CN110580552B - Universal regional environment information mobile sensing and predicting method - Google Patents
Universal regional environment information mobile sensing and predicting method Download PDFInfo
- Publication number
- CN110580552B CN110580552B CN201910863762.7A CN201910863762A CN110580552B CN 110580552 B CN110580552 B CN 110580552B CN 201910863762 A CN201910863762 A CN 201910863762A CN 110580552 B CN110580552 B CN 110580552B
- Authority
- CN
- China
- Prior art keywords
- data
- prediction
- time
- space
- value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000007613 environmental effect Effects 0.000 claims abstract description 51
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 28
- 230000008447 perception Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims 1
- 230000002194 synthesizing effect Effects 0.000 abstract 1
- 239000012080 ambient air Substances 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 239000003570 air Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A universal regional environment information mobile sensing and prediction method is characterized in that a mobile sensing node is used for collecting data and transmitting the data to a cloud server; then, carrying out space and structure analysis on the data by adopting a regional random variable analysis method at the cloud end, and obtaining an expression of covariance and a variation function; then, an improved random L-BFGS algorithm is utilized to improve a kriging algorithm, and the algorithm is used for carrying out universal regional environmental information spatial prediction to obtain a spatial prediction result of the environmental information; performing space-time prediction analysis by using the relation between time and space of the shared bicycle for acquiring the environmental data to obtain a space-time prediction result of the target area; and finally, synthesizing different prediction results aiming at time and space to give a final regional global environment prediction result graph.
Description
Technical Field
The invention relates to the field of data interpolation methods, in particular to a universal regional environment information mobile perception and prediction method.
Background
Ecological environment information is very important in environmental protection: the method is very important for environmental scientific research work; the method is very important for energy conservation and emission reduction; the method is very important for planning and deploying the city. The current way to collect environmental information is to place a large number of sensing nodes in the target area that monitor the ambient air quality. The wireless sensor network is convenient to deploy, and the monitorable area is wide, so that the wireless sensor network can be effectively monitored in the area with difficult power supply and the area with difficult human arrival. However, a large number of wireless sensor nodes are arranged in a city, which causes the problems of more redundant nodes, resource waste, high cost and the like.
Spatial interpolation may be a method of solving for unknown spatial data from data in a known space. It is based on the basic assumption of "first law of geography", that points closer in spatial position are more likely to have similar eigenvalues; and the farther away the points are, the less likely they have similar feature values. According to a set of known spatial data, whether in a discrete form or a partitioned form, a functional relation can be found from the data, so that the relation can be well approximated to the known data, and the value of any point in a range can be calculated according to the relation function. Although the current spatial data interpolation completion and prediction schemes are more, the schemes are all based on the traditional fixed sensor network scheme, and the moving sensing scheme described in the patent is not researched and valued enough.
At present, the cost for monitoring environmental air information by an environmental protection department is higher, so that the difficulty of arranging a large number of environmental information monitoring sites in a city is caused. The shared bicycle can become an ambient air sensing node widely distributed in cities, but no sensor module which is suitable for the shared bicycle and is used for collecting ambient air information exists at present.
Disclosure of Invention
The invention aims to provide an environment information mobile sensing and predicting scheme aiming at the problems of more redundant nodes, resource waste and overhigh cost caused by the massive arrangement of a fixed wireless sensor network, which can solve the problems of resource waste and more redundant nodes and also takes the error of acquiring the environment information at different time into consideration.
A universal regional environment information movement perception and prediction method comprises the following steps:
step 1: analyzing the data in space and structure by using the existing measured environmental data in a cloud database by adopting a regionalized random variable analysis method, and obtaining an expression of covariance and a variation function;
and 2, step: optimizing a variation function model by using an improved random L-BFGS algorithm, adopting a non-uniform small-batch sampling strategy, and approximating a Hessian matrix in the original random L-BFGS algorithm by updating a plurality of smaller Hessian matrices;
and 3, step 3: optimizing a kriging algorithm by using a variation function optimized by an improved random L-BFGS algorithm, predicting universal regional environment space information by using the algorithm, and transmitting a prediction result to a cloud end;
and 4, step 4: performing space-time prediction analysis by using the relation between the time and the space of the environment data collected by the shared bicycle to obtain a space-time prediction result of the target area, and transmitting the prediction result to a cloud database;
and 5: and analyzing the Kriging prediction result and the prediction result of the time space in the cloud database, taking the median of two prediction results from the prediction values of each longitude and latitude to obtain the final prediction value of the environmental information in the target area, and outputting a final environmental prediction result graph.
Further, in step 1, in the existing measured environment data, as if there are two data of the same type once latitude, it is necessary to select the data closest to the time point to be predicted.
Further, the step 1 comprises the following sub-steps:
step 1-1: the target area M where the environmental information needs to be detected is the target area y in the target area M i The value of the collected measured environment data is A (y) i ) Wherein y is l ＝y i + k, k being y i Move to y l N is the number of samples with a distance k between shifts, u is A (y) i ) The mean value of (a); the covariance calculation formula is:
step 1-2: the variation function can reflect the spatial variability of the environmental data through the structure of the function and various parameters, and the variation function expression is as follows:
in the formula, i is the number of the increments of each pair of environment data divided into k;
step 1-3: calculating a variation function value of the environment data, fitting to obtain a variation function, and fitting by using an exponential model:
calculating a theoretical environment information variation value beta (k) at each position of k, 1, 2, 3 0 And C, a, and substituting the values into beta (k) to obtain an environment information variation function formula.
Further, in step 3, the point y in the target area M i Is passing throughThe environmental data measured by the regional sensing module is A (y) i ) Then the predicted position y is needed o The predicted value of (a) is y i Weighted linear combination of data:
λ i is corresponding to A (y) i ) The coefficient of (a);
the environmental data not only have structural difference, also have spatial structure change, and the distribution rule of environmental data in the target area does not change because of the transform of position, so satisfy unbiased minimum variance: all the coefficients add to 1 and the variance between the predicted value and the known value is minimal, so the following expression is satisfied:
so that
Minimum;
where ε is the Lagrange multiplier, Cov (y) i ,y l ) For a known data point y i ,y l Cov (y) between o ,y l ) To predict point y o And known data point y l Covariance between, Cov (y) o ,y o ) To predict point y o The variance of (a); obtaining the weighting coefficient lambda of each known data point i Then, the environment data value of each known point is combined to obtain the final regional environment space information prediction result A 1 (y o )。
Further, in the step 4, setting the target area to generate global environment prediction data once an hour, wherein the collected environment data have latitude, longitude and time marks;
at t o The time needs to be y o Make a prediction of t i For the acquisition time, t, of a known data point io ＝t o -t i Let the time length of the time when the distance needs to be predicted be t io ；
Wherein the time influence factor
A distance influence factor of
Since the global environment information of the target area is predicted once an hour, it is necessary to follow t io For different sub-cases: t is t io ≤30，30＜t io ≤100，100 io < t three cases:
t io in the time period of ≦ 30, t in the known data points io Data y less than or equal to 30 i′ The data collected in this time period is close to the prediction time and is more accurate, so the spatiotemporal correlation coefficient in this time period is: eta ti≤30 ＝η ti ×η li The interpolation of the data during this period results in
In which n' is t io Number of data points ≦ 30, A (y) i ') is t io The value of the data point ≦ 30, A' (y) is t io The prediction result is less than or equal to 30;
30＜t io in the time period less than or equal to 100, the time influence factor and the distance influence factor are equally important, so the space-time coefficient is:
α io ＝-0.01t io +1, and 30 < t io A value within ≦ 100:
and for p io Sorting is performed with only the first 50% of ρ io Corresponding to y io Is
And alpha io The calculation is participated, and the rest is discarded; so that the interpolation of the data during this period of time results in
Wherein n' is 30 < t io Number of data points ≦ 100, A (y) i ") is 30 < t io The value of the data point ≦ 100, A "(y) 30 < t io The prediction result is less than or equal to 100.
100 io Within the time less than t, the time is too long from the time point needing to be predicted, and the result participating in prediction is not accurate, so that the data acquired within the time does not participate in calculation;
finally, obtaining a prediction result by utilizing time and space influence factors
A 2 (y o )＝A′(y)+A″(y)。
Further, in the step 5, the spatial prediction result a is paired in the cloud database 1 (y o ) And the prediction result A of the time space 2 (y o ) And analyzing, taking the median of two prediction results from the prediction values of each longitude and latitude to obtain the final prediction value of the environmental information in the target area, and outputting a final environmental survey result graph.
The invention achieves the following beneficial effects:
the method comprehensively utilizes the relation between time and space for acquiring the environmental data, predicts the global environmental data of the target area, utilizes a large number of distributed shared bicycles in the city to sense and predict the environmental data, conveniently and effectively predicts the environmental data in the city, saves the cost for monitoring the environmental information by an environmental protection department, and contributes to the development of green smart cities.
The invention provides a prediction algorithm related to a universal regional environment information mobile perception and prediction method, and utilizes a Kriging space interpolation algorithm and a space-time prediction algorithm to sacrifice part of data accuracy to obtain data time tolerance so as to obtain more accurate global environment information.
The invention provides a mobile sensing module adaptive to an urban shared bicycle, which can collect various important urban air environment data.
Drawings
FIG. 1 is a flow chart of the perception and prediction method of the present invention.
Fig. 2 is a schematic diagram of collecting perceptual environment data through a sharing bicycle in an embodiment of the present invention.
FIG. 3 is a diagram illustrating an environment prediction result of a target area according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further explained in detail by combining the drawings in the specification.
A universal regional environment information movement perception and prediction method comprises the following steps:
step 1: and (3) analyzing the data in space and structure by using the existing measured environmental data in a cloud database by adopting a regionalized random variable analysis method, and obtaining an expression of covariance and a variation function.
In step 1, in the existing measured environmental data, as if there are two data of the same type once latitude, it is necessary to select the data closest to the time point to be predicted.
The step 1 comprises the following sub-steps:
step 1-1: m is the target area where the environmental information needs to be detected, y is in the target area M i The value of the collected measured environment data is A (y) i ) Wherein y is l ＝y i + k, k being y i Move to y l N is the number of samples with a distance k between displacements, u is A (y) i ) The mean value of (a); the covariance calculation formula is:
step 1-2: the variation function can reflect the spatial variability of the environmental data through the structure of the function and various parameters, and the variation function expression is as follows:
where i is the number of copies that averages each pair of environmental data increments to k.
Step 1-3: calculating a variation function value of the environment data, fitting to obtain a variation function, and fitting by using an exponential model:
calculating the variation value beta (k) of each theoretical environmental information at the position k-1, 2, 3 0 And C, a, and substituting the values into beta (k) to obtain an environment information variation function formula.
And 2, step: the improved random L-BFGS algorithm is used for optimizing a variation function model, a non-uniform small-batch sampling strategy is adopted, and a Hessian matrix in the original random L-BFGS algorithm is approximated by updating a plurality of smaller Hessian matrices.
And step 3: and optimizing the kriging algorithm by using the variation function optimized by the improved random L-BFGS algorithm, predicting general regional environment space information by using the algorithm, and transmitting a prediction result to a cloud terminal.
In step 3, point y in target area M i The environmental data measured by the area sensing module is A (y) i ) Then the predicted position y is needed o The predicted value of (A) is y i Weighted linear combination of data:
λ i is corresponding to A (y) i ) The coefficient of (a).
The environmental data not only have structural difference, also have spatial structure change, and the distribution rule of environmental data in the target area does not change because of the transform of position, so satisfy unbiased minimum variance: all coefficients add to 1 and the variance between the predicted value and the known value is minimal, so the following expression is satisfied:
so that
And minimum.
Where ε is the Lagrange multiplier, Cov (y) i ,y l ) Is a known data point y i ,y l Covariance between, Cov (y) o ,y l ) To predict point y o And known data point y l Cov (y) between o ,y o ) To predict point y o The variance of (a); obtaining a weighting coefficient lambda of each known data point i Then, the environment data value of each known point is combined to obtain the final regional environment space information prediction result A 1 (y o )。
And 4, step 4: and performing space-time prediction analysis by using the relation between the time and the space of the environment data acquired by the shared bicycle to obtain a space-time prediction result of the target area, and transmitting the prediction result to the cloud database.
In the step 4, the target area is set to generate global environment prediction data once an hour, and the collected environment data have latitude, longitude and time marks.
At t o The time needs to be y o Making a prediction of t i For the acquisition time, t, of a known data point io ＝t o -t i Let the time length from the time when the prediction is needed be t io 。
Wherein the time influence factor
A distance influence factor of
Since the global environment information of the target area is predicted once an hour, it is necessary to follow t io For different sub-cases of (1): t is t io ≤30，30＜t io ≤100，100 io < t three cases.
t io In the time period of ≦ 30, t in the known data points io Data y less than or equal to 30 i′ The data collected in this time period is close to the prediction time and is more accurate, so the spatiotemporal correlation coefficient in this time period is as follows: eta ti≤30 ＝η ti ×η li The interpolation of the data during this period results in
In which n' is t io Number of data points ≦ 30, A (y) i ') is t io The value of the data point ≦ 30, A' (y) is t io Prediction results within less than or equal to 30.
30＜t io In the time period less than or equal to 100, the time influence factor and the distance influence factor are equally important, so the space-time coefficient is:
α io ＝-0.01t io +1, and 30 < t io A value within ≦ 100:
and for p io Sorting is performed with only the first 50% of ρ io Corresponding to y io Is
And alpha io Only participate in the calculation, the rest are discarded; so that the interpolation of the data during this period results in
Wherein n' is 30 < t io Number of data points ≦ 100, A (y) i ") is 30 < t io The value of the data point ≦ 100, A "(y) 30 < t io The prediction result is less than or equal to 100.
100 io Within the time less than t, the time is too long from the time point needing to be predicted, and the result of prediction is not accurate, so that the data acquired within the time is not involved in calculation.
Finally, obtaining a prediction result by utilizing time and space influence factors
A 2 (y o )＝A′(y)+A″(y)。
And 5: and analyzing the Kriging prediction result and the prediction result of the time space in the cloud database, taking the median of two prediction results from the prediction values of each longitude and latitude to obtain the final prediction value of the environmental information in the target area, and outputting a final environmental prediction result graph.
In step 5, the spatial prediction result A of the pair in the cloud database 1 (y o ) And the prediction result A of the time space 2 (y o ) And analyzing, taking the median of two prediction results from the prediction values of each longitude and latitude to obtain the final prediction value of the environmental information in the target area, and outputting a final environmental survey result graph.
Referring to fig. 2, one application scenario of the method is that the shared bicycle a acquires environmental data at three points A, B, C on a driving path in a rectangular target area, and the shared bicycle b acquires environmental data at D, E on the driving path. The environment data is processed by the method, that is, the environment prediction result map of the target area shown in fig. 3 is obtained through the process shown in fig. 1, and the shaded area in the map is the prediction area obtained through the ubiquitous area environment information movement perception and prediction algorithm.
The above description is only a preferred embodiment of the present invention, and the scope of the present invention is not limited to the above embodiment, but equivalent modifications or changes made by those skilled in the art according to the disclosure of the present invention should be included in the scope of the present invention as set forth in the appended claims.
Claims (5)
1. A universal regional environment information mobile perception and prediction method is characterized in that: comprises the following steps:
step 1: analyzing the data in space and structure by using the existing measured environmental data in a cloud database and adopting a regional random variable analysis method, and obtaining an expression of covariance and a variation function;
and 2, step: optimizing a variation function model by using an improved random L-BFGS algorithm, adopting a non-uniform small batch sampling strategy, and approximating a Hessian matrix in the original random L-BFGS algorithm by updating a plurality of smaller Hessian matrices;
and step 3: optimizing a kriging algorithm by using a variation function optimized by an improved random L-BFGS algorithm, predicting universal regional environment space information by using the algorithm, and transmitting a prediction result to a cloud end;
and 4, step 4: performing space-time prediction analysis by using the relation between time and space of the environment data acquired by the shared bicycle to obtain a space-time prediction result of a target area, and transmitting the prediction result to a cloud database;
in the step 4, setting the target area to generate global environment prediction data once in one hour, wherein the collected environment data have longitude and latitude and time marks;
at t o The time needs to be y o Making a prediction of t i For the acquisition time of a known data point, t io ＝t o -t i Let the time length from the time when the prediction is needed be t io ；
Wherein the time influence factor
A distance influencing factor of
Since the global environment information of the target area is predicted once an hour, it is necessary to follow t io For different sub-cases of (1): t is t io ≤30，30＜t io ≤100，100 io < t three cases:
t io in the time period of ≦ 30, t in the known data points io Data y less than or equal to 30 i′ The data collected in this time period is close to the prediction time and is more accurate, so the spatiotemporal correlation coefficient in this time period is: eta ti≤30 ＝η ti ×η li The interpolation result of the data in this period is
Wherein n' is t io Number of data points ≦ 30, A (y) i ') is t io The value of the data point ≦ 30, A' (y) is t io The prediction result is less than or equal to 30;
30＜t io in the time period less than or equal to 100, the time influence factor and the distance influence factor are equally important, so the space-time coefficient is:
α io ＝-0.01t io +1, and 30 < t io A value within ≦ 100:
and for p io Sorting is performed with only the first 50% of rho io Corresponding to y io Is
And alpha io Only participate in the calculation, the rest are discarded; so that the interpolation of the data during this period results in
Wherein n' is 30 < t io Number of data points ≦ 100, A (y) i ") is 30 < t io The value of a data point ≦ 100, A' (y) is 30 < t io The prediction result is less than or equal to 100;
100 io within the time less than t, the time is too long from the time point needing to be predicted, and the prediction is participated inThe result of (a) is not very accurate, so the data acquired in this period of time does not participate in the calculation;
finally, obtaining a predicted result A by using time and space influence factors 2 (y o )＝A′(y)+A″(y)；
And 5: and analyzing the Kriging prediction result and the prediction result of the time space in the cloud database, taking the median of two prediction results from the prediction values of each longitude and latitude to obtain the final prediction value of the environmental information in the target area, and outputting a final environmental prediction result graph.
2. The method as claimed in claim 1, wherein the method for motion perception and prediction of general regional environment information comprises: in step 1, in the existing measured environmental data, as if there are two data of the same type once latitude, it is necessary to select the data closest to the time point to be predicted.
3. The method for universal regional environment information mobile perception and prediction as claimed in claim 1, wherein: the step 1 comprises the following sub-steps:
step 1-1: the target area M where the environmental information needs to be detected is the target area y in the target area M i The value of the collected measured environment data is A (y) i ) Wherein y is l ＝y i + k, k being y i Move to y l N is the number of samples with a distance k between shifts, u is A (y) i ) The mean value of (a); the covariance calculation formula is:
step 1-2: the variation function can reflect the spatial variability of the environmental data through the structure of the function and various parameters, and the variation function expression is as follows:
in the formula, i is the number of the increments of each pair of environment data divided into k;
step 1-3: calculating a variation function value of the environment data, fitting to obtain a variation function, and fitting by using an exponential model:
calculating a theoretical environment information variation value beta (k) at each position of k, 1, 2, 3 0 And C, a, and substituting the values into beta (k) to obtain an environment information variation function formula.
4. The method for universal regional environment information mobile perception and prediction as claimed in claim 1, wherein: in said step 3, point y in target area M i The environmental data measured by the area sensing module is A (y) i ) Then the predicted position y is needed o The predicted value of (a) is y i Weighted linear combination of data:
λ i is corresponding to A (y) i ) The coefficients of (c);
the environmental data not only have structural difference, also have spatial structure change, and the distribution rule of environmental data in the target area does not change because of the transform of position, so satisfy unbiased minimum variance: all the coefficients add to 1 and the variance between the predicted value and the known value is minimal, so the following expression is satisfied:
so that
Minimum;
where ε is the Lagrange multiplier, Cov (y) i ,y l ) For a known data point y i ,y l Covariance between, Cov (y) o ,y l ) To predict point y o And known data point y l Cov (y) between o ,y o ) To predict point y o The variance of (a); obtaining a weighting coefficient lambda of each known data point i Then, the environment data value of each known point is combined to obtain the final regional environment space information prediction result A 1 (y o )。
5. The method as claimed in claim 1, wherein the method for motion perception and prediction of general regional environment information comprises: in the step 5, the spatial prediction result A is aligned in the cloud database 1 (y o ) And temporal spatial prediction of results A 2 (y o ) And analyzing, taking the median of two prediction results from the predicted values of each longitude and latitude to obtain the final predicted value of the environmental information in the target area, and outputting a final environmental survey result graph.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910863762.7A CN110580552B (en) | 2019-09-12 | 2019-09-12 | Universal regional environment information mobile sensing and predicting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910863762.7A CN110580552B (en) | 2019-09-12 | 2019-09-12 | Universal regional environment information mobile sensing and predicting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110580552A CN110580552A (en) | 2019-12-17 |
| CN110580552B true CN110580552B (en) | 2022-07-26 |
Family
ID=68812311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910863762.7A Active CN110580552B (en) | 2019-09-12 | 2019-09-12 | Universal regional environment information mobile sensing and predicting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110580552B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115510635B (en) * | 2022-09-19 | 2023-06-20 | 卓思韦尔(北京)信息技术有限公司 | Spatial environment monitoring method, device, equipment and computer readable storage medium |
| CN116910595B (en) * | 2023-09-14 | 2023-12-08 | 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) | Efficient storage method for hydraulic circular ecological restoration data |
| CN117390128B (en) * | 2023-12-12 | 2024-02-23 | 南京信息工程大学 | Urban physical environment intelligent mobile monitoring system and method based on Arduino platform |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106714336A (en) * | 2016-10-25 | 2017-05-24 | 南京邮电大学 | Wireless sensor network temperature monitoring method based on improved Kriging algorithm |
| CN107610021A (en) * | 2017-07-21 | 2018-01-19 | 华中农业大学 | The comprehensive analysis method of environmental variance spatial and temporal distributions |
-
2019
- 2019-09-12 CN CN201910863762.7A patent/CN110580552B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106714336A (en) * | 2016-10-25 | 2017-05-24 | 南京邮电大学 | Wireless sensor network temperature monitoring method based on improved Kriging algorithm |
| CN107610021A (en) * | 2017-07-21 | 2018-01-19 | 华中农业大学 | The comprehensive analysis method of environmental variance spatial and temporal distributions |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110580552A (en) | 2019-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Soh et al. | Adaptive deep learning-based air quality prediction model using the most relevant spatial-temporal relations | |
| CN110580552B (en) | Universal regional environment information mobile sensing and predicting method | |
| Singh et al. | Modeling and decision making in spatio-temporal processes for environmental surveillance | |
| CN106714336B (en) | Wireless sensor network temperature monitoring method based on improved kriging algorithm | |
| KR102116824B1 (en) | Positioning system based on deep learnin and construction method thereof | |
| WO2020043028A1 (en) | Method for predicting air pollution using historical air quality data features | |
| CN109068267B (en) | Indoor positioning method based on LoRa SX1280 | |
| JP2019040475A (en) | People flow estimation device, system, and program | |
| Xu et al. | Urban noise mapping with a crowd sensing system | |
| WO2020044127A1 (en) | Atmospheric pollution forecasting method | |
| Qaisar et al. | Energy baseline prediction for buildings: A review | |
| CN110366109B (en) | Positioning method and system for indoor target | |
| Lian et al. | Improved Indoor positioning algorithm using KPCA and ELM | |
| Jia et al. | A fingerprint-based localization algorithm based on LSTM and data expansion method for sparse samples | |
| CN109803234B (en) | Unsupervised fusion positioning method based on weight importance constraint | |
| CN117077843A (en) | Space-time attention fine granularity PM2.5 concentration prediction method based on CBAM-CNN-converter | |
| Zhang et al. | A nonstationary and non‐Gaussian moving average model for solar irradiance | |
| CN114375038B (en) | Positioning method, apparatus, base station, storage medium and computer program product | |
| Ara et al. | Ride Hailing Service Demand Forecast by Integrating Convolutional and Recurrent Neural Networks. | |
| Widjaja et al. | A general spatial-temporal framework for short-term building temperature forecasting at arbitrary locations with crowdsourcing weather data | |
| Ping et al. | Particle filter based time series prediction of daily sales of an online retailer | |
| CN108304510B (en) | Method for extracting association rule between city access behavior and POI type of public map service user | |
| CN117222003A (en) | Wi-Fi and Bluetooth signal fusion method applied to indoor positioning | |
| Abboud et al. | How opportunistic mobile monitoring can enhance air quality assessment? | |
| CN113723006B (en) | LS-SVM (least squares-support vector machine) -based single-station earth change magnetic field modeling prediction method and system |
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 |