Urban large-scale data collection method and system based on crowd sensing
A technology of large-scale data and group perception, applied in specific environment-based services, data processing applications, instruments, etc., can solve problems such as different costs of perception activities, and achieve the effect of low perception cost, strong practicability, and low perception error.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0050] The urban large-scale data collection method and system based on group sensing of the present invention will be described in detail below by taking the urban air quality perception task as an example. It should be noted that this embodiment only takes the urban air quality perception task as an example for illustration. Undoubtedly, the method and system for urban large-scale data collection based on group sensing in the present invention can also be applied to large-scale data collection in other cities The scene, such as noise, traffic conditions, flow of people, etc., will not be repeated here.
[0051] Such as figure 1 and figure 2 As shown, the large-scale urban data collection method based on group perception in this embodiment includes:
[0052] 1) Decompose the perception task into n perception cycles and m grids;
[0053] 2) Estimate the amount of information and perception cost of the unperceived grid;
[0054] 3) Select the appropriate target grid among ...
Embodiment 2
[0109] This embodiment is basically the same as Embodiment 1, and the main difference is that the step of inferring the sensing data in the unsensed grid based on the sensing data in step 5) of this embodiment includes:
[0110] 5.1B) Using the compressive sensing algorithm, the problem of inferring the sensing data in the unsensing grid based on the sensing data proposes a non-convex optimization problem as shown in the following formula:
[0111]
[0112] In the above formula, is the estimated matrix The rank of the estimated matrix is the matrix formed for the sensed data in the unsensed grid, Represents element point multiplication, S is the selection matrix, the element of the selection matrix S is 0 or 1, and the matrix element S in the selection matrix S ij Indicates whether to select the grid i to be sensed during the sensing cycle j, M is the actual measurement matrix, and the actual measurement matrix M records the sensing data in the grid that has been sen...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


