first-scale power feature vector and a first-scale temperature feature vector; wherein, the formula is:
wherein a is the width of the first convolution kernel in the x direction,For the first convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, w is the size of the first convolution kernel, X represents the power input vector or the temperature input vector, +.>Representing one-dimensional convolutional encoding of the power input vector or the temperature input vector; performing one-dimensional convolution coding on the power input vector and the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a second-scale power feature vector and a second-scale temperatureA degree feature vector; wherein, the formula is:
wherein b is the width of the second convolution kernel in the x direction,For a second convolution kernel parameter vector, +. >For a local vector matrix operating with a convolution kernel function, m is the size of the second convolution kernel, X represents the power input vector or the temperature input vector, +.>Representing one-dimensional convolutional encoding of the power input vector or the temperature input vector; and cascading the first scale power feature vector and the second scale power feature vector by using a multi-scale fusion layer of the multi-scale neighborhood feature extraction module to obtain the power time sequence feature vector, and cascading the first scale temperature feature vector and the second scale temperature feature vector to obtain the temperature time sequence feature vector.
In the cooling device 100 for stem cell transportation, the fusion module 140 is configured to fuse the power timing feature vector and the temperature timing feature vector based on a gaussian density map to obtain a collaborative correlation matrix. In order to mine the mapping relation between the power time sequence feature vector and the temperature time sequence feature vector, the power time sequence feature vector and the temperature time sequence feature vector are expected to be fused to map time sequence dynamic change mode features expressed by the temperature time sequence feature vector and related to the temperature of stem cells into the power time sequence feature vector, so that a cooperative correlation matrix is obtained. The collaborative correlation matrix contains time-series correlation characteristic information about temperature changes of stem cells and power changes of the cooling device.
In particular, in the technical solution of the present application, considering that the power timing feature vector and the temperature timing feature vector correspond to one feature distribution manifold in a high-dimensional feature space, and these feature distribution manifolds are due to their irregular shapes and scattering positions, if the power timing feature vector and the temperature timing feature vector are simply cascaded, it would be quite simple to stack these feature distribution manifolds according to the original positions and shapes, so that the boundaries of the newly obtained feature distribution manifolds become very irregular and complex.
Based on this, the applicant of the present application considered that gaussian density maps are widely used in deep learning for a priori based estimation of the objective posterior and can therefore be used to correct the data distribution, thus achieving the above objective. Specifically, in the technical scheme of the application, the power time sequence feature vector and the temperature time sequence feature vector are fused based on a Gaussian density chart to obtain a collaborative correlation matrix. Specifically, firstly, constructing a fused Gaussian density map of the power time sequence feature vector and the temperature time sequence feature vector, wherein the mean value vector of the fused Gaussian density map is a per-position mean value vector between the power time sequence feature vector and the temperature time sequence feature vector, and the value of each position in a covariance matrix of the fused Gaussian density map is a variance between feature values of corresponding positions between the power time sequence feature vector and the temperature time sequence feature vector. And further, performing Gaussian discretization on the Gaussian distribution of each position in the fused Gaussian density map to obtain a collaborative correlation matrix.
Here, when the power time sequence feature vector and the temperature time sequence feature vector are fused based on the gaussian density map to obtain the collaborative correlation matrix, the problem that the consistency and the correlation are poor in the fusion target dimension of the gaussian density map is caused by the fact that the correspondence between source data cannot be completely consistent along the time sequence although the power time sequence feature vector and the temperature time sequence feature vector both follow the multi-scale time sequence neighborhood distribution is considered, so that the fusion effect of the collaborative correlation matrix obtained based on the gaussian density map is affected, and the accuracy of the classification result obtained by the collaborative correlation matrix through the classifier is reduced.
Therefore, when calculating the joint gaussian density map of the power timing feature vector and the temperature timing feature vector, a gaussian probability density distribution distance index of the power timing feature vector and the temperature timing feature vector and the joint gaussian density map is further calculated, expressed as:
wherein,,and->The power timing feature vector and the temperature timing feature vector, +.>And->Is the mean vector and covariance matrix of the joint Gaussian density map, i.e. +. >A mean value vector representing the power timing characteristic vector and the temperature timing characteristic vector, and +.>A covariance matrix formed by position variances and representing the power time sequence characteristic vector and the temperature time sequence characteristic vector, wherein the vectors are column vectors,>representing difference in position->Representing matrix multiplication +.>Representing an exponential function operation with e as the base, < ->And->The first gaussian probability density distribution distance index and the second gaussian probability density distribution distance index are respectively.
Therefore, by calculating the Gaussian probability density distribution distance indexes of the power time sequence feature vector and the temperature time sequence feature vector and the corresponding combined Gaussian density map respectively, the feature distribution distance of the feature distribution of the target feature vector relative to the feature distribution distance of the combined Gaussian probability density distribution can be represented, and by weighting the power time sequence feature vector and the temperature time sequence feature vector respectively, the compatibility of the probability density combined distribution relative migration of the target feature vector to the Gaussian probability density on the target domain can be improved, so that the consistency and the correlation of the Gaussian probability density distribution on the fusion target dimension of the Gaussian density map are improved, the fusion effect of the collaborative feature matrix is improved, and the accuracy of the classification result obtained by the collaborative correlation matrix through the classifier is improved.
Fig. 4 is a block diagram of a fusion module in a cooling device for stem cell transport according to an embodiment of the present application. As shown in fig. 4, the fusion module 140 includes: a joint gaussian density map construction unit 141, configured to construct a joint gaussian density map of the power timing feature vector and the temperature timing feature vector, where a mean vector of the joint gaussian density map is a per-position mean vector between the power timing feature vector and the temperature timing feature vector, and a value of each position in a covariance matrix of the joint gaussian density map is a per-position variance of the power timing feature vector and the temperature timing feature vector; a gaussian probability density distribution distance index calculation unit 142, configured to calculate gaussian probability density distribution distance indexes of the power timing feature vector and the temperature timing feature vector with respect to the joint gaussian density map, respectively, so as to obtain a first gaussian probability density distribution distance index and a second gaussian probability density distribution distance index; a weighting correction unit 143, configured to weight the power timing feature vector and the temperature timing feature vector with the first gaussian probability density distribution distance index and the second gaussian probability density distribution distance index as weights to obtain a weighted power timing feature vector and a weighted temperature timing feature vector; and a collaborative fusion unit 144, configured to calculate a collaborative correlation matrix between the weighted power timing feature vector and the weighted temperature timing feature vector.
Specifically, in the embodiment of the application, a joint gaussian density map of the power timing feature vector and the temperature timing feature vector is constructed with the following formula; wherein, the formula is:
wherein,,representing a per-position mean vector between the power timing feature vector and the temperature timing feature vector, and +.>A covariance matrix formed by position variances representing the power timing eigenvector and the temperature timing eigenvector,>representing the joint gaussian density map.
Specifically, in the embodiment of the present application, the collaborative correlation matrix between the weighted power timing eigenvector and the weighted temperature timing eigenvector is calculated with the following formula; wherein, the formula is:
=/>
wherein the method comprises the steps ofA transpose vector representing the weighted power timing feature vector,>representing the weighted temperature timing feature vector, < >>Representing the collaborative correlation matrix,/->Representing matrix multiplication.
In the cooling device 100 for stem cell transportation, the regulation policy generating module 150 is configured to pass the collaborative correlation matrix through a classifier to obtain a classification result, where the classification result is used to indicate that the power value of the cooling device at the current time point should be increased or decreased. That is, in the technical solution of the present application, the labels of the classifier include that the power value of the cooling device at the current time point should be increased (first label), and that the power value of the cooling device at the current time point should be decreased (second label), wherein the classifier determines to which classification label the classification feature vector belongs through a soft maximum function. It should be understood that, in the technical scheme of the present application, the classification label of the classifier is a power value control policy label of the cooling device, so after the classification result is obtained, the power value of the cooling device can be adaptively adjusted based on the classification result, and then the temperature of the cooling device can be adapted to the real-time temperature change condition of the current stem cells under the power driving of the current cooling device.
Specifically, in the embodiment of the present application, the encoding process of the regulation policy generating module 150 includes: firstly, expanding the collaborative correlation matrix into a classification characteristic vector according to a row vector or a column vector through an expanding unit; then, inputting the classification feature vector into a Softmax classification function of the classifier through a probability unit to obtain a probability value of the classification feature vector belonging to each classification label; then, a classification label corresponding to the maximum probability value is determined as the classification result by a classification result generation unit.
In summary, the cooling device 100 for stem cell transportation according to the embodiment of the present application is illustrated, which adopts an artificial intelligence detection technology based on deep learning to mine the time sequence variation pattern features of the temperature value of the stem cells and the power value of the cooling device through a multi-scale neighborhood feature extraction module, and extract the time sequence variation cooperative feature between the two, so as to perform classification processing. Like this, the time sequence change cooperation condition between the temperature value of stem cell and the power value of heat sink carries out self-adaptation control to the power value of heat sink, and then makes the temperature of heat sink can adapt to the real-time temperature change condition of current stem cell under the power drive of current heat sink.
Exemplary method
Fig. 5 is a flow chart of a method of a cooling device for stem cell transportation according to an embodiment of the present application. As shown in fig. 5, a method of a cooling device for stem cell transportation according to an embodiment of the present application includes: s110, acquiring power values of the cooling device at a plurality of preset time points in a preset time period and temperature values of stem cells at the plurality of preset time points acquired by a temperature sensor; s120, arranging the power values of the cooling devices at a plurality of preset time points and the temperature values of the stem cells at a plurality of preset time points into a power input vector and a temperature input vector according to a time dimension respectively; s130, respectively passing the power input vector and the temperature input vector through a multi-scale neighborhood feature extraction module to obtain a power time sequence feature vector and a temperature time sequence feature vector; s140, fusing the power time sequence feature vector and the temperature time sequence feature vector based on a Gaussian density chart to obtain a collaborative correlation matrix; and S150, the collaborative correlation matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the power value of the cooling device at the current time point should be increased or decreased.
Here, it will be understood by those skilled in the art that various steps and operations in the above-described method of the cooling device for stem cell transportation have been described in detail in the above description of the cooling device for stem cell transportation 100 with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not intended to be limited to the details disclosed herein as such.
The block diagrams of the devices, apparatuses, devices, systems referred to in this application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent to the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (10)
1. A cooling device for stem cell transportation, comprising:
the monitoring module is used for acquiring power values of the cooling device at a plurality of preset time points in a preset time period and temperature values of the stem cells at the preset time points acquired by the temperature sensor;
The data structuring module is used for respectively arranging the power values of the cooling devices at the plurality of preset time points and the temperature values of the stem cells at the plurality of preset time points into a power input vector and a temperature input vector according to the time dimension;
the time sequence feature extraction module is used for respectively passing the power input vector and the temperature input vector through the multi-scale neighborhood feature extraction module to obtain a power time sequence feature vector and a temperature time sequence feature vector;
the fusion module is used for fusing the power time sequence feature vector and the temperature time sequence feature vector based on a Gaussian density chart to obtain a collaborative correlation matrix; and
and the regulation and control strategy generation module is used for enabling the collaborative correlation matrix to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the power value of the cooling device at the current time point should be increased or decreased.
2. The cooling device for stem cell transportation of claim 1, wherein the multi-scale neighborhood feature extraction module comprises: the system comprises a first convolution layer, a second convolution layer and a multi-scale fusion layer connected with the first convolution layer and the second convolution layer, wherein the first convolution layer and the second convolution layer are parallel to each other, and one-dimensional convolution kernels with different scales are respectively used for the first convolution layer and the second convolution layer.
3. The cooling device for stem cell transportation of claim 2, wherein the timing feature extraction module is further configured to:
using a first convolution layer of the multi-scale neighborhood feature extraction module to perform one-dimensional convolution coding on the power input vector and the temperature input vector respectively according to the following formula to obtain a first-scale power feature vector and a first-scale temperature feature vector;
wherein, the formula is:
wherein a is the width of the first convolution kernel in the x direction,For the first convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, w is the size of the first convolution kernel, X represents the power input vector or the temperature input vector, +.>Representing one-dimensional convolutional encoding of the power input vector or the temperature input vector;
using a second convolution layer of the multi-scale neighborhood feature extraction module to perform one-dimensional convolution coding on the power input vector and the temperature input vector respectively according to the following formula to obtain a second-scale power feature vector and a second-scale temperature feature vector;
wherein, the formula is:
wherein b is the width of the second convolution kernel in the x direction, For a second convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, m is the size of the second convolution kernel, X represents the power input vector or the temperature input vector, +.>Representing one-dimensional convolutional encoding of the power input vector or the temperature input vector; and
and cascading the first scale power feature vector and the second scale power feature vector by using a multi-scale fusion layer of the multi-scale neighborhood feature extraction module to obtain the power time sequence feature vector, and cascading the first scale temperature feature vector and the second scale temperature feature vector to obtain the temperature time sequence feature vector.
4. A cooling device for stem cell transportation according to claim 3, wherein the fusion module comprises:
a joint gaussian density map construction unit, configured to construct a joint gaussian density map of the power timing feature vector and the temperature timing feature vector, where a mean vector of the joint gaussian density map is a per-position mean vector between the power timing feature vector and the temperature timing feature vector, and a value of each position in a covariance matrix of the joint gaussian density map is a per-position variance of the power timing feature vector and the temperature timing feature vector;
The Gaussian probability density distribution distance index calculation unit is used for calculating the Gaussian probability density distribution distance indexes of the power time sequence feature vector and the temperature time sequence feature vector relative to the joint Gaussian density map respectively to obtain a first Gaussian probability density distribution distance index and a second Gaussian probability density distribution distance index;
the weighting correction unit is used for weighting the power time sequence feature vector and the temperature time sequence feature vector by taking the first Gaussian probability density distribution distance index and the second Gaussian probability density distribution distance index as weights so as to obtain a weighted power time sequence feature vector and a weighted temperature time sequence feature vector; and
and the collaborative fusion unit is used for calculating a collaborative correlation matrix between the weighted power time sequence feature vector and the weighted temperature time sequence feature vector.
5. The cooling device for stem cell transportation of claim 4, wherein the combined gaussian density map construction unit is further configured to:
constructing a joint gaussian density map of the power timing feature vector and the temperature timing feature vector in the following formula;
wherein, the formula is:
Wherein,,representing a per-position mean vector between the power timing feature vector and the temperature timing feature vector, and +.>Position-wise variance structure representing the power timing feature vector and the temperature timing feature vectorCovariance matrix formed->Representing the joint gaussian density map.
6. The cooling device for stem cell transportation according to claim 5, wherein the gaussian probability density distribution distance index calculation unit is further configured to:
calculating Gaussian probability density distribution distance indexes of the power time sequence feature vector and the temperature time sequence feature vector relative to the joint Gaussian density map respectively according to the following formula to obtain a first Gaussian probability density distribution distance index and a second Gaussian probability density distribution distance index;
wherein, the formula is:
wherein,,and->The power timing feature vector and the temperature timing feature vector, +.>And->Is the mean vector and covariance matrix of the joint Gaussian density map, i.e. +.>A mean value vector representing the power timing characteristic vector and the temperature timing characteristic vector, and +.>A covariance matrix formed by position variances and representing the power time sequence characteristic vector and the temperature time sequence characteristic vector, wherein the vectors are column vectors, >Representing difference in position->Representing a matrix multiplication of the number of bits,representing an exponential function operation with e as the base, < ->And->The first gaussian probability density distribution distance index and the second gaussian probability density distribution distance index are respectively.
7. The cooling device for stem cell transportation of claim 6, wherein the co-fusion unit is further configured to:
calculating the collaborative correlation matrix between the weighted power timing feature vector and the weighted temperature timing feature vector by the formula;
wherein, the formula is:
=/>wherein->A transpose vector representing the weighted power timing feature vector,>representing the weighted temperature timing feature vector, < >>Representing the collaborative correlation matrix,/->Representing matrix multiplication.
8. The cooling device for stem cell transportation of claim 7, wherein the regulatory strategy generation module comprises:
the unfolding unit is used for unfolding the collaborative correlation matrix into a classification characteristic vector according to a row vector or a column vector;
the probability unit is used for inputting the classification feature vector into a Softmax classification function of the classifier to obtain a probability value of the classification feature vector belonging to each classification label; and
And the classification result generation unit is used for determining the classification label corresponding to the maximum probability value as the classification result.
9. A method of cooling a device for stem cell transport, comprising:
acquiring power values of a cooling device at a plurality of preset time points in a preset time period and temperature values of stem cells at the plurality of preset time points acquired by a temperature sensor;
arranging the power values of the cooling devices at the preset time points and the temperature values of the stem cells at the preset time points into a power input vector and a temperature input vector according to the time dimension respectively;
respectively passing the power input vector and the temperature input vector through a multi-scale neighborhood feature extraction module to obtain a power time sequence feature vector and a temperature time sequence feature vector;
fusing the power time sequence feature vector and the temperature time sequence feature vector based on a Gaussian density chart to obtain a collaborative correlation matrix; and
and the collaborative correlation matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the power value of the cooling device at the current time point should be increased or decreased.
10. The method of claim 9, wherein fusing the power timing feature vector and the temperature timing feature vector based on a gaussian density map to obtain a collaborative correlation matrix comprises:
Constructing a joint Gaussian density map of the power time sequence feature vector and the temperature time sequence feature vector, wherein the mean vector of the joint Gaussian density map is a per-position mean vector between the power time sequence feature vector and the temperature time sequence feature vector, and the value of each position in a covariance matrix of the joint Gaussian density map is a per-position variance of the power time sequence feature vector and the temperature time sequence feature vector;
respectively calculating Gaussian probability density distribution distance indexes of the power time sequence feature vector and the temperature time sequence feature vector relative to the joint Gaussian density map to obtain a first Gaussian probability density distribution distance index and a second Gaussian probability density distribution distance index;
weighting the power time sequence feature vector and the temperature time sequence feature vector by taking the first Gaussian probability density distribution distance index and the second Gaussian probability density distribution distance index as weights to obtain a weighted power time sequence feature vector and a weighted temperature time sequence feature vector; and
and calculating a collaborative correlation matrix between the weighted power time sequence feature vector and the weighted temperature time sequence feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310202516.3A CN116451145A (en) | 2023-03-06 | 2023-03-06 | Cooling device and method for stem cell transportation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310202516.3A CN116451145A (en) | 2023-03-06 | 2023-03-06 | Cooling device and method for stem cell transportation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116451145A true CN116451145A (en) | 2023-07-18 |
Family
ID=87119123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310202516.3A Withdrawn CN116451145A (en) | 2023-03-06 | 2023-03-06 | Cooling device and method for stem cell transportation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116451145A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116678506A (en) * | 2023-08-02 | 2023-09-01 | 国检测试控股集团南京国材检测有限公司 | Wireless transmission heat loss detection device |
| CN116680557A (en) * | 2023-08-03 | 2023-09-01 | 山东省地质矿产勘查开发局第八地质大队(山东省第八地质矿产勘查院) | Real-time monitoring system and method for coal bed gas drilling engineering |
| CN117393921A (en) * | 2023-10-17 | 2024-01-12 | 浙江博时新能源技术有限公司 | Distributed energy storage device |
-
2023
- 2023-03-06 CN CN202310202516.3A patent/CN116451145A/en not_active Withdrawn
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116678506A (en) * | 2023-08-02 | 2023-09-01 | 国检测试控股集团南京国材检测有限公司 | Wireless transmission heat loss detection device |
| CN116678506B (en) * | 2023-08-02 | 2023-10-10 | 国检测试控股集团南京国材检测有限公司 | Wireless transmission heat loss detection device |
| CN116680557A (en) * | 2023-08-03 | 2023-09-01 | 山东省地质矿产勘查开发局第八地质大队(山东省第八地质矿产勘查院) | Real-time monitoring system and method for coal bed gas drilling engineering |
| CN116680557B (en) * | 2023-08-03 | 2023-10-27 | 山东省地质矿产勘查开发局第八地质大队(山东省第八地质矿产勘查院) | Real-time monitoring system and method for coal bed gas drilling engineering |
| CN117393921A (en) * | 2023-10-17 | 2024-01-12 | 浙江博时新能源技术有限公司 | Distributed energy storage device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | Exploiting sample uncertainty for domain adaptive person re-identification | |
| CN116451145A (en) | Cooling device and method for stem cell transportation | |
| CN109639710B (en) | Network attack defense method based on countermeasure training | |
| Pal | Soft computing for feature analysis | |
| CN105447473A (en) | PCANet-CNN-based arbitrary attitude facial expression recognition method | |
| Cai et al. | Multi-AUV collaborative target recognition based on transfer-reinforcement learning | |
| CN111047054A (en) | Two-stage countermeasure knowledge migration-based countermeasure sample defense method | |
| Mikhaylenko et al. | Analysis of the predicting neural network person recognition system by picture image | |
| CN109657693B (en) | Classification method based on correlation entropy and transfer learning | |
| Yang et al. | Random subspace supervised descent method for regression problems in computer vision | |
| CN118134017A (en) | Method for predicting social network link by adopting impulse neural network | |
| CN109858543B (en) | Image memorability prediction method based on low-rank sparse representation and relationship inference | |
| Li et al. | Self-distillation with meta learning for knowledge graph completion | |
| Duan et al. | Clustering based on supervised learning of exemplar discriminative information | |
| Kang et al. | Unsupervised domain adaptation for 3D point clouds by searched transformations | |
| Gowgi et al. | Temporal self-organization: A reaction–diffusion framework for spatiotemporal memories | |
| Bao et al. | Contextual vision transformers for robust representation learning | |
| CN114462526A (en) | Classification model training method and device, computer equipment and storage medium | |
| Tian et al. | Multiscale and multilevel enhanced features for ship target recognition in complex environments | |
| Huang et al. | Training few-shot classification via the perspective of minibatch and pretraining | |
| Ma et al. | Multi-spatial information joint guidance evolutionary algorithm for dynamic multi-objective optimization with a changing number of objectives | |
| Lu et al. | A study on mobile customer churn based on learning from soft label proportions | |
| Huo et al. | An improved kernel correlation filter for complex scenes target tracking | |
| Zhong et al. | Topological structural analysis based on self-adaptive growing neural network for shape feature extraction | |
| CN116825217B (en) | Method for preparing high-purity phosphorus pentafluoride |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230718 |
|
| WW01 | Invention patent application withdrawn after publication |