CN114158049A - Bluetooth communication identity recognition method, system, computer and storage medium - Google Patents
Bluetooth communication identity recognition method, system, computer and storage medium Download PDFInfo
- Publication number
- CN114158049A CN114158049A CN202111528957.XA CN202111528957A CN114158049A CN 114158049 A CN114158049 A CN 114158049A CN 202111528957 A CN202111528957 A CN 202111528957A CN 114158049 A CN114158049 A CN 114158049A
- Authority
- CN
- China
- Prior art keywords
- white noise
- data
- clock jitter
- data flow
- flow
- 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.)
- Granted
Links
- 238000004891 communication Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000000513 principal component analysis Methods 0.000 claims abstract description 16
- 238000005065 mining Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 30
- 238000013507 mapping Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000010801 machine learning Methods 0.000 claims description 10
- 238000005111 flow chemistry technique Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 238000000265 homogenisation Methods 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims 1
- 238000005206 flow analysis Methods 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 9
- 230000008901 benefit Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000036544 posture Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000005336 cracking Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/08—Access security
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/18—Network architectures or network communication protocols for network security using different networks or channels, e.g. using out of band channels
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention provides an identity recognition method, an identity recognition system, a computer and a storage medium for Bluetooth communication, and belongs to the technical field of identity recognition of Bluetooth communication. In the face of a large amount of flow sent to the slave equipment by the Bluetooth master equipment, the operation flow, the operation white noise and the data flow of the smooth operation accompanied by the white noise are distinguished through flow analysis, the operation white noise and the clock jitter data flow of the smooth operation connected with the white noise are extracted and combined respectively; and respectively carrying out Fourier transform on the combined two types of clock jitter data flow to obtain clock jitter data with equal data length and unchanged original characteristics. And (3) projecting the clock jitter data flow to a two-dimensional plane by utilizing kernel principal component analysis, and performing deep feature mining to realize fine feature mining and personal identification of the Bluetooth communication user. The technical problems of long time, high difficulty and low efficiency of user portrait in the prior art are solved.
Description
Technical Field
The present application relates to an identity recognition method, and more particularly, to an identity recognition method, system, computer and storage medium for bluetooth communication, and belongs to the technical field of bluetooth communication identity recognition.
Background
The Bluetooth master-slave equipment carries out encryption communication according to a Bluetooth protocol, and the characteristics of a Bluetooth chip in the aspect of data stream processing design cause that the Bluetooth chip needs to consume time to reconstruct a data packet written with a new instruction when the master equipment is in conversion operation, so that a time interval sequence of the data packet in a communication transmission process has slight time difference mutation. After the conversion operation, the time interval between the first data packet sent by the bluetooth device and the previous data packet is instantly enlarged and finally gradually restored. Therefore, the time interval between packet sequences corresponding to operations, the number of packets, and the duration of packet interval instability are different. There are a lot of white noises, which are not valid data packets, between these characteristic data packet combinations, and the white noises of different users are different when the same operation or operation switching is repeatedly performed. At present, if identity judgment is required to be carried out on a user, the user needs to be depicted by collecting behavior habits and behavior characteristics of the user for a long time, and the identity of the user can be recognized only when the user carries out a series of long-time operations.
However, there is currently no method for achieving identification of a user of bluetooth communication by only analyzing white noise between single or few operations.
Disclosure of Invention
The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to determine the key or critical elements of the present invention, nor is it intended to limit the scope of the present invention. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.
In view of this, in order to solve the technical problems of long time, high difficulty and low efficiency of user portrayal in the prior art, the invention provides an identity recognition method, an identity recognition system, a computer and a storage medium for bluetooth communication.
The first scheme is as follows: the invention provides an identity recognition method of Bluetooth communication, which is characterized in that data flow characteristics of encrypted communication correspond to users of current equipment, and the users are portrayed according to behavior habits so as to judge the identity of the user executing the current operation behavior; the method specifically comprises the following steps:
collecting white noise and clock jitter data of smooth operation connected with the white noise, and performing combination and length homogenization treatment on the collected data to obtain the white noise with the same characteristics and length as the original characteristics and the clock jitter data flow of the smooth operation connected with the white noise;
step two, respectively taking the number of data packets of the white noise jitter data and the time interval between every two data packets as white noise data flow characteristics, taking the number of data packets of the jitter data of smooth operation connected with the white noise and the time interval between every two data packets as the data flow characteristics of the smooth operation connected with the white noise, and respectively mining and classifying the detail characteristics of the two types of processed clock jitter data flow by utilizing a kernel function through a nonlinear characteristic mapping function and linear principal component analysis;
and step three, judging and predicting the unknown user data flow characteristics needing identity judgment by using the linear principal component analysis method optimized in the step two, thereby realizing identity identification.
Preferably, the first step is a specific method of collecting white noise and clock jitter data of a smoothing operation connected to the white noise, and performing combination and length normalization processing on the collected data, and includes the following steps:
recording the arrival time of a data packet and the byte amount sent to a slave device by a master device every second, and smoothing broken data and packet loss conditions;
step two, according to the characteristics of the Bluetooth equipment, dividing the time jitter of the flow data into corresponding flow data during operation and white noise which does not correspond to the operation;
combining the clock jitters of corresponding continuous data packet time intervals to further obtain white noise data flow which does not correspond to operation and smooth operation data flow connected with the white noise;
step three, white noise clock jitter data flow and clock jitter data flow of smooth operation connected with the white noise are respectively combined together;
performing Fourier transform on white noise clock jitter data flow and clock jitter data flow of smooth operation connected with white noise, converting discrete points into a frequency domain, uniformly sampling 20 points on the frequency domain, and performing inverse Fourier transform on sampling points to obtain clock jitter data with equal data length and unchanged original characteristics;
and step one and five, white noise which is consistent with the original characteristics and is consistent with the length and clock jitter data flow of smooth operation connected with the white noise are respectively obtained.
Preferably, the specific method for mining and analyzing the detail features of the processed data traffic in the second step is as follows:
step two, mapping a training set formed by user flow data characteristics of a sample library to a high-dimensional space by utilizing a kernel function through a nonlinear characteristic mapping function, wherein the available functions are a Radial Basis Function (RBF) and a Sigmoid function, and the RBF formula is as follows:
wherein xtIs the center of the spherical kernel, x is the attribute vector, and s is the hyper-parameter; the Sigmoid function is formulated as: k (x)t，x)＝tanh(γxTxt+ r), wherein γ and r are hyperparameters;
secondly, calculating a covariance matrix by taking the training set mapped to the high-dimensional space as a feature matrix, selecting principal components according to a mapping result, projecting the converted training set to a two-dimensional plane through linear principal component analysis, and performing nonlinear regression and classification on the dimensionality-reduced data set through iterative convergence according to an initial value of the linear principal component analysis result;
step two, analyzing a verification set formed by training sets of the two types of data streams through 10 times of cross verification, and verifying and optimizing the accuracy of the method in the step two;
preferably, the specific method for performing the discrimination prediction on the unknown user data traffic characteristics needing identity discrimination in the third step is that the method includes the following steps:
step three, mapping a test set formed by unknown user flow data characteristics needing identity discrimination to a high-dimensional space by utilizing the kernel function of the optimized parameters in the step two through a nonlinear characteristic mapping function;
and step two, according to the optimized principal component setting in the step two, projecting the converted test set to a two-dimensional plane through linear principal component analysis, performing nonlinear regression and classification prediction, and outputting a classification result.
Preferably, the specific method for performing fourier transform on the white noise clock jitter data traffic and the clock jitter data traffic of the smoothing operation connected to the white noise in the first step is implemented by the following formula:
where x (n) is the data traffic and n is the length of the data traffic.
Preferably, the specific method for performing inverse fourier transform on the four sampling points in the first step is implemented by the following formula:
the second scheme is that the Bluetooth communication identity recognition system comprises a clock jitter data flow processing module and a flow characteristic machine learning module; the clock jitter data flow processing module is used for white noise and clock jitter data collection, combination and length homogenization treatment of smooth operation connected with the white noise; the flow characteristic machine learning module is used for mining and analyzing the detail characteristics of the clock jitter data flow output by the clock jitter data flow processing module to realize the identification of different users.
The third scheme is as follows: a computer comprising a memory storing a computer program and a processor implementing the steps of one of the methods of identification of bluetooth communication when executing the computer program.
And the scheme is as follows: a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, implements one of the aspects described herein for identification of bluetooth communications.
The invention has the following beneficial effects: under the condition that Bluetooth encryption communication is not cracked violently, identity recognition of Bluetooth communication is achieved through homogenization treatment of clock jitter data length of smooth operation connected with white noise or white noise and a machine learning model based on a radial basis function, ciphertext data flow characteristics do not need to correspond to user operation, whether a current user of Bluetooth communication is a common user or not can be judged from short-time operation, and identity recognition can be carried out. The invention greatly reduces the equipment cost required by the Bluetooth encryption communication identity recognition, only needs to update the content of the training set, has universality and generalizability, greatly improves the efficiency of the Bluetooth communication identity recognition, and greatly facilitates the research of technical researchers on the behaviors and identities of Bluetooth communication users. The technical problems of long time, high difficulty and low efficiency of user portrait in the prior art are solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic process flow diagram;
FIG. 2 is a schematic flow chart of the steps;
FIG. 3 is a schematic diagram of clock jitter data flow combining white noise of different users;
FIG. 4 is a graph of the combined smooth-moving clock jitter data flow for different users in conjunction with white noise;
FIG. 5 is a schematic diagram of white noise and clock jitter data traffic of uniform length processed by different users;
FIG. 6 is a graph of smooth moving clock jitter data flow with uniform length connected to white noise processed by different users.
Detailed Description
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Embodiment 1, this embodiment is described with reference to fig. 1 to 6, which illustrate an identity recognition method for bluetooth communication, in which a data traffic characteristic of encrypted communication corresponds to a user of a current device, and the user is portrayed according to a behavior habit, so as to determine a user identity for executing a current operation behavior;
firstly, the arrival time of a data packet and the byte amount sent by the master device to the slave device per second are recorded, and the broken data and the packet loss condition are smoothed. The characteristics of the bluetooth chip in terms of the design of data stream processing result in that the time interval between the first data packet sent by the bluetooth device after the conversion operation and the previous data packet is instantly enlarged and then gradually restored. According to the frequently occurring continuous operation and the occurred operation of the Bluetooth equipment, the clock jitters of the corresponding continuous data packet time intervals are combined, and then white noise data flow which does not correspond to the operation and smooth operation data flow connected with the white noise are obtained.
Then, the white noise clock jitter data traffic and the smooth clock jitter data traffic connected to the white noise are combined together, respectively. The two data are subjected to Fourier transform, and the formula is as follows:
where x (n) is the data traffic and n is the length of the data traffic, the discrete points are transformed into the frequency domain after the transformation. And uniformly sampling the sampling points with the number larger than the clock jitter in a frequency domain according to the Nyquist theorem. And performing inverse Fourier transform on the sampling points, wherein the formula is as follows:
white noise with the same length and the same original characteristic and clock jitter data flow of smooth operation connected with the white noise are respectively obtained.
For example, the wireless platform is used for capturing Bluetooth communication data between a Bluetooth mouse and a computer, and the current user identity is required to be identified. Different users have different habits of using the mouse, namely, the user adjusts the mouse to the most comfortable state before operating the mouse according to instinct, and different postures of holding the mouse to the most comfortable state are caused by different hand shapes and muscle strength of people, so that different jitter detail characteristics before operation are caused, namely, clock jitter data flow difference of white noise. In addition, since the user adjusts the hand posture and the mouse position before starting the operation to facilitate the action, the two actions of adjusting the hand posture and finding the arm fulcrum do not occur simultaneously, i.e., the process includes white noise and smooth movement immediately thereafter. White noise and smoothly moving clock jitter data traffic connected to the white noise are extracted as shown in fig. 3 and 4. White noise of which the user set is consistent with the length of the current user and smoothly moving clock jitter data traffic connected with the white noise are respectively obtained, as shown in fig. 5 and 6.
Aiming at the characteristics of the processed clock jitter data flow, respectively adopting a Radial Basis Function (RBF) capable of learning the characteristic length scale of the sample similarity and the applicationAnd taking the Sigmoid function with characteristic complex difference conditions as a kernel function to perform kernel principal component analysis. Wherein the radial basis function is: RBF:
wherein xtIs the center of the spherical kernel, x is the attribute vector, and s is the hyper-parameter; the Sigmoid function is:
K(xt,x)＝tanh(yxTxt+ r) where y and r are hyperparameters. And then, obtaining cores and parameters which enable the task performance to be optimal by utilizing grid search, analyzing test sets of the two types of data streams through 10 times of cross validation, and comparing the error rates of the two types of data streams through principal component analysis of the two types of kernel functions to obtain a kernel principal component analysis method based on the radial basis function, so that the identity recognition of the Bluetooth communication is better realized.
Embodiment 2, an identity recognition system of bluetooth communication, including clock jitter data traffic processing module and traffic characteristic machine learning module; the clock jitter data flow processing module is used for white noise and clock jitter data collection, combination and length homogenization treatment of smooth operation connected with the white noise; the flow characteristic machine learning module is used for mining and analyzing the detail characteristics of the clock jitter data flow output by the clock jitter data flow processing module to realize the identification of different users.
The clock jitter data flow processing module and the flow characteristic machine learning module are in a sequential hierarchical structure, and are sequentially formed in the Bluetooth communication identity recognition process and perform data analysis and identity judgment.
Specifically, the clock jitter data traffic processing module is mainly responsible for white noise and collection, combination and length homogenization processing of the clock jitter data of the smooth operation connected with the white noise. The module is prepared for wireless communication traffic during bluetooth communication acquired using the radio platform.
Specifically, the data dimension of the obtained clock jitter is high, the feature attribute is complex, and the training set is mapped to a high-dimensional space by a kernel function through a nonlinear feature mapping function. And then selecting principal components according to the mapping result, projecting the converted training set to a two-dimensional plane through linear principal component analysis, and performing nonlinear regression and classification, thereby realizing the identity recognition of the Bluetooth communication.
Abbreviations and key terms of the invention have the following meanings:
bluetooth communication: a radio technology supporting short-distance communication of devices using a decentralized network structure and a fast frequency hopping and short packet technology;
identity recognition: under a certain scene, the data flow characteristics of encrypted communication correspond to the user of the current equipment, the user is portrayed according to behavior habits, and the identity of the user executing the current operation behavior is further judged;
clock jitter detail characteristics: the characteristic of the time interval jitter of the data packets caused by the non-stationary operation of the Bluetooth master device comprises two attributes including the jitter of the size of the time interval between the data packets and the jitter of the number of the unstable time intervals;
and (3) nuclear principal component analysis: a nonlinear data processing method projects data of an original space to a high-dimensional feature space through a nonlinear mapping-kernel function, and then carries out data processing based on principal component analysis in the high-dimensional feature space.
The advantages of the invention are as follows:
on the basis of not cracking Bluetooth communication violently and not cracking ciphertext data, a current user does not need to operate at high frequency for a long time, and the identity of a Bluetooth communication user is efficiently judged by analyzing white noise and clock jitter data flow of smooth operation connected with the white noise and by using a machine learning method based on kernel principal component analysis.
The key points of the invention are as follows:
1. depicting a user by using the processed white noise with equal length or the clock jitter data of the smooth operation connected with the white noise;
2. through the general machine learning module based on the kernel principal component analysis data flow characteristics, the problem of Bluetooth communication identity recognition is efficiently solved.
In embodiment 3, the computer device of the present invention may be a device including a processor, a memory, and the like, for example, a single chip microcomputer including a central processing unit, and the like. And the processor is used for implementing the steps of the recommendation method capable of modifying the relationship-driven recommendation data based on the CREO software when executing the computer program stored in the memory.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Embodiment 4, computer-readable storage Medium embodiment
The computer readable storage medium of the present invention may be any form of storage medium that can be read by a processor of a computer device, including but not limited to non-volatile memory, ferroelectric memory, etc., and the computer readable storage medium has stored thereon a computer program that, when the computer program stored in the memory is read and executed by the processor of the computer device, can implement the above-mentioned steps of the CREO-based software that can modify the modeling method of the relationship-driven modeling data.
The computer program comprises computer program code which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The present invention has been disclosed in an illustrative rather than a restrictive sense, and the scope of the present invention is defined by the appended claims.
Claims (9)
1. An identity recognition method of Bluetooth communication is characterized in that data flow characteristics of encrypted communication correspond to a user of current equipment, the user is portrayed according to behavior habits, and the identity of the user executing current operation behaviors is further judged; the method specifically comprises the following steps:
collecting white noise and clock jitter data of smooth operation connected with the white noise, and performing combination and length homogenization treatment on the collected data to obtain the white noise with the same characteristics and length as the original characteristics and the clock jitter data flow of the smooth operation connected with the white noise;
step two, respectively taking the data packets of the white noise jitter data and the quantity and time intervals of the clock jitter data packets which are connected with the white noise and are smoothly operated as detail features, and mining and classifying the detail features of the two types of processed clock jitter data flow by utilizing a kernel function through a nonlinear feature mapping function and linear principal component analysis;
and step three, judging and predicting the unknown user data flow characteristics needing identity judgment by using the linear principal component analysis method optimized in the step two, thereby realizing identity identification.
2. The identity recognition method of claim 1, wherein the step of searching the book to collect white noise and clock jitter data of a smoothing operation connected with the white noise, and performing a combination and length normalization process on the collected data comprises the following steps:
recording the arrival time of a data packet and the byte amount sent to a slave device by a master device every second, and smoothing broken data and packet loss conditions;
step two, according to the characteristics of the Bluetooth equipment, dividing the time jitter of the flow data into corresponding flow data during operation and white noise which does not correspond to the operation;
combining the clock jitters of corresponding continuous data packet time intervals to further obtain white noise data flow which does not correspond to operation and smooth operation data flow connected with the white noise;
step three, white noise clock jitter data flow and clock jitter data flow of smooth operation connected with the white noise are respectively combined together;
performing Fourier transform on white noise clock jitter data flow and clock jitter data flow of smooth operation connected with white noise, converting discrete points into a frequency domain, uniformly sampling 20 points on the frequency domain, and performing inverse Fourier transform on sampling points to obtain clock jitter data with equal data length and unchanged original characteristics;
and step one and five, white noise which is consistent with the original characteristics and is consistent with the length and clock jitter data flow of smooth operation connected with the white noise are respectively obtained.
3. The identity recognition method according to claim 1, wherein the specific method for mining and analyzing the detail features of the processed data traffic in the second step is:
mapping a training set formed by user traffic data characteristics of a sample library to a high-dimensional space by utilizing a kernel function through a nonlinear characteristic mapping function;
secondly, calculating a covariance matrix by taking the training set mapped to the high-dimensional space as a feature matrix, selecting principal components according to a mapping result, projecting the converted training set to a two-dimensional plane through linear principal component analysis, and performing nonlinear regression and classification on the dimensionality-reduced data set through iterative convergence according to an initial value of the linear principal component analysis result;
and step three, analyzing a verification set consisting of part of training sets of the two types of data streams through 10 times of cross verification, and verifying and optimizing the accuracy of the method in the step two.
4. The identity recognition method according to claim 1, wherein the specific method for performing the discrimination prediction on the unknown user data traffic characteristics to be subjected to the identity discrimination in the third step is that the method comprises the following steps:
step three, mapping a test set formed by unknown user flow data characteristics needing identity discrimination to a high-dimensional space by utilizing the kernel function in the step two through a nonlinear characteristic mapping function;
and step two, according to the optimization method in the step two, projecting the converted test set to a two-dimensional plane through linear principal component analysis, performing nonlinear regression and classification prediction, and outputting a classification result.
5. The method according to claim 2, wherein the fourier transform of the white noise clock jitter data flow and the smooth clock jitter data flow connected to the white noise is performed by the following equation:
where x (n) is the data traffic and n is the length of the data traffic.
6. The identity recognition method of claim 2, wherein the specific method of performing inverse fourier transform on the first four sampling points is realized by the following formula:
7. an identity recognition system of Bluetooth communication is characterized by comprising a clock jitter data flow processing module and a flow characteristic machine learning module; the clock jitter data flow processing module is used for white noise and clock jitter data collection, combination and length homogenization treatment of smooth operation connected with the white noise; the flow characteristic machine learning module is used for mining and analyzing the detail characteristics of the clock jitter data flow output by the clock jitter data flow processing module to realize the identification of different users.
8. A computer comprising a memory storing a computer program and a processor, the processor implementing the steps of the identification method according to any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the identification method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111528957.XA CN114158049B (en) | 2021-12-14 | 2021-12-14 | Bluetooth communication identity recognition method, system, computer and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111528957.XA CN114158049B (en) | 2021-12-14 | 2021-12-14 | Bluetooth communication identity recognition method, system, computer and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114158049A true CN114158049A (en) | 2022-03-08 |
| CN114158049B CN114158049B (en) | 2024-03-26 |
Family
ID=80450820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111528957.XA Active CN114158049B (en) | 2021-12-14 | 2021-12-14 | Bluetooth communication identity recognition method, system, computer and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114158049B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598625A (en) * | 2019-09-10 | 2019-12-20 | 北京望问信息科技有限公司 | Identity recognition technology based on pulse wave non-reference characteristics |
| CN113326801A (en) * | 2021-06-22 | 2021-08-31 | 哈尔滨工程大学 | Human body moving direction identification method based on channel state information |
-
2021
- 2021-12-14 CN CN202111528957.XA patent/CN114158049B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598625A (en) * | 2019-09-10 | 2019-12-20 | 北京望问信息科技有限公司 | Identity recognition technology based on pulse wave non-reference characteristics |
| CN113326801A (en) * | 2021-06-22 | 2021-08-31 | 哈尔滨工程大学 | Human body moving direction identification method based on channel state information |
Non-Patent Citations (3)
| Title |
|---|
| 张君昌;陈媛媛;: "基于改进KPCA的语音特征提取方法", 计算机仿真, no. 06 * |
| 敖世亮;: "低功耗蓝牙加密通信过程中的流量分析――攻击威胁与防护", 中国新通信, no. 04 * |
| 黄少驰;朱晓蕾;: "一种基于射频指纹的通信个体识别方法", 航天电子对抗, no. 01 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114158049B (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Decorrelation of neutral vector variables: Theory and applications | |
| US20200057958A1 (en) | Identification and application of hyperparameters for machine learning | |
| WO2022042123A1 (en) | Image recognition model generation method and apparatus, computer device and storage medium | |
| US11182426B2 (en) | Audio retrieval and identification method and device | |
| CN108922543B (en) | Model base establishing method, voice recognition method, device, equipment and medium | |
| CN109308912B (en) | Music style recognition method, device, computer equipment and storage medium | |
| CN114241779B (en) | Short-time prediction method, computer and storage medium for urban expressway traffic flow | |
| CN112509600A (en) | Model training method and device, voice conversion method and device and storage medium | |
| CN109766476B (en) | Video content emotion analysis method and device, computer equipment and storage medium | |
| CN112767927A (en) | Method, device, terminal and storage medium for extracting voice features | |
| CN111027643B (en) | Training method of deep neural network model, man-machine interaction recognition method, device, electronic equipment and storage medium | |
| CN112347910A (en) | Signal fingerprint identification method based on multi-mode deep learning | |
| CN115187450A (en) | Image generation method, image generation device and related equipment | |
| CN109783381B (en) | Test data generation method, device and system | |
| JP2013068938A (en) | Signal processing apparatus, signal processing method, and computer program | |
| CN110889009A (en) | Voiceprint clustering method, voiceprint clustering device, processing equipment and computer storage medium | |
| TWI725877B (en) | Electronic device and voice recognition method | |
| CN114158049B (en) | Bluetooth communication identity recognition method, system, computer and storage medium | |
| CN116778946A (en) | Separation method of vocal accompaniment, network training method, device and storage medium | |
| CN114158039B (en) | Traffic analysis method, system, computer and storage medium for low-power consumption Bluetooth encryption communication | |
| Xu et al. | Unraveling the veil of subspace rip through near-isometry on subspaces | |
| CN109815474B (en) | Word sequence vector determination method, device, server and storage medium | |
| WO2022156064A1 (en) | Flash memory chip reliability level prediction method, apparatus, and storage medium | |
| CN103390404A (en) | Information processing apparatus, information processing method and information processing program | |
| CN108206024B (en) | Voice data processing method based on variational Gaussian regression process |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |