Signal processing device and signal processing method
The signal processing device employs a GAN-based approach to generate and distinguish pseudo signals from normal signals, setting a threshold to reduce error rates, addressing the inefficiencies of conventional error correction methods by optimizing signal processing without redundant bits.
Patent Information
- Application Number
- JP2024034517
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-03-07
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-03-07
AI Technical Summary
Conventional error correction techniques face challenges in reducing signal error rates due to increased communication overhead and processing load from adding redundant bits, making it difficult to efficiently minimize signal errors.
A signal processing device utilizing a machine learning model, specifically a GAN, to generate pseudo signals with different patterns from normal signals, and a discriminator to identify these signals, setting a threshold to minimize error rates without adding redundant bits, through adversarial learning.
The method effectively reduces signal error rates by optimizing a threshold based on machine learning parameters, minimizing errors in noisy transmission signals without increasing communication overhead or processing load.
Smart Images

Figure 0007587072000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a signal processing device and a signal processing method, and more particularly to a processing technique for a transmission signal to which noise has been added. [Background technology]
[0002] Conventionally, there are known techniques for correcting errors in signals caused by noise that occurs during signal transmission. Patent Document 1 discloses a technique for reducing data errors in transmission characteristics by performing error correction coding on data on the transmitting side and performing error correction on the receiving side according to the coding. Also, for example, Hamming code, BCH code, etc. are known as error correction methods.
[0003] However, among conventional error correction techniques, the method of adding redundant bits to data during data transmission has the problem of increasing communication traffic due to the addition of redundant bits, and there is also the problem of the large processing load required for error correction. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Patent No. 7241851 [Patent Document 2] JP 2013-038676 A Summary of the Invention [Problem to be solved by the invention]
[0005] With conventional techniques, it has been difficult to reduce the signal error rate more easily.
[0006] The present invention has been made to solve the above-mentioned problems, and has an object to more easily reduce the signal error rate. [Means for solving the problem]
[0007] In order to solve the above-mentioned problems, the signal processing device of the present invention includes a setting unit configured to set each pattern of a data sequence of a transmission signal having a data sequence of a set length as a normal signal, a generator that generates a pseudo signal, which is a data sequence having a different pattern from the pattern of the data sequence of the normal signal, and a learning unit configured to learn a machine learning model having a discriminator that discriminates between the pseudo signal generated by the generator and the normal signal, a determination unit configured to determine a threshold value for suppressing the error rate between the normal signal and the pseudo signal in the transmission signal to which noise has been added, based on parameters of the machine learning model optimized by learning by the learning unit, and a notification unit configured to notify a device receiving the transmission signal of the determined threshold value.
[0008] In addition, in the signal processing device according to the present invention, the decision unit may set the threshold value based on a first expected value indicated by an objective function of the machine learning model at which the classifier will classify the normal signal as a normal signal, and a second expected value at which the classifier will classify the pseudo signal generated by the generator as a pseudo signal.
[0009] In addition, in the signal processing device according to the present invention, the learning unit may adjust a value of the first expected value until the generator generates the pseudo signal having a data sequence pattern different from each other for each pattern of the data sequence of the normal signal set by the setting unit, and train the generator and the discriminator in an adversarial manner.
[0010] In addition, the signal processing device of the present invention may further include a collection unit configured to collect a variance of the noise from the device, and the determination unit may determine the threshold value based on the variance collected by the collection unit, the first expected value, and the second expected value.
[0011] In order to solve the above-mentioned problems, the signal processing method of the present invention includes a setting step of setting each pattern of a data sequence of a transmission signal having a data sequence of a set length as a normal signal, a learning step of learning a machine learning model having a generator that generates a pseudo signal, which is a data sequence having a different pattern from the pattern of the data sequence of the normal signal, and a discriminator that discriminates between the pseudo signal generated by the generator and the normal signal, a determination step of determining a threshold value for suppressing the error rate between the normal signal and the pseudo signal in the transmission signal to which noise has been added, based on parameters of the machine learning model optimized by learning in the learning step, and a notification step of notifying a device receiving the transmission signal of the determined threshold value.
[0012] In addition, in the signal processing method according to the present invention, the determining step may set the threshold value based on a first expected value indicated by an objective function of the machine learning model at which the classifier will classify the normal signal as a normal signal, and a second expected value indicated by an objective function of the machine learning model at which the classifier will classify the pseudo signal generated by the generator as a pseudo signal.
[0013] In addition, in the signal processing method according to the present invention, the learning step may adjust a value of the first expected value until the generator generates the pseudo signal having a data sequence pattern different from each other for each pattern of the data sequence of the normal signal set in the setting step, and train the generator and the discriminator in an adversarial manner.
[0014] In addition, the signal processing method of the present invention may further include a collection step of collecting the variance of the noise from the device, and the determination step may determine the threshold value based on the variance collected in the collection step, the first expected value, and the second expected value. Effect of the Invention
[0015] According to the present invention, a threshold value for suppressing the error rate between a normal signal and a pseudo signal in a transmission signal to which noise has been added is determined based on parameters of a machine learning model optimized by learning by a learning unit, so that the error rate of the signal can be reduced more easily. [Brief description of the drawings]
[0016] [Figure 1] FIG. 1 is a block diagram showing a configuration of a signal processing system including a signal processing device according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a block diagram showing a configuration of a learning unit included in the signal processing device according to this embodiment. [Diagram 3] FIG. 3 is a diagram for explaining a learning unit included in the signal processing device according to the present embodiment. [Figure 4] FIG. 4 is a diagram for explaining a learning unit included in the signal processing device according to the present embodiment. [Diagram 5] FIG. 5 is a block diagram showing a hardware configuration of a signal processing device according to the present embodiment. [Figure 6] FIG. 6 is a sequence diagram showing an overview of the operation of the signal processing system according to the present embodiment. [Figure 7] FIG. 7 is a flowchart showing the operation of the signal processing device according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0017] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will now be described in detail with reference to FIGS.
[0018] [Signal processing system configuration] First, an overview of a signal processing system including a signal processing device 1 according to an embodiment of the present invention will be described. Fig. 1 is a block diagram showing a configuration of a signal processing system including a signal processing device 1 according to an embodiment of the present invention.
[0019] The signal processing system according to this embodiment is provided in a communication network having, for example, a communication path L of a wireless section and a communication path C of a wired section. As shown in Fig. 1, the signal processing system includes a signal processing device 1, a communication terminal 2, a base station 3, and a core device 4. The signal processing device 1, the base station 3, and the core device 4 are each connected to a network NW such as a LAN, a WAN, or the Internet. A communication path L of a wireless section is provided between the communication terminal 2 and the base station 3, and a communication path C of a wired section is provided between the base station 3 and the core device 4.
[0020] The communication terminal 2 is a user terminal such as a smartphone or a tablet terminal, and performs wireless communication with a base station 3 in the communication area where the communication terminal 2 is located via a wireless communication path L. The communication terminal 2 communicates with a core device 4 via the base station 3.
[0021] The base station 3 is a base station conforming to a predetermined communication standard such as LTE, 5G, or 6G, and establishes communication with the communication terminal 2 and transmits data to the communication terminal 2 by wireless communication. The base station 3 also communicates with the core device 4 via a communication path C of a wired section such as a backhaul link, and exchanges data and control information. The base station 3 has a communication interface (not shown) for communicating with the signal processing device 1.
[0022] The core device 4 is a device provided in a core network that complies with a predetermined communication standard such as LTE, 5G, or 6G. For example, in the case of a 5G communication network, it includes a UPF (User Plane Function) in the U-plane and a UDR (Unified Data Repository) in the C-plane. The core device 4 has a communication interface (not shown) for communicating with the signal processing device 1.
[0023] Noise occurring on the communication path L in the wireless section between the communication terminal 2 and the base station 3 may cause a bit error, for example, when a digital transmission signal transmitted by the communication terminal 2 is decoded by the receiving base station 3. Also, noise occurring on the communication path C in the wired section between the base station 3 and the core device 4 may cause a bit error, for example, when a digital transmission signal transmitted by the base station 3 is decoded by the receiving core device 4. The noise occurring on the communication paths L and C is, in particular, Gaussian noise that follows a normal distribution.
[0024] Here, in order to improve the error rate of a transmission signal, a method is known in which the most likely signal is determined from the received transmission signals using maximum likelihood detection (MLD) and signal separation is performed based on the maximum likelihood determination (see Patent Document 2). This method, called maximum likelihood detection, creates replicas of the received signal for all possible combinations of transmitted symbols, compares them with the received signal, and determines the most likely one as having been transmitted.
[0025] In maximum likelihood detection, when Gaussian noise is added to a binary digital signal, the appropriate threshold value ρ0 that minimizes the bit error rate is expressed by the following equation (1).
number
[0026] In the above formula (1), S0 is 0, S1 is 1, and σ 2 denotes the variance of Gaussian noise, P[S0] denotes the probability that S0 = 0, and P[S1] denotes the probability that S1 = 1. The threshold ρ0 expressed in the above equation (1) is known to be applied, for example, to a matched filter that minimizes the error rate of a binary signal.
[0027] In the signal processing system according to this embodiment, the threshold value ρ0 in the above formula (1) is applied as a threshold value ρ0' for suppressing the error rate between a normal signal and a pseudo signal in a transmission signal, i.e., for minimizing the error rate. A normal signal refers to, for example, a data string of each pattern of a transmission signal of a data string of a set length transmitted from a communication terminal 2 to a base station 3. For example, in the case of a transmission signal of a binary digital signal of 3 bits length, 2 3 There are normal signals with two different data strings. On the other hand, a pseudo signal is a data string that has a different pattern from the pattern of the data string of a normal signal. A normal signal is a data string that does not contain bit errors, and a pseudo signal corresponds to a data string in which a bit error occurs in the data string of a normal signal due to the addition of Gaussian noise.
[0028] For example, 2 3 In the case of a normal signal with two data string patterns, eight data string patterns, 000, 001, 010, 011, 100, 101, 110, and 111, are defined as normal signals. In contrast, for example, a pseudo signal for data string 111 among the eight normal signal patterns is a data string other than 111, and for example, any of 000, 001, 010, 011, 100, 101, and 110 can be a pseudo signal for data string 111 related to a normal signal.
[0029] The threshold value ρ0′ for minimizing the error rate between a normal signal and a pseudo signal in a transmission signal is expressed by the following equation (2) based on the above equation (1).
number
[0030] In the above equation (2), S0 is 0, i.e., a pseudo signal, S1 is 1, i.e., a normal signal, and σ 2 denotes the variance of Gaussian noise. E D(x)=1 is the expected value (first expected value) at which the discriminator 122 included in the learning unit 12 that performs learning of a GAN (generative adversarial network) described later identifies a normal signal as a normal signal (so-called real data), and E D(x)=0indicates an expected value (second expected value) at which a discriminator 122 included in the learning unit 12, which will be described later, discriminates a pseudo signal as a pseudo signal (so-called fake data).
[0031] In this way, the signal processing system according to the present embodiment determines the threshold value ρ0' for suppressing the error rate between the normal signal and the pseudo signal using the above formula (2). That is, the base station 3 can adopt the determined threshold value ρ0' as a judgment threshold value for a transmission signal to which Gaussian noise specific to the communication environment including the communication path L related to the wireless section and the base station 3 has been added. Therefore, when the transmission signal is decoded at the receiving base station 3, the error rate between the normal signal and the pseudo signal can be minimized. The same applies to the case of a transmission signal to which Gaussian noise specific to the communication environment including the communication path C related to the wired section and the core device 4 has been added.
[0032] [Signal processing unit functional blocks] As shown in FIG. 1, the signal processing device 1 includes a setting unit 10, a collecting unit 11, a learning unit 12, a determining unit 13, a storage unit 14, and a notifying unit 15.
[0033] The setting unit 10 sets each pattern of the data string of the transmission signal having the set length as a normal signal. Specifically, in the case of n data strings (n is an integer of 2 or more), the setting unit 10 sets 2 n As described above, in the case of a data string with a length of 3 bits, each of the eight data strings is set as a normal signal.
[0034] The collection unit 11 collects the noise variance from the device. Specifically, the collection unit 11 collects the Gaussian noise variance σ 2 The variance of Gaussian noise is 2 The values used are calculated from the distortion of the voltage value of the pilot signal in each of the base station 3 and the core device 4.
[0035] The learning unit 12 adversarially trains a GAN having a generator 121 and a discriminator 122. More specifically, the learning unit 12 trains a GAN (machine learning model) having a generator 121 that generates a pseudo signal, which is a data string having a different pattern from the pattern of a data string of a normal signal, and a discriminator 122 that discriminates between the pseudo signal generated by the generator 121 and a normal signal.
[0036] 3 and 4 are diagrams showing schematic diagrams of the neural network configuration of the generator 121 and the discriminator 122 of the GAN used by the learning unit 12. As shown in FIG. 3, the generator 121 is configured of a neural network having an input layer, a hidden layer, and an output layer. The generator 121 is a model that generates a pseudo signal from random noise. A vector of Gaussian noise is randomly sampled and input to the input node of the generator 121 (m samples z1 to z m The generator 121 performs a multiplication and accumulation operation on the input and weight parameters and performs threshold processing using an activation function to output G(z1) to G(z n ) to output.
[0037] The classifier 122 shown in Fig. 4 is configured with a neural network having an input layer, a hidden layer, and an output layer. In the example of Fig. 4, m sampled data strings x1 to x m is given. The discriminator 122 outputs, for example, 1 or 0 through a product-sum operation of the input and weight parameters and a threshold process using an activation function. The discriminator 122 outputs an output y=1 when it correctly discriminates the training data related to the input normal signal as a normal signal. On the other hand, it outputs an output y=0 when it correctly discriminates the training data related to the input pseudo signal as a pseudo signal. In this way, the discriminator 122 is a model that correctly distinguishes between a normal signal, which is real data, and a pseudo signal, which is fake data generated by the generator 121.
[0038] The learning unit 12 calculates a first expected value E of an objective function E of the GAN described later until the generator 121 generates pseudo signals having different data sequence patterns for each pattern of the data sequence of the normal signal set by the setting unit 10.D(x)=1 The value of the first expectation E is adjusted, and the generator 121 and the classifier 122 are trained adversarially. D(x)=1 is the expected value at which the discriminator 122 discriminates a normal signal as a normal signal.
[0039] 2 is a block diagram for explaining the adversarial learning of GAN by the learning unit 12. The generator 121 of the GAN adopted by the learning unit 12 is represented as a function G, and the discriminator 122 is represented as a function D. Furthermore, real data which is a normal signal is represented as x, a predicted value which is an output by the discriminator 122 is represented as y, and a correct label is represented as t. The correct label t is set to 1 for real data which is a normal signal, and 0 for fake data which is a pseudo signal generated by the generator 121. At this time, the discriminator 122 calculates the cross entropy E CE It can be expressed as:
[0040]
number
[0041] The first term in the brace of the above equation (3) represents t n lny n In the above, the predicted value y n is the correct label for the normal signal, t n = 1. On the other hand, the second term in the braces represents (1-t n )ln(1-y n ), the predicted value y n The correct label value (1-t n ) = 0. In this way, the cross entropy E CE is maximized when the predicted value matches the correct label value.
[0042] Here, the generator 121 constituting the GAN has parameters w G ,θ G and function G(w G ,θ G ) The discriminator 122 also uses the parameter w D ,θD and function D(w D ,θ D The cross entropy E in the above equation (3) CE The objective function E of the GAN including the generator 121 and the discriminator 122 based on the above can be expressed by the following equation (4).
number
[0043] The first term of the above formula (4) represents E D(x)=1 lnD(w D ,θ D ) is the first expected value at which the discriminator 122 discriminates a normal signal as a normal signal. D(x)=0 ln(1-D(G(w G ,θ G ),(w D ,θ D )) is a second expected value at which the discriminator 122 discriminates the pseudo signal generated by the generator 121 as a pseudo signal. In GAN learning, the generator 121 and the discriminator 122 are adversarially trained by min-max optimization of the objective function E. Therefore, the generator 121 is trained to be able to generate a pseudo signal that deceives the discriminator 122, and the discriminator 122 is trained to discriminate the pseudo signal generated by the generator 121 as a pseudo signal.
[0044] In learning by the classifier 122, when a normal signal is given, the classifier 122 maximizes the first term of the objective function E in the above equation (4) by outputting an output close to y=1. On the other hand, when a pseudo signal is given, the classifier 122 learns to maximize the second term of the objective function E by outputting an output close to y=0.
[0045] In the learning of the generator 121, D(G(w G ,θ G ),(w D ,θ D )) (D(Gz))) in Figure 2 is close to 1. G ,θ G) (G(z) in FIG. 2), that is, by deceiving the discriminator 122, the objective function E is minimized. The learning unit 12 uses a learning procedure in which the parameters of the generator 121 and the discriminator 122 are updated alternately. The learning procedure of the generator 121 and the discriminator 122 by the learning unit 12 will be described in detail later.
[0046] The learning unit 12 learns two of the transmission signals. n For each normal signal in the data sequence of the pattern, the generator 121 and the discriminator 122 are alternately trained. n The first expected value E is calculated until the generator 121 generates pseudo signals having different data sequence patterns for each normal signal of the data sequence. D(x)=1 The generator 121 and the discriminator 122 are trained adversarially by adjusting the value of
[0047] For example, consider a case where, among normal signals of eight patterns of 3-bit data sequences, a pseudo signal of the data sequence 101 is generated by the generator 121 for a normal signal of a certain data sequence 111, and a pseudo signal of the data sequence 101 is also generated by the generator 121 for a normal signal of another data sequence 110. In this case, the learning unit 12 repeats the first expected value E until the pseudo signals generated for the data sequences 111 and 110 of normal signals become data sequences with different patterns. D(x)=1 The value of is adjusted and learning is repeated between the generator 121 and the discriminator 122. Therefore, the data strings of the pseudo signals become data strings with patterns that do not overlap with each other.
[0048] When the objective function E of the GAN is optimized, the learning unit 12 calculates a first expected value E D(x)=1 The value of and the second expected value E D(x)=0 The value of is passed to the determination unit 13.
[0049] The determination unit 13 determines a threshold value for suppressing an error rate between a normal signal and a pseudo signal in a transmission signal to which noise has been added, based on the parameters of the machine learning model optimized by the learning unit 12. More specifically, the determination unit 13 determines a first expected value E D(x)=1 The value of and the second expected value E D(x)=0 The determination unit 13 calculates the threshold value ρ0′ that minimizes the error rate between the normal signal and the pseudo signal by substituting the value of ρ0′ into the above equation (2). The determination unit 13 also calculates the variance σ 2 Substitute into equation (2) above.
[0050] The storage unit 14 stores information about the models of the generator 121 and the discriminator 122 of the GAN, and the above formulas (1) to (4) used by the learning unit 12 and the determination unit 13.
[0051] The notification unit 15 notifies the determined threshold value ρ0′ to the base station 3 or the core device 4, which is a device that receives the transmission signal.
[0052] [Hardware configuration of the signal processing device] Next, an example of a hardware configuration for realizing the signal processing device 1 having the above-mentioned functions will be described with reference to FIG.
[0053] 5, the signal processing device 1 can be realized by, for example, a computer including a processor 102, a main storage device 103, a communication interface 104, an auxiliary storage device 105, and an input / output I / O 106, which are connected via a bus 101, and a program for controlling these hardware resources. The signal processing device 1 can also include a display device 107 connected via the bus 101.
[0054] The main memory device 103 prestores programs for the processor 102 to perform various controls and calculations. The processor 102 and the main memory device 103 realize the functions of the signal processing device 1, such as the setting unit 10, the collecting unit 11, the learning unit 12, the determining unit 13, and the notifying unit 15 shown in FIG.
[0055] The communication interface 104 is an interface circuit for network connection between the signal processing device 1 and various external electronic devices.
[0056] The auxiliary storage device 105 is composed of a readable / writable storage medium and a drive for reading and writing various information such as programs and data from and to the storage medium. The auxiliary storage device 105 can use a semiconductor memory such as a hard disk or a flash memory as the storage medium.
[0057] The auxiliary storage device 105 has a program storage area for storing the GAN learning program executed by the signal processing device 1. The auxiliary storage device 105 realizes the storage unit 14 described in FIG. 1. The auxiliary storage device 105 also has an area for storing information on the base station 3, the core device 4, and the communication paths L and C for which the threshold value ρ0′ is to be set. Furthermore, the auxiliary storage device 105 may have, for example, a backup area for backing up the above-mentioned data and programs.
[0058] The input / output I / O 106 is an input / output device that inputs signals from an external device and outputs signals to an external device.
[0059] The display device 107 is configured with an organic EL display, a liquid crystal display, etc. The notification unit 15 can also be realized by the display device 107.
[0060] [Operation of the signal processing device] Next, the operation of the signal processing device 1 having the above-mentioned configuration will be described with reference to the sequence diagram of FIG. 6 and the flowchart of FIG.
[0061] Fig. 6 is an operation sequence showing an overview of the operation of a signal processing system including the signal processing device 1. In the example of Fig. 6, the case where the target device for setting the threshold value ρ0' is the core device 4 is illustrated. First, in the core device 4, the variance σ 2 The signal processing device 1 measures the variance of the inherent Gaussian noise measured by the core device 4 and transmits it to the signal processing device 1. 2 is collected (step S1).
[0062] Next, the signal processing device 1 performs adversarial learning of the GAN to optimize parameters of the generator 121 and the discriminator 122 (step S100). The learning process of step S100 will be described in detail later with reference to the flowchart in FIG.
[0063] Thereafter, the signal processing device 1 calculates a first expected value E of the objective function E of the above formula (4) obtained as a result of the learning process. D(x)=1 The value of and the second expected value E D(x)=0 The value of σ σ , as well as the variance of the Gaussian noise specific to the core device 4 collected in step S1 2 Based on this, the signal processing device 1 determines a threshold value ρ0′ that minimizes the error rate between a normal signal and a pseudo signal in the transmission signal (step S13). After that, the signal processing device 1 notifies the core device 4 of the threshold value ρ0′ determined in step S13 (step S14).
[0064] The core device 4 that has received the notification sets the voltage value of the judgment threshold based on the threshold ρ0' (step S101). Note that the process shown in Fig. 6 is performed for each device, and for example, when there are multiple base stations 3, the threshold ρ0' is determined for each base station 3. Similarly, for the core device 4, the threshold ρ0' is determined for each of the UPF and UDR.
[0065] Next, the operation of the signal processing device 1 will be described with reference to the flowchart of Fig. 7 and the block diagram of the learning unit 12 of Fig. 2. Note that steps S1, S13, and S14 in Fig. 7 are similar to steps S1, S13, and S14 described with reference to Fig. 6.
[0066] First, the collection unit 11 receives the variance σ of Gaussian noise from the base station 3 or core device 4, which is the device for which the threshold ρ0' is to be determined. 2 (Step S1). Next, the setting unit 10 sets each pattern of the data string of the transmission signal of the set length as a normal signal (Step S2). Specifically, the setting unit 10 sets two patterns of the transmission signal of n-bit length. n Each of the signal patterns is set as a normal signal. For example, when n=3, 8 patterns of data strings are set as normal signals. The normal signals set by the setting unit 10 are training data used by the learning unit 12.
[0067] 2, the normal signal set in step S2 is used as training data 124 to be input when training the classifier 122. In the example of FIG. 2, the training data 124 of the data sequence 111 is provided to the classifier 122.
[0068] Next, the learning unit 12 n A normal signal having a signal pattern is input to the classifier 122 as training data 124, and the parameter w of the classifier 122 is set so as to classify the normal signal as a normal signal (y=1). D ,θ D (Step S3). In Step S3, the learning unit 12 can cause the discriminator 122 to learn the normal signal using, for example, the backpropagation method. In Step S3, the discriminator 122 capable of discriminating a normal signal from a normal signal is constructed in advance.
[0069] Next, the learning unit 12 generates Gaussian noise 120 and provides a random vector of the generated Gaussian noise 120 as an input to the generator 121 (step S4). Next, the generator 121 generates a random vector of the generated Gaussian noise 120 based on the input z and the weight parameter w G ,θ GA product-sum operation and a threshold process using an activation function are performed to generate a pseudo signal G(z) (step S5). Note that, for example, if the pattern of the data sequence of a normal signal is 111, a pseudo signal may be a data sequence with a pattern other than 111, such as 101.
[0070] Next, the classifier 122 is trained. The classifier 122 is trained by using the parameter w D ,θ D First, the learning unit 12 provides the training data 124 of the normal signal set in step S2 as an input to the discriminator 122, and calculates the gradient dE / dw so that the objective function E of the above formula (4) is maximized. D ,dE / dθ D Calculate the parameter w by backpropagation method. D ,θ D (Step S6). Note that the label of the training data 124 is set to 1 (normal signal).
[0071] Next, the learning unit 12 provides the pseudo signal generated by the generator 121 in step S5 to the discriminator 122 as an input, and calculates the gradient dE / dw so that the objective function E in the above equation (4) is maximized. D ,dE / dθ D Calculate the parameter w by backpropagation method. D ,θ D (Step S7). That is, in steps S6 and S7, in order to maximize the objective function E in the above formula (4), the first term is updated as D(w D ,θ D )=1 is output, and the second term is D(G(w G ,θ G ),(w D ,θ D ))=0. In addition, in the training data 124, the label is set to 0 (pseudo signal).
[0072] The learning of the classifier 122 in steps S6 and S7 corresponds to the dashed arrow in FIG. 2, in which a classifier error is calculated from block 125 of objective function E based on output 123 from the classifier 122, and the error is then back-propagated to the classifier 122.
[0073] Next, the generator 121 is trained. In training of the generator 121, the parameters of the discriminator 122 are fixed. The training unit 12 trains the generator 121 so that a pseudo signal is generated when random Gaussian noise 120 is given to the generator 121. Specifically, the training unit 12 trains the generator 121 by using a gradient -dE / dw G ,-dE / dθ G Calculate the parameter w by backpropagation method. G ,θ G is updated (step S8).
[0074] The learning in step S8 corresponds to the arrow indicated by the dashed line in which the error is back-propagated to the generator 121 shown in Fig. 2. That is, based on the output 123 when the pseudo signal generated by the generator 121 shown in Fig. 2 is input to the discriminator 122, a generator error is calculated in the block 125 of the objective function E, and corresponds to the arrow indicated by the dashed line in which the error is back-propagated to the generator 121.
[0075] Thereafter, until the value of the objective function E reaches the Nash equilibrium and converges (step S9: NO), the learning of the discriminator 122 and the generator 121 from step S4 to step S8 is repeated. On the other hand, if the value of the objective function E has converged (step S9: YES), n The remaining 2 of the normal signal data strings of the pattern n For the data string of the -1 pattern as well, the processes from step S2 to step S9 are repeated until the generator 121 and the discriminator 122 are trained (step S10: NO).
[0076] Then the remaining 2 nWhen the generator 121 and the discriminator 122 have been trained on the data sequence of −1 pattern (step S10: YES), the training unit 12 judges whether or not pseudo signals with mutually different data sequence patterns have been generated by the generator 121 for each signal pattern of a normal signal (step S11). For example, in the case of a data sequence of 8 patterns with a 3-bit length, the generator 121 generates a pseudo signal of the data sequence 101 for a data sequence 111 of a normal signal, and the generator 121 also generates a pseudo signal of the data sequence 101 for a data sequence 110 of another normal signal. In this case, in step S11, it is judged whether or not the data sequences of the pseudo signals generated for the data sequences 111 and 110 of the normal signals are data sequences of 8 different patterns. That is, the patterns of the data sequences of the pseudo signals generated for the normal signals of the 8 patterns are not overlapped with each other.
[0077] When pseudo signals related to data strings of different patterns have not been generated for normal signals of all patterns of data strings (step S11: NO), the learning unit 12 calculates the first term of the objective function E, i.e., the first expected value E D(x)=1 The value of is changed and adjusted, and the learning process from step S2 to step S10 is repeated. Therefore, in the above example of eight patterns of data strings, the patterns of the eight pseudo signal data strings generated for each of the eight patterns of normal signal data strings are different from each other and there are no overlapping signals.
[0078] Thereafter, when pseudo signals of data strings with different patterns are generated for normal signals of all patterns of data strings (step S11: YES), the learning unit 12 calculates the first expected value E D(x)=1 and the second expected value E D(x)=0 (Step S12).
[0079] Next, the determination unit 13 applies the first expected value E determined in step S12 to the above equation (2). D(x)=1 and the second expected value E D(x)=0and the variance σ of the Gaussian noise collected from the base station 3 or core device 4, which is the device to be processed and collected in step S1, is 2 and determines the threshold value ρ0′ (step S13). After that, the notification unit 15 notifies the determined threshold value ρ0′ to the base station 3 or the core device 4, which is the device to be processed (step S14).
[0080] As described above, according to the signal processing device 1 of the present embodiment, a data sequence of each pattern of a transmission signal having a data sequence of a set length is set as a normal signal, and adversarial learning of a GAN is performed having a generator 121 that generates a pseudo signal, which is a data sequence having a different pattern from the pattern of the data sequence of the normal signal, and a classifier 122 that distinguishes between the pseudo signal generated by the generator 121 and the normal signal. Furthermore, a first expected value E of the objective function E optimized by learning is D(x)=1 and the second expected value E D(x)=0 Using this, a threshold value ρ0' that minimizes the error rate between the normal signal and the pseudo signal of the transmission signal is determined. Therefore, the error rate of the signal can be reduced more easily without adding redundant bits.
[0081] In addition, according to the signal processing device 1 of this embodiment, a GAN machine learning model having a generator 121 and a discriminator 122 is constructed for each base station 3 and each core device 4, so that the process of reducing the bit error rate for each device can be realized with a simpler configuration.
[0082] The above describes embodiments of the signal processing device and signal processing method of the present invention. However, the present invention is not limited to the described embodiments, and various modifications that may be envisioned by a person skilled in the art can be made within the scope of the invention described in the claims. [Explanation of symbols]
[0083] 1...signal processing device, 10...setting unit, 11...collection unit, 12...learning unit, 13...decision unit, 14...memory unit, 15...notification unit, 2...communication terminal, 3...base station, 4...core device, 101...bus, 102...processor, 103...main memory device, 104...communication interface, 105...auxiliary memory device, 106...input / output I / O, 107...display device, 120...noise, 121...generator, 122...discriminator, 123...output, 124...training data, 125...block of objective function E, C, L...communication path, NW...network.
Claims
1. A setting unit configured to set each pattern of a data string of a transmission signal, which is a data string of a set length, as a normal signal; a learning unit configured to learn a machine learning model having a generator that generates a pseudo signal, which is a data sequence having a different pattern from a data sequence pattern of the normal signal, and a classifier that distinguishes between the pseudo signal generated by the generator and the normal signal; A determination unit configured to determine a voltage value of a judgment threshold for the transmission signal, based on parameters of the machine learning model optimized by learning by the learning unit, in order to suppress an error rate between the normal signal and the pseudo signal when an apparatus receives the transmission signal to which noise has been added; and a notification unit configured to notify the device receiving the transmission signal of the determined voltage value of the determination threshold; A signal processing device comprising:
2. 2. The signal processing device according to claim 1, The determination unit sets a voltage value of the judgment threshold based on a first expected value at which the classifier classifies the normal signal as a normal signal, and a second expected value at which the classifier classifies the pseudo signal generated by the generator as a pseudo signal, both of which are indicated by an objective function of the machine learning model.
23. A signal processing device comprising:
3. 3. The signal processing device according to claim 2, The learning unit adjusts a value of the first expected value until the generator generates the pseudo signal having a data sequence pattern different from each other for each pattern of the data sequence of the normal signal set by the setting unit, and causes the generator and the discriminator to learn in an adversarial manner.
23. A signal processing device comprising:
4. 3. The signal processing device according to claim 2, further comprising a collector configured to collect the variance of the noise from the device; The determination unit determines a voltage value of the determination threshold based on the variance collected by the collection unit, the first expected value, and the second expected value.
23. A signal processing device comprising:
5. a setting step of setting each pattern of a data string of a transmission signal having a set length as a normal signal; a learning step of learning a machine learning model having a generator that generates a pseudo signal, which is a data sequence having a different pattern from a pattern of a data sequence of the normal signal, and a classifier that distinguishes between the pseudo signal generated by the generator and the normal signal; a determining step of determining a voltage value of a judgment threshold for the transmission signal, based on parameters of the machine learning model optimized by learning in the learning step, in order to suppress an error rate between the normal signal and the pseudo signal when the transmission signal to which noise has been added is received by an apparatus; a notification step of notifying the device receiving the transmission signal of the determined voltage value of the judgment threshold; A signal processing method comprising:
6. 6. The signal processing method according to claim 5, The determining step sets a voltage value of the judgment threshold based on a first expected value at which the classifier classifies the normal signal as a normal signal and a second expected value at which the classifier classifies the pseudo signal generated by the generator as a pseudo signal, both of which are indicated by an objective function of the machine learning model. A signal processing method comprising:
7. 7. The signal processing method according to claim 6, The learning step adjusts a value of the first expectation value until the generator generates pseudo signals having data sequence patterns different from each other for each pattern of the data sequence of the normal signal set in the setting step, and causes the generator and the discriminator to learn in an adversarial manner. A signal processing method comprising:
8. 7. The signal processing method according to claim 6, Further comprising a step of collecting the variance of the noise from the device; The determining step determines a voltage value of the judgment threshold based on the variance collected in the collecting step, the first expected value, and the second expected value. A signal processing method comprising:
Citation Information
Patent Citations
Reception device, reception method, and reception program
JP2013038676A
Data generation system, learning device, data generation device, data generation method and data generation program
JP2021056677A
Error correction circuit, error correction device, error correction method, and communication device
JP7241851B1
