Data semantic dual-driven joint spectrum map construction and signal source positioning method

Abstract

The invention discloses a data semantic dual-driven joint spectrum map construction and signal source positioning method. The method comprises the following steps: acquiring spectrum data and preprocessing the spectrum data; establishing a frequency-space domain combined three-dimensional spectrum map representation model; creating a binary city map and a binary sampling position map; the training set trains the network; calculating the total loss; updating the weight parameters; judging whether the current iteration frequency reaches the set maximum frequency or not; inputting the verification set data into a neural network model for spectrum map construction and signal source positioning; and processing an output result to obtain a complete frequency spectrum map and a grid position of the signal source in the target area. According to the method, a binary city map and a binary sampling location map are introduced as semantic knowledge to extract spatial information influencing signal propagation, a multi-task learning joint training framework sharing a bottom layer is designed, and meanwhile, spectrum map construction and signal source positioning are realized; and the precision of spectrum map construction and signal source positioning in a complex urban environment is remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of wireless communications, and in particular relates to a data-semantics dual-driven joint spectrum map construction and signal source positioning method. Background Art

[0002] With the rapid development of wireless communication technology and the continuous increase in the number of wireless devices in urban environments, signal source positioning has become increasingly important in modern cities. Complex electromagnetic environments, high-density building obstructions, and multipath effects often lead to a lack of line-of-sight between user equipment (UE) and global positioning system (GPS) satellites, which affects the positioning effect, especially in dense urban areas. In order to meet the above challenges, positioning methods based on spectrum maps have gradually become a research hotspot. Spectrum map construction is an effective technology that can characterize the distribution and utilization of spectrum resources at different frequencies in the area of ​​interest. By constructing a high-precision spectrum map, the propagation characteristics of electromagnetic signals can be more intuitively reflected, thereby improving the accuracy of signal source positioning.

[0003] In recent years, deep learning has promoted the development of spectrum map construction and signal source localization by learning the propagation rules of signals in an end-to-end manner directly from raw spectrum data. Wang X, Wang X, Mao S, et al. proposed an indoor positioning method based on spectrum map in their paper "Indoor Radio Map Construction and Localization With Deep Gaussian Processes" (IEEE Internet Things J., vol.7, no.11, pp.11238-11249, 2020). This method first uses Deep Map to generate an accurate and complete spectrum map, and then achieves positioning through deep Gaussian process. Experiments have shown that the positioning accuracy of this method in indoor scenes is significantly better than that of traditional methods. However, due to the wide range of urban environments and limited sampling data, this method has limited positioning accuracy in large-scale outdoor scenes. To this end, Yapar C, Levie R, Kutyniok G, et al. designed a positioning network LocUNet specifically for urban environments in their paper "Real-Time Outdoor Localization Using Radio Maps: A Deep Learning Approach" (IEEE Trans. Wireless Commun., vol. 22, no. 12, pp. 9703-9717, 2023). By using the estimated complete spectrum map and the RSS measurement value of the user to be located, the positioning of users in dense urban scenes is achieved. However, this method relies heavily on the accuracy of spectrum map construction. If there is a large error in the spectrum map, the target position cannot be accurately located.

[0004] The patent application number CN202310813202.7 proposes a joint solution method for locating radiation sources and constructing spectrum maps in combination with terrain. This method optimizes the radiation source position and propagation model parameters through joint iteration, and obtains the final result after iterative convergence. Although this method achieves the joint optimization of spectrum map construction and radiation source positioning, it fails to effectively cope with dynamically changing environments, and the calculation is relatively complex and there is a problem of limited computing resources.

[0005] In summary, most deep learning methods follow the strategy of "build first, then locate", focusing on the high-precision construction of spectrum maps under sparse data, and the positioning effect is highly dependent on the construction accuracy of the spectrum map. In addition, existing methods are usually unable to effectively cope with dynamically changing environments and the need for real-time updates, and with limited computing resources, the spectrum map construction and positioning process may face high computational complexity. Therefore, it is urgent to develop new spectrum map construction and radiation source positioning methods. Summary of the invention

[0006] The technical problem to be solved by the present invention is to address the deficiencies of the above-mentioned prior art and provide a data-semantics dual-driven joint spectrum map construction and signal source positioning method. Based on a joint training framework, spectrum map construction and signal source positioning are simultaneously realized, and city maps and sampling location maps are introduced as semantic knowledge. This not only significantly improves the construction accuracy of spectrum maps in complex urban environments and reduces the positioning error of signal sources, but also maintains a low network complexity, and has broad application potential in actual communication scenarios.

[0007] In order to achieve the above technical objectives, the technical solution adopted by the present invention is:

[0008] The data-semantics-driven joint spectrum map construction and signal source localization method includes:

[0009] Step 1: Multiple sensing nodes randomly deployed in the target area collect spectrum data and perform data normalization preprocessing;

[0010] Step 2, spatially discretize the target area and establish a frequency-space joint three-dimensional spectrum map representation model as spectrum data;

[0011] Step 3, creating a binary city map and a binary sampling location map as semantic knowledge;

[0012] Step 4, using the training set consisting of semantic knowledge and spectrum data to train a neural network model for spectrum map construction and signal source location;

[0013] Step 5, respectively calculate the loss of the spectrum map construction task and the loss of the signal source localization task, and sum them up by weight parameters to obtain the total loss of the neural network model;

[0014] Step 6: Use a dynamic adjustment mechanism to update the weight parameters according to the weight adjustment factor and the loss threshold;

[0015] Step 7, determine whether the current number of iterations reaches the set maximum number of iterations. If so, proceed to step 8. If not, increase the number of iterations by one and return to step 4 to continue training.

[0016] Step 8, input the validation set data into the neural network model for spectrum map construction and signal source location to obtain the output result;

[0017] Step 9: Process the output result to obtain a complete spectrum map and the grid position of the signal source in the target area.

[0018] To optimize the above technical solutions, the specific measures taken also include:

[0019] The above step 2 includes:

[0020] The target area is spatially discretized and a two-dimensional spectrum map completion model is established. The model completes the grid values ​​in the target area after spatial discretization according to the collected data and the unmonitored frequencies to form a corresponding two-dimensional spectrum map, and then obtains a three-dimensional spectrum map representation model of the target area in the frequency-space domain. The specific details are as follows:

[0021] (1) If there are m sensing nodes in the grid I = (i, j), the grid is assigned the normalized average value of the spectrum data collected by these m sensing nodes; otherwise, the grid is assigned 0, and the frequency f that can be monitored in the target area is obtained. k Incomplete spectrum graph S on k ;

[0022] (2) setting all the values ​​of the spectrum map grids on the unmonitored frequency f0 to 0, forming a blank two-dimensional spectrum map E0 on the unmonitored frequency f0 as the target spectrum map to be inferred;

[0023] (3) The frequency f that can be monitored in the target area k Incomplete spectrum graph S on k The blank two-dimensional spectrum map E0 at the unmonitored frequency f0 is stacked in ascending order according to the frequency dimension to obtain a frequency-space domain joint three-dimensional spectrum map representation model of the target area.

[0024] Step 3 above creates a binary city map as follows:

[0025]

[0026] Where Z i,j represents the value of the binary city map at the grid I = (i, j) in the target area after spatial discretization;

[0027] Create a binary sample location map as follows:

[0028]

[0029] Among them, M i,j Represents the value of the binary sampling position map at the grid I = (i, j) in the target area after spatial discretization.

[0030] The above step 4 is as follows:

[0031] (1) Feature fusion of semantic knowledge and spectral data to obtain data semantic fusion features;

[0032] (2) The data semantic fusion features are respectively input into the spectrum map construction network DSD-UNet and the signal source localization network DSD-ResNet of the neural network model. DSD-UNet completes the incomplete spectrum map to reflect the distribution of signal strength in the entire area. The features of the frequency-space joint three-dimensional spectrum map representation model extracted by the spectrum map construction network DSD-UNet are input into the signal source localization network DSD-ResNet. DSD-ResNet locates the signal source to grasp the precise location of different signal sources in the area.

[0033] The above (1) is specifically as follows: the frequency-space joint three-dimensional spectrum map representation model, the binary city map, and the binary sampling location map are divided into three channels and input into the shared layer of the neural network model, and the underlying features are extracted through the shared layer to realize the feature fusion of semantic knowledge and spectrum data.

[0034] The loss of the spectrum map construction task described in step 5 above is calculated as follows:

[0035]

[0036] Where K represents the total number of frequency points; N×N represents the total number of spectrum map grids; E k,i,j Indicates frequency f k The received signal strength at each grid point on the spectrum map; P k,i,j Indicates frequency f k The received signal strength of the corresponding grid point on the real spectrum map; represents the loss of the spectrum map construction task.

[0037] The calculation formula for the loss of the signal source localization task described in step 5 above is as follows:

[0038]

[0039] Among them, p t Indicates the confidence of the model prediction; α t represents the sample weight hyperparameter; γ represents the focusing parameter; Represents the loss of the signal source localization task.

[0040] The total loss of the neural network model described in step 5 above is:

[0041]

[0042] in, Represents the total loss of the neural network model; represents the weight parameter of the spectrum map construction task, Represents the weight parameter of the signal source localization task.

[0043] The updating formula of the weight parameter described in step 6 above is as follows:

[0044]

[0045] in, represents the weight parameter of the spectrum map construction task; represents the updated spectrum map construction task weight parameter; Represents the weight parameter of the signal source localization task; represents the updated weight parameter of the signal source localization task; β represents the weight adjustment factor; represents the loss of the spectrum map construction task; represents the loss of the signal source localization task; loss threshold for the spectrum map construction task; Loss threshold for the signal source localization task.

[0046] The above step 9 denormalizes the data output by the spectrum map construction network of the neural network model to obtain a complete spectrum map:

[0047] P=(P max -P min )·P out +P min

[0048] Among them, P represents the spectrum data after anti-normalization, P min represents the minimum value of the spectrum data output by the spectrum map construction network, P max represents the maximum value of the spectrum data output by the spectrum map construction network, P out Represents the spectrum data output by the spectrum map construction network;

[0049] The signal source position mask output by the signal source localization network of the neural network model is processed to extract the area marked as the signal source in the mask. The coordinates corresponding to the area are the grid positions of the signal source in the target area.

[0050] The present invention has the following beneficial effects:

[0051] First, to address the problems of low accuracy in spectrum map construction and large signal source positioning errors caused by limited data in urban environments, the present invention introduces binary city maps and binary sampling position maps as semantic knowledge, and proposes a data-semantics dual-driven method to extract spatial information that affects signal propagation, which is beneficial to the intrinsic mechanism of signal propagation in the spatial domain reasoning by neural networks.

[0052] Second, the present invention designs a neural network framework for joint spectrum map construction and signal source localization driven by both data and semantics. Based on the multi-task learning idea of ​​sharing the underlying layer, the spectrum map construction and signal source localization tasks are collaboratively optimized, thereby realizing information sharing and mutual promotion between different tasks. By jointly training and collaboratively optimizing the two tasks, the accuracy of spectrum map construction in complex urban environments is significantly improved, and the positioning error of signal sources is reduced, especially in scenarios with low sampling density and multiple signal sources.

[0053] Third, in the network framework designed by the present invention, three-dimensional convolution is used to construct a frequency-space domain joint three-dimensional spectrum map representation model, so that the network can achieve complete spectrum map construction without sampling all frequencies of the spectrum data, thereby improving the integrity of the spectrum map construction.

[0054] Fourth, the present invention adopts MSE and FocalLoss as loss functions for the spectrum map construction task and the signal source location task respectively, and realizes the collaborative optimization of multi-task learning by dynamically adjusting the weight parameters. Specifically, a dynamic adjustment mechanism is adopted to update the weight parameters in real time according to the weight adjustment factor and the loss threshold, ensuring that the model can quickly adapt to more difficult tasks during the training process, while ensuring the balanced optimization of the two tasks, thereby improving the training efficiency and performance of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a flow chart of the method of the present invention;

[0056] Figure 2 It is a network structure framework diagram of the present invention;

[0057] Figure 3 It is a comparison chart of the visualization effects of the spectrum maps constructed by the present invention and other methods;

[0058] Figure 4 is a comparison diagram of spectrum map construction errors of the present invention and other methods in different scenarios;

[0059] Figure 5 It is a comparison chart of signal source positioning errors of the present invention and other methods in different scenarios. DETAILED DESCRIPTION

[0060] The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings.

[0061] The data-semantics-driven joint spectrum map construction and signal source localization method of the present invention aims to solve the problems of low spectrum map construction accuracy and large signal source localization error caused by limited data in urban environments. It innovatively introduces binary city maps and binary sampling location maps as semantic knowledge, and proposes a data-semantics-driven method to extract spatial information that affects signal propagation. On this basis, a data-semantics-driven joint spectrum map construction and signal source localization framework is designed. Through joint training and collaborative optimization of the two tasks, the accuracy of spectrum map construction and signal source localization in complex urban environments is significantly improved, especially in low sampling density and multiple signal source scenarios. Figure 1-Figure 2 The specific steps of the method of the present invention are described as follows.

[0062] Step 1: spectrum data acquisition and preprocessing.

[0063] The first step is to select the target area And randomly deploy N R The number of sensing nodes is determined according to the sampling density. The collected spectrum data is uploaded to the central database for preprocessing.

[0064] The second step is to perform maximum and minimum normalization operations on the collected spectrum data, and the spectrum data will be normalized to [0,1]. The spectrum data is normalized to:

[0065]

[0066] Where P represents the real spectrum data, P min Represents the minimum value of all spectrum data, P max represents the maximum value of all spectrum data, and P′ represents the normalized spectrum data.

[0067] Step 2: Establish a three-dimensional spectrum map representation model that combines frequency and space domains.

[0068] The first step is to target the area Perform spatial discretization;

[0069] The second step is to establish a two-dimensional spectrum map completion model;

[0070] If there are m sensing nodes in the grid I = (i, j), the received signal strength value of the grid is the average of the received signal strengths of these m sensing nodes. Otherwise, the received signal strength value at the grid is set to 0. That is, if there are m sensing nodes in the grid I = (i, j), the grid is assigned the normalized average of the spectrum data collected by these m sensing nodes, otherwise, the grid is assigned 0, and the frequency f that can be monitored in the target area is obtained. k Incomplete spectrum graph S on k .

[0071] The third step is to establish a three-dimensional spectrum map representation model that combines frequency and space domains.

[0072] In the embodiment of the present invention, due to the complex propagation characteristics of the urban environment and the performance limitations of the sampling receiver, some frequency bands may not be monitored, and the sensing node cannot obtain spectrum data on all frequencies. Therefore, the values ​​of the spectrum map on the unmonitored frequency f0 are all set to 0, forming a blank two-dimensional spectrum map, and the spectrum map on this frequency is the target spectrum map to be inferred. Then, the frequency f0 that can be monitored in the target area is k The incomplete spectrum S k The blank spectrum map E0 on the unmonitored frequency f0 is stacked in ascending order according to the frequency dimension. Thus, a three-dimensional spectrum map representation model of the frequency-space domain joint can be obtained.

[0073] Step 3, create a binary city map and a binary sampling location map as semantic knowledge.

[0074] The first step is to create a binary city map according to the following rules

[0075]

[0076] Where I = (i, j) represents the position coordinates of the grid within the target area, Z i,j Represents the value of the binary city map at grid I = (i, j).

[0077] The second step is to create a binary sampling location map according to the following rules

[0078]

[0079] Where I = (i, j) represents the position coordinates of the grid in the target area, M i,j Represents the value of the binary sampling position map at grid I = (i, j).

[0080] Step 4: Input the training set data into the network model.

[0081] The first step is to extract data semantic fusion features;

[0082] The frequency-space joint three-dimensional spectrum map representation model, binary city map and binary sampling location map are divided into three channels and input into the shared layer of the network. The underlying features are extracted through the shared layer to achieve the feature fusion of semantic knowledge and spectrum data.

[0083] In the second step, the data semantic fusion features are input into the spectrum map construction network and the signal source localization network respectively;

[0084] A multi-task learning framework with shared underlying layers is designed. Spectrum map construction and signal source localization share the same underlying features, and then are split into two networks to perform two different tasks: spectrum map construction and signal source localization. DSD-UNet is responsible for completing the missing spectrum map to reflect the distribution of signal strength in the entire area; DSD-ResNet is used to locate the signal source. The features of the frequency-space joint three-dimensional spectrum map representation model extracted by the spectrum map construction network DSD-UNet are input into the signal source localization network DSD-ResNet. By inputting the features extracted by DSD-UNet, DSD-ResNet can use the signal propagation laws learned in the spectrum map construction task to make up for the impact of insufficient data, thereby more accurately grasping the locations of different signal sources in the area.

[0085] In the third step, some features of the spectrum map construction network are integrated into the signal source localization network to alleviate the impact of severe lack of spectrum data in low sampling density scenarios.

[0086] In the embodiment of the present invention, due to the limited amount of available spectrum data and the serious lack of spectrum data, even with the help of semantic knowledge to assist neural network reasoning, it is still difficult to effectively solve the problem of feature loss and resolution degradation caused by insufficient data, which in turn affects the precise positioning of the signal source. To this end, some features in the spectrum map construction network are integrated into the signal source positioning network to alleviate the impact of serious lack of spectrum data in low sampling density scenarios.

[0087] Step 5: Calculate the network loss.

[0088] The spectrum map construction is a regression problem. MSE is used to measure the difference between the completed spectrum map and the true spectrum map. The calculation formula is as follows:

[0089]

[0090] Where K represents the total number of frequency points; N×N represents the total number of grids in the spectrum map; K×N×N represents the total number of samples, including the number of all frequencies and their corresponding grid points; E k,i,j Indicates frequency f k The received signal strength at each grid point on the spectrum map; P k,i,j Indicates frequency f k The received signal strength of the corresponding grid point on the real spectrum map; represents the loss of the spectrum map construction task.

[0091] Since the signal source localization task outputs the signal source position mask, Focal Loss is used as the objective function, and the calculation formula is as follows:

[0092]

[0093] Among them, p t Represents the confidence of the model prediction: for the signal source location, the probability of the prediction being positive is p; for the non-signal source location, the probability is 1-p; α t represents the sample weight hyperparameter, which is used to adjust the weights of positive and negative samples. γ represents the focusing parameter, which is used to reduce the impact of negative samples on the loss; Represents the loss of the signal source localization task.

[0094] After calculating the spectrum map construction error and signal source location error Finally, the total loss function of the network is designed as:

[0095]

[0096] in, represents the total loss of the network; represents the loss of the spectrum map construction task; represents the loss of the spectrum map construction task; weight parameter and Control the contribution of completion error and localization error to the total loss respectively.

[0097] When all batches of data in the training data are fully back-propagated, it is considered an epoch.

[0098] Step 6: After inputting the test set data into the network, update the weight parameters according to the test results.

[0099] In the overall loss of the network, the weight parameter and It is not fixed during the training process, but is adjusted through error feedback. Initially, the two tasks are assigned the same weight. In the subsequent training process, the threshold in the current window is obtained by recording the historical test errors of each task and calculating the average error in the sliding window. When the error of a task exceeds its threshold, it means that the task is currently difficult to optimize, and the weight parameter of the task needs to be adjusted by multiplying it by the weight adjustment factor β. On the contrary, if the error of the task is lower than the threshold, the weight remains unchanged. The weight update method is as follows:

[0100]

[0101] in, represents the weight parameter of the spectrum map construction task; represents the updated spectrum map construction task weight parameter; represents the loss of the spectrum map construction task; Represents the weight parameter of the signal source localization task; Represents the updated weight parameter of the signal source localization task; represents the loss of the signal source localization task; β represents the weight adjustment factor.

[0102] Through this dynamic adjustment mechanism, the model can automatically balance the losses of the two tasks of spectrum completion and radiation source localization during the training process, enabling the network to quickly adapt to more difficult tasks in the early stages of training, and maintain a balance between the two tasks in the later stages, thereby improving the efficiency and effectiveness of joint training.

[0103] Step 7: Determine whether the network training is complete.

[0104] Determine whether the current epoch has reached the set maximum epoch. If so, proceed to step 8. If not, increase the epoch by one and return to step 4 to continue training the network.

[0105] Step 8: Input the validation set data into the network.

[0106] Step 9: Process the output results to obtain a complete spectrum map and signal source location.

[0107] Denormalize the data output by the spectrum map construction network to obtain a complete spectrum map:

[0108] P=(P max -P min )·P out +P min

[0109] Among them, P represents the spectrum data after anti-normalization, P min represents the minimum value of the spectrum data output by the spectrum map construction network, P max represents the maximum value of the spectrum data output by the spectrum map construction network, P out Represents the spectrum data output by the spectrum map construction network.

[0110] The signal source location mask output by the signal source localization network is processed to extract the area marked as the signal source in the mask. The coordinates corresponding to this area are the grid positions of the signal source in the target area.

[0111] The effect of the present invention is further described below in conjunction with simulation experiments.

[0112] 1. Simulation conditions and parameter settings:

[0113] The simulation experiment of the present invention is carried out on the simulation platform of Python 3.10 and Pytorch 1.12.1.

[0114] The computer CPU model is Intel Core i9, and it is equipped with an independent graphics card model NVIDIA GeForce RTX 3090.

[0115] The sensing nodes are randomly deployed in the target area with a sampling density of 5%, 10%, 15%, and 20%, and the number of signal sources is single or multiple.

[0116] The simulation experiment covers eight scenarios in total with four sampling densities and two numbers of signal sources.

[0117] In addition, in each scenario, the training set contains 20,000 samples, the test set contains 1,000 samples, and the validation set contains 200 samples.

[0118] The maximum number of iterations for network training is 50, the initial learning rate is set to 0.0003, the Adam optimization algorithm is used as the network training optimizer, and the sample size of each batch is 64.

[0119] 2. Simulation content:

[0120] Figure 3 The comparison of the visualization effect of the spectrum map constructed by the present invention and other methods in the scenario of multiple signal sources with a sampling density of 5% is shown. Figure 3 The image in the upper left corner is the actual spectrum map. Figure 4 The figure in the upper right corner is the spectrum map estimated by the proposed method. Figure 4 The lower left image is the spectrum map estimated by CGAN. Figure 4 The lower right corner is the spectrum map obtained by Kriging estimation. By comparison, it can be seen that the spectrum map constructed by the present invention is closer to the real spectrum map, and can show a more accurate fit in terms of the spatial distribution of the spectrum map and the change of signal strength. Compared with the traditional method, the present invention shows a significant advantage in the recovery of the details of the spectrum map, indicating the superiority of the proposed model in the visualization of spectrum map construction.

[0121] Figure 4 The comparison of spectrum map construction errors of the present invention and other methods in different scenarios is shown. Figure 4The horizontal axis represents the sampling density, and the vertical axis represents the spectrum map construction error. The broken line marked with a square represents the spectrum map construction error of the method of the present invention under different sampling density conditions in the scenario of multiple signal sources; the broken line marked with a diamond represents the spectrum map construction error of the CGAN method under different sampling density conditions in the scenario of multiple signal sources; the broken line marked with an inverted triangle represents the spectrum map construction error of the Kriging method under different sampling density conditions in the scenario of multiple signal sources; the broken line marked with a circle represents the spectrum map construction error of the method of the present invention under different sampling density conditions in the scenario of a single signal source; the broken line marked with a star represents the spectrum map construction error of the CGAN method under different sampling density conditions in the scenario of a single signal source; the broken line marked with an x ​​represents the spectrum map construction error of the Kriging method under different sampling density conditions in the scenario of a single signal source.

[0122] Figure 4 The results show that with the increase of sampling density, the construction error of each method tends to decrease. This is because a higher sampling density can provide more spectral data, thereby more accurately learning the signal propagation characteristics. In addition, the accuracy of the method of the present invention is improved by about 25.92% compared with the CGAN method and by about 43.87% compared with the Kriging method. In particular, in the multi-signal source scenario with a sampling density of 5%, the RMSE of the method of the present invention is 2.17dB lower than that of the CGAN method and 3.97dB lower than that of the Kriging method. These results fully demonstrate the effectiveness of the method of the present invention in various sampling density and signal source number scenarios, especially in low sampling density and multi-signal source scenarios.

[0123] Figure 5 The comparison of signal source positioning errors between the present invention and other methods in different scenarios is demonstrated. Figure 5 (a) shows the signal source positioning errors of the present invention and other methods at different sampling densities in a multi-signal source scenario. Figure 5 (b) shows the signal source positioning error of the present invention and other methods at different sampling densities in a single signal source scenario.

[0124] Figure 5The horizontal axis represents the sampling density, and the vertical axis represents the average positioning error. The results show that the method of the present invention is significantly better than other methods in positioning effect. The KNN method and the K-means method perform poorly in positioning accuracy. Although LocUNet can have a low positioning error in single signal source and high sampling density scenarios, the effect decreases under low sampling density. In contrast, the method of the present invention can achieve a positioning error close to 0 in single signal source scenarios and low sampling density scenarios, and maintain stable positioning performance in multi-signal source scenarios. It can accurately distinguish the positions of multiple signal sources and achieve ultra-low error positioning. Compared with the positioning ambiguity or error amplification problems often faced by traditional methods in complex scenes, the proposed method demonstrates excellent robustness and positioning accuracy. The experimental results further verify the adaptability of the present invention in complex environments and its significant positioning performance advantages.

[0125] Based on the above simulation results and analysis, the data and semantics dual-driven joint spectrum map construction and signal source localization method proposed in this invention is superior to existing methods in terms of spectrum map detail recovery capability, spectrum map construction accuracy and signal source localization error, especially in low sampling density and multiple signal source scenarios. This method not only significantly improves the accuracy of spectrum maps and signal source localization, but also maintains a low network complexity, making it have a wide range of application potential in actual communication scenarios.

[0126] The above are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should be regarded as the protection scope of the present invention.

Claims

1. A data-semantics-driven joint spectrum map construction and signal source localization method, characterized in that: include: Step 1: Multiple sensing nodes randomly deployed in the target area collect spectrum data and perform data normalization preprocessing; Step 2, spatially discretize the target area and establish a frequency-space joint three-dimensional spectrum map representation model as spectrum data; Step 3, creating a binary city map and a binary sampling location map as semantic knowledge; Step 4, using the training set consisting of semantic knowledge and spectrum data to train a neural network model for spectrum map construction and signal source location; Step 5, respectively calculate the loss of the spectrum map construction task and the loss of the signal source localization task, and sum them up by weight parameters to obtain the total loss of the neural network model; Step 6: Use a dynamic adjustment mechanism to update the weight parameters according to the weight adjustment factor and the loss threshold; Step 7, determine whether the current number of iterations reaches the set maximum number of iterations. If so, proceed to step 8. If not, increase the number of iterations by one and return to step 4 to continue training. Step 8, input the validation set data into the neural network model for spectrum map construction and signal source location to obtain the output result; Step 9: Process the output result to obtain a complete spectrum map and the grid position of the signal source in the target area.

2. The data-semantics dual-driven joint spectrum map construction and signal source localization method according to claim 1 is characterized in that: The step 2 comprises: The target area is spatially discretized and a two-dimensional spectrum map completion model is established. The model completes the grid values ​​in the target area after spatial discretization according to the collected data and the unmonitored frequencies to form a corresponding two-dimensional spectrum map, and then obtains a three-dimensional spectrum map representation model of the target area in the frequency-space domain. The specific details are as follows: (1) If there are m sensing nodes in the grid I = (i, j), the grid is assigned the normalized average value of the spectrum data collected by these m sensing nodes; otherwise, the grid is assigned 0, and the frequency f that can be monitored in the target area is obtained. k Incomplete spectrum graph S on k ; (2) setting all the values ​​of the spectrum map grids on the unmonitored frequency f0 to 0, thereby forming a blank two-dimensional spectrum map E0 on the unmonitored frequency f0 as the target spectrum map to be inferred; (3) The frequency f that can be monitored in the target area k Incomplete spectrum graph S on k The blank two-dimensional spectrum map E0 at the unmonitored frequency f0 is stacked in ascending order according to the frequency dimension to obtain a frequency-space domain joint three-dimensional spectrum map representation model of the target area.

3. The data-semantics dual-driven joint spectrum map construction and signal source localization method according to claim 1 is characterized in that: The step 3 creates a binary city map as follows: Where Z i,j represents the value of the binary city map at the grid I = (i, j) in the target area after spatial discretization; Create a binary sample location map as follows: Among them, M i,j Represents the value of the binary sampling position map at the grid I = (i, j) in the target area after spatial discretization.

4. The data-semantics dual-driven joint spectrum map construction and signal source localization method according to claim 1 is characterized in that: The step 4 is specifically as follows: (1) Feature fusion of semantic knowledge and spectral data to obtain data semantic fusion features; (2) The data semantic fusion features are respectively input into the spectrum map construction network DSD-UNet and the signal source localization network DSD-ResNet of the neural network model. DSD-UNet completes the incomplete spectrum map to reflect the distribution of signal strength in the entire area. The features of the frequency-space joint three-dimensional spectrum map representation model extracted by the spectrum map construction network DSD-UNet are input into the signal source localization network DSD-ResNet to locate the signal source, thereby grasping the location of different signal sources in the area.

5. The data-semantics dual-driven joint spectrum map construction and signal source localization method according to claim 4 is characterized in that: Specifically, the (1) is as follows: dividing the frequency-space joint three-dimensional spectrum map representation model, the binary city map, and the binary sampling location map into three channels and inputting them into the shared layer of the neural network model, extracting the underlying features through the shared layer, and realizing the feature fusion of semantic knowledge and spectrum data.

6. The data-semantics dual-driven joint spectrum map construction and signal source localization method according to claim 1, characterized in that: The loss of the spectrum map construction task in step 5 is calculated as follows: Where K represents the total number of frequency points; N×N represents the total number of spectrum map grids; E k,i,j Indicates frequency f k The received signal strength at each grid point on the spectrum map; P k,i,j Indicates frequency f k The received signal strength of the corresponding grid point on the real spectrum map; represents the loss of the spectrum map construction task.

7. The data-semantics dual-driven joint spectrum map construction and signal source localization method according to claim 1, characterized in that: The calculation formula for the loss of the signal source localization task in step 5 is as follows: Among them, p t Indicates the confidence of the model prediction; α t represents the sample weight hyperparameter; γ represents the focusing parameter; Represents the loss of the signal source localization task.

8. The data-semantics dual-driven joint spectrum map construction and signal source localization method according to claim 1, characterized in that: The total loss of the neural network model in step 5 is: in, Represents the total loss of the neural network model; represents the weight parameter of the spectrum map construction task, Represents the weight parameter of the signal source localization task.

9. The data-semantics dual-driven joint spectrum map construction and signal source localization method according to claim 1, characterized in that: The updating formula of the weight parameter in step 6 is as follows: in, represents the weight parameter of the spectrum map construction task; represents the updated spectrum map construction task weight parameter; Represents the weight parameter of the signal source localization task; represents the updated weight parameter of the signal source localization task; β represents the weight adjustment factor; represents the loss of the spectrum map construction task; represents the loss of the signal source localization task; loss threshold for the spectrum map construction task; Loss threshold for the signal source localization task.

10. The data-semantics dual-driven joint spectrum map construction and signal source localization method according to claim 1, characterized in that: The step 9 denormalizes the data output by the spectrum map construction network of the neural network model to obtain a complete spectrum map: P=(P max -P min )·P out +P min Among them, P represents the spectrum data after denormalization, P min represents the minimum value of the spectrum data output by the spectrum map construction network, P max represents the maximum value of the spectrum data output by the spectrum map construction network, P out Represents the spectrum data output by the spectrum map construction network; The signal source position mask output by the signal source localization network of the neural network model is processed to extract the area marked as the signal source in the mask. The coordinates corresponding to the area are the grid positions of the signal source in the target area.

Images