CN116390139A - Equipment detection method and device based on neural network, computer equipment and medium - Google Patents
Equipment detection method and device based on neural network, computer equipment and medium Download PDFInfo
- Publication number
- CN116390139A CN116390139A CN202310269953.7A CN202310269953A CN116390139A CN 116390139 A CN116390139 A CN 116390139A CN 202310269953 A CN202310269953 A CN 202310269953A CN 116390139 A CN116390139 A CN 116390139A
- Authority
- CN
- China
- Prior art keywords
- data set
- neural network
- matrix
- equipment
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 97
- 238000001514 detection method Methods 0.000 title claims abstract description 80
- 239000011159 matrix material Substances 0.000 claims abstract description 91
- 238000012549 training Methods 0.000 claims abstract description 61
- 238000012360 testing method Methods 0.000 claims abstract description 53
- 238000004891 communication Methods 0.000 claims abstract description 49
- 238000004364 calculation method Methods 0.000 claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 45
- 230000006870 function Effects 0.000 claims description 81
- 230000000694 effects Effects 0.000 claims description 26
- 238000005562 fading Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 17
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000001314 paroxysmal effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
- H04B17/364—Delay profiles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
- H04B17/3911—Fading models or fading generators
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer And Data Communications (AREA)
- Debugging And Monitoring (AREA)
Abstract
The embodiment of the application provides a device detection method, device, computer equipment and medium based on a neural network, and belongs to the technical field of communication. The method comprises the following steps: acquiring a training data set and a test data set; constructing an indication variable function according to the active state and the time delay value of the data set equipment; inputting the indicating variable function into a neural network for summation calculation, and outputting a covariance matrix; performing gradient calculation on the training data set and the test data set according to the covariance matrix, the preset first matrix, the preset second matrix and the preset learnable parameters to obtain gradient information; carrying out iterative updating on the gradient information and the indication variable function to obtain an updated variable; and iterating the neural network according to the updated variable, inputting the communication signal of the equipment to be detected into the iterated neural network, and determining the active state of the equipment to be detected. The method and the device can avoid high-complexity operation in the iterative algorithm and improve the detection accuracy of the active users.
Description
Technical Field
The present disclosure relates to the field of communications technologies, and in particular, to a device detection method, device, computer device, and medium based on a neural network.
Background
Along with the development of communication technology, large-scale machine communication becomes a main mode for connecting a large number of terminals of the internet of things, wherein active users directly perform data transmission on the allocated wireless communication resources in a scheduling-free random access process. Existing access procedures can be broadly divided into two categories. The first type is to utilize the paroxysmal nature of machine communication service, and adopt a method based on compressed sensing to realize the detection of active equipment by jointly estimating the activity state and the instantaneous channel of the equipment. In contrast, another class is to directly detect active devices based on the covariance of samples of the signal received by the access point using the probability distribution of the channel. Compared with the method based on compressed sensing, the method based on covariance does not need to estimate an instantaneous channel, so that a more accurate detection result of active equipment can be obtained. Although existing active device detection algorithms have somewhat better detection capabilities, implementation of these algorithms typically requires solving a high-dimensional non-convex problem. However, solving such non-convex problems requires designing an iterative algorithm with higher computational complexity, which does not meet the requirements of practical applications, thereby affecting the detection capability of active devices.
Disclosure of Invention
The main purpose of the embodiments of the present application is to provide a device detection method, device, computer device and medium based on a neural network, which can avoid high complexity operation in an iterative algorithm, and improve detection accuracy for active users.
To achieve the above object, a first aspect of an embodiment of the present application proposes a device detection method based on a neural network, the method including:
acquiring a training data set and a test data set, wherein the training data set and the test data set are obtained by calculating communication signals collected by an access point by a preset data generating function, and the access point comprises at least one device;
constructing an indicating variable function according to the training data set and the active state and the time delay value of the equipment in the test data set;
inputting the indicating variable function into the neural network for summation calculation, and outputting a covariance matrix;
performing gradient calculation on the training data set and the test data set according to the covariance matrix, the preset first matrix, the preset second matrix and the preset learnable parameters to obtain gradient information;
iteratively updating the gradient information and the indicated variable function based on the learnable parameters to obtain updated variables;
And iterating the neural network according to the updated variable, inputting the communication signal of the equipment to be detected into the iterated neural network for activity detection, and determining the activity state of the equipment to be detected.
In some embodiments, further comprising:
acquiring a characteristic sequence of equipment and a time delay value corresponding to the characteristic sequence;
and obtaining an equivalent characteristic sequence of the equipment according to the characteristic sequence and the time delay value.
In some embodiments, the training data set and the test data set are derived according to the steps of:
acquiring small-scale fading channel information between the equipment and the access point and transmitting power of the equipment;
calculating the distance between the equipment and the access point to obtain a distance value;
inputting the distance value into a preset loss model to obtain large-scale fading information;
generating a first function according to the transmitting power, the large-scale fading information and the equivalent characteristic sequence;
obtaining the data generating function according to the small-scale fading channel information, the first function and a preset Gaussian distribution value;
and inputting communication signals collected by the access point into the data generating function for calculation, and outputting the training data set and the test data set.
In some embodiments, the inputting the indicator variable function into the neural network for summation calculation, outputting a covariance matrix, includes:
acquiring the noise power of the access point;
and inputting the noise power, the first function, the indicating variable function and a preset identity matrix into the neural network for summation calculation, and outputting a covariance matrix.
In some embodiments, the learnable parameters include a penalty factor; the gradient calculation is performed on the training data set and the test data set according to the covariance matrix, the preset first matrix, the preset second matrix and the preset learnable parameters to obtain gradient information, and the gradient information comprises:
performing matrix approximation operation on the covariance matrix according to the first matrix and the second matrix to obtain an approximation matrix;
and carrying out gradient calculation on the training data set and the test data set according to the approximate matrix and the penalty factors to obtain the gradient information.
In some embodiments, the learnable parameter comprises an iteration step; the step of iteratively updating the gradient information and the indicated variable function based on the learnable parameters to obtain updated variables includes:
Multiplying the iteration step length with the gradient information to obtain a product result;
and obtaining the updated variable according to the indicated variable function and the product result.
In some embodiments, the iterating the neural network according to the updated variable, and inputting the device to be detected into the iterated neural network to perform active detection, and determining the active state of the device to be detected includes:
generating an iterative formula according to the updated variable and the learnable parameter;
iterating the neural network according to the iteration formula;
and inputting the equipment to be detected into the iterative neural network to perform activity detection, and determining the activity state of the equipment to be detected.
A second aspect of an embodiment of the present application proposes a device detection apparatus based on a neural network, the apparatus including:
the data acquisition module is used for acquiring a training data set and a test data set, wherein the training data set and the test data set are obtained by calculation of communication signals collected by an access point by a preset data generation function, and the access point comprises at least one device;
the function construction module is used for constructing an indication variable function according to the training data set and the active state and the time delay value of the equipment in the test data set;
The iterative computation module is used for inputting the indicating variable function into the neural network to carry out summation computation and outputting a covariance matrix;
the gradient calculation module is used for carrying out gradient calculation on the training data set and the test data set according to the covariance matrix, the preset first matrix, the preset second matrix and the preset learnable parameters to obtain gradient information;
the iterative updating module is used for carrying out iterative updating on the gradient information and the indication variable function based on the learnable parameters to obtain an updated variable;
and the activity detection module is used for iterating the neural network according to the updated variable, inputting the communication signal of the equipment to be detected into the iterated neural network for activity detection, and determining the activity state of the equipment to be detected.
A third aspect of the embodiments of the present application proposes a computer device comprising a memory and a processor, wherein the memory stores a computer program, which when executed by the processor is adapted to carry out the method according to any of the embodiments of the first aspect of the present application.
A fourth aspect of the embodiments of the present application proposes a storage medium being a computer readable storage medium storing a computer program for performing the method according to any one of the embodiments of the first aspect of the present application when the computer program is executed by a computer.
According to the equipment detection method, the equipment detection device, the computer equipment and the medium based on the neural network, the training data set and the test data set are obtained through calculation according to the communication signals collected by the access points of the data generation function, the indicating variable function is constructed according to the equipment activity states in the training data set and the test data set, the subsequent deep expansion is facilitated, the indicating variable function is input into the neural network for summation calculation, the covariance matrix is output, the subsequent training of the neural network is facilitated, then gradient calculation is carried out on the training data set and the test data set according to the covariance matrix, the preset first matrix, the preset second matrix and the preset learnable parameters to obtain gradient information, the learnable parameters and the preset matrix are introduced to avoid inversion operation in the calculation process, the calculation complexity is reduced, iterative update is carried out on the gradient information and the indicating variable function based on the learnable parameters to obtain an updating variable, the detection performance of the equipment is improved, finally the neural network is iterated according to the updating variable, the communication signals of the equipment to be detected are input into the neural network after iteration, the neural network to be detected, the iteration state to be detected is determined, and the iteration frequency of the neural network is improved, and the activity detection performance of the neural network is improved.
Drawings
Fig. 1 is a flowchart of a device detection method based on a neural network according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for neural network-based device detection provided in another embodiment of the present application;
fig. 3 is a specific flowchart of step S101 in fig. 1;
fig. 4 is a specific flowchart of step S103 in fig. 1;
fig. 5 is a specific flowchart of step S104 in fig. 1;
fig. 6 is a specific flowchart of step S105 in fig. 1;
fig. 7 is a specific flowchart of step S106 in fig. 1;
FIG. 8 is a schematic diagram of a neural network-based device detection method provided in one specific example of the present application;
FIG. 9 is a schematic diagram of a neural network-based device detection method provided in another specific example of the present application;
FIG. 10 is a block diagram of a module structure of an active user and data detection device provided in an embodiment of the present application;
fig. 11 is a schematic hardware structure of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
It should be noted that although functional block division is performed in a device diagram and a logic sequence is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the block division in the device, or in the flowchart. The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the present application.
Along with the development of communication technology, large-scale machine communication becomes a main mode for connecting a large number of terminals of the internet of things, wherein active users directly perform data transmission on the allocated wireless communication resources in a scheduling-free random access process. Existing access procedures can be broadly divided into two categories. The first type is to utilize the paroxysmal nature of machine communication service, and adopt a method based on compressed sensing to realize the detection of active equipment by jointly estimating the activity state and the instantaneous channel of the equipment. In contrast, another class is to directly detect active devices based on the covariance of samples of the communication signal received by the access point using the probability distribution of the channel. Compared with the method based on compressed sensing, the method based on covariance does not need to estimate an instantaneous channel, so that a more accurate detection result of active equipment can be obtained.
Although the active device detection algorithms of the related art have somewhat better detection capabilities, implementation of these algorithms typically requires solving a high-dimensional non-convex problem. However, the iterative algorithm with higher computational complexity is required to solve the non-convex problem, and the requirement of practical application is not met. Therefore, innovation on an access method of large-scale machine communication is very necessary, and a low-complexity solution idea is explored.
Based on this, a main purpose of the embodiments of the present application is to provide a device detection method, device, computer device and medium based on a neural network, which can avoid high complexity operation in an iterative algorithm, and improve detection accuracy for active users.
The equipment detection method based on the neural network can be applied to a terminal, a server side or software running in the terminal or the server side. In some embodiments, the terminal may be a smart phone, tablet, notebook, desktop, or smart watch, etc.; the server side can be configured as an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), basic cloud computing services such as big data and artificial intelligent platforms and the like; the software may be an application or the like that implements the above method, but is not limited to the above form.
Embodiments of the present application may be used in a variety of general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
Referring to fig. 1, fig. 1 is a flowchart of a specific method of a device detection method based on a neural network according to an embodiment of the present application. In some embodiments, the neural network-based device detection method includes, but is not limited to, steps S101 to S106.
Step S101, acquiring a training data set and a test data set;
it should be noted that the training data set and the test data set are calculated from communication signals collected by an access point by a preset data generating function, and the access point includes at least one device.
In some embodiments, a training data set is acquired along with a test data set to facilitate subsequent iterations of the neural network and training.
Step S102, constructing an indication variable function according to the training data set and the active state and the time delay value of the equipment in the test data set;
step S103, inputting the indication variable function into a neural network for summation calculation, and outputting a covariance matrix;
step S104, carrying out gradient calculation on a training data set and the test data set according to a covariance matrix, a preset first matrix, a preset second matrix and preset learnable parameters to obtain gradient information;
step S105, carrying out iterative updating on the gradient information and the indication variable function based on the learnable parameters to obtain an updated variable;
and S106, iterating the neural network according to the updated variable, inputting the communication signal of the equipment to be detected into the iterated neural network for activity detection, and determining the activity state of the equipment to be detected.
In steps S101 to S106 of some embodiments, a training data set and a test data set are obtained, an indication variable function is constructed according to active states and time-varying values of devices in the training data set and the test data set, so that the devices can be detected jointly, then the indication variable function is input into a neural network to perform summation calculation to obtain a covariance matrix, the subsequent training of the neural network is facilitated, gradient calculation is performed on the training data set and the test data set according to the covariance matrix, a preset first matrix, a preset second matrix and preset learnable parameters to obtain gradient information, inverse operation in a calculation process can be avoided by introducing the learnable parameters and the preset matrix, calculation complexity is reduced, then the gradient information and the indication variable function are updated iteratively based on the learnable parameters to obtain updated variables, detection performance of the neural network on the devices is improved, finally iteration is performed on the neural network according to the updated variables, the neural network after the devices to be detected are input into the iteration is performed on the neural network to perform active detection, the number of iterations of the neural network to be detected is determined, and accordingly the number of iterations of the neural network on the active states of the devices to be detected is reduced.
Referring to fig. 2, fig. 2 is a flowchart of a specific method of a device detection method based on a neural network according to another embodiment of the present application. In some embodiments, the neural network-based device detection method includes, but is not limited to, steps S201 to S202.
Step S201, obtaining a characteristic sequence of equipment and a time delay value corresponding to the characteristic sequence;
step S202, obtaining the equivalent characteristic sequence of the equipment according to the characteristic sequence and the time delay value.
In steps S201 through S202 of some embodiments, each device has a unique signature sequence during the transmission of the communication signal by the device
Wherein L is the length of the characteristic sequence, and the transmission of the characteristic sequence is accompanied by an unknown time delay t due to the characteristics of asynchronous transmission k E {0, …, T }, where T represents the maximum possible time delay, so the equivalent signature sequence with time delay for a device can be shown in equation (1) as follows:
it will be appreciated that when device k is in an active state, denoted as a k =1, otherwise a k =0. Thus, the active state and time delay of the device constitute an indicator variable function, as shown in equation (2) below:
it is noted that b is if and only if device k is in active state and the delay is t k,t =1. Thus, the detection of active devices by an access point in unsynchronized mass machine communications can be mathematically equivalent to the detection of b k,t E {0,1 }. Specifically, the method comprisesEach access point transmits the received communication signals to the central processing unit via a forward link, and the central processing unit then performs detection of the associated active devices. The active device detection task is typically modeled as a high-dimensional non-convex problem. To solve such non-convex problems, an iterative algorithm needs to be designed, and a specific description is given below.
Referring to fig. 3, fig. 3 is a specific flowchart of step S101 provided in the embodiment of the present application. In some embodiments, step S101 includes, but is not limited to, step S301 and step S306 in particular.
Step S301, small-scale fading channel information between equipment and an access point is obtained, and the transmitting power of the equipment is obtained;
in some embodiments, small-scale fading channel information between a kth device and an mth access point is obtained
Transmit power beta of device k Wherein beta is k ＝23dBm。
It should be noted that each element in the small-scale fading channel information follows the rayleigh distribution.
Step S302, calculating the distance between the equipment and the access point to obtain a distance value;
In some embodiments, the distance between the device and the access point is calculated, resulting in a distance value d.
Step S303, inputting the distance value into a preset loss model to obtain large-scale fading information;
in some embodiments, the distance value d is input into a predetermined loss model g k,m ＝128.1+37.6log 10 (d) Obtaining large-scale fading information g k,m 。
Step S304, generating a first function according to the transmitting power, the large-scale fading information and the equivalent characteristic sequence;
in some embodiments, according to the transmit power beta k Large-scale fading information g k,m Equivalent feature sequence s k,t Forming a first function z k,t,m 。
Step S305, generating a function according to the small-scale fading channel information, the first function and a preset Gaussian distribution value;
in some embodiments, the channel information is faded according to small dimensions
First function z k,t,m Preset gaussian distribution value W m Obtaining a data generating function Y m Wherein, the specific process is shown in the following formula (3):
the W is m Is subject to a gaussian distribution with a mean of 0 and a variance of 1.
In step S306, the communication signals collected by the access point are input into the data generating function to calculate, and the training data set and the test data set are output.
In some embodiments, the communication signal collected by the access point is input into the data generating function to perform calculation, and a training data set and a test data set are output, where the number of samples in the training data set and the test data set can be set according to the actual needs of the user, in this embodiment, 1280000 training samples are independently generated according to the formula (3) each time to form the training data set, 100000 verification set samples are generated to form the test data set, each training period includes 10000 cycles, and data in each cycle is transmitted to the neural network in a batch form, and the batch of one time is 128.
Referring to fig. 4, fig. 4 is a specific flowchart of step S103 provided in the embodiment of the present application. In some embodiments, step S103 specifically includes, but is not limited to, step S401 and step S402.
Step S401, obtaining the noise power of an access point;
and step S402, the noise power, the first function, the indicating variable function and a preset identity matrix are input into a neural network for summation calculation, and a covariance matrix is output.
In steps S401 to S402 of some embodiments, the noise power of the access point is obtained
And performing conjugate transposition calculation on the first function to obtain +.>
Noise power +.>
First function z k,t,m Indicating variable function->
Preset identity matrix I L+T Are all input into the neural network and the first function z k,t,m First function after conjugate transpose->
Indicating variable function +.>
Summation is carried out and the sum is added with noise power +>
And a preset identity matrix I L+T Is added to the products of (2) to obtain a covariance matrix +.>
The specific formula (4) is as follows:
referring to fig. 5, fig. 5 is a specific flowchart of step S104 provided in the embodiment of the present application. In some embodiments, step S104 specifically includes, but is not limited to, steps S501 to S502.
It should be noted that the learnable parameters include penalty factors.
Step S501, performing matrix approximation operation on the covariance matrix according to the first matrix and the second matrix to obtain an approximation matrix;
in some embodiments, since the original active detection algorithm needs to perform an inversion operation on the covariance matrix, which results in higher computational complexity and higher iteration number, the method does not meet the requirements of practical applications, and therefore, the method passes through the first matrix a (i) And a second matrix B (i) For covariance matrix
Performing matrix approximation operation to obtain an approximation matrix
Therefore, the computational complexity of the traditional iterative algorithm is reduced, the inversion operation of a matrix is avoided, and the detection efficiency of the equipment is improved.
It should be noted that the first matrix and the second matrix need to be consistent with the dimensions of the covariance matrix.
Step S502, gradient calculation is carried out on the training data set and the test data set according to the approximate matrix and the penalty factors, and gradient information is obtained.
In some embodiments, the matrix is approximated
And performing gradient calculation on the training data set and the test data set by using the penalty factor rho to obtain gradient information +.>
Therefore, the inversion operation of the matrix is avoided, the calculation complexity is reduced, the learning capacity of the neural network is improved by introducing the penalty factor, and the calculation accuracy is improved, wherein the specific process is shown in the following formula (5):
It will be appreciated that N represents the number of antennas per access point,
representing the objective function at +.>
The gradient information of the object function, wherein the specific expression form of the object function can be derived according to the maximum likelihood criterion based on covariance, and the embodiment is not particularly limited.
Referring to fig. 6, fig. 6 is a specific flowchart of step S105 provided in the embodiment of the present application. In some embodiments, step S105 specifically includes, but is not limited to, steps S601 to S602.
It should be noted that the learnable parameters include iteration steps.
Step S601, multiplying the iteration step length by gradient information to obtain a product result;
step S602, obtaining updated variables according to the indicated variable function and the product result.
In steps S601 to S602 of some embodiments, the iteration step η is combined with the gradient information
Multiplying to obtain product result, and according to the instruction variable function +.>
The product result gets the update variable +.>
Wherein, the specific process is shown in the following formula (6):
wherein eta (i) Representing the step size of the i-th iteration,
representing the updated variables of the algorithm after one gradient descent.
Referring to fig. 7, fig. 7 is a specific flowchart of step S106 provided in the embodiment of the present application. In some embodiments, step S106 specifically includes, but is not limited to, steps S701 through S703.
Step S701, generating an iterative formula according to the updated variable and the learnable parameters;
in some embodiments, an iterative formula is generated from the updated variables and the learnable parameters, wherein the specific formula (7) is as follows:
wherein,,
Π [0,1] represents min (max (. Cndot.,. Cndot.0)), 1.
Step S702, iterating the neural network according to an iteration formula;
in some embodiments, the neural network is iterated according to an iteration formula, one iteration process of the iteration algorithm is regarded as one layer of the neural network, convergence can be completed through fewer layers, and learnable parameters are introduced in the iteration process to train in a supervised learning mode, so that the detection accuracy of the equipment is improved.
Step S703, inputting the communication signal of the device to be detected into the iterated neural network for activity detection, and determining the activity state of the device to be detected.
In some embodiments, a communication signal of a device to be detected is input into an iterative neural network to detect a device state, where the communication signal of the device to be detected carries a feature sequence of the device to be detected, and the feature sequence of the device to be detected and a delay value corresponding to the feature sequence are obtained to form an equivalent of the device to be detected Characteristic sequences, and calculate according to formulas (3) to (7), output
Thereby determining the active state of the device to be detected.
In order to more clearly describe the flow of the neural network-based device detection method, a specific example will be described below.
Example one:
referring to fig. 8, fig. 8 is a schematic diagram of a device detection method based on a neural network according to a specific example of the present application;
firstly, the communication signals collected by the access point are input into a data generating function for calculation, a training data set and a test data set are output, wherein the number of samples in the training data set and the test data set can be set according to the actual requirement of a user, 1280000 training samples are independently generated according to a formula (3) each time to form the training data set, 100000 verification set samples are generated to form the test data set, each training period comprises 10000 cycles, data in each cycle is transmitted into the neural network in a batch form, the batch is 128 for one time, then the training data set and the test data set are input into the neural network for training based on the device detection method in the embodiment, an indicating variable function is constructed according to the active state and the time delay value of the devices in the training data set and the test data set, initializing the indicating variable function, inputting the indicating variable function into a neural network for summation calculation to obtain a covariance matrix, introducing a first matrix and a second matrix to perform matrix approximation operation on the covariance matrix to obtain an approximation matrix, performing gradient calculation on a training data set and a test data set through a learnable penalty factor to obtain gradient information, performing iterative update on the gradient information and the indicating variable function based on the learnable parameter to obtain an updated variable, thereby effectively reducing the calculation complexity of a traditional iterative algorithm, finally iterating the neural network according to the updated variable, regarding one iteration process of the iterative algorithm as a layer of the neural network, performing active detection on the neural network after the equipment to be detected is input and iterated, determining the active state of the equipment to be detected, the active device detection capability of the network is improved.
Referring to fig. 8, it can be seen that the device detection method based on the neural network in this embodiment has good convergence, and requires fewer layers to complete convergence, where I is the different layers of the neural network.
Referring to fig. 9, fig. 9 is a schematic diagram of a device detection method based on a neural network according to another specific example of the present application;
referring to fig. 9, it can be seen that, compared with the existing coordinate descent algorithm and penalty function method, the method of the embodiment has lower false alarm probability and missing detection probability, so that the accuracy of detecting the active state of the device can be improved.
Referring to fig. 10, fig. 10 is a block diagram of a device detection apparatus based on a neural network according to an embodiment of the present application, configured to execute the device detection method based on a neural network according to any one of the foregoing embodiments, where the device includes:
a data acquisition module 801, configured to acquire a training data set and a test data set, where the training data set and the test data set are obtained by calculating a communication signal collected by an access point by a preset data generating function, and the access point includes at least one device;
a function construction module 802, configured to construct an indication variable function according to the training data set and the activity state and the time delay value of the device in the test data set;
The iterative computation module 803 is configured to input the indicated variable function into the neural network to perform summation computation, and output a covariance matrix;
the gradient calculation module 804 is configured to perform gradient calculation on the training data set and the test data set according to the covariance matrix, the preset first matrix, the preset second matrix, and the preset learnable parameters, so as to obtain gradient information;
the iterative updating module 805 is configured to iteratively update the gradient information and the indicator variable function based on the learnable parameters to obtain an updated variable;
the activity detection module 806 is configured to iterate the neural network according to the updated variable, input the device to be detected into the iterated neural network to perform activity detection, and determine an activity state of the device to be detected.
The device detection apparatus based on the neural network in the embodiment of the present application is configured to execute the device detection method based on the neural network in the above embodiment, and the specific processing procedure is the same as the device detection method based on the neural network in the above embodiment, which is not described in detail herein.
The embodiment of the application also provides a computer device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used for executing the device detection method based on the neural network in the embodiment of the application when the computer program is executed by the processor.
The hardware configuration of the computer device is described in detail below with reference to fig. 11. The computer device includes: a processor 910, a memory 920, an input/output interface 930, a communication interface 940, and a bus 950.
The processor 910 may be implemented by a general-purpose CPU (Central Processin Unit, central processing unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc. for executing related programs to implement the technical solutions provided in the embodiments of the present application;
the Memory 920 may be implemented in the form of a Read Only Memory (ROM), a static storage device, a dynamic storage device, or a random access Memory (Random Access Memory, RAM). The memory 920 may store an operating system and other application programs, and when the technical solutions provided in the embodiments of the present application are implemented by software or firmware, relevant program codes are stored in the memory 920, and the processor 910 invokes a device detection method based on a neural network to perform the embodiments of the present application;
an input/output interface 930 for inputting and outputting information;
The communication interface 940 is configured to implement communication interaction between the device and other devices, and may implement communication in a wired manner (e.g., USB, network cable, etc.), or may implement communication in a wireless manner (e.g., mobile network, WIFI, bluetooth, etc.); and a bus 950 for transferring information between components of the device (e.g., processor 910, memory 920, input/output interface 930, and communication interface 940);
wherein processor 910, memory 920, input/output interface 930, and communication interface 940 implement communication connections among each other within the device via a bus 950.
The embodiment of the present application also provides a storage medium, which is a computer readable storage medium, where a computer program is stored, and when the computer program is executed by a computer, the computer is configured to perform a device detection method based on a neural network as in the above embodiment of the present application.
The memory, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The embodiments described in the embodiments of the present application are for more clearly describing the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application, and as those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.
It will be appreciated by those skilled in the art that the solutions shown in fig. 1-7 are not limiting to embodiments of the present application, and may include more or fewer steps than illustrated, or may combine certain steps, or different steps.
The above described apparatus embodiments are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Those of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
The terms "first," "second," "third," "fourth," and the like in the description of the present application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in this application, "at least one" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown 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 may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including multiple instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing a program.
Preferred embodiments of the present application are described above with reference to the accompanying drawings, and thus do not limit the scope of the claims of the embodiments of the present application. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and spirit of the embodiments of the present application shall fall within the scope of the claims of the embodiments of the present application.
Claims (10)
1. A method for detecting a device based on a neural network, the method comprising:
acquiring a training data set and a test data set, wherein the training data set and the test data set are obtained by calculating communication signals collected by an access point by a preset data generating function, and the access point comprises at least one device;
constructing an indicating variable function according to the training data set and the active state and the time delay value of the equipment in the test data set;
inputting the indicating variable function into the neural network for summation calculation, and outputting a covariance matrix;
performing gradient calculation on the training data set and the test data set according to the covariance matrix, the preset first matrix, the preset second matrix and the preset learnable parameters to obtain gradient information;
iteratively updating the gradient information and the indicated variable function based on the learnable parameters to obtain updated variables;
and iterating the neural network according to the updated variable, inputting the communication signal of the equipment to be detected into the iterated neural network for activity detection, and determining the activity state of the equipment to be detected.
2. The device detection method according to claim 1, characterized by further comprising:
acquiring a characteristic sequence of equipment and a time delay value corresponding to the characteristic sequence;
and obtaining an equivalent characteristic sequence of the equipment according to the characteristic sequence and the time delay value.
3. The device detection method according to claim 2, wherein the training data set and the test data set are obtained according to the steps of:
acquiring small-scale fading channel information between the equipment and the access point and transmitting power of the equipment;
calculating the distance between the equipment and the access point to obtain a distance value;
inputting the distance value into a preset loss model to obtain large-scale fading information;
generating a first function according to the transmitting power, the large-scale fading information and the equivalent characteristic sequence;
obtaining the data generating function according to the small-scale fading channel information, the first function and a preset Gaussian distribution value;
and inputting communication signals collected by the access point into the data generating function for calculation, and outputting the training data set and the test data set.
4. The apparatus detection method according to claim 3, wherein inputting the indicated variable function into the neural network for summation calculation, outputting a covariance matrix, comprises:
Acquiring the noise power of the access point;
and inputting the noise power, the first function, the indicating variable function and a preset identity matrix into the neural network for summation calculation, and outputting a covariance matrix.
5. The device detection method of claim 1, wherein the learnable parameter comprises a penalty factor; the gradient calculation is performed on the training data set and the test data set according to the covariance matrix, the preset first matrix, the preset second matrix and the preset learnable parameters to obtain gradient information, and the gradient information comprises:
performing matrix approximation operation on the covariance matrix according to the first matrix and the second matrix to obtain an approximation matrix;
and carrying out gradient calculation on the training data set and the test data set according to the approximate matrix and the penalty factors to obtain the gradient information.
6. The device detection method of claim 1, wherein the learnable parameter comprises an iteration step; the step of iteratively updating the gradient information and the indicated variable function based on the learnable parameters to obtain updated variables includes:
Multiplying the iteration step length with the gradient information to obtain a product result;
and obtaining the updated variable according to the indicated variable function and the product result.
7. The device detection method according to claim 1, wherein the iterating the neural network according to the updated variable, and inputting the device to be detected into the iterated neural network to perform active detection, and determining the active state of the device to be detected includes:
generating an iterative formula according to the updated variable and the learnable parameter;
iterating the neural network according to the iteration formula;
and inputting the equipment to be detected into the iterative neural network to perform activity detection, and determining the activity state of the equipment to be detected.
8. A neural network-based device detection apparatus, the apparatus comprising:
the data acquisition module is used for acquiring a training data set and a test data set, wherein the training data set and the test data set are obtained by calculation of communication signals collected by an access point by a preset data generation function, and the access point comprises at least one device;
the function construction module is used for constructing an indication variable function according to the training data set and the active state and the time delay value of the equipment in the test data set;
The iterative computation module is used for inputting the indicating variable function into the neural network to carry out summation computation and outputting a covariance matrix;
the gradient calculation module is used for carrying out gradient calculation on the training data set and the test data set according to the covariance matrix, the preset first matrix, the preset second matrix and the preset learnable parameters to obtain gradient information;
the iterative updating module is used for carrying out iterative updating on the gradient information and the indication variable function based on the learnable parameters to obtain an updated variable;
and the activity detection module is used for iterating the neural network according to the updated variable, inputting the communication signal of the equipment to be detected into the iterated neural network for activity detection, and determining the activity state of the equipment to be detected.
9. A computer device comprising a memory and a processor, wherein the memory has stored therein a computer program which, when executed by the processor, is adapted to carry out the method of any one of claims 1 to 7.
10. A storage medium, characterized in that the storage medium is a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for performing the method according to any one of claims 1 to 7 when the computer program is executed by a computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310269953.7A CN116390139A (en) | 2023-03-14 | 2023-03-14 | Equipment detection method and device based on neural network, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310269953.7A CN116390139A (en) | 2023-03-14 | 2023-03-14 | Equipment detection method and device based on neural network, computer equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116390139A true CN116390139A (en) | 2023-07-04 |
Family
ID=86963966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310269953.7A Pending CN116390139A (en) | 2023-03-14 | 2023-03-14 | Equipment detection method and device based on neural network, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116390139A (en) |
-
2023
- 2023-03-14 CN CN202310269953.7A patent/CN116390139A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070117B (en) | Data processing method and device | |
| Huang et al. | A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation | |
| CN110378488B (en) | Client-side change federal training method, device, training terminal and storage medium | |
| CN111709533A (en) | Distributed training method and device of machine learning model and computer equipment | |
| JP2019061565A (en) | Abnormality diagnostic method and abnormality diagnostic device | |
| CN109120462A (en) | Prediction technique, device and the readable storage medium storing program for executing of opportunistic network link | |
| CN111537884B (en) | Method and device for acquiring service life data of power battery, computer equipment and medium | |
| WO2009014898A2 (en) | Local computation of rank contributions | |
| CN103559205A (en) | Parallel feature selection method based on MapReduce | |
| CN113159273B (en) | Neural network training method and related equipment | |
| CN111461164A (en) | Sample data set capacity expansion method and model training method | |
| CN113726545B (en) | Network traffic generation method and device for generating countermeasure network based on knowledge enhancement | |
| CN112100619B (en) | Malicious file detection method, system, equipment and computer storage medium | |
| CN110958565B (en) | Method and device for calculating signal distance, computer equipment and storage medium | |
| CN113449188A (en) | Application recommendation method and device, electronic equipment and readable storage medium | |
| CN116390139A (en) | Equipment detection method and device based on neural network, computer equipment and medium | |
| Nguyen et al. | Federated pca on grassmann manifold for iot anomaly detection | |
| CN113807522B (en) | Method and device for generating Bayesian network structure, electronic equipment and storage medium | |
| CN111459990B (en) | Object processing method, system, computer readable storage medium and computer device | |
| Kalam et al. | 5g traffic forecasting using federated learning | |
| CN113792185B (en) | Method, apparatus, computer device and storage medium for estimating missing signal | |
| CN113038596B (en) | Indoor positioning method, device, equipment and computer readable storage medium | |
| CN113468771B (en) | Vibration estimation method using structure intrinsic parameters | |
| CN114723576B (en) | Data processing model generation method, data processing method and device | |
| US20230334096A1 (en) | Graph data processing method and apparatus, computer device, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |