A spectrum data detection method based on deletion search and its application

Abstract

The present application discloses a spectrum data detection method based on deletion search, including: step S1, defining the coordinate position set of L sample points under the best deployment scheme; step S2, deleting one sample point from the coordinate position set in turn, and obtaining L deployment schemes based on the deleted different sample points; step S3, obtaining the spectrum detection data set corresponding to the L deployment schemes, calculating the completion performance of the L deployment schemes respectively according to the completion algorithm, and updating the best deployment scheme to the deployment scheme with the smallest error according to the completion performance; step S4, repeating steps S2 and S3, continuously updating the best deployment scheme, until the sample points reach a preset number, outputting the current best deployment scheme for data detection. It can solve the problem that the change of 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 completion algorithm model, affecting the efficiency and 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 deletion search, a spectrum data detection device based on deletion 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 communications, 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 cognition. Spectrum mapping is a series of processes from spectrum data acquisition to spectrum map visualization, 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 number of spectrum sampling data and its distribution in space, while the latter affects the prediction accuracy of spectrum data at unknown locations. At present, in the 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, the 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. By optimizing the deployment plan, measurement data containing more spectrum map-related information can be obtained. In terms of spectrum data completion, the correlation of limited spectrum measurement data is fully explored by selecting and optimizing the completion algorithm model to improve the accuracy of spectrum data prediction at unknown locations. In practical applications, as the sensor deployment location changes in specific scenarios, the correlation of the training data samples obtained by detection will be inconsistent with the correlation of the completion algorithm model, which will affect the overall efficiency and performance of spectrum mapping. Summary of the invention

[0004] In response to at least one defect or improvement need in the prior art, the present invention provides a spectrum data detection method and application based on deletion search, aiming to solve the problem that changes in the deployment location of existing sensors lead to inconsistencies between the correlation of training data samples acquired through detection and the correlation of the completion algorithm model, thereby affecting the efficiency and performance of the overall spectrum map construction.

[0005] To achieve the above object, according to a first aspect of the present invention, a spectrum data detection method based on deletion search is provided, comprising: step S1, defining a coordinate position set s of L sample points under the optimal deployment scheme opt ; Step S2, initializing the coordinate position set to a set of all M sample points, from the coordinate position set Sopt In step S3, a spectrum detection data set corresponding to the L deployment schemes is obtained, and the completion performance of the L deployment schemes is calculated according to the completion algorithm, and the optimal deployment scheme is updated to a deployment scheme with the smallest error according to the completion performance; in step S4, steps S2 and S3 are repeated to continuously update the optimal deployment scheme until the sample points reach the preset sensor deployment number, and the current optimal deployment scheme is output for data detection.

[0006] In one embodiment of the present invention, the calculation of the completion performance of L deployment schemes respectively according to the completion algorithm includes: mapping the deployment position set of the L deployment schemes to a position coordinate set according to the completion algorithm to obtain a predicted spectrum data set that corresponds one-to-one to 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.

[0007] In one embodiment of the present invention, the spectrum data detection method based on deletion search further includes: step S5, obtaining the coordinate position set S of the optimal deployment solution outputted in step S4 opt The complement of rest ; In order from S opt and S rest Select a sample point from each set to exchange, calculate and compare the RMSE of the completion error of the two sets before and after the exchange opt and RMSE swap ; If RMSE opt Less than or equal to RMSE swap , then find the next pair of sample points; if RMSE opt Greater than RMSE swap , then swap the two points and update S synchronously opt and S rest , and continue to look for the next pair of sample points.

[0008] In one embodiment of the present invention, the spectrum data detection method based on deletion search further includes: iterating step S5 and setting the algorithm end condition as: opt No update, indicating the coordinate location set S of the current deployment plan opt The algorithm has the optimal solution; or the number of iteration cycles reaches the set upper limit.

[0009] According to a second aspect of the present invention, a spectrum data detection device based on deletion search is also provided, which includes: an optimal deployment scheme definition module, used to define a coordinate position set S of L sample points under the optimal deployment scheme opt ; A sample point deletion module is used to initialize the coordinate position set to all M sample point sets, from the coordinate position set S opt A sample point is deleted one by one in sequence, and L deployment schemes are obtained based on the deleted different sample points, wherein the number of sample points of each deployment scheme is L=M-1; an optimal deployment scheme updating module is used to obtain a spectrum detection data set corresponding to the L deployment schemes, and the completion performance of the L deployment schemes is calculated according to the completion algorithm, and the optimal deployment scheme is updated to a deployment scheme with the smallest error according to the completion performance; a deployment scheme output module is used to continuously update the optimal deployment scheme until the sample points reach a preset sensor deployment number, and the optimal deployment scheme is output for data detection.

[0010] In one embodiment of the present invention, the optimal deployment scheme update module is specifically used to: map the deployment location set of L deployment schemes to a location coordinate set according to a completion algorithm to obtain a predicted spectrum data set that corresponds one-to-one to a real spectrum data set; calculate the error value between the predicted spectrum data set and the real spectrum data set according to a root mean square error algorithm to obtain the completion performance.

[0011] In one embodiment of the present invention, the spectrum data detection device based on deletion search further includes: a data exchange update module, configured to obtain a coordinate position set S of the optimal deployment solution output by the deployment solution output module. opt The complement of rest ; In order from S opt and S rest Select a sample point from each set to exchange, calculate and compare the RMSE of the completion error of the two sets before and after the exchange opt and RMSE swap ; If RMSE opt Less than or equal to RMSE swap , then find the next pair of sample points; if RMSE opt Greater than RMSE swap , then the two selected points are exchanged and S is updated synchronously opt and S rest , and continue to look for the next pair of sample points.

[0012] In one embodiment of the present invention, the spectrum data detection device based on deletion search further includes: an iterative loop module, which is used to iteratively loop the execution steps of the data exchange update module, and set the algorithm end condition as: S optNo update, indicating the coordinate location set S of the current deployment plan opt The algorithm has the optimal solution; or the number of iteration cycles reaches the set upper limit.

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

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

[0015] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0016] A heuristic algorithm for joint optimization of sensor deployment and spectrum data completion is proposed. The algorithm adopts the idea of ​​greedy optimization and designs a deterministic deletion search method to improve the efficiency of searching for the best sensor deployment plan under a specific completion algorithm. By jointly optimizing the sensor deployment location and spectrum data completion, the correlation of the measured training data samples and the correlation of the completion algorithm model are matched with each other, 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 described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flowchart of a spectrum data detection method based on deletion search provided in an embodiment of the present application;

[0019] Figure 2 A schematic diagram of simulation results of an urban open area data set provided in an embodiment of the present application;

[0020] Figure 3 A schematic diagram of simulation results of a data set of high-rise buildings in an urban area provided in an embodiment of the present application;

[0021] Figure 4 A schematic diagram of the structure of a spectrum data detection device based on deletion search provided in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0023] Figure 6 A schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with 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 intended 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 and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. 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 includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

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

[0027] 1) Coordinate position set. Assume that there are M coordinate points of interest in the target area, and the set of these discrete coordinates is: S = {(x i ,y i )|1≤i≤M}.

[0028] 2) Real spectrum data set. A set of spectrum data that corresponds one-to-one to discrete points in a coordinate position set. The real spectrum data set of M coordinate points is κ = {p i |1≤i≤M}.

[0029] 3) Deployment location set. The location set of spectrum detection sensors. Assuming the number of sensors is N, the deployment location set is

[0030] 4) Spectrum detection data set. The spectrum detection data set corresponding to the discrete points in the deployment location set, κ N ={p j |1≤j≤N},κ N ∈κ.

[0031] 5) Spectrum Completion Algorithm Set. A set of optional spectrum completion algorithms. The set of L spectrum completion algorithms is Ψ = {ψ k |1≤k≤L}.

[0032] 6) Predict the spectrum data set. According to a specific completion algorithm ψ, the spectrum detection data set κ N Mapped to the coordinate position set, the set of predicted spectrum data corresponding to the real spectrum set is and

[0033] like Figure 1 As shown, the first embodiment of the present invention proposes a spectrum data detection method based on deletion search, for example, including: step S1, defining a coordinate position set S of L sample points under the optimal deployment scheme opt ; Step S2, initializing the coordinate position set to a set of all M sample points, from the coordinate position set S opt In step S3, a sample point is deleted one by one, and L deployment schemes are obtained based on the deleted sample points, wherein the number of sample points of each deployment scheme is L=M-1; in step S4, a spectrum detection data set corresponding to the L deployment schemes is obtained, and the completion performance of the L deployment schemes is calculated according to the completion algorithm, and the best deployment scheme is updated to a deployment scheme with the smallest error according to the completion performance; in step S5, steps S2 and S3 are repeated to continuously update the best deployment scheme until the sample points reach a preset number of sensor deployments, and the best deployment scheme is output for data detection.

[0034] Specifically, in step S1, for example, the best deployment solution S opt Expressed as: S opt ={(x i ,y i )|1≤i≤L},|S opt |=L; where L represents the number of sample points, (x i ,y i ) represents the coordinates of the sample points. opt Initialized to a set of all M sample points. Obviously, the initialized S opt The number of sample points L is equal to M.

[0035] In step S2, for example, an exhaustive method is used to select the sample point set S opt Delete one sample point at a time in the , and record the set of sample points obtained after deleting the i-th point as S i , expressed as:

[0036] S i ={(x j ,y j)|(1≤j≤i-1)∪(j≤i+1≤L)}

[0037] Through the above steps, L deployment schemes can be obtained based on the deleted sample points, namely: S1, S2, ..., S L .

[0038] In step S3, for example, spectrum detection data sets corresponding to L deployment schemes are obtained, and the completion performance of the above L deployment schemes is calculated according to the selected completion algorithm ψ. Specifically, the deployment location sets of the L deployment schemes are mapped to the location coordinate set to obtain a predicted spectrum data set that corresponds one-to-one to the real spectrum data set. Taking the root mean square error RMSE as an example, the error value between the predicted spectrum data set and the real spectrum data set is calculated, which is expressed as: RMSE1, RMSE2, ..., RMSE L .

[0039] The completion algorithms mentioned are, for example, inverse distance weighting (IDW) and Kriging. IDW is a global interpolation construction method and a deterministic construction method. Its basic principle is that the spectrum value at the unknown position is equal to the weighted sum of the sampled data at the known position. Kriging interpolation is one of the main methods in traditional statistics. It is based on the theory of variogram and structural analysis, and uses the attributes of known points in the neighborhood to perform linear unbiased estimation of unknown points.

[0040] Currently, in other implementations of the present application, a completion algorithm different from the above method may also be used to map the deployment location set of L deployment schemes to a location coordinate set to obtain a predicted spectrum data set that corresponds one-to-one to the actual spectrum data set. The present application is not limited to this.

[0041] Furthermore, the greedy priority idea is adopted to retain the smallest error value RMSE min , and the current best deployment solution S opt Updated to obtain RMSE min Corresponding to the deployment plan, the number of sample points in the coordinate position set of the deployment plan is L=M-1.

[0042] In step S4, the above sample point deletion operation is repeated, and the minimum error RMSE is continuously updated. min and the best deployment solution S opt Until S opt When the number of sample points L is equal to the preset number of sensor deployments N, the loop ends. Obviously, the above loop needs to be repeated MN times.

[0043] In one embodiment, the method further includes step S5, for example, for the best deployment solution S obtained in step S4 opt , and also calculate Sopt The complement of rest , let S rest =SS opt , represents the set of unselected points, that is, S opt The complement of . Obviously, S rest All points in are in the location coordinate set S, but not in the deployment location set S opt middle.

[0044] Secondly, from S opt and S rest Select a point from each set, swap the two points, and calculate and compare the RMSE of the completion error of the two sets before and after the swap. opt and RMSE swap If RMSE opt Less than or equal to RMSE swap , then find the next pair of sample points; if RMSE opt Greater than RMSE swap , then swap the two points and update S synchronously opt and S rest , and continue to look for the next pair of sample points.

[0045] In one embodiment, for example, the above-mentioned exchange operation in step S5 is iterated and looped. To ensure the efficiency of the algorithm, the algorithm termination condition is set as follows: 1. In a complete round of iterative search, S opt No update, indicating the coordinate location set S of the current deployment plan opt It is already the optimal solution of this algorithm; 2. The number of loop iterations reaches the set upper limit.

[0046] The pseudo code of the algorithm is as follows:

[0047] Input: coordinate location set s; real spectrum data set k; number of sensors N;

[0048] Output: Minimum spectrum map construction error RMSE min and the optimal deployment location set S opt ;

[0049] Phase 1: Deterministic deletion search

[0050]

[0051] Phase 2: Refined Stochastic Optimization

[0052]

[0053]

[0054] The following is explained in conjunction with specific embodiments:

[0055] 1. Dataset

[0056] The dataset provided by the 16th (2019) China Postgraduate Mathematical Modeling Contest A - Wireless Channel Modeling was used, and two different typical scenes were selected from them: open areas in urban areas and high-rise buildings in urban areas. Considering the computational complexity, 200 sample data were randomly selected from the two scene datasets, and the coordinates (X, Y) and label data (RSRP) were retained as the training set for this experiment.

[0057] 2. Metrics

[0058] The root mean square error (RMSE) is used to evaluate the performance of spectrum mapping, and the calculation formula is as follows:

[0059]

[0060] in, It means to find the L2 norm, M is the cardinality of the sample point set, that is, the number of coordinate points in the set.

[0061] The simulation results are as follows Figure 2 and 3 As shown, where: Figure 2 This is the simulation result of the urban open area dataset. Figure 3 This is the simulation result of the urban high-rise building data set. The solid line indicates the use of the inverse distance weighted completion algorithm, and the dotted line indicates the use of the Kriging completion algorithm. The colors of each curve are as shown in the legend. Gray indicates random deployment, yellow indicates clustered deployment, red indicates genetic algorithm, and green indicates the heuristic algorithm proposed by this invention.

[0062] The random deployment mentioned here refers to randomly selecting N points from the coordinate position set as the deployment position set, and calculating the average of 50 random results as the estimated error value of the method. Cluster 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 find the point closest to the cluster center from each cluster and add it to the deployment position set. Genetic algorithms can solve complex combinatorial optimization problems and can quickly solve better optimization results.

[0063] From the simulation results Figure 2 and Figure 3It 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 (green 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: random deployment is 5.46, cluster deployment is 4.87, genetic algorithm is 3.07, and heuristic algorithm is 2.43. In the high-rise building area in the urban area, the average error of the number of sensors when using two different completion algorithms is as follows: random deployment is 9.07, cluster deployment is 8.86, genetic algorithm is 6.25, and heuristic algorithm is 5.26. Overall, the heuristic algorithm proposed in this embodiment has a performance improvement of 49% compared with random deployment, 45% compared with cluster deployment, and 18% compared with genetic algorithm.

[0064] In summary, the first embodiment of the present invention proposes a spectrum data detection method based on deletion search, which improves the efficiency of searching for the best sensor deployment scheme under a specific completion algorithm by adopting a heuristic algorithm based on greedy optimization and designing a deterministic deletion search method. In addition, by jointly optimizing the sensor deployment position and spectrum data completion, the correlation of the measured training data samples and the correlation of the completion algorithm model are matched with each other, thereby effectively improving the accuracy of spectrum mapping.

[0065] In addition, if Figure 4 As shown, the second embodiment of the present invention proposes a spectrum data detection device 20 based on deletion search, for example, including: an optimal deployment plan definition module 201, a sample point deletion module 202, an optimal deployment plan update module 203 and a deployment plan output module 204.

[0066] The optimal deployment solution definition module 201 is used to define the coordinate position set S of L sample points under the optimal deployment solution. opt The sample point deletion module 202 is used to initialize the coordinate position set to all M sample point sets, from the coordinate position set S opt Delete one sample point at a time, and obtain L deployment plans based on the deleted different sample points, wherein the number of sample points of each deployment plan is L=M-1; the best deployment plan updating module 203 is used to obtain the spectrum detection data set corresponding to the L deployment plans, calculate the completion performance of the L deployment plans according to the completion algorithm, and update the best deployment plan to a deployment plan with the smallest error according to the completion performance; the deployment plan output module 204 is used to continuously update the best deployment plan until the sample points reach the preset sensor deployment number, and output the best deployment plan for data detection.

[0067] In one embodiment, the optimal deployment scheme update module 203 is specifically used to: map the deployment location set of L deployment schemes to a location coordinate set according to a completion algorithm to obtain a predicted spectrum data set that corresponds one-to-one to the real spectrum data set; calculate the error value between the predicted spectrum data set and the real spectrum data set according to a root mean square error algorithm to obtain the completion performance.

[0068] In one embodiment, the spectrum data detection device 20 based on deletion search further includes: a data exchange update module, which is used to obtain the coordinate position set S of the best deployment solution output by the deployment solution output module. opt The complement of rest ; In order from S opt and S rest Select a point from each set, swap the two points, and calculate and compare the RMSE of the completion error of the two sets before and after the swap. opt and RMSE swap ; If RMSE opt Less than or equal to RMSE swap , then find the next pair of sample points; if RMSE opt Greater than RMSE swap , then the two selected points are exchanged and s is updated synchronously opt and rest , and continue to look for the next pair of sample points.

[0069] In one embodiment, the spectrum data detection device 20 based on deletion search further includes: an iterative loop module, which is used to iteratively loop the execution steps of the data exchange update module, and set the algorithm end condition as: S opt No update, indicating the coordinate location set S of the current deployment plan opt The optimal solution of the algorithm is reached; or the number of loop iterations reaches the set upper limit.

[0070] The spectrum data detection method based on deletion search implemented by the spectrum data detection device 20 based on deletion search disclosed in the second embodiment of the present invention is as described in the first embodiment, so it will not be described in detail here. Optionally, the various modules and the above-mentioned other operations or functions in the second embodiment are respectively for implementing the spectrum data detection method based on deletion search described in the first embodiment, and the beneficial effects of this embodiment are the same as the beneficial effects of the spectrum data detection method based on deletion search described in the first embodiment, so for the sake of brevity, they will not be repeated here.

[0071] like Figure 5As shown, the third embodiment of the present invention further proposes an electronic device, for example, comprising: 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 executes the method as described in the first embodiment, and the beneficial effects of the electronic device provided by this embodiment are the same as the beneficial effects of the spectrum data detection method based on deletion search provided by the first embodiment.

[0072] like Figure 6 As shown, the fourth embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when executed by a processor, and the beneficial effects of the computer-readable storage medium provided by this embodiment are the same as the beneficial effects of the spectrum data detection method based on deletion search provided by the first embodiment.

[0073] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0074] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0075] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0076] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0077] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0078] If the 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 is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program code.

[0079] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct the relevant hardware. The program may be stored in a computer-readable memory, and the memory may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0080] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0081] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0082] It will be easily understood by those skilled in the art 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 substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A spectrum data detection method based on deletion search, characterized in that: include: Step S1: define the coordinate position set of L sample points under the optimal deployment solution ; Step S2, initializing the coordinate position set to a set of all M sample points, Delete one sample point at a time, and obtain L deployment schemes based on the deleted different sample points, where the number of sample points in each deployment scheme is L=M-1; Step S3, obtaining spectrum detection data sets corresponding to L deployment schemes, calculating the completion performance of the L deployment schemes respectively according to the completion algorithm, and updating the best deployment scheme to a deployment scheme with the smallest error according to the completion performance; Step S4, repeating steps S2 and S3, continuously updating the optimal deployment plan, until the sample points reach the preset number of sensor deployments, outputting the current optimal deployment plan for data detection; Step S5, obtaining the coordinate position set of the optimal deployment solution output in step S4 The complement of ; In order from and Select a sample point from each set to exchange, calculate and compare the completion error of the two sets before and after the exchange and ;like Less than or equal to , then find the next pair of sample points; if Greater than , then the two selected points are exchanged and updated synchronously and , and continue to look for the next pair of sample points; Step S5 is iterated and the algorithm termination condition is set as follows: No update, indicating the coordinate location set of the current deployment plan is the optimal solution of the algorithm; Or the number of iteration cycles reaches the set upper limit; The calculating the complement performance of the L deployment schemes respectively according to the complement algorithm includes: mapping the deployment position sets of the L deployment schemes to the position coordinate set according to the complement algorithm to obtain a predicted spectrum data set corresponding to the real spectrum data set one by one; The error value between the predicted spectrum data set and the real spectrum data set is calculated according to a root mean square error algorithm to obtain the completion performance.

2. A spectrum data detection device based on deletion search, characterized in that: include: The optimal deployment solution definition module is used to define the coordinate position set of L sample points under the optimal deployment solution. ; The sample point deletion module is used to initialize the coordinate position set to all M sample point sets, and remove all M sample point sets from the coordinate position set. Delete one sample point at a time, and obtain L deployment schemes based on the deleted different sample points, where the number of sample points in each deployment scheme is L=M-1; The best deployment scheme updating module is used to obtain the spectrum detection data set corresponding to the L deployment schemes, calculate the completion performance of the L deployment schemes according to the completion algorithm, and update the best deployment scheme to the deployment scheme with the smallest error according to the completion performance; A deployment plan output module is used to continuously update the optimal deployment plan until the sample points reach a preset number of sensor deployments, and then output the current optimal deployment plan for data detection; A data exchange update module is used to obtain the coordinate position set of the optimal deployment plan output by the deployment plan output module The complement of ; In order from and Select a sample point from each set to exchange, calculate and compare the completion error of the two sets before and after the exchange and ;like Less than or equal to , then find the next pair of sample points; if Greater than , then the two selected points are exchanged and updated synchronously and , and continue to look for the next pair of sample points; The iterative loop module is used to iterate the execution steps of the data exchange update module and set the algorithm end condition as follows: No update, indicating the coordinate location set of the current deployment plan The algorithm is optimally solved; or the number of iteration cycles reaches the set upper limit; The optimal deployment plan update module is specifically used to: map the deployment location set of L deployment plans to a location coordinate set according to the completion algorithm, and obtain a predicted spectrum data set that corresponds one-to-one to the real spectrum data set; calculate 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.

3. An electronic device, characterized in that: include: A memory and one or more processors connected to the memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the steps of the method according to claim 1.

4. 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 claim 1.

Images