A Spectrum Data Detection Method and Application Based on Incremental Search

Abstract

The present application discloses a spectrum data detection method based on incremental search, including: Step S1, defining a set of coordinate positions of L sample points under the optimal deployment scheme; Step S2, initializing the set of coordinate positions as a set of k sample points among all M sample points, and successively adding one sample point to the set of coordinate positions to obtain M - L deployment schemes; Step S3, obtaining a set of spectrum detection data corresponding to the M - L deployment schemes, respectively calculating the complementation performance according to the complementation algorithm, and updating the optimal deployment scheme to the deployment scheme with the minimum error; Step S4, repeating Step S2 and Step S3, continuously updating the optimal deployment scheme, and outputting the optimal deployment scheme for data detection until the number of sample points reaches the preset number of sensors. It can solve the problem that the change in the existing sensor deployment position leads to the inconsistency between the correlation of the training data samples obtained by detection and the correlation of the complementation algorithm model, thereby affecting the performance of the overall spectrum map construction.

Description

Technical Field

[0001] The present application relates to the technical field of spectrum mapping, and more specifically, to a spectrum data detection method based on incremental search, a spectrum data detection device based on incremental search, an electronic device, and a computer-readable storage medium. Background Art

[0002] Spectrum maps have a wide range of applications in the field of wireless communication, such as network planning, interference coordination and suppression, power control, resource allocation, multi-hop routing, dynamic spectrum access, etc., and have become a key technology for electromagnetic environment perception. Spectrum mapping is a series of processes from spectrum data acquisition to visual presentation of spectrum maps, including sensor deployment, spectrum situation completion, data visual analysis, situation evolution prediction, etc. Among them, sensor deployment and spectrum data completion are two key links in spectrum mapping. The former determines the quantity and spatial distribution of spectrum sampling data, while the latter affects the prediction accuracy of spectrum data at unknown locations. Currently, in these two directions of sensor deployment and spectrum data completion, many scholars have proposed many effective methods for different scenarios.

[0003] However, in the existing spectrum mapping process, these two links of sensor deployment and spectrum data completion are usually designed independently. The research on sensor deployment mainly focuses on how to reasonably select deployment locations to reduce costs, improve spectrum detection performance and efficiency, etc. Through the optimization of the deployment plan, measurement data containing more information related to the spectrum map can be obtained. In terms of spectrum data completion, mainly by selecting and optimizing the completion algorithm model, the correlation of limited spectrum measurement data is fully exploited to improve the prediction accuracy of spectrum data at unknown locations. In practical applications, as the deployment locations of sensors change in a specific scenario, the correlation of the detected training data samples is inconsistent with the correlation of the completion algorithm model, thereby affecting the overall efficiency and performance of spectrum mapping. Summary of the Invention

[0004] In view of at least one defect or improvement requirement of the prior art, the present invention provides a spectrum data detection method and application based on incremental search, aiming to solve the problem that the change in the deployment location of existing sensors leads to the inconsistency between the correlation of the detected training data samples and the correlation of the completion algorithm model, thereby affecting the overall efficiency and performance of spectrum map construction.

[0005] To achieve the above object, according to the first aspect of the present invention, there is provided a spectrum data detection method based on incremental search, including: Step S1, defining a coordinate position set of L sample points under the optimal deployment plan ; Step S2, the coordinate position set Initialize a set of k sample points out of all M sample points, for the coordinate position set Add one sample point to the set of the k sample points in sequence, and obtain M - k deployment schemes based on different added sample points; Step S3, obtain the spectrum detection data sets corresponding to the M - k deployment schemes, calculate the completion performances of the M - k deployment schemes respectively according to the completion algorithm, and update the best deployment scheme to the deployment scheme with the smallest error according to the completion performance; Step S4, repeat Step S2 and S3, continuously update the best deployment scheme, and output the best deployment scheme for data detection until the number of sample points reaches the preset number of sensors.

[0006] In an embodiment of the present invention, the mapping of the coordinate position set Initialize it as a set of k sample points out of all M sample points, including: clustering the coordinates of the M sample points into k clusters according to the Euclidean distance, and respectively selecting the coordinate positions closest to the cluster centers from each cluster to obtain an initialized deployment set containing k sample points .

[0007] In an embodiment of the present invention, the calculating the completion performances of the M - k deployment schemes respectively according to the completion algorithm includes: mapping the deployment position sets of the M - k deployment schemes to the position coordinate sets according to the completion algorithm to obtain a predicted spectrum data set in one-to-one correspondence with the true spectrum data set; calculating the error value between the predicted spectrum data set and the true spectrum data set according to the root mean square error algorithm to obtain the completion performance.

[0008] In an embodiment of the present invention, the spectrum data detection method based on incremental search further includes: Step S5, obtain the coordinate position set of the complement of the best deployment scheme output in Step S4; select one sample point from and in sequence for swapping, calculate and compare the completion errors of the two sets before and after swapping and ; if is less than or equal to , then find the next pair of sample points; if is greater than , then swap the two points, and synchronously update and , and continue to find the next pair of sample points.

[0009] In an embodiment of the present invention, the spectrum data detection method based on incremental search further includes: performing an iterative loop on Step S5, and setting the algorithm end condition as: in a complete round of iterative search There is no update, indicating that the current deployment set is already the optimal solution of the algorithm; or the number of loop iterations reaches the set upper limit.

[0010] According to the second aspect of the present invention, there is also provided a spectrum data detection device based on incremental search, which includes: an optimal deployment scheme definition module for defining a set of coordinate positions of L sample points under the optimal deployment scheme ; a sample point addition module for initializing the set of coordinate positions as a set of partial k sample points among all M sample points, adding one sample point to the set of k sample points in sequence, and obtaining M - k deployment schemes based on different added sample points; an optimal deployment scheme update module for obtaining a set of spectrum detection data corresponding to the M - k deployment schemes, calculating the completion performance of the M - k deployment schemes respectively according to the completion algorithm, and updating the optimal deployment scheme to the deployment scheme with the minimum error according to the completion performance; a deployment scheme output module for continuously updating the optimal deployment scheme until the number of sample points reaches a preset number, and outputting the optimal deployment scheme for data detection.

[0011] In an embodiment of the present invention, the sample point addition module is specifically used for: clustering the coordinates of M sample points into k clusters according to the Euclidean distance, and respectively selecting the coordinate position closest to the cluster center from each cluster to obtain an initialized deployment set containing k sample points .

[0012] In an embodiment of the present invention, the spectrum data detection device based on incremental search further includes: a data exchange and update module for obtaining the complement set of the set of coordinate positions of the optimal deployment scheme output by the deployment scheme output module ; respectively selecting one sample point from and in sequence for swapping, calculating and comparing the completion errors of the two sets before and after the swap and ; if is less than or equal to , then looking for the next pair of sample points; if is greater than , then swapping the two points, and synchronously updating and , and continuing to look for the next pair of sample points.

[0013] According to the third aspect of the present invention, there is also provided an electronic device, including: a memory and one or more processors connected to the memory, the memory stores a computer program, and the processor is used to execute the computer program to implement the steps of the method described in any one of the above embodiments.

[0014] According to the fourth aspect of the present invention, there is also provided a computer-readable storage medium storing computer-executable instructions for executing the steps of the method described in any one of the above embodiments.

[0015] Generally speaking, compared with the prior art by the above technical solutions conceived by the present invention, the following beneficial effects can be achieved:

[0016] By proposing a heuristic algorithm for jointly optimizing sensor deployment and spectrum data completion, which adopts the idea of greedy optimization and designs a deterministic incremental search method, the efficiency of searching for the optimal sensor deployment scheme under a specific completion algorithm is improved. And by jointly optimizing the sensor deployment location and spectrum data completion, the correlation of the measured training data samples is matched with the correlation of the completion algorithm model, thereby effectively improving the accuracy of spectrum mapping. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of a spectrum data detection method based on incremental search provided by an embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of the simulation results of the urban open area data set provided by an embodiment of the present application;

[0020] Figure 3 It is a schematic diagram of the simulation results of the urban high-rise building data set provided by an embodiment of the present application;

[0021] Figure 4 It is a schematic structural diagram of a spectrum data detection device based on incremental search provided by an embodiment of the present application;

[0022] Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention;

[0023] Figure 6 It is a schematic structural diagram of a computer-readable storage medium provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0025] The terms "first", "second", "third", etc. in the specification, claims and above-mentioned drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0026] First, the definitions of the nouns involved in this application are explained:

[0027] 1) Set of coordinate positions. Assume that there are M interesting coordinate points in the target area, and the set of these discrete coordinates is: .

[0028] 2) Set of true spectrum data. The set of spectrum data corresponding one-to-one to the discrete points in the set of coordinate positions. The set of true spectrum data for M coordinate points is .

[0029] 3) Set of deployment positions. The set of positions where the spectrum detection sensors are deployed. Assume the number of sensors is N, and the set of deployment positions is .

[0030] 4) Set of spectrum detection data. The set of spectrum detection data corresponding one-to-one to the discrete points in the set of deployment positions, .

[0031] 5) Set of spectrum completion algorithms. The set of optional spectrum completion algorithms is .

[0032] 6) Set of predicted spectrum data. According to a specific completion algorithm , the set of spectrum detection data is mapped onto the set of coordinate positions to obtain the set of predicted spectrum data corresponding one-to-one to the true spectrum set as .

[0033] Such as Figure 1As shown in the figure, the first embodiment of the present invention proposes a spectrum data detection method based on incremental search, for example, including: Step S1, defining a set of coordinate positions of L sample points under the optimal deployment scheme ; Step S2, adding one sample point in turn from the set of k sample points, and denoting the sample point set obtained after adding the i-th sample point as , obtaining M - k deployment schemes based on different added sample points; Step S3, obtaining a set of spectrum detection data corresponding to the M - k deployment schemes, respectively calculating the completion performance of the M - k deployment schemes according to the completion algorithm, and updating the optimal deployment scheme to the deployment scheme with the minimum error according to the completion performance; Step S4, repeating Step S2 and Step S3, continuously updating the optimal deployment scheme, and outputting the optimal deployment scheme for data detection until the number of sample points reaches the preset quantity.

[0034] Specifically, in Step S1, for example, the optimal deployment scheme is represented as: ; where L represents the number of sample points, represents the sample point coordinates.

[0035] In Step S2, for example, the clustering (K-means) method is used to initialize the deployment set , that is, the coordinates of M samples are clustered into k clusters according to the Euclidean distance, and the coordinate positions closest to the cluster centers are selected from each cluster respectively to obtain an initialized deployment set containing k points . Among them, the parameter k can be set and adjusted according to the sample scale M and the number of sensor deployments N.

[0036] Secondly, an exhaustive method is used to sequentially add a new sample point (not in the initialized coordinate position set ) from the sample point set . Obviously, there are M - k new sample points, so that a combination of M - k deployment sets is obtained, and the i-th set is denoted as ., which is represented as:

[0037]

[0038] Through the above steps, M - k deployment schemes can be obtained based on different added sample points, which are respectively: .

[0039] In Step S3, for example, a set of spectrum detection data corresponding to the M - k deployment schemes is obtained, and according to the selected completion algorithm , calculate the completion performance of the above M-k deployment solutions respectively. Specifically, map the deployment location sets of the M-k deployment solutions to the location coordinate sets to obtain a predicted spectrum data set that corresponds one-to-one with the true spectrum data set. Taking the root mean square error RMSE as an example, calculate the error value between the predicted spectrum data set and the true spectrum data set, which is expressed as: .

[0040] The completion algorithms mentioned above are, for example, inverse distance weighting (IDW), Kriging, etc. Inverse distance weighting is a global interpolation construction method, belonging to the deterministic construction method. Its basic principle is that the spectrum value at an unknown location is equal to the weighted sum of the sampling data at known locations. Kriging interpolation method is one of the main methods in traditional statistics. It is based on the variogram theory and structural analysis, and linearly and unbiasedly estimates unknown points through the attributes of known points within the neighborhood range.

[0041] Currently, in other embodiments of the present application, a completion algorithm different from the above method can also be used to map the deployment location sets of the M-k deployment solutions to the location coordinate sets to obtain a predicted spectrum data set that corresponds one-to-one with the true spectrum data set. The present application is not limited thereto.

[0042] Furthermore, adopt the greedy priority idea to retain the smallest error value among them , and update the current best deployment solution to the deployment solution corresponding to obtaining . At this time, the number of sample points L in the coordinate position set of the deployment solution is k + 1.

[0043] In step S4, repeat the above operation of adding sample points and continuously update the minimum error and the best deployment solution . Until the number of sample points L in is equal to the preset number of sensor deployments N, and the loop ends. Obviously, the above loop needs to be repeated N - k times.

[0044] In one embodiment, the method further includes, for example, step S5. For the best deployment solution obtained in step S4, also calculate 's complement , let , representing the set of unselected points, that is, 's complement. Obviously, all the points in are in the location coordinate set , but not in the deployment location set .

[0045] Secondly, sequentially select from and Select one point from each of them, swap the two selected points, and calculate and compare the completion errors of the two sets before and after the swap and . If is less than or equal to , then find the next pair of sample points; if is greater than , then swap the two points and synchronously update and , and continue to find the next pair of sample points.

[0046] In one embodiment, for example, iterate and loop the above swapping operation of step S5. To ensure the algorithm efficiency, set the algorithm end conditions as: 1. In a complete round of iterative search, is not updated, indicating that the current deployment set is already the optimal solution of this algorithm; 2. The number of loop iterations reaches the set upper limit.

[0047] The pseudo-code of this algorithm is as follows:[[]]END

[0048] Input: Set of coordinate positions ; Set of real spectrum data ; Number of sensors ;

[0049] Output: Minimum spectrum map construction error and set of optimal deployment positions ;

[0050] Phase 1: Deterministic incremental search

[0051] 1: Initialization: = [], = [], initialize the deployment set using K-Means , ;

[0052] 2:

[0053] 3:

[0054] 4: ;

[0055] 5: ;

[0056] 6: ;

[0057] 7:

[0058] 8: Calculate the corresponding completion error according to the error formula ​ ;

[0059] 9: Add and to and ;

[0060] 10:

[0061] 11: ;

[0062] 12: ;

[0063] 11: = [], = [];

[0064] 13:

[0065] 14: , .

[0066] Phase 2: Fine-grained Stochastic Optimization

[0067] 1: Initialization: The output from Phase 1, the output from Phase 1;

[0068] 2:

[0069] 3:

[0070] 4:

[0071] 5: Replace in with ;

[0072] 6: The complemented error;

[0073] 7: The complemented error;

[0074] 8:

[0075] 9: , go back to step 3;

[0076] 10:

[0077] 11:

[0078] 12:

[0079] 13: If a complete cycle iteration has no update, or the loop reaches the maximum number of iterations;

[0080] 14:

[0081] 15: , .

[0082] The following is illustrated with specific embodiments:

[0083] 1. Dataset

[0084] Use the dataset provided by Problem A of the 16th China Postgraduate Mathematical Modeling Contest - Wireless Channel Modeling, and select two different typical scenarios: open area in the urban area and high-rise buildings in the urban area. Considering the computational complexity, randomly select 200 sample data from the datasets of these two scenarios respectively, and retain the coordinates (X, Y) and label data (RSRP) as the training set for this experiment.

[0085] 2. Metric

[0086] Use the root mean square error (RMSE) to evaluate the spectrum mapping performance, and the calculation formula is as follows:

[0087]

[0088] where represents the L2 norm, and M is the cardinality of the sample point set, that is, the number of coordinate points in the set.

[0089] The simulation results are as Figure 2 and 3 shown, where: Figure 2 is the simulation result of the dataset in the open area of the urban area, Figure 3 is the simulation result of the dataset of high-rise buildings in the urban area. The solid line represents the use of the inverse distance weighted completion algorithm, and the dashed line represents the use of the Kriging completion algorithm. The colors of each curve are as shown in the legend, gray represents random deployment, yellow represents clustering deployment, red represents the genetic algorithm, and green represents the heuristic algorithm proposed by the present invention.

[0090] The random deployment mentioned above refers to randomly selecting N points from the set of coordinate positions as the deployment position set, and calculating the average value of 50 random results as the estimated error value of this method. The clustering deployment refers to using the K-Means tool to cluster all coordinate points in the coordinate position set into N clusters according to the Euclidean distance, and finding the point closest to the cluster center from each cluster and adding it to the deployment position set. The genetic algorithm can solve complex combinatorial optimization problems and can quickly obtain better optimization results.

[0091] From the simulation results Figure 2 and Figure 3 it can be seen that the heuristic algorithm proposed in this embodiment has obvious advantages over the random algorithm, clustering algorithm, and genetic algorithm. First, in two different scenarios, the best solutions under the joint optimization of deployment and completion are all obtained by the heuristic algorithm (blue curve) proposed in this embodiment. Among them, in the open area of the urban area, the average error (RMSE) of the number of sensors when using two different completion algorithms is as follows: 5.46 for random deployment, 4.87 for clustering deployment, 3.07 for genetic algorithm, and 2.46 for heuristic algorithm. And in the area of high-rise buildings in the urban area, the average error of the number of sensors when using two different completion algorithms is as follows: 9.07 for random deployment, 8.86 for clustering deployment, 6.25 for genetic algorithm, and 5.61 for heuristic algorithm. Overall, the heuristic algorithm proposed in this embodiment has a 46% performance improvement compared to random deployment, a 43% improvement compared to clustering deployment, and a 15% improvement compared to genetic algorithm.

[0092] In summary, a spectrum data detection method based on incremental search proposed in the first embodiment of the present invention, by proposing a heuristic algorithm for jointly optimizing sensor deployment and spectrum data completion, this algorithm adopts the idea of greedy optimization and designs a deterministic incremental search method, which improves the efficiency of searching for the best sensor deployment scheme under a specific completion algorithm, and through jointly optimizing the sensor deployment position and spectrum data completion, realizes the mutual matching of the correlation of the measured training data samples and the correlation of the completion algorithm model, thereby effectively improving the accuracy of spectrum mapping.

[0093] In addition, as Figure 4 shown, a spectrum data detection device 20 based on incremental search proposed in the second embodiment of the present invention, for example, includes: an optimal deployment scheme definition module 201, a sample point addition module 202, an optimal deployment scheme update module 203, and a deployment scheme output module 204.

[0094] Among them, the optimal deployment scheme definition module 201 is used to define the coordinate position set of L sample points under the optimal deployment scheme ; the sample point addition module 202 is used to add the coordinate position set Initialize a set of k sample points from all M sample points, sequentially add one sample point to the set of k sample points, and obtain M - k deployment schemes based on different added sample points; the optimal deployment scheme update module 203 is used to obtain the set of spectrum detection data corresponding to the M - k deployment schemes, calculate the completion performance of the M - k deployment schemes respectively according to the completion algorithm, and update the optimal deployment scheme to the deployment scheme with the smallest error according to the completion performance; the deployment scheme output module 204 is used to continuously update the optimal deployment scheme, and output the optimal deployment scheme for data detection until the number of sample points reaches the preset quantity.

[0095] In one embodiment, the sample point adding module 202 is specifically configured to: cluster the coordinates of M sample points into k clusters according to the Euclidean distance, and respectively select the coordinate positions closest to the cluster centers from each cluster to obtain an initialization deployment set containing k sample points .

[0096] In one embodiment, the spectrum data detection device 20 based on incremental search further includes: a data exchange and update module, configured to obtain the set of coordinate positions of the optimal deployment scheme output by the deployment scheme output module of the complement ; sequentially select one sample point from and respectively for swapping, calculate and compare the completion errors of the two sets before and after the swap and ; if is less than or equal to , then find the next pair of sample points; if is greater than , then swap the two points, and synchronously update and , and continue to find the next pair of sample points.

[0097] The spectrum data detection method based on incremental search implemented by the spectrum data detection device 20 based on incremental search disclosed in the second embodiment of the present invention is as described in the foregoing first embodiment, so details will not be described herein again. Optionally, each module in the second embodiment and the above other operations or functions are respectively for implementing the spectrum data detection method based on incremental search described in the first embodiment, and the beneficial effects of this embodiment are the same as those of the spectrum data detection method based on incremental search described in the foregoing first embodiment. For the sake of brevity, they will not be elaborated herein.

[0098] As Figure 5As shown in the figure, the third embodiment of the present invention further provides an electronic device, for example, including: at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit is caused to execute the method described in the first embodiment, and the beneficial effects of the electronic device provided in this embodiment are the same as those of the spectrum data detection method based on incremental search provided in the first embodiment.

[0099] As Figure 6 shown in the figure, the fourth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented, and the beneficial effects of the computer-readable storage medium provided in this embodiment are the same as those of the spectrum data detection method based on incremental search provided in the first embodiment.

[0100] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0101] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0102] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some service interfaces. The indirect couplings or communication connections of the devices or units can be in an electrical or other form.

[0103] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, in each embodiment of the present application, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0105] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned memory includes: USB flash drives, read-only memories (ROM), random access memories (RAM), mobile hard disks, magnetic disks, or optical discs, etc., which can store program codes.

[0106] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory. The memory can include: flash drives, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs, etc.

[0107] The above are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. After considering the specification and practicing the present disclosure herein, those skilled in the art will readily think of other embodiments of the present disclosure. The present application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not described in the present disclosure. The specification and embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

[0108] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0109] Those skilled in the art can easily understand that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A spectrum data detection method based on incremental search, characterized in that, Including: Step S1, define the coordinate position set of L sample points under the optimal deployment plan ; Step S2, initialize the set of coordinate positions as a set of k sample points out of all M sample points, and add one sample point to the set of k sample points in sequence. Based on the different added sample points, M - k deployment schemes are obtained; Step S3: Obtain the spectrum detection data sets corresponding to M - k deployment schemes, calculate the completion performance of the M - k deployment schemes respectively according to the completion algorithm, and update the best deployment scheme to the deployment scheme with the minimum error according to the completion performance; Step S4: Repeat Step S2 and S3, continuously update the best deployment scheme until the number of sample points reaches the preset number of sensors, and then output the best deployment scheme for data detection; Step S5: Obtain the set of coordinate positions of the optimal deployment plan output in Step S4 complement set ; Select one sample point from each of and in sequence for swapping, calculate and compare the completion errors of the two sets before and after the swap and ; If is less than or equal to , then find the next pair of sample points; if is greater than , then swap the two points, and synchronously update and , and continue to find the next pair of sample points; Iteratively loop through step S5 and set the algorithm termination condition as: in a complete round of iterative search there is no update, indicating that the current deployment set is already the optimal solution of the algorithm; or the number of loop iterations reaches the set upper limit.

2. The spectrum data detection method based on incremental search according to claim 1, wherein The set of coordinate positions is initialized as a set of k sample points out of all M sample points, including: Cluster the coordinates of M sample points into k clusters according to the Euclidean distance, and select the coordinate positions closest to the cluster centers from each cluster respectively to obtain an initial deployment set containing k sample points 。 3. The spectrum data detection method based on incremental search according to claim 1, wherein The calculating the completion performance of the M - k deployment schemes respectively according to the completion algorithm includes: Mapping the deployment location sets of the M - k deployment schemes to the location coordinate sets according to the completion algorithm to obtain a predicted spectrum data set that corresponds one - to - one with the real spectrum data set; Calculating the error value between the predicted spectrum data set and the real spectrum data set according to the root - mean - square error algorithm to obtain the completion performance.

4. A spectrum data detection device based on incremental search, characterized in that, Including: Optimal deployment scheme definition module, which is used to define the set of coordinate positions of L sample points under the optimal deployment scheme ; A sample point addition module, used to initialize the coordinate position set as a set of k sample points out of all M sample points, sequentially add one sample point to the set of k sample points, and obtain M-k deployment schemes based on different added sample points; Best deployment scheme update module, which is used to obtain the spectrum detection data sets corresponding to M - k deployment schemes, calculate the completion performance of the M - k deployment schemes respectively according to the completion algorithm, and update the best deployment scheme to the deployment scheme with the minimum error according to the completion performance; Deployment scheme output module, which is used to continuously update the best deployment scheme until the number of sample points reaches the preset number, and then output the best deployment scheme for data detection; A data exchange and update module, which is used to obtain the set of coordinate positions of the optimal deployment plan output by the deployment plan output module complementary set ; respectively select one sample point from and in sequence for exchange, calculate and compare the completion errors of the two sets before and after the exchange and ; if is less than or equal to , then look for the next pair of sample points; if is greater than , then exchange the two points, and synchronously update and , and continue to look for the next pair of sample points; Iteratively loop through the steps performed by the data exchange update module, and set the algorithm termination condition as: in a complete round of iterative search there is no update, indicating that the current deployment set is already the optimal solution of the algorithm; or the number of loop iterations reaches the set upper limit.

5. The spectrum data detection device based on incremental search according to claim 4, characterized in that The sample point adding module is specifically used for: Cluster the coordinates of M sample points into k clusters according to the Euclidean distance, and select the coordinate positions closest to the cluster centers from each cluster respectively to obtain an initial deployment set containing k sample points .

6. An electronic device, characterized in that, Including: A memory and one or more processors connected to the memory, the memory stores a computer program, and the processor is used to execute the computer program to implement the steps of the method according to any one of claims 1 - 3.

7. A computer-readable storage medium, characterized in that, The computer - readable storage medium stores computer - executable instructions, and the computer - executable instructions are used to execute the steps of the method according to any one of claims 1 - 3.

Images