CN111695614B - Dynamic monitoring sensor layout and multi-source information fusion method and system - Google Patents
Dynamic monitoring sensor layout and multi-source information fusion method and system Download PDFInfo
- Publication number
- CN111695614B CN111695614B CN202010470476.7A CN202010470476A CN111695614B CN 111695614 B CN111695614 B CN 111695614B CN 202010470476 A CN202010470476 A CN 202010470476A CN 111695614 B CN111695614 B CN 111695614B
- Authority
- CN
- China
- Prior art keywords
- data
- sensor
- fusion
- layout
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry
Abstract
The embodiment of the invention provides a method and a system for fusing sensor layout and multi-source information for dynamic monitoring. The method comprises the following steps: optimizing layout of the environmental sensor and the physiological sensor according to a preset sensor layout model; the sensor layout model is constructed based on a two-dimensional plan view and the relation between the positions of the environmental sensor and the physiological sensor; performing periodic information extraction data on the optimized environmental sensor and physiological sensor, and performing data fusion on the verified data by using a preset multi-source information fusion model to obtain a three-level dynamic evaluation decision; the multi-source information fusion model is obtained based on combination of homogenous sensor data fusion and heterogeneous sensor data fusion. The embodiment of the invention realizes reasonable layout of the sensors, and carries out three-level dynamic evaluation decision of breeding individuals, breeding groups and breeding groups on living animals by utilizing a multisource information fusion model constructed in advance.
Description
Technical Field
The invention relates to the technical field of cultivation and multisource information fusion, in particular to a method and a system for dynamically monitoring sensor layout and multisource information fusion.
Background
Many researchers now use multiple sensors to monitor and collect related data, and often place the related sensors on a subjective basis. However, the randomly placed sensors are not accurate enough when data monitoring and acquisition are performed, so that on one hand, the waste of resources is caused, and more sensors are needed; on the other hand, inaccuracy of data can be caused, and problems such as redundancy of acquired data can also cause difficulty in subsequent data processing.
The existing sensor related data monitoring and collecting methods have more or less problems, so how to provide a method for reasonably distributing the sensor and carrying out three-level dynamic evaluation decision on breeding individuals, breeding groups and breeding groups through multi-source information fusion becomes a problem to be solved.
Disclosure of Invention
It is an aim of embodiments of the present invention to provide a dynamically monitored sensor layout and multisource information fusion method and system that overcomes or at least partially addresses the above problems.
In order to solve the above technical problems, in one aspect, an embodiment of the present invention provides a method for dynamically monitoring sensor layout and multi-source information fusion, including:
optimizing layout of the environmental sensor and the physiological sensor according to a preset sensor layout model; the sensor layout model is constructed based on a two-dimensional plan view and the relation between the positions of the environmental sensor and the physiological sensor;
performing periodic information extraction data on the optimized environmental sensor and physiological sensor, and performing data fusion on the data passing verification by using a preset multi-source information fusion model to obtain a three-level dynamic evaluation decision; the multi-source information fusion model is obtained based on combination of homogenous sensor data fusion and heterogeneous sensor data fusion.
Further, before the optimizing layout of the environmental sensor and the physiological sensor according to the preset sensor layout model, the method further includes:
and performing dimension reduction on the three-dimensional space living environment and the three-dimensional geometric features of living animals to obtain the two-dimensional plan.
Further, the optimizing layout of the environmental sensor and the physiological sensor according to the preset sensor layout model specifically includes:
Performing preliminary matching on the position of the environment sensor, the position of the physiological sensor and the two-dimensional plan to obtain a matching set;
calculating to obtain the maximum monitoring ratio of the environmental sensor and the physiological sensor according to the matching set and the constraint variable;
and determining the optimized layout according to the maximum monitoring ratio of the sensor.
Further, before the data passing the verification is subjected to data fusion by using a preset multi-source information fusion model, the method further comprises:
carrying out preliminary fusion on the homogeneous sensor data according to the space-time weight of the data to obtain various homogeneous data;
and determining optimizing weights according to the relative time relation, carrying out heterogeneous sensor data fusion on the plurality of homogeneous data, and constructing to obtain the multisource information fusion model.
Further, the preliminary fusion of the homogeneous sensor data according to the data space-time weights specifically includes:
calculating the data space-time weight according to the data space importance and the data time importance, and carrying out data fusion processing on the homogeneous sensor according to the data space-time weight to obtain the various homogeneous data;
the data space importance is:
∑l n at t m Total number, k, of time data sets m,n At t m A certain data value l at a moment m,n The number of occurrences;
the data time importance is:
Y μ,v v data included in the μ time period, n is the number of sensors, k' m,n Data value l for the μ -period m,n The number of occurrences;
the data space-time weight reconstruction model is as follows:
further, determining the optimizing weight according to the relative time relation to perform heterogeneous sensor data fusion on the plurality of homogeneous data specifically includes:
setting an European space, wherein an optimizing variable, a weight optimizing device and a classification optimizing device exist;
converting the relative time relation required by the optimal path found by the weight optimizer into the optimizing weight;
and the classification optimizer classifies the optimizing variables, and performs heterogeneous sensor data fusion with the optimizing weights according to classification results.
Further, the three-level dynamic evaluation decision comprises:
health evaluation of cultivated individuals: carrying out data fusion on single animal physiological information data according to the multi-source information fusion model to obtain individual data fusion information and individual health assessment decision;
and (3) evaluating the situation of the breeding group: carrying out data fusion on the individual data fusion information and the physiological information of the current animal group according to the multi-source information fusion model to obtain group data fusion information and group situation assessment decision;
Breeding population prediction and evaluation: and carrying out data fusion on the group data fusion information and the processed environmental sensor data according to the multi-source information fusion model to obtain a group prediction evaluation decision.
Further, before the breeding population prediction evaluation, the method further comprises the following steps:
and pre-classifying the group data fusion information, and carrying out data fusion according to the data weight sequences of different groups.
Further, the method further comprises the following steps:
and after each stage of fusion is finished, carrying out data quality evaluation and data diagnosis on the fusion information data, and if the data quality evaluation and the data diagnosis pass, taking the fusion information data as input data of the next stage.
In another aspect, an embodiment of the present invention provides a system for dynamically monitoring sensor layout and multi-source information fusion, including:
and an optimization module: the sensor layout method comprises the steps of optimizing layout of an environmental sensor and a physiological sensor according to a preset sensor layout model; the sensor layout model is constructed based on a two-dimensional plan view and the relation between the positions of the environmental sensor and the physiological sensor;
and an evaluation module: the method comprises the steps of performing periodic information extraction data on an optimized environment sensor and a physiological sensor, and performing data fusion on the data passing verification by using a preset multi-source information fusion model to obtain a three-level dynamic evaluation decision; the multi-source information fusion model is obtained based on combination of homogenous sensor data fusion and heterogeneous sensor data fusion.
According to the sensor layout and multisource information fusion method and system for dynamic monitoring, which are provided by the embodiment of the invention, the sensor is reasonably laid out and three-level dynamic evaluation decision on 'cultured individuals, cultured groups and cultured groups' is realized by adopting the preset sensor layout model to lay out the sensor and processing the obtained data through the multisource information fusion model.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for dynamically monitoring sensor layout and multi-source information fusion according to an embodiment of the present invention;
FIG. 2 is a schematic view of a vitamin reduction two-dimensional plan provided by an embodiment of the present invention;
FIG. 3 is a flow chart of a multi-sensor optimized layout process according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a three-level dynamic evaluation decision flow provided by an embodiment of the present invention;
FIG. 5 is a flowchart of a multi-sensor data fusion flowchart according to an embodiment of the present invention;
FIG. 6 is a schematic flow chart of a dynamically monitored sensor layout and multisource information fusion system according to an embodiment of the present invention;
FIG. 7 is a schematic flow chart of another dynamically monitored sensor layout and multisource information fusion system according to an embodiment of the present invention;
fig. 8 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
An embodiment of the present invention provides a method for fusing dynamically monitored sensor layout and multi-source information, and fig. 1 is a schematic flow diagram of the method for fusing dynamically monitored sensor layout and multi-source information, as shown in fig. 1, where the method includes:
Step S101, optimizing layout of an environmental sensor and a physiological sensor according to a preset sensor layout model; the sensor layout model is constructed based on a two-dimensional plan view and the relation between the positions of the environmental sensor and the physiological sensor;
specifically, according to the method for integrating sensor layout and multisource information for dynamic monitoring in the above embodiment, in the above step S101, basic information of a farm such as an area, a shape, etc. is collected, basic information of a living animal such as the number, the size, etc. is collected, and a two-dimensional plan is obtained according to the living environment of the living animal in a three-dimensional space and the dimension reduction of the three-dimensional geometric feature of the living animal; optimizing the layout of the environmental sensors of the farm by using a pre-built sensor layout model, calculating the number of animals to be monitored by using a preset animal density model based on the farm information, and performing physiological sensor layout on the batch of living animals by using the pre-built sensor layout model;
the sensor layout model is constructed based on a two-dimensional plan view and the relation between the positions of the environmental sensor and the physiological sensor, a certain constraint is added to the sensor by the sensor layout model, the situation that a plurality of sensors monitor the same grid or the sensors do not monitor the whole two-dimensional plane completely is avoided, but the monitoring ratio is more than 100% is avoided, influences of the sizes of the living animals, the number of animals, the monitoring mechanism of the sensors and the like on the physiological sensor layout of the living animals are comprehensively considered, a matching set is obtained by primarily matching the positions of the environmental sensor and the physiological sensor with the two-dimensional plan view, the maximum monitoring ratio of the environmental sensor and the physiological sensor is calculated according to the matching set and constraint variables, and the optimal layout of the sensor is obtained according to the maximum monitoring ratio of the sensor.
Step S102, periodically extracting data from the optimized environmental sensor and physiological sensor, and carrying out data fusion on the data passing verification by using a preset multisource information fusion model to obtain a three-level dynamic evaluation decision; the multi-source information fusion model is obtained based on combination of homogenous sensor data fusion and heterogeneous sensor data fusion.
Specifically, according to the method for dynamically monitoring sensor layout and multi-source information fusion in the above embodiment, in the above step S102, periodic information extraction is performed on the environmental sensor and physiological sensor data based on the pre-constructed sensor layout model layout, and data fusion is performed on the verified data by using the pre-constructed multi-source information fusion model to perform three-level dynamic evaluation decision on "cultured individual-cultured population";
carrying out preliminary fusion on the homogeneous sensor data according to the space-time weight of the data to obtain various homogeneous data; then determining optimizing weights according to the relative time relation to perform heterogeneous sensor data fusion on the multiple homogeneous data, and constructing and obtaining the multisource information fusion model according to the method;
The measured environmental sensor and physiological sensor data after the optimization layout are subjected to multi-source information fusion according to the preset multi-source information fusion model, whether the layout of the environmental sensor and the physiological sensor is reasonable can be verified in turn, and in addition, the data processed by the multi-source information fusion model can be input by a user.
According to the sensor layout and multisource information fusion method for dynamic monitoring, which is provided by the embodiment of the invention, the sensor layout is carried out by adopting the preset sensor layout model, and the obtained data is processed by the multisource information fusion model, so that the reasonable layout of the sensor is realized, and the three-level dynamic evaluation decision of 'cultured individuals, cultured groups and cultured groups' is realized.
Based on any one of the above embodiments, before the optimizing layout of the environmental sensor and the physiological sensor according to the preset sensor layout model, the method further includes:
and performing dimension reduction on the three-dimensional space living environment and the three-dimensional geometric features of living animals to obtain the two-dimensional plan.
Specifically, according to the method for fusing sensor layout and multisource information for dynamic monitoring in the embodiment, fig. 2 is an intention of a two-dimensional planar graph for reducing vitamins provided by the embodiment of the invention, as shown in fig. 2, basic information such as area, shape and the like of a farm is collected, basic information such as quantity, size and the like of living animals is collected, a two-dimensional grid plan is obtained according to the three-dimensional space living environment of the living animals and the three-dimensional geometrical feature dimension reduction of the living animals, the dimension reduction method firstly grids a cultivation space, namely the three-dimensional space living environment, and a living animal 3D model, namely the three-dimensional geometrical feature of the living animals, then establishes a mapping relation between the 3D grid and a 2D image, adds slits to the three-dimensional grid, and divides the three-dimensional grid into a disc structure of a sheet, maps X, Y, Z three-dimensional coordinates of the 3D space to U, V two-dimensional coordinates of the 2D image, so as to realize dimension reduction treatment on the cultivation space and the living animal 3D model. The dimension reduction method can enable the three-dimensional model to establish direct mapping connection with the two-dimensional plane, and the sensor positions arranged in the two-dimensional plane graph can be directly projected to the three-dimensional space to represent real positions.
According to the sensor layout and multisource information fusion method for dynamic monitoring, disclosed by the embodiment of the invention, the dimension reduction is carried out on the living environment of the three-dimensional space and the three-dimensional geometric characteristics of living animals, so that the two-dimensional processing of the three-dimensional model is realized, the processing difficulty is reduced, and the early preparation is carried out for reasonably laying out the sensors.
Based on any one of the above embodiments, further, the optimizing layout of the environmental sensor and the physiological sensor according to the preset sensor layout model specifically includes:
preliminary matching is carried out on the positions of the environmental sensor and the physiological sensor and the two-dimensional plan, so as to obtain a matching set;
calculating to obtain the maximum monitoring ratio of the environmental sensor and the physiological sensor according to the matching set and the constraint variable;
and determining the optimized layout according to the maximum monitoring ratio of the sensor.
Specifically, according to the method for dynamically monitoring sensor layout and multi-source information fusion in the above embodiment, fig. 3 is a schematic flow chart of a multi-sensor optimization layout flow provided by the embodiment of the present invention, as shown in fig. 3, a three-dimensional space living environment and three-dimensional geometric features of living animals are subjected to dimension reduction, after the two-dimensional plan is obtained, the two-dimensional plan is divided into a plurality of key grids, and a grid set is defined as follows:
Placing a required number of sensors at any position in the two-dimensional plan, the set of positions of the sensors is:
according to the monitoring mechanism of various sensors and the characteristics of the partitioned areas, the positions of the sensors are primarily matched with the key grids, and the matching result is defined as:
f(R,V)＝{(R (1,1) ,V (1,1) ),(R (2,2) ,V (2,2) ),…(R (i,j) ,V (i,j) )}
wherein (i=1, 2 …, m), (j=1, 2, …, n);
let the monitoring range of k sensors be s= { S, respectively 1 ,S 2 ,…，S k Then the maximum monitoring ratio that k sensors can reach is:
wherein Sigma S represents the maximum monitoring ratio of k sensors, k is the number of sensors for measuring the same parameter, S T The method is characterized in that the method is a total monitoring grid area, and epsilon is a constraint variable;
in particular, in order to avoid the situation of overstoring during the same type of sensor layout, that is, the situation that a plurality of sensors monitor the same grid or that the sensors do not all monitor the whole two-dimensional plane, but the monitoring ratio is greater than 100% occurs. Therefore, a certain constraint needs to be added, and a constraint variable is specifically added to optimize the layout:
wherein S is c Representing the grid area where k sensors of the same type are simultaneously monitoring.
In particular, the model calculation result is limited to obtain the optimal number of sensors and layout positions, and the optimal number of sensors and the layout positions are judged by the rules of table 1:
Table 1 shows the corresponding layout level judgment of different layout rules
| Layout rules | Maximum monitoring ratio Sigma V | Number of sensors | Layout level |
| 1 | 90％-100％ | Optimum number of | Optimum for the production of a product |
| 2 | 80％-90％ | Number of excellent products | Excellent (excellent) |
| 3 | 60％-80％ | Sub-optimal number | Suboptimal |
| 4 | ＜60％ | Number of differences | Difference of difference |
For the living animal physiological sensor layout, factors such as the size of the culture environment, the size of animals, the number of animals, the monitoring mechanism of the sensor and the like need to be comprehensively considered. In addition to following the above-described sensor layout rules, it should be noted that: the physiological sensor has a specific monitoring mechanism, and is mainly placed on the abdomen, the pulse and the heart rate, the neck, the legs and the like when monitoring the blood sugar of living animals. The sensors are arranged on the animal body, and the monitoring range needs to be concentrated as much as possible to achieve the aim of data accuracy.
Dividing a dimension-reduced living animal two-dimensional map into specific functional areas according to the rules, and directly matching the specific sensors required to be used with the functional areas according to the working principle. The layout level is required to be that the number of the set wearable sensors is suitable for basically covering a specific functional area, so that the preset functional area range is avoided being exceeded; the number of the embedded or implanted sensors is required to be selected according to the size and health degree of animals due to damage to the animals, and the number of the embedded or implanted sensors for monitoring the same index is not more than three when the embedded or implanted sensors reach the maximum monitoring range.
Setting the sampling area as x, the sampling number as m, the sampling animal number as n and the cultivation range as S T In general, the area occupied by an adult sheep is about 1.5-2 square meters, m sampling parties are sampled in the monitoring area according to the quincuncial shape, and the length and the width of each sampling party are required to be consistent, namely the sampling areas are equal. The total living animal number in the sample formula is n, and the average occupied area of the individual animals can be calculatedThe range of motion of the special cultured animals is 2 rho 0 . Dividing the total cultivation range by the average movable area of individual animals to obtain animal density to be monitored in the cultivation range>ρ is the animal density to be monitored by installing a sensor in a specific monitoring range, and the overall information of the animals in the cultivation area can be analyzed based on the density.
According to the sensor layout and multisource information fusion method for dynamic monitoring, which is provided by the embodiment of the invention, the reasonable layout of the sensors is realized by reasonably setting the sensor layout model and by arranging various sensors of the sensor layout model.
Based on any one of the foregoing embodiments, before the data that passes the verification is fused by using a preset multi-source information fusion model, the method further includes:
carrying out preliminary fusion on the homogeneous sensor data according to the space-time weight of the data to obtain various homogeneous data;
And determining optimizing weights according to the relative time relation, carrying out heterogeneous sensor data fusion on the plurality of homogeneous data, and constructing to obtain the multisource information fusion model.
Specifically, according to the method for fusing the dynamically monitored sensor layout and the multi-source information in the embodiment, the homogeneous sensor data are preliminarily fused according to the space-time weight of the data, so that various homogeneous data are obtained; then determining optimizing weights according to the relative time relation to perform heterogeneous sensor data fusion on the multiple homogeneous data, and constructing and obtaining the multisource information fusion model according to the method;
the multi-source information fusion model also has data quality evaluation and diagnosis functions, including checking whether the previous level data is input and missing; fusion data distortion analysis, and the like. The specific flow comprises the following steps: the multisource information fusion model sets self-adaptive dynamic data extraction time to extract sensor data for three-stage fusion, and after each stage of fusion is finished, the fusion data are transmitted to a data quality evaluation and diagnosis center for diagnosis, and if diagnosis is transmitted without errors, the sensor data are used as input data of the next stage; if the data is not received in a certain level of decision overtime, extracting the sensor data again, if the sensor data is still unsuccessful, giving an alarm to the user, solving the problem by the user, and if the other levels are in an automatic dormancy state in the user processing stage, waiting to receive effective data and then restarting; the data quality assessment and diagnosis center compares the fusion data with the data true value, and re-fuses the fusion data with deviation exceeding a preset threshold value after weight optimization adjustment until the fusion data meets the requirement, and then inputs the fusion data into a next-stage decision model.
According to the sensor layout and multisource information fusion method for dynamic monitoring, which is provided by the embodiment of the invention, the data are processed by reasonably constructing a multisource information fusion model, so that three-level dynamic evaluation decision on 'cultured individuals-cultured groups' is realized.
Based on any one of the foregoing embodiments, further, the performing preliminary fusion on the homogeneous sensor data according to the data space-time weights specifically includes:
calculating the data space-time weight according to the data space importance and the data time importance, and carrying out data fusion processing on the homogeneous sensor according to the data space-time weight to obtain the various homogeneous data;
the data space importance is:
∑l n at t m Total number, k, of time data sets m,n At t m A certain data value l at a moment m,n The number of occurrences;
the data time importance is:
Y μ,v v data included in the μ time period, n is the number of sensors, k' m,n Data value l for the μ -period m，n The number of occurrences;
the data space-time weight reconstruction model is as follows:
in particular, according to the dynamically monitored sensor layout and multisource information fusion method of the embodiment,
since the monitored data remains substantially unchanged for a certain period of time, a data threshold value phi is given, and each time the monitored data exceeds the threshold value, the inflection point is used as an initial value of the next stage.
The spatio-temporal weight reconstruction model is therefore:
step 1, let y t ＝y 0 + -phi, where y 0 Data initial value, y t Phi is a data threshold for the last phase final value (i.e., the next phase initial value). Dividing each sensor data into a set of time periods y= { Y 1，ν ，Y 2，v ，…，Y μ，ν V is the number of data contained in a certain period of time;
step 2, assuming n sensors, at t m The time monitored dataset is l= { l m，1 ，l m，2 ，…，l m，n Thus t m A certain data value l at a moment m，n Number of occurrences k m，n Ratio to the entire dataset as data space importanceWherein Sigma l n At t m The total number of time data sets. In particular, in the process of determining the spatial importance, if a certain numerical value appears more times, the measurement results of a plurality of sensors at the same time are more true.
Step 3, making the data time importantWherein Y is μ，ν Representation muV data included in the time period, n being the number of sensors, k' m，n Data value l for the μ -period m，n Number of occurrences. In particular, in the time importance judging process, if a certain number of times appears, it is indicated that the change of the measurement results of the plurality of sensors is not significant in a certain time.
Step 4, the final data space-time weight reconstruction model is as follows
And carrying out homogeneous sensor data fusion processing by using the weight obtained in the formula: let w calculated by the model QD ＝(w 1 ，w 2 ，…，w n ) The homogeneity sensor monitoring data is a= (a) 1 ，a 2 ，…，a n ) Then the data fusion result x=w 1 a 1 +w 2 a 2 +…+w n a n 。
According to the sensor layout and multi-source information fusion method for dynamic monitoring, which is provided by the embodiment of the invention, the homoplasmic sensor data fusion processing is carried out through the weights, so that the homoplasmic sensor data fusion is realized.
Based on any one of the foregoing embodiments, further, the determining the optimizing weight according to the relative time relation performs heterogeneous sensor data fusion on the multiple homogeneous data, and specifically includes:
setting an European space, wherein an optimizing variable, a weight optimizing device and a classification optimizing device exist;
converting the relative time relation required by the optimal path found by the weight optimizer into the optimizing weight;
and the classification optimizer classifies the optimizing variables, and performs heterogeneous sensor data fusion with the optimizing weights according to classification results.
Specifically, according to the method for fusing the dynamically monitored sensor layout and the multi-source information in the embodiment, homogeneous sensor data is initially fused by calculating weights according to the method, and then the fusion is performedHeterogeneous sensor data fusion. According to the embodiment of the invention, heterogeneous sensor data fusion is performed after the optimizing weight is determined based on the relative time relation. Firstly, setting an NxD European space, wherein the state of the variable to be optimized is Y i ＝(y i1 ,y i2 ,…,y iD ) The state of the weight optimizer i is X i ＝(x i1 ,x i2 ,…,x iD ) The state of the classification optimizer j is X j ＝(x j1 ,x j2 ,…,x jD ) And an output optimizer k. Wherein x is id The position of the nth optimizer in the D (d=1, 2, …, D) dimension variable space to be optimized;
the one-to-one correspondence between the optimizers and the variables to be optimized is specified, and the initial Euclidean distance between each optimizer and the corresponding variable to be optimized is equal. Sequencing the variables to be optimized through priori knowledge to obtain initial weight theta n 。
Order theThen l (X) i ,Y i ) For the optimal path of the optimizer i, the basic optimizing step length of the optimizer is alpha, and the time t is needed for each optimizing 0 The optimizing device i moves one step length to any p directions at the initial position and then returns to the initial position, the direction closest to the target variable value is selected to advance to the position of the next step length, then the steps are repeated until the variable state position corresponding to the optimizing device i is reached, and the time t required by the optimal path is recorded.
Converting the relative time relation required by each optimizer i to find the optimal path into an optimizing weight w n ＝(w 1 ,w 2 ,…,w D )。
The classification optimizer j corresponds to each variable Y to be optimized i The classification optimizer j classifies the data of each variable according to a preset classification rule, and the optimizing weight obtained by the weight optimizer through optimizing is finally transmitted to the output optimizer k Calculating an output decision, wherein->The boundary value corresponding to each variable.
According to the sensor layout and multisource information fusion method for dynamic monitoring, which is provided by the embodiment of the invention, heterogeneous sensor data fusion is carried out after the optimizing weight is determined based on the relative time relation, so that fusion of the heterogeneous sensor data is realized.
Based on any one of the above embodiments, further, the three-level dynamic evaluation decision specifically includes:
health evaluation of cultivated individuals: carrying out data fusion on single animal physiological information data according to the multi-source information fusion model to obtain individual data fusion information and individual health assessment decision;
and (3) evaluating the situation of the breeding group: carrying out data fusion on the individual data fusion information and the physiological information of the current animal group according to the multi-source information fusion model to obtain group data fusion information and group situation assessment decision;
breeding population prediction and evaluation: and carrying out data fusion on the group data fusion information and the processed environmental sensor data according to the multi-source information fusion model to obtain a group prediction evaluation decision.
Specifically, according to the method for dynamically monitoring sensor layout and multi-source information fusion in the above embodiment, fig. 4 is a schematic diagram of a three-level dynamic evaluation decision flow provided in the embodiment of the present invention, as shown in fig. 4, and the health evaluation of the cultivated individuals: the information monitored by each sensor is used as input data, and the data of the physiological information monitoring of the single animal is subjected to data fusion decision by using the method, so that the health state can be estimated according to the decision of the body temperature, the blood oxygen saturation and the like of the animal, and the behavior state can be estimated according to the decision of the heart rate, the exercise amount and the like;
And (3) evaluating the situation of the breeding group: the number of animals is monitored by the culture environment obtained by the sensor layout method, information obtained by data fusion of the first-stage animal individuals is used as second-stage input data, physiological information of the batch of animal groups is subjected to data fusion processing, and health conditions of the animal groups and behavior information of the groups in the monitoring time under the culture environment can be obtained by decision making;
breeding population prediction and evaluation: and simultaneously taking the second-stage data fusion information and the processed environmental sensor data information as third-stage input data, and then processing by using a preset data fusion method to obtain the prediction of the population condition of the cultured animals under the environmental change of the farm.
According to the sensor layout and multisource information fusion method for dynamic monitoring, which is provided by the embodiment of the invention, the sensor layout is carried out by adopting the preset sensor layout model, and the obtained data is processed by the multisource information fusion model, so that the reasonable layout of the sensor is realized, and the three-level dynamic evaluation decision of 'cultured individuals, cultured groups and cultured groups' is realized.
Based on any of the above embodiments, further comprising, prior to the breeding population predictive evaluation:
And pre-classifying the group data fusion information, and carrying out data fusion according to the data weight sequences of different groups.
Specifically, according to the sensor layout and multisource information fusion method for dynamic monitoring in the embodiment, particularly when the dynamic evaluation of the breeding population is carried out, the accuracy of fusion data can be affected due to the fact that deviations exist in the physiological states of living animals of different populations in different environments of the breeding farm, so that the model can pre-classify data transmitted at the second level, weight sorting is carried out on the importance of the data of different populations, and then data fusion processing is carried out.
According to the sensor layout and multisource information fusion method for dynamic monitoring, which is provided by the embodiment of the invention, the accuracy of three-level dynamic evaluation decision of 'cultured individuals-cultured groups' is further improved by pre-classifying the group data fusion information.
Based on any of the above embodiments, further comprising:
and after each stage of fusion is finished, carrying out data quality evaluation and data diagnosis on the fusion information data, and if the data quality evaluation and the data diagnosis pass, taking the fusion information data as input data of the next stage.
Specifically, according to the sensor layout and multi-source information fusion method for dynamic monitoring in the above embodiment, since the data fusion result of each stage of the three-stage decision model is used as the input of the next stage of data, in order to ensure normal operation, the multi-source information fusion model has data quality evaluation and diagnosis functions, including checking whether the previous stage of data is input or not and missing; fusion data distortion analysis, and the like. The specific flow comprises the following steps: the multisource information fusion model sets self-adaptive dynamic data extraction time to extract sensor data for three-stage fusion, and after each stage of fusion is finished, the fusion data are transmitted to a data quality evaluation and diagnosis center for diagnosis, and if diagnosis is transmitted without errors, the sensor data are used as input data of the next stage; if the data is not received in a certain level of decision overtime, extracting the sensor data again, if the sensor data is still unsuccessful, giving an alarm to the user, solving the problem by the user, and if the other levels are in an automatic dormancy state in the user processing stage, waiting to receive effective data and then restarting; the data quality assessment and diagnosis center compares the fusion data with the data true value, and re-fuses the fusion data with deviation exceeding a preset threshold value after weight optimization adjustment until the fusion data meets the requirement, and then inputs the fusion data into a next-stage decision model.
According to the sensor layout and multisource information fusion method for dynamic monitoring, which is provided by the embodiment of the invention, through carrying out data quality evaluation and data diagnosis on fusion information data, each level of data is tested, and the accuracy of three-level dynamic evaluation decision of breeding individuals, breeding groups and breeding groups is further improved.
Further, on the basis of the above embodiment, fig. 5 is a flow chart of a multi-sensor data fusion flow chart provided by the embodiment of the present invention, where in the three-level cultivation risk prediction evaluation, the optimizing weights of the environmental temperature, the relative humidity, the animal skin temperature, the heart rate, etc. are calculated to be w n = (0.4,0.3,0.2,0.1), the range of the decision value Y for making a safe cultivation risk decision is
Therefore, when the decision value Y is between 26.2 and 53.3, the output decision of the output optimizer k is safe. In particular, in order to avoid that the data calculated by the decision value meets the safety decision, but a certain evaluation factor has reached a severe condition. A decision protection mechanism needs to be added into the classification optimizer, if at least one variable data in a certain decision reaches a bad state, the classification optimizer does not perform subsequent decision calculation, but directly outputs the bad decision, as shown in table 2.
Table 2 is an output decision rule table
Further, on the basis of the above embodiment, the embodiment of the present invention provides a system for dynamically monitoring sensor layout and multi-source information fusion, which is used for executing the method for dynamically monitoring sensor layout and multi-source information fusion in the above method embodiment. Fig. 6 is a schematic flow chart of a dynamically monitored sensor layout and multi-source information fusion system according to an embodiment of the present invention, as shown in fig. 6, the system includes: an optimization module 601, an evaluation module 602; wherein, the liquid crystal display device comprises a liquid crystal display device,
the optimization module 601: the sensor layout method comprises the steps of optimizing layout of an environmental sensor and a physiological sensor according to a preset sensor layout model; the sensor layout model is constructed based on a two-dimensional plan view and the relation between the positions of the environmental sensor and the physiological sensor;
specifically, according to the sensor layout and multisource information fusion system for dynamic monitoring in the above embodiment, in the above optimization module 601, basic information of a farm such as an area, a shape, etc. is collected, basic information of a living animal such as the number, the size, etc. is collected, and a two-dimensional plan is obtained according to the living environment of the living animal in a three-dimensional space and the dimension reduction of the three-dimensional geometric feature of the living animal; the optimizing module 601 utilizes a pre-built sensor layout model to optimize the layout of the environmental sensor of the farm, utilizes a preset animal density model to calculate the number of animals to be monitored based on the information of the farm, and utilizes the pre-built sensor layout model to perform physiological sensor layout on the batch of living animals;
The sensor layout model adds a certain constraint to the sensors to avoid that a plurality of sensors monitor the same grid or the sensors do not monitor the whole two-dimensional plane completely, but the monitoring ratio is more than 100%, and comprehensively considers the influences of the sizes of the culture environment, the sizes of animals, the number of animals, the monitoring mechanism of the sensors and the like on the layout of the physiological sensors of living animals, and the like, and the positions of the environmental sensors and the physiological sensors are primarily matched with the two-dimensional plane graph to obtain a matched set; calculating to obtain the maximum monitoring ratio of the environmental sensor and the physiological sensor according to the matching set and the constraint variable; and obtaining the sensor layout model according to the maximum monitoring ratio of the sensor.
The evaluation module 602: the method comprises the steps of performing periodic information extraction data on an optimized environment sensor and a physiological sensor, and performing data fusion on the data passing verification by using a preset multi-source information fusion model to obtain a three-level dynamic evaluation decision; the multi-source information fusion model is obtained based on combination of homogenous sensor data fusion and heterogeneous sensor data fusion.
Specifically, according to the dynamically monitored sensor layout and multisource information fusion system of the above embodiment, in the above-mentioned evaluation module 602, periodic information extraction is performed on the environmental sensor and physiological sensor data based on the pre-constructed sensor layout model layout, and the evaluation module 602 performs data fusion on the verified data by using the pre-constructed multisource information fusion model to perform three-level dynamic evaluation decision on "cultured individual-cultured population";
Carrying out preliminary fusion on the homogeneous sensor data according to the space-time weight of the data to obtain various homogeneous data; then determining optimizing weights according to the relative time relation to perform heterogeneous sensor data fusion on the multiple homogeneous data, and constructing and obtaining the multisource information fusion model according to the method;
the evaluation module 602 performs multi-source information fusion on the measured environmental sensor and physiological sensor data after the optimized layout according to a preset multi-source information fusion model, so that whether the layout of the environmental sensor and the physiological sensor is reasonable can be verified in turn, and in addition, the data processed by the multi-source information fusion model can be input by a user.
It should be noted that, the system of the embodiment of the present invention may be used to implement the technical scheme of the embodiment of the sensor layout and multisource information fusion method for dynamic monitoring shown in fig. 1, and its implementation principle and technical effects are similar, and are not repeated here.
According to the sensor layout and multisource information fusion system for dynamic monitoring, which is provided by the embodiment of the invention, the sensor layout is carried out by adopting the preset sensor layout model, and the obtained data is processed by the multisource information fusion model, so that the reasonable layout of the sensors is realized, and the three-level dynamic evaluation decision of 'cultured individuals, cultured groups and cultured groups' is realized.
Based on any of the above embodiments, further comprising: the system comprises an interaction module, a knowledge base and a quality assessment and diagnosis center module.
And an interaction module: the user can input data through the interaction module, observe and output decision results, and display instructions for conclusion and solving processes according to questions of the user.
Knowledge processing module: the system is used for providing relevant basic knowledge for a sensor layout and multi-source information fusion system for dynamic monitoring, storing the acquired and processed knowledge in a knowledge base, and a knowledge processing module can expand and modify the content in the knowledge base and can also realize an automatic learning function.
Quality assessment and diagnosis center module: for transmitting to the quality assessment and diagnosis center module after the relevant basic knowledge is transmitted to the knowledge processing module for processing, for qualitatively assessing the acquired expert knowledge, for determining applicability, feedback correction is carried out according to actual running conditions, corrected data are retransmitted to a knowledge acquisition and processing system, and the corrected data are transmitted to a knowledge base for storage by the system;
in the multi-sensor data fusion process, a quality evaluation and diagnosis center module dynamically adjusts data extraction time according to data (extraction interval time is adaptively changed according to dynamic characteristics of monitored data), extracts multi-sensor data obtained after layout, and because of the large number of sensors, in order to ensure normal operation of a system and avoid errors of data extraction of the system, data are verified after data input, and mainly comprises whether the data to be fused are successfully input, whether the data are available or not, and the like, if the data are wrong, the center can send an alarm to remind a worker to perform data inspection and re-input. If the effective data input still does not exist in the system after the extraction period is exceeded, the system sends a dormancy application to the user terminal, and a user can select whether the system is dormant, check the reason that the data is not input in time and enable the system to re-extract and process the sensor data;
The quality evaluation and diagnosis center module is specifically used for checking whether the previous level data is input or not and missing; fusion data distortion analysis, and the like. The specific flow comprises the following steps: the multisource information fusion model sets self-adaptive dynamic data extraction time to extract sensor data for three-stage fusion, and after each stage of fusion is finished, the fusion data are transmitted to a data quality evaluation and diagnosis center module for diagnosis, and if diagnosis is transmitted without errors, the sensor data are used as input data of the next stage; if the data is not received in a certain level of decision overtime, extracting the sensor data again, if the sensor data is still unsuccessful, giving an alarm to the user, solving the problem by the user, and if the other levels are in an automatic dormancy state in the user processing stage, waiting to receive effective data and then restarting; the data quality assessment and diagnosis center compares the fusion data with the data true value, and re-fuses the fusion data with deviation exceeding a preset threshold value after weight optimization adjustment until the fusion data meets the requirement, and then inputs the fusion data into a next-stage decision model.
According to the sensor layout and multisource information fusion method for dynamic monitoring, which is provided by the embodiment of the invention, the sensor layout is carried out by adopting the preset sensor layout model, and the obtained data is processed by the multisource information fusion model, so that the reasonable layout of the sensor is realized, and the three-level dynamic evaluation decision of 'cultured individuals, cultured groups and cultured groups' is realized.
Based on any one of the above embodiments, further, fig. 7 is a schematic flow chart of another dynamically monitored sensor layout and multi-source information fusion system according to an embodiment of the present invention, as shown in fig. 7, where the system includes: the system comprises an input/output module, a comprehensive database, an interpreter, a knowledge base, a knowledge acquisition and processing system and a data quality evaluation and diagnosis center; wherein, the liquid crystal display device comprises a liquid crystal display device,
and an input/output module: the user can input data and observe and output decision results through the module.
Comprehensive database: dedicated to storing raw data, intermediate results and final conclusions needed in the reasoning process, often as temporary storage areas.
An interpreter: the conclusion and solving process can be explained according to the questioning of the user.
Knowledge base, knowledge acquisition and processing system: the knowledge acquisition and processing system can expand and modify the content in the knowledge base and can realize the automatic learning function.
Data quality assessment and diagnosis center: the functions of which include,
(1) After the related basic knowledge is transmitted to a knowledge acquisition and processing system for processing, the related basic knowledge is transmitted to a data quality evaluation and diagnosis center, the acquired expert knowledge is qualitatively evaluated, applicability is determined, feedback correction is carried out according to actual running conditions, corrected data is retransmitted to the knowledge acquisition and processing system, and the corrected data is transmitted to a knowledge base for storage by the system for standby;
(2) In the multi-sensor data fusion process, a data quality evaluation and diagnosis center extracts multi-sensor data obtained after layout according to data dynamic adjustment data extraction time (extraction interval time is adaptively changed according to dynamic characteristics of monitoring data), and because of the large number of sensors, in order to ensure normal operation of a system and avoid errors of data extraction of the system, data are verified after data input, the data mainly comprise whether data to be fused are successfully input, whether the data are available or not, and the like, and if the data are wrong, the center can send an alarm to remind a worker to perform data inspection and re-input. If the effective data input in the system still does not exist after the extraction period is exceeded, the system sends a dormancy application to the user terminal, and the user can select whether the system is dormant, check the reason that the data is not input in time and enable the system to re-extract and process the sensor data.
According to the sensor layout and multisource information fusion method for dynamic monitoring, which is provided by the embodiment of the invention, the sensor layout is carried out by adopting the preset sensor layout model, and the obtained data is processed by the multisource information fusion model, so that the reasonable layout of the sensor is realized, and the three-level dynamic evaluation decision of 'cultured individuals, cultured groups and cultured groups' is realized.
Examples are as follows:
fig. 8 is a schematic physical structure of an electronic device according to an embodiment of the present invention, as shown in fig. 8, where the electronic device may include: a processor 801, a communication interface (Communications Interface) 802, a memory 803, and a communication bus 804, wherein the processor 801, the communication interface 802, and the memory 803 communicate with each other through the communication bus 804. The processor 801 may call logic instructions in the memory 803 to perform the following method: optimizing layout of the environmental sensor and the physiological sensor according to a preset sensor layout model; the sensor layout model is constructed based on a two-dimensional plan view and the positions of the environmental sensor and the physiological sensor; performing periodic information extraction data on the optimized environmental sensor and physiological sensor, and performing data fusion on the data passing verification by using a preset multi-source information fusion model to obtain a three-level dynamic evaluation decision; the multi-source information fusion model is obtained based on combination of homogenous sensor data fusion and heterogeneous sensor data fusion.
Further, the logic instructions in the memory 803 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, embodiments of the present invention further provide a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform the transmission method provided in the above embodiments, for example, including: optimizing layout of the environmental sensor and the physiological sensor according to a preset sensor layout model; the sensor layout model is constructed based on a two-dimensional plan view and the positions of the environmental sensor and the physiological sensor; performing periodic information extraction data on the optimized environmental sensor and physiological sensor, and performing data fusion on the data passing verification by using a preset multi-source information fusion model to obtain a three-level dynamic evaluation decision; the multi-source information fusion model is obtained based on combination of homogenous sensor data fusion and heterogeneous sensor data fusion.
The system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for dynamically monitoring sensor layout and multi-source information fusion, comprising:
performing preliminary matching on the position of the environmental sensor, the position of the physiological sensor and the two-dimensional plan according to a preset sensor layout model to obtain a matching set; calculating to obtain the maximum monitoring ratio of the environmental sensor and the physiological sensor according to the matching set and the constraint variable; determining an optimized layout according to the maximum monitoring ratio of the sensor and performing the optimized layout on the environmental sensor and the physiological sensor; the sensor layout model is constructed based on a two-dimensional plan view and the relation between the positions of the environmental sensor and the physiological sensor;
carrying out preliminary fusion on the homogeneous sensor data according to the space-time weight of the data to obtain various homogeneous data;
determining optimizing weights according to the relative time relation, carrying out heterogeneous sensor data fusion on the multiple homogeneous data, and constructing to obtain a multisource information fusion model;
performing periodic information extraction data on the optimized environmental sensor and physiological sensor, and performing data fusion on the data passing verification by using the multi-source information fusion model to obtain a three-level dynamic evaluation decision; the multi-source information fusion model is obtained based on combination of homogenous sensor data fusion and heterogeneous sensor data fusion.
2. The method for fusing dynamically monitored sensor layout and multi-source information according to claim 1, wherein the position of an environmental sensor, the position of a physiological sensor and a two-dimensional plan are preliminarily matched according to a preset sensor layout model to obtain a matched set; calculating to obtain the maximum monitoring ratio of the environmental sensor and the physiological sensor according to the matching set and the constraint variable; before determining an optimized layout according to the maximum monitoring ratio of the sensor and optimizing the layout of the environmental sensor and the physiological sensor, the method further comprises:
and performing dimension reduction on the three-dimensional space living environment and the three-dimensional geometric features of living animals to obtain the two-dimensional plan.
3. The method for fusing dynamically monitored sensor layout and multi-source information according to claim 1, wherein the preliminary fusing of homogeneous sensor data according to data spatiotemporal weights specifically comprises:
calculating the data space-time weight according to the data space importance and the data time importance, and carrying out data fusion processing on the homogeneous sensor according to the data space-time weight to obtain the various homogeneous data;
the data space importance is:
∑l n At t m Total number, k, of time data sets m,n At t m A certain data value l at a moment m,n The number of occurrences;
the data time importance is:
Y μ,ν v data included in the mu time period, n is the number of sensors, k' m,n Data value l for the μ -period m,n The number of occurrences;
the data space-time weight reconstruction model is as follows:
4. the method for dynamically monitoring sensor layout and multisource information fusion according to claim 1, wherein determining the optimizing weight according to the relative time relation performs heterogeneous sensor data fusion on the plurality of homogeneous data, and specifically comprises:
setting an European space, wherein an optimizing variable, a weight optimizing device and a classification optimizing device exist;
converting the relative time relation required by the optimal path found by the weight optimizer into the optimizing weight;
and the classification optimizer classifies the optimizing variables, and performs heterogeneous sensor data fusion with the optimizing weights according to classification results.
5. The method for dynamically monitoring sensor layout and multi-source information fusion according to claim 1, wherein the three-level dynamic evaluation decision comprises:
health evaluation of cultivated individuals: carrying out data fusion on single animal physiological information data according to the multi-source information fusion model to obtain individual data fusion information and individual health assessment decision;
And (3) evaluating the situation of the breeding group: carrying out data fusion on the individual data fusion information and the physiological information of the current animal group according to the multi-source information fusion model to obtain group data fusion information and group situation assessment decision;
breeding population prediction and evaluation: and carrying out data fusion on the group data fusion information and the processed environmental sensor data according to the multi-source information fusion model to obtain a group prediction evaluation decision.
6. The method of dynamically monitored sensor placement and multisource information fusion according to claim 5, further comprising, prior to said breeding population predictive evaluation:
and pre-classifying the group data fusion information, and carrying out data fusion according to the data weight sequences of different groups.
7. The method of dynamically monitored sensor placement and multisource information fusion of claim 5, further comprising:
and after each stage of fusion is finished, carrying out data quality evaluation and data diagnosis on the fusion information data, and if the data quality evaluation and the data diagnosis pass, taking the fusion information data as input data of the next stage.
8. A dynamically monitored sensor layout and multisource information fusion system, comprising:
And an optimization module: the method comprises the steps of performing preliminary matching on the position of an environmental sensor, the position of a physiological sensor and a two-dimensional plan according to a preset sensor layout model to obtain a matching set; calculating to obtain the maximum monitoring ratio of the environmental sensor and the physiological sensor according to the matching set and the constraint variable; determining an optimized layout according to the maximum monitoring ratio of the sensor and performing the optimized layout on the environmental sensor and the physiological sensor; the sensor layout model is constructed based on a two-dimensional plan view and the positions of the environmental sensor and the physiological sensor;
the fusion module is used for primarily fusing the homogeneous sensor data according to the space-time weight of the data to obtain various homogeneous data;
the construction module is used for determining optimizing weights according to the relative time relation to perform heterogeneous sensor data fusion on the multiple homogeneous data, and constructing to obtain a multisource information fusion model;
and an evaluation module: the method comprises the steps of performing periodic information extraction data on an optimized environmental sensor and a physiological sensor, and performing data fusion on the data which passes verification by using the multi-source information fusion model to obtain a three-level dynamic evaluation decision; the multi-source information fusion model is obtained based on combination of homogenous sensor data fusion and heterogeneous sensor data fusion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010470476.7A CN111695614B (en) | 2020-05-28 | 2020-05-28 | Dynamic monitoring sensor layout and multi-source information fusion method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010470476.7A CN111695614B (en) | 2020-05-28 | 2020-05-28 | Dynamic monitoring sensor layout and multi-source information fusion method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111695614A CN111695614A (en) | 2020-09-22 |
| CN111695614B true CN111695614B (en) | 2023-08-25 |
Family
ID=72478584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010470476.7A Active CN111695614B (en) | 2020-05-28 | 2020-05-28 | Dynamic monitoring sensor layout and multi-source information fusion method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695614B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114113487B (en) * | 2021-12-02 | 2022-11-22 | 江苏云聚汇科技有限公司 | Volatile organic compound online monitoring system and method |
| CN116540616B (en) * | 2023-07-06 | 2023-09-08 | 北京邮电大学 | Novel household resource scheduling decision control system and method and application thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009015552A1 (en) * | 2007-08-02 | 2009-02-05 | Jiankang Wu | Body sign dynamically monitoring system |
| CN107992904A (en) * | 2017-12-22 | 2018-05-04 | 重庆邮电大学 | Forest Ecology man-machine interaction method based on Multi-source Information Fusion |
| CN108932581A (en) * | 2018-06-06 | 2018-12-04 | 深圳大学 | The autonomous cognitive method and system of more physics domain information fusions |
| CN109357696A (en) * | 2018-09-28 | 2019-02-19 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Multiple Source Sensor information merges closed loop test framework |
| CN111178617A (en) * | 2019-12-24 | 2020-05-19 | 嘉兴恒创电力设计研究院有限公司 | Multi-sensor management method based on perception decision guidance |
-
2020
- 2020-05-28 CN CN202010470476.7A patent/CN111695614B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009015552A1 (en) * | 2007-08-02 | 2009-02-05 | Jiankang Wu | Body sign dynamically monitoring system |
| CN107992904A (en) * | 2017-12-22 | 2018-05-04 | 重庆邮电大学 | Forest Ecology man-machine interaction method based on Multi-source Information Fusion |
| CN108932581A (en) * | 2018-06-06 | 2018-12-04 | 深圳大学 | The autonomous cognitive method and system of more physics domain information fusions |
| CN109357696A (en) * | 2018-09-28 | 2019-02-19 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Multiple Source Sensor information merges closed loop test framework |
| CN111178617A (en) * | 2019-12-24 | 2020-05-19 | 嘉兴恒创电力设计研究院有限公司 | Multi-sensor management method based on perception decision guidance |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111695614A (en) | 2020-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108597617B (en) | Epidemic disease grading prediction method and device, computer device and readable storage medium | |
| US9861308B2 (en) | Method and system for monitoring stress conditions | |
| CN111695614B (en) | Dynamic monitoring sensor layout and multi-source information fusion method and system | |
| CN106777909A (en) | Gestational period health risk assessment system | |
| CN110458109A (en) | A kind of tealeaves disease recognition system and working method based on image recognition technology | |
| CN110619332B (en) | Data processing method, device and equipment based on visual field inspection report | |
| CN111242491A (en) | Medical big data visualization analysis method, medium, equipment and system | |
| CN112992375A (en) | Early warning method, early warning device, equipment and medium for diseases | |
| CN110503320B (en) | Vaccine resource allocation method, device and storage medium | |
| CN112289446A (en) | Computer system for predicting myopia of teenagers | |
| CN114240874A (en) | Bone age assessment method and device based on deep convolutional neural network and feature fusion and computer readable storage medium | |
| CN114628033A (en) | Disease risk prediction method, device, equipment and storage medium | |
| CN111930601A (en) | Deep learning-based database state comprehensive scoring method and system | |
| CN112397204B (en) | Method, device, computer equipment and storage medium for predicting altitude sickness | |
| CN112168188B (en) | Processing method and device for pressure detection data | |
| CN114511898A (en) | Pain recognition method and device, storage medium and electronic equipment | |
| CN114470719B (en) | Full-automatic posture correction training method and system | |
| CN107564588B (en) | Physiological health data prediction device | |
| CN112233126B (en) | Windowing method and device for medical image | |
| Rojo et al. | Accelerating Executive Function Assessments With Group Sequential Designs | |
| CN110638455B (en) | Server, system, device and medium for evaluating user rehabilitation status | |
| Kibret | A Bayesian Network Meta-analysis for Binary Outcome: A Simulation Study | |
| KR102362582B1 (en) | Method, server and computer program product for preprocessing statistical data | |
| KR101809046B1 (en) | Method and device for re-arranging data for analyzing the gene expression of orthologous gene | |
| CN113179970B (en) | Method and system for distinguishing stress state of fish |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |