CN115967451A

CN115967451A - Wireless router signal processing method and device and wireless router applying same

Info

Publication number: CN115967451A
Application number: CN202310231809.4A
Authority: CN
Inventors: 唐俊; 肖宇辉; 罗敏; 刘冰香; 韩涛
Original assignee: Microgrid Union Technology Chengdu Co ltd
Current assignee: Microgrid Union Technology Chengdu Co ltd
Priority date: 2023-03-13
Filing date: 2023-03-13
Publication date: 2023-04-14
Anticipated expiration: 2043-03-13
Also published as: CN115967451B

Abstract

The invention discloses a signal processing method and device of a wireless router and the wireless router using the same. The method comprises the steps of sampling signal frequency of a transmitting signal of the wireless router, obtaining a time domain distribution graph of the transmitting signal through Fourier transform after determining a discrete sequence, obtaining the time domain distribution graph of the transmitting signal with speckle noise after sampling for multiple times, and obtaining a training reference time domain distribution graph of the transmitting signal without the speckle noise by collecting standard transmitting signal parameters of the wireless router; furthermore, a hybrid structure is constructed to generate an antagonistic network, the hybrid structure is trained by the acquired parameters to generate the antagonistic network, the hybrid structure generates the antagonistic network to form a trained generated antagonistic network, and the trained generated antagonistic network automatically performs speckle noise elimination on the transmitted signals before the signals are transmitted by the wireless router, so that the aim of improving the stability of the transmitted signals of the wireless router is fulfilled.

Description

Wireless router signal processing method and device and wireless router applying same

Technical Field

The invention relates to the technical field of wireless routers and manufacturing, in particular to a signal processing method and device of a wireless router and the wireless router applying the signal processing method and device.

Background

The wireless router is used for user to surf the internet and has a wireless coverage function.

Because the wireless router relies on the air medium for signal transmission, speckle noise is inevitably generated by the coherence, so that the transmission rate of the wireless signal is reduced, the transmission quality of the wireless signal is affected by the speckle noise, and the transmission quality of the wireless signal is greatly reduced once the wireless router encounters a wall or a large-volume home.

Therefore, when a wireless router transmits a wireless signal, a solution is needed to remove speckle noise in the wireless signal.

Disclosure of Invention

The invention aims to overcome the defects of the prior art and provide a wireless router signal processing method and device and a wireless router using the same, so as to achieve the purposes of effectively eliminating speckle noise in a signal transmitted by the wireless router and improving the stability of the signal transmitted by the wireless router.

The purpose of the invention is realized by the following technical scheme: a wireless router signal processing method comprises the following steps:

step S1: carrying out signal frequency sampling on a transmitting signal of a wireless router, determining a discrete sequence, carrying out Fourier transform on the discrete sequence, and determining a time domain distribution diagram of the transmitting signal;

step S2: repeating the step S1 to sample the signal frequency for multiple times to obtain N emission signal time domain distribution graphs with speckle noise;

and step S3: importing standard signal transmission parameters of a wireless router into a database, determining a discrete sequence of the standard signal transmission frequency parameters, and performing Fourier transform on the sequence to obtain a training reference time domain distribution map without speckle noise;

and step S4: selecting a transmitting signal time domain distribution graph containing speckle noise and a training reference time domain distribution graph without the speckle noise to be matched in pairs to form a data set, setting part of the data set as a training data set, and setting the rest part as a testing training set;

step S5: constructing a hybrid structure to generate a countermeasure network;

step S6: importing the training data set in the step S4 into the hybrid structure generation countermeasure network constructed in the step S5 to obtain a trained generation countermeasure network;

step S7: and finishing the elimination of speckle noise in the transmitted signal according to the trained generation countermeasure network, and finishing the adjustment of the frequency domain of the transmitted signal.

Further, the step S5 is implemented as follows:

step S51: carrying out normalization processing on the training data set and the test training set by adopting a normalization formula;

step S52: constructing a generator;

step S53: constructing a discriminator;

step S54: designing a generator parameter optimization objective function, wherein the formula is as follows:

；

is the pixel mean square loss->

For sensing loss, is>

And &>

Coefficient of mean square loss and perceptual loss of pixel->

And

is defined as follows:

；

；

in the formula, the first step is that,

indicates the output of the generator, is asserted>

Represents a reference image, is>

Represents the output of the VGG-19 network feature extraction, based on the comparison result>

The width, the height and the channel number of the image are respectively, i and n are constant definition values, and the specific numerical value is determined by the quadrant value of the function;

step S55: and updating network parameters of the generator and the discriminator to complete the generation of the countermeasure network by the mixed structure.

Further, the step S4 further includes the following steps: and segmenting the data set into a training data set and a testing data set.

Preferably, the data set segmentation principle is as follows:

carrying out weighted average processing on data in the data set to obtain a weighted average value, and comparing a single data point in the data set with the weighted average value to obtain a maximum data difference value and a minimum data difference value;

and taking the average value of the maximum data difference value and the minimum data difference value as a segmentation point, when the data difference value is larger than or equal to the segmentation point, segmenting the data into a test data set, and when the data difference value is smaller than the segmentation point, segmenting the data into a training data set.

It should be noted that the generator includes an encoder and a decoder which are constructed by a dense connection network to form a U-Net structure, and the time domain distribution map is input into the encoder to be down-sampled and output through the decoder to be up-sampled.

Preferably, the specific steps of adjusting the frequency of the transmission signal according to the trained counterpoise network are as follows:

and eliminating a transmitted signal time domain distribution graph with high speckle noise by the trained generated countermeasure network, performing time domain-frequency domain transformation on the output time domain signal graph, and performing inverse Fourier transform on the frequency domain to determine a transmitted signal of the wireless router.

A wireless router signal processing apparatus, comprising:

the first signal processing module is used for carrying out signal frequency sampling on a transmitting signal of the wireless router, determining a discrete sequence, carrying out Fourier transform on the discrete sequence and determining a time domain distribution diagram of the transmitting signal;

the second signal processing module is used for determining a transmitting signal time domain distribution graph with speckle noise and a training reference time domain distribution graph without speckle noise according to the acquired data;

the third signal processing module is used for constructing a hybrid structure generation countermeasure network and a trained generation countermeasure network, filtering signals through the trained generation countermeasure network and determining a time domain of the signals transmitted by the wireless router;

and the fourth signal processing module is used for carrying out time domain-frequency domain transformation and simultaneously carrying out inverse Fourier transform on the frequency domain to determine the signal transmitted by the wireless router.

A computer-readable storage medium having stored thereon a computer program for executing the method according to any one of the above aspects of the invention.

A wireless router signal processing terminal, comprising: a processor, a memory for storing the processor-executable instructions; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the functions of any aspect of the present invention, such as generating, receiving, sending, or processing data and/or information involved in the above method;

the processing terminal may be formed by a chip, or may include a chip and other discrete devices.

In one possible design, the processing terminal further includes a memory for storing necessary program instructions and data. The processor and the memory may be decoupled, disposed on different devices, connected in a wired or wireless manner, or coupled on the same device.

The beneficial effects of the invention are:

1) According to the invention, the time domain distribution diagram of the transmitted signal for removing the noise such as speckle noise can be obtained only by integrating the deep learning network of the mixed structure without changing the hardware and the structure of the conventional wireless router, and the stability of the transmitted signal of the wireless router is effectively improved by removing the speckle noise.

2) The deep learning method provided by the invention has the capability of efficiently removing speckle noise and other noises, and can analyze tiny and important emission frequency signals covered by the speckle noise while removing the speckle noise and other noises.

3) The invention avoids repeated sampling operation and greatly reduces data processing amount.

4) The invention avoids the input power loss of the sample arm of the time domain distribution diagram of the transmitted signal, maintains the detection sensitivity, ensures that the subsequent data analysis can be stored in a more accurate range, and greatly improves the accuracy of the signal transmission of the wireless router.

Drawings

FIG. 1 is a flow chart of the steps of signal processing according to the present invention;

FIG. 2 is a diagram of a hybrid fabric generative countermeasure network architecture constructed in accordance with the present invention;

FIG. 3 is a schematic diagram of the frequency characteristics of signals transmitted by a wireless router in an embodiment not using the present invention;

FIG. 4 is a schematic diagram of the frequency characteristics of signals transmitted by a wireless router according to the present invention;

FIG. 5 is a schematic diagram of a signal processing apparatus according to the present invention;

fig. 6 is a schematic diagram of a signal processing terminal according to the present invention.

Detailed Description

The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.

The first embodiment is as follows:

referring to fig. 1, the invention discloses a signal processing method of a wireless router, which comprises the following steps:

here, the following approach is taken to segment the data set:

taking the average value of the maximum data difference value and the minimum data difference value as a segmentation point, when the data difference value is larger than or equal to the segmentation point, segmenting the data into a test data set, and when the data difference value is smaller than the segmentation point, segmenting the data into a training data set;

step S5: constructing a hybrid structure to generate a countermeasure network;

It should be noted that, the specific steps of adjusting the frequency of the transmission signal according to the trained generation countermeasure network are as follows:

and eliminating a transmission signal time domain distribution graph with high speckle noise by the trained generation countermeasure network, performing time domain-frequency domain transformation on the output time domain signal graph, and performing inverse Fourier transform on the frequency domain to determine a transmission signal of the wireless router.

By the method, the time domain distribution diagram of the transmitted signals with the noises such as speckle noise removed can be obtained only by integrating the deep learning network of the mixed structure under the condition that the hardware and the structure of the conventional wireless router are not changed, and the strength of the transmitted signals of the wireless router is effectively improved by removing the speckle noise.

Example two:

referring to fig. 2, the present invention discloses a specific method for generating a countermeasure network by a hybrid structure:

firstly, a training data set and a test training set are subjected to normalization processing by adopting a normalization formula;

gradually constructing a generator;

constructing a discriminator after the generator;

designing generator parameters for generator parameters to optimize an objective function, the formula of which is as follows:

；

is the pixel mean square loss->

For perception of loss>

And &>

Coefficient of mean square loss and perceptual loss of pixel->

And

is defined as follows:

；

；

in the formula, the first step is that,

indicates the output of the generator, is asserted>

Represents a reference image, <' > based on>

and finally, updating the network parameters of the generator and the discriminator through a formula to complete the generation of the countermeasure network by the mixed structure.

Example three:

referring to fig. 3 and 4, the embodiment temporarily constructs a wireless router transmission signal acquisition for explanation, and the system is used for acquiring a transmission signal image containing a large amount of speckle noise and a corresponding speckle noise-free transmission signal reference image. The emission signal source adopts a central wavelength of 850 nm. For a wideband signal source with a full width at half maximum of 165 nm, the output signal is divided by a 50: the fiber coupler of 50 is split to the sample and reference arms. The interference signal enters a 2048-pixel spectrometer, and the signal detected by the spectrometer is transmitted to a computer. In this embodiment, the spectrometer and the two-dimensional scanning galvanometer are synchronized by a computer generated trigger signal. Other elements have two identical collimators and two polarization controllers.

The invention uses the data set produced by the method as input to train and generate the confrontation network, the optimizer is an Adam optimizer before training, and the learning rate is

The batch size and the number of training steps were set to 1 and 35 ten thousand respectively to obtain the optimal model parameters. Coefficient in generator objective function pick>

And coefficient->

1 and 0.1, respectively, the arbiter uses the cross entropy loss function as its objective function.

The optimal parameters of the model are obtained after the training of the confrontation network is completed, and the trained model and the parameters thereof are integrated on the conventional processor system, so that the embodiment can be explained. In order to prove that the wireless router has the function of automatically removing noises such as electronic noise, speckle noise and the like compared with the conventional router, the wireless router without the wireless router and the wireless router with the wireless router respectively perform waveform comparison of transmission signals.

Fig. 3 shows a waveform diagram of a transmission signal acquired by a wireless router under the condition of not using the invention, and fig. 4 shows a waveform comparison of the transmission signal acquired by the same wireless router under the condition of using the invention. It can be seen that the image formed without the invention has a great deal of speckle noise, which seriously affects the waveform of the transmitted signal, and the peak value of the waveform is affected by the speckle noise to show irregular peaks and valleys, as shown in fig. 4. The oscillogram of the transmitting signal obtained by using the method well removes the speckle noise, the electronic noise and other noises of the image, improves the stability of the oscillogram and leads the transmitting signal of the wireless router to tend to be stable.

In order to verify that the invention has high time resolution, the example further uses the invention to continuously collect the multi-frame transmission signal time domain distribution diagram, and the test system obtains 800 frames of time consumed by removing the transmission signal time domain distribution diagram with speckle noise and other noises. In the test, the acquisition of 800 frames of emission signal time domain distribution graphs for removing speckle noise and other noises takes 115.8 seconds, each frame of picture is only 144.7 milliseconds on average, and compared with a frequency modulation mode of a conventional wireless router, the wireless router has higher time resolution.

It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

Example four:

referring to fig. 5, the present invention further comprises a wireless router signal processing apparatus,

the second signal processing module is used for determining a transmitting signal time domain distribution graph with speckle noise and a training reference time domain distribution graph without speckle noise according to the collected data;

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one type of logical functional division, and other divisions may be realized in practice, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

Example five:

referring to fig. 6, a computer readable storage medium stores a computer program for executing the method according to any one of the above aspects of the present invention.

A wireless router signal processing terminal, comprising: a processor, a memory for storing the processor-executable instructions; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the functions of any of the above aspects of the invention, such as generating, receiving, sending, or processing data and/or information involved in the above methods;

the memory is a storage unit in the chip, such as a register, a cache, etc., and the memory may also be a storage unit outside the chip in the terminal, such as a ROM or other types of static storage devices that can store static information and instructions, a RAM, etc.

It will be appreciated that the memory herein can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory.

The non-volatile memory may be ROM, programmable Read Only Memory (PROM), erasable PROM (EPROM), electrically Erasable PROM (EEPROM), or flash memory.

Volatile memory can be RAM, which acts as external cache memory. There are many different types of RAM, such as Static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and DSRAMs.

The foregoing is illustrative of the preferred embodiments of this invention, and it is to be understood that the invention is not limited to the precise form disclosed herein and that various other combinations, modifications, and environments may be resorted to, falling within the scope of the concept as disclosed herein, either as described above or as apparent to those skilled in the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

1. A signal processing method of a wireless router is characterized in that: the method comprises the following steps:

and step S3: importing standard signal transmission parameters of a wireless router into a database, determining a discrete sequence of the standard signal transmission frequency parameters, and performing Fourier transform on the discrete sequence to obtain a training reference time domain distribution map without speckle noise;

step S5: constructing a hybrid structure to generate a countermeasure network;

step S7: and eliminating speckle noise in the transmitting signals according to the trained generation countermeasure network, and adjusting the frequency domain of the transmitting signals.

2. The signal processing method of the wireless router of claim 1, wherein: the step S5 is implemented as follows:

step S52: constructing a generator;

step S53: constructing a discriminator;

step S54: designing a generator parameter optimization objective function;

3. The signal processing method of the wireless router of claim 1, wherein: the step S4 further includes the steps of: and segmenting the data set into a training data set and a testing data set.

4. The signal processing method of claim 3, wherein: the data set segmentation principle is as follows:

5. The signal processing method of claim 2, wherein:

the generator comprises a U-Net structure formed by an encoder and a decoder which are constructed by dense connection networks, and the time domain distribution diagram is input into the encoder to be sampled and output through the decoder to be sampled.

6. The signal processing method of the wireless router of claim 1, wherein: the specific steps of finishing the elimination of the speckle noise in the transmitting signal and finishing the adjustment of the frequency domain of the transmitting signal according to the trained generation countermeasure network are as follows:

7. A wireless router signal processing apparatus, characterized in that: the method comprises the following steps:

8. A computer-readable storage medium, characterized in that: the storage medium stores a computer program for executing a wireless router signal processing method according to any one of claims 1 to 6.

9. A wireless router signal processing terminal, characterized by: the method comprises the following steps:

a processor, a memory to store the processor-executable instructions;

the processor is configured to read the executable instructions from the memory and execute the instructions to implement a wireless router signal processing method according to any one of claims 1 to 6.