Improved radar signal sorting algorithm and device based on FCM algorithm, and storage device

By combining data field theory and potential values ​​to construct weight coefficients, and improving the objective function, the problem that the traditional fuzzy C-mean algorithm needs to be determined in advance and is sensitive to noise in radar signal sorting, achieving a more stable clustering effect and noise immunity.

CN118962600AActive Publication Date: 2024-11-15CHINA UNIV OF GEOSCIENCES (WUHAN)

Patent Information

Application Number
CN202411005261.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-11-15
Estimated Expiration
2044-07-25

AI Technical Summary

Technical Problem

In the traditional fuzzy C-mean algorithm, there is a problem that the number of clusters needs to be determined in advance and is sensitive to noise in radar signal sorting, resulting in unstable clustering results.

Method used

Using an improved method based on FCM algorithm, through the combination of data field theory and potential entropy, the number of class centers is adaptively determined, and the weight coefficient is constructed using potential values, the objective function is improved to eliminate noise points and outliers, and iteratively calculate clustering result.

Benefits of technology

It significantly improves the noise resistance and clustering effect of the FCM algorithm, ensures the accuracy and robustness of classification, can handle unbalanced data sets, and overcomes the disadvantage of traditional algorithms that need to give the number of class hearts in advance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118962600A_ABST
    Figure CN118962600A_ABST
Patent Text Reader

Abstract

The invention provides an improved radar signal sorting algorithm and device based on an FCM algorithm and a storage device, and relates to the field of radar signal sorting, and the method comprises the steps: extracting pulse width, carrier frequency and arrival angle according to pulse description word data received by a radar, and carrying out the normalization processing; calculating a field intensity function and a potential value of each point according to a data field theory; calculating the change condition of the potential entropy along with the radiation factor, and selecting the optimal radiation factor according to the minimum value of the potential entropy; calculating a potential value according to the optimal radiation factor, and removing noise points; adaptively determining the number of class centers according to the distribution of the potential values of the data points; calculating a weight coefficient according to the correlation between the data points and the potential value; and calculating an improved objective function according to the weight coefficient and the adaptive class number, and performing iteration to obtain an optimal clustering result. The method has the beneficial effects that the noise immunity of the FCM algorithm is remarkably improved, and the classification effect is ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of radar signal sorting, and in particular to an improved radar signal sorting algorithm, device and storage device based on an FCM algorithm. Background Art

[0002] As the electromagnetic environment becomes more complex, electronic reconnaissance technology faces increasing challenges. Radar receivers usually receive multiple radar signals, which are aliased together in the order of arrival time. In order to obtain the parameter information of each radar signal, it must be processed by de-aliasing. This process is called radar signal sorting. Clustering algorithms play an important role in this field, which helps to discover the correlation between unknown data.

[0003] The fuzzy C-means algorithm (FCM) is a clustering algorithm that divides data points into different clusters, where each data point has a certain degree of membership, indicating the possibility that it belongs to each cluster. The general steps for radar signal sorting using FCM are: first, preprocessing steps such as standardization and feature extraction are required to ensure that the data is suitable for cluster analysis. Then the number of clusters is determined, and some clustering evaluation indicators (such as silhouette coefficient, DB index, etc.) are generally used to assist in determining the optimal number of clusters. Finally, the FCM algorithm is used to calculate the degree of membership of each data point with the class center by minimizing the objective function, thereby determining the category of the data point.

[0004] However, the traditional FCM algorithm has two defects: 1. The number of clusters needs to be determined in advance, and the clustering effect depends on the selection of the number of initial cluster centers; 2. It is sensitive to noise, which may lead to unstable clustering results. When processing data such as radar signals, noise and outliers are a common problem. Summary of the invention

[0005] In order to solve the problem that the clustering effect depends on the selection of the number of initial cluster centers and the clustering result is unstable, the present invention provides a radar signal sorting algorithm, device and storage device improved based on the FCM algorithm. The radar signal sorting algorithm improved based on the FCM algorithm mainly includes:

[0006] S1: Extract pulse width, carrier frequency, and arrival angle according to the pulse description word data received by the radar to form three-dimensional coordinate data, and perform normalization on the three-dimensional coordinate data;

[0007] S2: According to the data field theory, the field intensity function and the potential value formula of each point are obtained;

[0008] S3: Calculate the change of potential entropy with radiation factor based on the normalized data, and select the optimal radiation factor based on the minimum value of potential entropy;

[0009] S4: Calculate the potential value according to the optimal radiation factor and remove noise points;

[0010] S5: Adaptively determine the number of class centers based on the distribution of potential values ​​of data points;

[0011] S6: Calculate the weight coefficient according to the correlation and potential value between the data points;

[0012] S7: Calculate the improved objective function according to the weight coefficient and the adaptive number of clusters, and iterate to obtain the best clustering result.

[0013] A storage device stores instructions and data for implementing an improved radar signal sorting algorithm based on an FCM algorithm.

[0014] A radar signal sorting device improved based on FCM algorithm comprises: a processor and a storage device; the processor loads and executes instructions and data in the storage device to implement a radar signal sorting algorithm improved based on FCM algorithm.

[0015] The technical solution provided by the present invention has the following beneficial effects: the present invention combines the FCM algorithm with the data field theory, and overcomes the shortcoming that the traditional FCM is easily affected by noise by eliminating noise and outliers. According to the data field theory and the idea of ​​the regional growing algorithm, the number of clusters can be accurately obtained without prior information, thereby improving the clustering effect. The weight coefficient is constructed in combination with the potential value, and the objective function is improved, thereby solving the problem that the traditional FCM algorithm cannot accurately sort when the amount of data between classes is very different. The present invention utilizes the data field theory to significantly improve the noise resistance of the FCM algorithm and ensure the classification effect. The number of class centers is adaptively determined, thereby overcoming the shortcoming that the traditional FCM algorithm needs to give the number of class centers in advance. It effectively handles unbalanced data sets that the traditional FCM algorithm cannot handle, thereby improving the accuracy and robustness of classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0017] Figure 1 It is a flow chart of a radar signal sorting algorithm improved based on the FCM algorithm in an embodiment of the present invention.

[0018] Figure 2 1 is a diagram of noisy data and a diagram of sorted results in an embodiment of the present invention, wherein (a) is a diagram of the original data without sorting and containing noise, and (b) is a diagram of the sorting result using the improved FCM algorithm.

[0019] Figure 3It is a schematic diagram of the sorting results of different data sets (three radars, four radars, and five radars) by the three algorithms DF-FCM, SC-KMEANS, and RI-FCM in an embodiment of the present invention.

[0020] Figure 4 It is a schematic diagram of the sorting results of the unbalanced data set by the three algorithms DF-FCM, SC-KMEANS and RI-FCM in an embodiment of the present invention.

[0021] Figure 5 It is a schematic diagram of the operation of the hardware device in the embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0023] Please refer to Figure 1 , Figure 1 This is a flow chart of a radar signal sorting algorithm improved based on the FCM algorithm in an embodiment of the present invention. The DF-FCM algorithm provided by the present invention realizes the adaptation of the initial number of classes by introducing data field theory, and eliminates noise and outliers at the same time, specifically including:

[0024] S1: According to the PDW (pulse description word) data received by the radar, the three parameters of pulse width, carrier frequency and arrival angle are obtained, and parsed and processed to ensure the accuracy and consistency of the data. Then these parameters are normalized to ensure that the values ​​of different parameters are comparable.

[0025] S2: Based on the data field theory, the formula for calculating the field strength function and the potential value of each point is obtained. The field strength function represents the interaction force between data points. The field strength function is:

[0026]

[0027] Among them, d(x a ,x b ) represents the data object x a With x b is the Euclidean distance, and σ is the radiation factor.

[0028] The potential value is the midpoint of the data field for x a The generated field strength function and is used to measure the influence of the position and characteristics of the data point in the data set on the overall data. The potential value function is:

[0029]

[0030] The denser the data points, the larger the potential value, which can eliminate free noise points.

[0031] S3: Use potential entropy to represent the uncertainty between data objects in the data field, calculate the change of potential entropy with radiation factor, and select the optimal radiation factor σ according to the minimum value of potential entropy. Assume that the potential value of the i-th data point is The expression of potential entropy is as follows:

[0032]

[0033] In the formula is the standardization factor.

[0034] From the above formula, we can conclude that When the radiation factor σ is infinitely close to 0, The potential entropy is logn. When the radiation factor is very large, If there is no correlation between data points, they cannot be sorted according to the potential value. Only when the radiation factor σ is selected appropriately, the potential value of each sample will change significantly, thereby minimizing the uncertainty between samples, that is, the potential entropy reaches the minimum value. This optimal radiation factor can achieve the best classification effect and the clearest grouping of data.

[0035] S4: The potential value of each data point is obtained based on the optimal radiation factor, and the data points with lower potential values ​​are eliminated. Generally speaking, the noise point will deviate from the cluster center of the pulse signal, and the distance will exceed the radiation range of the cluster center, that is, greater than 3σ. Therefore, the formula of the field strength function can be modified to set the interaction force between data points greater than 3σ to 0. The field strength function is as follows:

[0036]

[0037] Recalculate the potential value for each data point. Remove those data points with low potential values, as these points may be noise or unrepresentative information. By retaining data points with higher potential values, subsequent classification and analysis can be performed more accurately.

[0038] S5: Adaptively determine the number of class centers based on the distribution of the potential values ​​of the data points. The specific process is:

[0039] First, the initial class center is selected: the point with the largest potential value is taken as the first class center.

[0040] Then perform region expansion: for the selected class center, find the nearest point around it and determine whether the potential value of the point is less than the potential value of the class center. If so, it is classified into this class. Continue to find the point (point a) closest to any point in this class and determine whether the potential value of point a is less than the potential value of the point (point b) closest to point a in the current cluster. If the condition is met, point a is included in the current cluster. Repeat the above expansion process until there are no points that meet the conditions within a certain distance from the class center.

[0041] New centroid selection: From the remaining unclassified data points, select the point with the largest potential value as the new centroid, and repeat the above operation. When the number of remaining unclassified data points is less than a certain proportion of the total number of data points, stop selecting new centroids, and the number of centroids at this time is the estimated number of clusters.

[0042] S6: Obtain the weight coefficient according to the correlation between data points. The weight coefficient describes the similarity or correlation between data points. For a data point, the denser the surrounding data points, the greater the average similarity, and the greater the influence on the clustering result, so it is necessary to give the data point a greater weight. The calculation formula for the correlation between data points is:

[0043]

[0044] Where d(x j ,x i ) represents the distance between the jth data point and the ith data point, represents the potential value of the jth data point.

[0045] Weight coefficient V j The expression is as follows:

[0046]

[0047] From the above formula, we can know that when the distance d(x j ,x i ) is closer, the weight w j The larger it is, the weight of the core points can be increased and the weight of the edge points can be reduced, which further enhances the noise resistance of the algorithm and can also handle unbalanced data sets well.

[0048] S7: Use the improved objective function based on the weight coefficient to iterate and obtain the membership matrix and classification results.

[0049] The improved objective function is:

[0050] Both

[0051] According to the Lagrange multiplier method, we can obtain the membership matrix and cluster center that minimizes J. The cluster center c i for:

[0052]

[0053] Membership matrix u ij for:

[0054]

[0055] Iteration stop condition:

[0056] mx ij {|J (t+1) -J (t) |}<ε (10)

[0057] Among them, C represents the number of clusters, N represents the number of data points, and v j represents the weight coefficient of the jth data point, represents the mth power of the membership matrix, c k represents the kth cluster center, c i represents the i-th cluster center, m represents the fuzzy weight coefficient, ε represents the error threshold, J (t+1) represents the objective function value of the t+1th iteration, J (t) Represents the objective function value at the tth iteration.

[0058] When the iteration stops, the effective classification of the original data set is completed and an accurate classification result is obtained.

[0059] In this specific embodiment, in order to evaluate the performance of the algorithm proposed in the present invention, detailed experiments will be conducted on different radar data sets, and multiple algorithms will be used for comparison. The research is mainly conducted in three aspects, namely, noise resistance research, data set sorting performance research of different radars, and research on unbalanced data sets.

[0060] Noise Immunity Study:

[0061] A data set containing four radars was generated through simulation, and different degrees of Gaussian noise were added to each parameter during the simulation to make the data distribution closer to the actual radar data. Subsequently, the performance of the algorithm was compared with other algorithms under different noise levels to evaluate its noise resistance.

[0062] Figure 2 (a) is the original data without sorting and with noise, and (b) is the sorting result after the improved FCM algorithm.

[0063] Table 1 shows the corresponding evaluation index values ​​when using different algorithms under different noise ratios. This paper uses four evaluation indicators to evaluate the performance of the algorithm: accuracy, F1 value, Rand coefficient and silhouette coefficient. The larger the value of the above evaluation indicators, the better the clustering effect.

[0064] Table 1 Clustering results of different algorithms

[0065]

[0066] From Table 1, we can see that the improved algorithm can achieve a better sorting effect for noisy data. As the proportion of noise data gradually increases, the fluctuations of accuracy, F1 value, Rand coefficient and silhouette coefficient are small, and the overall algorithm has strong anti-noise performance. From the perspective of various evaluation index values, the clustering effect of the other two algorithms is lower than that of the DF-FCM algorithm, and when the proportion of noise is high, the radar data of two categories that are close in space will be classified into one category, resulting in a significant decrease in various evaluation indicators. The silhouette coefficient values ​​of different algorithms are all lower than 0.5. The main reason is that in order to simulate the real situation when generating data, Gaussian noise is added to the radar parameters, making the data overall loose, so the values ​​of the silhouette coefficient are small.

[0067] Algorithm performance experiment:

[0068] In order to test the accuracy of the adaptive number of classes of this algorithm and compare its performance with other algorithms, three radar data sets were generated, including three, four and five radar data, respectively, to simulate different radar signal scenarios that may be encountered in the real world, so as to ensure the robustness and effect verification of the algorithm under the background of diverse data. Then, the improved DF-FCM algorithm was used to conduct experimental comparison with the SC-KMEANS algorithm (the KMEANS algorithm that realizes adaptive KMEANS algorithm combined with the silhouette coefficient) and the RI-FCM algorithm (the fuzzy C mean algorithm that realizes adaptive C value combined with the Rand coefficient).

[0069] Figure 3 The following are the sorting results of DF-FCM, SC-KMEANS, and RI-FCM algorithms on three data sets. DF-FCM-1 (Figure a), SC-KMEANS-1 (Figure b), and RI-FCM-1 (Figure c) are the sorting results of the three algorithms on three radar data sets. DF-FCM-2 (Figure d), SC-KMEANS-2 (Figure e), and RI-FCM-2 (Figure f) are the sorting results of the three algorithms on four radar data sets. DF-FCM-3 (Figure g), SC-KMEANS-3 (Figure h), and RI-FCM-3 (Figure i) are the sorting results of the three algorithms on five radar data sets. The same color and shape represent the same category. Figure 3 It can be seen that the DF-FCM algorithm can accurately classify the three data sets, while the SC-KMEANS algorithm incorrectly classifies the four-radar and five-radar data sets into three categories, and the RI-FCM algorithm classifies the four-radar data set into five categories and the five-radar data set into six categories.

[0070] Table 2 is the corresponding result data table:

[0071] Table 2 Clustering results of different algorithms

[0072]

[0073] As can be seen from Table 2, for the three-radar data set, the three algorithms can accurately identify the correct number of classes and can perform sorting well. However, for the four-radar and five-radar data sets, the RI-FCM and SC-KMEANS algorithms did not identify the correct number of classes, resulting in poor final results. The main reason is that the radar data points are separated to a large extent, while the core points are very dense, which results in the inaccurate determination of the correct number of classes during the adaptive process, and ultimately leads to incorrect sorting.

[0074] Research on Imbalanced Datasets:

[0075] The traditional fuzzy C-means clustering algorithm has a poor sorting effect on unbalanced data sets, while the DF-FCM algorithm improves the objective function of the traditional FCM algorithm by combining the weight factor of the potential value and can better handle this situation. Figure 4 Table 3 shows the sorting results of the three algorithms DF-FCM, SC-KMEANS and RI-FCM on the data set. Table 3 shows the corresponding clustering result evaluation index values:

[0076] Table 3 Clustering results of different algorithms under unbalanced data sets

[0077]

[0078] Figure 4 (a) is the result of the DF-FCM algorithm after the data field improvement, (b) is the result of the adaptive KMEANS algorithm, and (c) is the result of the adaptive fuzzy C-means clustering combined with the Rand coefficient. There are eight radars in the unbalanced data set. Only the DF-FCM algorithm can correctly sort out the three radars with fewer pulses, while the SC-KMEANS algorithm and the RI-FCM algorithm will mistakenly sort two radars into one radar, or classify radar pulses with a larger amount of data into two radars. The reason for the SC-KMEANS algorithm to misclassify is that the data points between classes are close, resulting in the classification of two close radar data into one class. The reason for the RI-FCM misclassification is that it believes that the influence of each data point on the clustering result is the same. At this time, if the number of radars in the data set is very different, the radars with fewer data points will be regarded as the edge of the adjacent class and thus classified together. The improved algorithm proposed in this paper combines the concept of potential value proposed in the data field and the average similarity between data points, constructs weight coefficients, and improves the objective function, so that the algorithm can handle this kind of data set well.

[0079] See also Figure 5 , Figure 54 is a schematic diagram of the working of the hardware device of an embodiment of the present invention, wherein the hardware device specifically comprises: a radar signal sorting device 401 improved based on the FCM algorithm, a processor 402 and a storage device 403.

[0080] A radar signal sorting device 401 improved based on the FCM algorithm: The radar signal sorting device 401 improved based on the FCM algorithm implements the radar signal sorting algorithm improved based on the FCM algorithm.

[0081] Processor 402: The processor 402 loads and executes the instructions and data in the storage device 403 to implement the radar signal sorting algorithm improved based on the FCM algorithm.

[0082] Storage device 403: The storage device 403 stores instructions and data; the storage device 403 is used to implement the radar signal sorting algorithm improved based on the FCM algorithm.

[0083] 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, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A radar signal sorting algorithm based on the improved FCM algorithm, characterized by: include: S1: Extract pulse width, carrier frequency, and arrival angle according to the pulse description word data received by the radar to form three-dimensional coordinate data, and perform normalization on the three-dimensional coordinate data; S2: According to the data field theory, the field intensity function and the potential value formula of each point are obtained; S3: Calculate the change of potential entropy with radiation factor based on the normalized data, and select the optimal radiation factor based on the minimum value of potential entropy; S4: Calculate the potential value according to the optimal radiation factor and remove noise points; S5: Adaptively determine the number of class centers based on the distribution of potential values ​​of data points; S6: Calculate the weight coefficient according to the correlation and potential value between the data points; S7: Calculate the improved objective function according to the weight coefficient and the adaptive number of clusters, and iterate to obtain the best clustering result.

2. The radar signal sorting algorithm improved based on the FCM algorithm as claimed in claim 1, characterized in that: In S2, the field strength function is: Among them, d(x a ,x b ) represents the data object x a With x b The Euclidean distance, σ is the radiation factor, and m represents the fuzzy weighting coefficient The potential value is the midpoint of the data field for x a The generated field strength function and is used to measure the influence of the position and characteristics of the data point in the data set on the overall data; the potential value function is: in, represents the potential value, represents the field strength function, d(x a ,x i ) represents the data object x a With x i The Euclidean distance, x i Represents the i-th data object.

3. The radar signal sorting algorithm improved based on the FCM algorithm as claimed in claim 1, characterized in that: In S3, the expression of potential entropy is as follows: in, represents potential entropy, S is the normalization factor, represents the potential value of the ith data point, and n represents the number of data points.

4. The radar signal sorting algorithm improved based on the FCM algorithm as claimed in claim 1, characterized in that: The specific process of S5 is as follows: (1) Initial centroid selection: The point with the largest potential value is taken as the first centroid; (2) Region expansion: For the selected cluster center, find the nearest point around it and determine whether the potential value of the point is less than the potential value of the cluster center. If so, it is classified into the cluster and the point a that is closest to any point in the cluster is found. Determine whether the potential value of the point a is less than the potential value of the point b that is closest to the point a in the current cluster. If the condition is met, point a is classified into the current cluster. Repeat the above expansion process until there are no points that meet the condition within a certain distance from the cluster center. (3) New centroid selection: From the remaining unclassified data points, select the point with the largest potential value as the new centroid. Repeat the above operation. When the number of remaining unclassified data points is less than a certain proportion of the total number of data points, stop selecting new centroids. The number of centroids at this time is the estimated number of clusters.

5. The radar signal sorting algorithm improved based on the FCM algorithm as claimed in claim 1, characterized in that: In S6, the calculation formula for the correlation between data points is: Among them, H j represents the correlation between the jth data point and the ith data point, d(x j ,x i ) represents the distance between the jth data point and the i-th data point, represents the potential value of the jth data point, represents the potential value of the ith data point, and n represents the number of data points.

6. The radar signal sorting algorithm improved based on the FCM algorithm as claimed in claim 5, characterized in that: In S6, the expression of the weight coefficient is: Among them, V j Represents the weight coefficient.

7. The radar signal sorting algorithm improved based on the FCM algorithm as claimed in claim 1, characterized in that: In S7, the improved objective function is: According to the Lagrange multiplier method, the membership matrix and cluster center that minimize the objective function J are obtained. The cluster center c i for: Membership matrix u ij for: Iteration stop condition: max ij {|J (t+1) -J (t) |}<ε Among them, C represents the number of clusters, N represents the number of data points, and v j represents the weight coefficient of the jth data point, represents the mth power of the membership matrix, c k represents the kth cluster center, c i represents the i-th cluster center, m represents the fuzzy weight coefficient, ε represents the error threshold, J (t+1) represents the objective function value of the t+1th iteration, J (t) Represents the objective function value at the tth iteration.

8. A storage device, characterized in that: The storage device stores instructions and data for implementing the radar signal sorting algorithm improved based on the FCM algorithm as described in any one of claims 1 to 7.

9. A radar signal sorting device based on the improved FCM algorithm, characterized in that: include: Processor and storage device; the processor loads and executes instructions and data in the storage device to implement the radar signal sorting algorithm improved based on the FCM algorithm as described in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Multi-mode radar signal sorting method based on data field hierarchical clustering

    CN105005029A

  • Radar signal sorting method based on potential distance graph combined PCA and improved cloud model

    CN113625242A

  • Density peak clustering algorithm based on dynamic K neighbor representative points

    CN113657419A

  • A hybrid method to identify optimal initial cluster center for clustering

    IN201841029493A

  • Apparatus and method for detecting and removing outliers using sensitivity score

    IN201841036828A

Cited By

  • Multifunctional radar signal sorting method and system based on hypergraph

    CN119902174A