Space-frequency coding and modulation scheme joint identification method for MIMO-OFDM system under unknown noise

Abstract

This invention specifically relates to a joint identification method for space-frequency coding and modulation schemes in MIMO-OFDM systems under unknown noise conditions. The method includes: designing a feature extraction mechanism based on interpolated trajectory maps, utilizing the differences in the trajectory structure of different combinations of space-frequency coding and modulation schemes in the complex plane, and extracting interpolated trajectory maps from the signal after generalized linear regularization denoising through nonlinear rotation and linear interpolation; introducing a gray-level enhancement mechanism based on the cumulative distribution function, using the cumulative distribution function mapping mechanism to adaptively enhance the gray-level information in regions with low frequency occurrences in the trajectory map; and designing a joint identification network based on a multiple attention mechanism, constructing a shallow ResNet network incorporating the multiple attention mechanism to enhance the feature representation ability of channel information and key spatial structure information, thereby achieving joint identification of space-frequency coding and modulation schemes. Simulation results show that the method of this invention has good joint identification performance and noise adaptability under unknown noise environments, and does not rely on any prior information.

Description

Technical Field

[0001] This invention relates to the field of communication signal recognition technology in cognitive radio, and in particular to a method and system for joint recognition of space-frequency coding and modulation scheme of multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) signals under unknown noise. Background Technology

[0002] Signal recognition, as a crucial component of intelligent communication receiving systems, holds significant application value in fields such as electromagnetic spectrum monitoring, electromagnetic spectrum warfare, and cognitive radio. Currently, Multiple-Input Multiple-Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) systems have become an important technology in modern wireless communication systems due to their combination of the spatial diversity advantages of MIMO and the frequency-selective fading resistance of OFDM. With the widespread application of MIMO-OFDM systems, the demand for signal structure information at the receiver is constantly increasing. Spatial-frequency coding, by introducing frequency domain redundancy between adjacent subcarriers, can effectively improve the system's anti-fading capability and transmission reliability. Therefore, accurate identification of spatial-frequency coding types has become an important prerequisite for subsequent parameter estimation, signal detection, and demodulation processing.

[0003] Numerous research achievements have been made in SFBC-OFDM identification of MIMO-OFDM signals. Existing technologies can be broadly classified into two categories: traditional identification methods and intelligent identification methods. Traditional identification methods mainly extract the statistical features of the signal and combine them with classification criteria such as hypothesis testing, peak detection, decision trees, or support vector machines to achieve signal identification. The basic idea is to use methods such as probability statistics, cross-correlation analysis, and random matrix theory to model and discriminate the received signal.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] This invention provides a method for joint identification of space-frequency coding and modulation scheme in MIMO-OFDM systems under unknown noise conditions, which addresses the problem that current space-frequency coding identification technologies are insufficient in adapting to changes in noise statistical characteristics under unknown noise environments.

[0006] Other features and advantages of the invention will become apparent from the following detailed description, or may be learned in part by practice of the invention.

[0007] According to a first aspect of the present invention, a method for joint identification of space-frequency coding and modulation scheme in a MIMO-OFDM system under unknown noise is provided, the method comprising: Step 1: Design a feature extraction mechanism based on interpolation trajectory map. Utilize the differences in the complex plane trajectory structure caused by different combinations of space frequency coding and modulation methods, and extract the interpolation trajectory map from the signal after generalized linear regularization noise reduction through nonlinear rotation and linear interpolation. Step 2: Introduce a gray-scale enhancement mechanism based on the cumulative distribution function. Using the cumulative distribution function mapping mechanism, adaptively enhance the gray-scale information of the low-frequency regions in the interpolation trajectory map, and extract the interpolation trajectory map after gray-scale mapping. Step 3: Design a joint recognition network based on a multi-attention mechanism. Construct a shallow ResNet network that incorporates a multi-attention mechanism to enhance the feature representation capabilities of channel information and key spatial structure information. Input the enhanced interpolated trajectory map into the joint recognition network based on the multi-attention mechanism to achieve joint recognition of space-frequency coding and modulation methods.

[0008] In some exemplary embodiments, the feature extraction mechanism based on the interpolation trajectory map specifically includes: The received signal is preprocessed with generalized regular noise reduction, and the FISTA algorithm is used to solve for the noise-reduced signal. The noise-reduced signal is converted from parallel to serial, and the converted serial symbol sequence is then subjected to nonlinear rotation mapping. The discrete trajectory points are connected using a linear interpolation method to generate an interpolated trajectory map.

[0009] In some exemplary embodiments, the step of performing parallel-to-serial conversion on the noise-reduced signal and applying nonlinear rotation mapping to the converted serial symbol sequence specifically involves: make For the first parallel-to-serial transformation in the complex plane Each symbol is represented as: Perform a nonlinear phase transformation on it:

[0010] in, For the transformation parameters, , Indicates the first The corresponding coordinate values ​​of each symbol.

[0011] In some exemplary embodiments, the connection of discrete trajectory points using a linear interpolation method specifically involves: Let two adjacent trajectory points be respectively and , Using interpolation parameters, a linear interpolation method is used to connect the discrete trajectory points:

[0012] in, This represents the intermediate trajectory point obtained by linear interpolation of two adjacent trajectory points.

[0013] In some exemplary embodiments, the grayscale enhancement mechanism based on the cumulative distribution function specifically includes: By incorporating pixel value statistical distribution information, the interpolation trajectory map is divided into different matrix regions; A gray-level mapping relationship is constructed based on the cumulative distribution function corresponding to the matrix element values; Adaptive grayscale enhancement is performed on the interpolated trajectory map based on the aforementioned grayscale mapping relationship.

[0014] In some exemplary embodiments, the construction of the gray-level mapping relationship based on the cumulative distribution function corresponding to the matrix element values ​​specifically includes: Let the cumulative distribution function corresponding to a certain element value in the feature map matrix be... Its grayscale mapping relationship is expressed as: .

[0015] In some exemplary embodiments, the joint recognition network based on the multi-attention mechanism specifically includes: Use the grayscale-enhanced interpolated trajectory map as the network input; An SE attention mechanism is introduced to improve the residual block and enhance the ability to represent channel features; Introducing a CA coordinate attention mechanism enhances the ability to represent spatial structural features; An improved shallow ResNet network is constructed to output the joint identification result of space frequency coding and modulation mode.

[0016] According to a second aspect of the present invention, a joint identification system for space-frequency coding and modulation scheme of a MIMO-OFDM system under unknown noise is provided, the system comprising: The feature extraction module is designed with a feature extraction mechanism based on interpolation trajectory maps. It utilizes the differences in the trajectory structure of the complex plane caused by different combinations of space frequency coding and modulation methods to extract interpolation trajectory maps from the signal after generalized linear regularization noise reduction through nonlinear rotation and linear interpolation. The grayscale mapping module introduces a grayscale enhancement mechanism based on the cumulative distribution function. By using the cumulative distribution function mapping mechanism, the grayscale information of the low-frequency regions in the trajectory map is adaptively enhanced, thereby improving the feature map's ability to represent edge trajectories and sparse structural information. A joint identification module for space-frequency coding and modulation schemes is designed. A joint identification network based on a multi-attention mechanism is constructed, and a shallow ResNet network with multi-attention mechanism is introduced to enhance the feature representation ability of channel information and key spatial structure information, so as to realize the joint identification of space-frequency coding and modulation schemes. According to a third aspect of the present invention, a computer program product is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the method for joint identification of space-frequency coding and modulation mode of MIMO-OFDM system under unknown noise as described in the first aspect is implemented.

[0017] According to a fourth aspect of the present invention, an electronic device is provided, comprising: Processor; and Memory for storing the executable instructions of the processor; The processor is configured to implement the joint identification method of space-frequency coding and modulation mode of MIMO-OFDM system under unknown noise as described in the first aspect when executing the executable instructions.

[0018] The embodiments of this invention provide a method for joint identification of space-frequency coding and modulation schemes in MIMO-OFDM systems under unknown noise conditions. This method utilizes the differences in the complex plane trajectory structure caused by different combinations of space-frequency coding and modulation schemes. After generalized linear regularization denoising, the method extracts an interpolated trajectory map through nonlinear rotation and linear interpolation, thereby effectively representing the joint structural features of the space-frequency coding and modulation schemes. Simultaneously, a gray-level enhancement mechanism based on the cumulative distribution function is introduced. This mechanism adaptively enhances the gray-level information in low-frequency regions of the trajectory map using the cumulative distribution function mapping relationship, thereby improving the feature map's ability to represent edge trajectories and sparse structural information, and enhancing the robustness and discriminative ability of the features in unknown noise environments. Furthermore, the gray-level enhanced interpolated trajectory map is used as network input to construct a shallow ResNet network incorporating a multiple attention mechanism, enhancing the feature representation ability of channel information and key spatial structure information, thus achieving joint identification of space-frequency coding and modulation schemes. Therefore, this invention can effectively improve the accuracy and robustness of joint identification in unknown noise environments, and has good engineering application value.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0021] Figure 1 This is a flowchart of the research on the joint identification method of space frequency coding and modulation mode of MIMO-OFDM system under unknown noise provided in the embodiments of the present invention.

[0022] Figure 2 This is a block diagram of the joint identification system for space-frequency coding and modulation mode of MIMO-OFDM system under unknown noise provided in an embodiment of the present invention.

[0023] In the diagram: 1. Joint feature extraction module; 2. Gray-scale mapping enhancement module; 3. Space frequency coding and modulation mode joint identification module.

[0024] Figure 3 This is a schematic diagram illustrating the joint identification accuracy of space-frequency coding and modulation scheme in a MIMO-OFDM system under unknown noise, provided by an embodiment of the present invention.

[0025] Figure 4 This is a schematic diagram illustrating the accuracy of joint identification of subcarrier number variation space-frequency coding and modulation method under unknown noise, provided by an embodiment of the present invention. Detailed Implementation

[0026] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the invention will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0027] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0028] Among related technologies, there are SFBC-OFDM signal recognition based on the central limit theorem (Gao M, Li Y, Dobre OA, et al. Blind identification of SFBC-OFDM signals based on the central limit theorem[J]. IEEE Transactions on Wireless Communications, 2019, 18(7):3500-3514.), SFBC-OFDM signal recognition based on subspace decomposition and random matrix theory (Gao M, Li Y, Dobre OA, et al. Blind identification of SFBC-OFDM signals using subspace decompositions and random matrix theory[J]. IEEE Transactions on Vehicular Technology, 2018, 67(10): 9619-9630.), and SFBC-OFDM signal recognition based on cross-correlation function (Marey M, Dobre OA. Automatic identification of space-frequency block coding for OFDM systems[J]. IEEE Transactions on Wireless Communications, 2017, 16(1):117-128.), and blind recognition of space-frequency block codes based on frequency domain cross-correlation sequences and peak detection (Yan Wenjun, Zhang Yuyuan, Ling Qing, et al. Blind recognition algorithm of space-frequency block codes based on frequency domain cross-correlation sequences and peak detection [J]. Systems Engineering and Electronics, 2021, 43(12): 3709-3715.). The intelligent recognition method is based on feature extraction and automatically recognizes signals by constructing a deep neural network. It has the advantages of strong feature learning ability, high recognition accuracy and good generalization performance.For example, there are SFBC-OFDM recognition methods based on deep multi-level residual networks (Zhang Yuyuan, Zhang Limin, Yan Wenjun. A method for space-frequency block code recognition under low signal-to-noise ratio based on deep multi-level residual networks [J]. Acta Electronica Sinica, 2022, 50(1): 79-88.), and SFBC-OFDM recognition methods based on cross-correlation feature maps and extended dense convolutional networks (Zhang Yuyuan, Zhang Limin, Yan Wenjun. An SFBC-OFDM recognition method based on cross-correlation feature maps and extended dense convolutional networks [J]. Systems Engineering & Electronics, 2021, 43(9): 2657-2664.).

[0029] In the current research context of non-cooperative communication, SFBC-OFDM recognition technology typically focuses on studying recognition performance under specific conditions such as Gaussian noise and impulse noise, while few studies systematically consider the SFBC-OFDM recognition problem in unknown noise environments. Furthermore, most current SFBC-OFDM recognition algorithms revolve around the coding type itself, rarely considering modulation scheme information, which easily leads to feature aliasing interference. Therefore, in complex unknown noise environments, existing methods still need further improvement in terms of noise adaptability and joint discrimination capabilities.

[0030] Based on the above analysis, the problems and shortcomings of the existing technology are as follows: Current space-frequency coding identification techniques mostly focus on specific conditions such as Gaussian noise and impulse noise, lacking adaptability to changes in noise statistical characteristics under unknown noise environments. This limits the robustness of these methods in complex environments. Furthermore, existing space-frequency coding type identification techniques typically only identify the SFBC-OFDM coding type itself, rarely considering modulation scheme information in conjunction. Since there is a strong correlation between modulation scheme and space-frequency coding, existing methods are insufficient in exploring the differences and complementarities between different categories of features, easily leading to feature aliasing interference and affecting overall identification performance.

[0031] The challenges in addressing these issues and shortcomings lie in the following: achieving joint identification of SFBC-OFDM and modulation schemes in unknown noise environments requires effectively suppressing the impact of changes in noise statistical characteristics on the signal feature extraction process without relying on prior noise distribution models. Simultaneously, it necessitates fully exploring the differences and correlations between space-frequency coding and modulation schemes to construct a unified feature representation. Furthermore, enhancing the network's ability to represent key channel information and spatial structure information during joint identification is crucial. Therefore, balancing robustness of feature extraction, effectiveness of feature representation, and accuracy of joint classification in complex unknown noise environments presents significant technical challenges.

[0032] The significance of addressing the above problems and shortcomings is that achieving joint identification of SFBC-OFDM and modulation schemes under unknown noise conditions is crucial for improving signal analysis and subsequent reception processing capabilities in complex wireless communication environments. This invention proposes a joint identification method for SFBC-OFDM and modulation schemes in unknown noise environments. It extracts complex plane trajectory structure features by constructing interpolated trajectory maps and utilizes a gray-level enhancement mapping scheme based on the cumulative distribution function to improve the representation ability of edge trajectories and sparse structure information. Furthermore, it combines a shallow ResNet network incorporating a multiple attention mechanism to achieve joint identification of SFBC-OFDM and modulation schemes, thereby providing technical support for communication signal monitoring and intelligent sensing in complex electromagnetic environments.

[0033] To address the shortcomings and deficiencies of existing technologies, this invention provides a research method for joint identification of space-frequency coding and modulation schemes in MIMO-OFDM systems under unknown noise conditions. This mainly involves a feature extraction mechanism based on interpolated trajectory maps, a gray-level mapping mechanism based on cumulative distribution functions, and the use of a shallow ResNet classification network incorporating multiple attention to jointly identify the space-frequency coding and modulation schemes of signals. Specifically, it includes: designing a feature extraction mechanism based on interpolated trajectory maps, utilizing the differences in the trajectory structure of different combinations of space-frequency coding and modulation schemes on the complex plane, and extracting interpolated trajectory maps from signals after generalized linear regularization denoising through nonlinear rotation and linear interpolation; introducing a gray-level enhancement mechanism based on cumulative distribution functions, using the cumulative distribution function mapping mechanism to adaptively enhance the gray-level information in low-frequency regions of the trajectory map, improving the feature map's representation ability of edge trajectories and sparse structural information; and designing a joint identification network based on a multiple attention mechanism, constructing a shallow ResNet network incorporating multiple attention mechanisms to enhance the feature representation ability of channel information and key spatial structural information, thereby achieving joint identification of space-frequency coding and modulation schemes.

[0034] like Figure 1 As shown in the embodiment of the present invention, the method for joint identification of space-frequency coding and modulation scheme of MIMO-OFDM system under unknown noise includes the following steps: S101, Design a feature extraction mechanism based on interpolation trajectory map, which utilizes the differences in the complex plane trajectory structure of different combinations of space frequency coding and modulation methods to extract the interpolation trajectory map of the signal after generalized linear regularization noise reduction through nonlinear rotation and linear interpolation. S102 introduces a gray-level enhancement mechanism based on the cumulative distribution function. By using the cumulative distribution function mapping mechanism, the gray-level information of the low-frequency region in the trajectory map is adaptively enhanced, thereby improving the feature map's ability to represent edge trajectories and sparse structural information. S103, design a joint recognition network based on a multi-attention mechanism, construct a shallow ResNet network that incorporates a multi-attention mechanism, enhance the feature representation ability of channel information and key spatial structure information, and realize the joint recognition of space-frequency coding and modulation mode.

[0035] like Figure 2 As shown in the embodiment of the present invention, the joint identification system for space-frequency coding and modulation scheme of MIMO-OFDM system under unknown noise includes: A joint feature extraction module is designed to create a feature extraction mechanism based on interpolation trajectory maps. By utilizing the differences in the trajectory structure of complex planes caused by different combinations of space frequency coding and modulation methods, the interpolation trajectory map is extracted from the signal after generalized linear regularization noise reduction through nonlinear rotation and linear interpolation. The grayscale mapping enhancement module introduces a grayscale enhancement mechanism based on the cumulative distribution function. By utilizing the cumulative distribution function mapping mechanism, the grayscale information of the low-frequency regions in the trajectory map is adaptively enhanced, thereby improving the feature map's ability to represent edge trajectories and sparse structural information. A joint identification module for space-frequency coding and modulation schemes is designed. A joint identification network based on a multi-attention mechanism is constructed. A shallow ResNet network with multi-attention mechanism is introduced to enhance the feature representation ability of channel information and key spatial structure information, so as to realize the joint identification of space-frequency coding and modulation schemes.

[0036] The present invention will be further described below with reference to embodiments.

[0037] Example 1 The present invention provides a method for joint identification of space-frequency coding and modulation scheme in a MIMO-OFDM system under unknown noise, comprising the following steps: The first step, joint feature extraction, involves designing a feature extraction mechanism based on interpolation trajectory maps. By utilizing the differences in the trajectory structure of complex planes caused by different combinations of spatial frequency coding and modulation methods, the interpolation trajectory map is extracted from the signal after generalized linear regularization noise reduction through nonlinear rotation and linear interpolation. The main purpose of this step is to suppress unknown distributed noise and extract joint features.

[0038] First, the received signal is preprocessed with generalized regularization noise reduction. The highly linear structure of generalized linear regularization is used to suppress some outliers caused by unknown noise in the MIMO-OFDM signal. The FISTA algorithm is then used to solve the problem and obtain the denoised signal.

[0039] Next, the denoised signal is converted from parallel to serial, and the converted serial symbol sequence is then subjected to nonlinear rotation mapping. Let... For the first parallel-to-serial transformation in the complex plane Each symbol is represented as: Perform a nonlinear phase transformation on it:

[0040] in, To transform the parameters, this embodiment uses... This is to enhance the identifiability of different SFBCs at the trajectory level.

[0041] Next, a linear interpolation method is introduced to perform interpolation continuity processing on discrete trajectory points. Let two adjacent trajectory points be... and , Using interpolation parameters, a linear interpolation method is used to connect the discrete trajectory points:

[0042] By interpolating, the continuity and stability of the trajectory structure are effectively enhanced while maintaining the basic geometric shape of the trajectory, and the interpolated trajectory map is extracted.

[0043] The second step introduces a gray-level enhancement mechanism based on the cumulative distribution function. This mechanism uses the cumulative distribution function mapping to adaptively enhance the gray-level information in areas with low frequency of occurrence in the trajectory map, improving the feature map's ability to represent edge trajectories and sparse structural information. This includes: First, statistical distribution information of pixel values ​​is introduced to divide the interpolation trajectory map into different matrix regions. Let the cumulative distribution function corresponding to a certain element value in the feature map matrix be... Its grayscale mapping relationship is expressed as:

[0044] Then, the interpolated trajectory map is processed according to the grayscale mapping relationship to extract the grayscale-mapped interpolated trajectory map.

[0045] The third step involves designing a joint recognition network based on a multiple attention mechanism. This involves constructing a shallow ResNet network incorporating the multiple attention mechanism to enhance the feature representation capabilities of channel information and key spatial structure information, thereby achieving joint recognition of space-frequency coding and modulation schemes. This includes: First, the interpolated trajectory map after grayscale enhancement mapping is used as the network input, and adaptive pooling is used instead of fixed-size pooling to adapt to input features of different sizes and ensure the consistency of feature mapping dimensions.

[0046] Subsequently, the SE attention mechanism was introduced to improve the residual block, thereby enhancing the network's ability to express discriminative channel features. The CA coordinate attention mechanism was further introduced to improve the network's ability to represent key position and spatial structure features. Based on this, an improved shallow ResNet network was constructed to achieve joint recognition of space-frequency coding and modulation scheme.

[0047] The technical effects of the present invention will be described in detail below with reference to simulation.

[0048] To evaluate the performance of this invention, simulation verification was performed. A 4×4 MIMO-OFDM system was used, with Ricean channels, and the simulation generated AL, STBC3. , The communication signal comprises 16 joint types, including four coding schemes and four modulation schemes: BPSK, QPSK, 8PSK, and 16QAM. The background noise is unknown, composed of four random noise types, and its distribution is variable and unpredictable. The specific settings are as follows: shape parameters of alpha-stabilized noise. =1.6, the scale parameter of generalized Gaussian noise =1.6, the scaling parameter of the mixed generalized Gaussian noise is set to 1.6. =1.6 and =1.7, Gaussian noise follows a normal distribution with a mean of 1.7, i.e. The received signal undergoes generalized linear regularized noise reduction. Utilizing the differences in the complex plane trajectory structure caused by different combinations of space-frequency coding and modulation schemes, an interpolated trajectory map is extracted through nonlinear rotation and linear interpolation. Then, a gray-level enhancement mapping mechanism based on the cumulative distribution function is used to adaptively enhance the gray-level information in low-frequency regions of the trajectory map. Finally, the gray-level enhanced interpolated trajectory map is input into a shallow ResNet network with a multi-attention mechanism to achieve joint recognition of space-frequency coding and modulation schemes. The recognition accuracy of each joint type of space-frequency coding and modulation scheme under different signal-to-noise ratios is as follows: Figure 3 As shown, with the increase of signal-to-noise ratio, the noise impact on the received signal gradually decreases, the trajectories of various joint types become clearer, and the recognition accuracy of each joint type continuously increases. Increasing the number of receiving antennas while keeping the channel conditions unchanged results in the following recognition accuracies for various space-time coding types: Figure 4 As shown. From Figure 4 As can be seen, the recognition performance of the method of the present invention continuously improves with the increase of the number of subcarriers. This is because, under the same OFDM block count, the more subcarriers there are, the more symbols can be obtained after demodulation of the received signal, the more samples are involved in complex plane trajectory statistics and grayscale mapping, the clearer the effective information of edge trajectories and sparse regions, the stronger the separability of feature maps, and the higher the recognition accuracy.

[0049] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented, in whole or in part, as a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0050] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0051] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the claims.

[0052] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is defined only by the appended claims.

Claims

1. A method for joint identification of space-frequency coding and modulation scheme in a MIMO-OFDM system under unknown noise, characterized in that, The method includes: Step 1: Design a feature extraction mechanism based on interpolation trajectory map. Utilize the differences in the complex plane trajectory structure caused by different combinations of space frequency coding and modulation methods, and extract the interpolation trajectory map from the signal after generalized linear regularization noise reduction through nonlinear rotation and linear interpolation. Step 2: Introduce a gray-scale enhancement mechanism based on the cumulative distribution function. Using the cumulative distribution function mapping mechanism, adaptively enhance the gray-scale information of the low-frequency regions in the interpolation trajectory map, and extract the interpolation trajectory map after gray-scale mapping. Step 3: Design a joint recognition network based on a multi-attention mechanism. Construct a shallow ResNet network that incorporates a multi-attention mechanism to enhance the feature representation capabilities of channel information and key spatial structure information. Input the enhanced interpolated trajectory map into the joint recognition network based on the multi-attention mechanism to achieve joint recognition of space-frequency coding and modulation methods.

2. The method according to claim 1, characterized in that, The feature extraction mechanism based on interpolation trajectory graphs specifically includes: The received signal is preprocessed with generalized regular noise reduction, and the FISTA algorithm is used to solve for the noise-reduced signal. The noise-reduced signal is converted from parallel to serial, and the converted serial symbol sequence is then subjected to nonlinear rotation mapping. The discrete trajectory points are connected using a linear interpolation method to generate an interpolated trajectory map.

3. The method according to claim 2, characterized in that, The process of performing parallel-to-serial conversion on the denoised signal and then applying nonlinear rotation mapping to the converted serial symbol sequence specifically involves: make For the first parallel-to-serial transformation in the complex plane Each symbol is represented as: Perform a nonlinear phase transformation on it: in, For the transformation parameters, , Indicates the first The corresponding coordinate values ​​of each symbol.

4. The method according to claim 3, characterized in that, The method of connecting discrete trajectory points using linear interpolation is as follows: Let two adjacent trajectory points be respectively and , Using interpolation parameters, a linear interpolation method is used to connect the discrete trajectory points: in, This represents the intermediate trajectory point obtained by linear interpolation of two adjacent trajectory points.

5. The method according to claim 1, characterized in that, The grayscale enhancement mechanism based on the cumulative distribution function specifically includes: By incorporating pixel value statistical distribution information, the interpolation trajectory map is divided into different matrix regions; A gray-level mapping relationship is constructed based on the cumulative distribution function corresponding to the matrix element values; Adaptive grayscale enhancement is performed on the interpolated trajectory map based on the aforementioned grayscale mapping relationship.

6. The method according to claim 5, characterized in that, The gray-level mapping relationship is constructed based on the cumulative distribution function corresponding to the matrix element values, specifically as follows: Let the cumulative distribution function corresponding to a certain element value in the feature map matrix be... Its grayscale mapping relationship is expressed as: 。 7. The method according to claim 1, characterized in that, The joint recognition network based on the multi-attention mechanism specifically includes: Use the grayscale-enhanced interpolated trajectory map as the network input; An SE attention mechanism is introduced to improve the residual block and enhance the ability to represent channel features; Introducing a CA coordinate attention mechanism enhances the ability to represent spatial structural features; An improved shallow ResNet network is constructed to output the joint identification result of space frequency coding and modulation mode.

8. A joint identification system for space-frequency coding and modulation scheme of a MIMO-OFDM system under unknown noise, characterized in that, The system includes: The feature extraction module is designed with a feature extraction mechanism based on interpolation trajectory maps. It utilizes the differences in the trajectory structure of the complex plane caused by different combinations of space frequency coding and modulation methods to extract interpolation trajectory maps from the signal after generalized linear regularization noise reduction through nonlinear rotation and linear interpolation. The grayscale mapping module introduces a grayscale enhancement mechanism based on the cumulative distribution function. By using the cumulative distribution function mapping mechanism, the grayscale information of the low-frequency regions in the trajectory map is adaptively enhanced, thereby improving the feature map's ability to represent edge trajectories and sparse structural information. A joint identification module for space-frequency coding and modulation schemes is designed. A joint identification network based on a multi-attention mechanism is constructed, and a shallow ResNet network with multi-attention mechanism is introduced to enhance the feature representation ability of channel information and key spatial structure information, so as to realize the joint identification of space-frequency coding and modulation schemes.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for joint identification of space frequency coding and modulation mode of MIMO-OFDM system under unknown noise as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the method for joint identification of space-frequency coding and modulation scheme of MIMO-OFDM system under unknown noise as described in any one of claims 1 to 7 by executing the executable instructions.

Images