CN109428660B - Method and system for identifying wireless channel based on hidden Markov model - Google Patents
Method and system for identifying wireless channel based on hidden Markov model Download PDFInfo
- Publication number
- CN109428660B CN109428660B CN201710770689.XA CN201710770689A CN109428660B CN 109428660 B CN109428660 B CN 109428660B CN 201710770689 A CN201710770689 A CN 201710770689A CN 109428660 B CN109428660 B CN 109428660B
- Authority
- CN
- China
- Prior art keywords
- hidden markov
- markov model
- wireless channel
- identifying
- channel
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000013598 vector Substances 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000007704 transition Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 230000009131 signaling function Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000008054 signal transmission Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 abstract description 3
- 238000005457 optimization Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 239000006185 dispersion Substances 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- H04B17/318—Received signal strength
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention relates to the technical field of wireless communication, and discloses a method and a system for identifying a wireless channel based on a hidden Markov model, which are used for efficiently and accurately identifying an unknown wireless channel so as to improve the stability of wireless signal transmission. The method for identifying the wireless channel based on the hidden Markov model comprises the following steps: a. extracting 4-dimensional feature vectors for expressing different wireless channel features from a measured data packet of a known scene; b. training a stable hidden Markov model aiming at a wireless channel of each known scene by using the extracted 4-dimensional characteristic vector of each known scene as the input of the hidden Markov model, and classifying the wireless channel; c. and identifying the unknown wireless channel by using the trained hidden Markov model. The method is suitable for quickly and accurately identifying the wireless channel.
Description
Technical Field
The invention relates to the technical field of wireless communication, in particular to a method and a system for identifying a wireless channel based on a hidden Markov model.
Background
With the rapid development of wireless communication, wireless technology brings new learning and living experiences for people. The wireless system is composed of a signal transmitting terminal, a wireless channel and a signal receiver. In the traditional research, a plurality of manufacturers research the sending end of the signal and the wireless terminal. However, the study of wireless signals is still in the beginning.
The signal transmitting end and the signal receiving end of the mobile communication are conducted through an electromagnetic path, the electromagnetic path is closely related to the surrounding physical environment, and in different environments, wireless channels have some differentiated characteristics due to multipath effects. Mathematical descriptions of the radio channel characteristics of a typical environment are of great research interest to identify unknown radio channels. Through the difference of the characteristics, the self-adaptive optimization of the network has great practical significance. In a typical application, a mathematical representation of a wireless channel is calculated based on characteristics of the channel, the mathematical representation is unique and based on realistic channel characteristics, and the mathematical representation is used to encrypt a plurality of transmitted wireless data to form a dynamic key generation system based on the characteristics of the wireless channel.
At present, researches on mathematical modeling of wireless channel characteristics are mainly statistical modeling methods and deterministic modeling methods. The disadvantages of these methods are the high algorithm complexity and the inability to apply known models to estimate unknown models.
Hidden Markov Models (HMMs) are state estimation models that were first utilized in speech recognition by Baker, et al, a scholarian at Chimerron university in the card, and were first well applied in the field of speech recognition. At present, the hidden Markov model is used in the field of wireless signal processing, which is a new trend, and in the hidden Markov process, the result of the previous state will influence the recognition result of the next state. This is similar to the process of multipath effects on a wireless signal, where the previous received signal and the next received signal have a correlation. Thus, a hidden markov model is a model well suited for analyzing wireless signals.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method and a system for identifying a wireless channel based on a hidden Markov model, which can efficiently and accurately identify an unknown wireless channel so as to improve the stability of wireless signal transmission.
In one aspect, an embodiment of the present invention provides a method for identifying a wireless channel based on a hidden markov model, which includes:
a. extracting 4-dimensional feature vectors for expressing different wireless channel features from a measured data packet of a known scene;
b. training a stable hidden Markov model aiming at a wireless channel of each known scene by using the extracted 4-dimensional characteristic vector of each known scene as the input of the hidden Markov model, and classifying the wireless channel;
c. and identifying the unknown wireless channel by using the trained hidden Markov model.
As a further optimization, in step a, the 4-dimensional feature vector includes: the multipath number, the time delay mean value, the time delay variance and the time delay expansion value of the wireless channel.
As a further optimization, the extraction method of the number of the multipath of the wireless channel is as follows:
determining the number of the multipath signals arriving at the time k according to the relationship among the power of the multipath signals received at the time k, the power of the single-path multipath signals and the multipath number, and accumulating the multipath numbers of all the time k, wherein the method comprises the following steps:
in the formula (1), N represents the number of multipath signals of the wireless channel, and N (k) represents the number of multipath signals arriving at the receiver at the k-th time, and the value is the energy E (k) of all multipath signals arriving at the k-th time and the energy P of single-path multipath signals arriving at the k-th timer(k) The ratio of (a) to (b), namely:
substituting equations (1) and (2) in conjunction with the actual received signal function r (n, k) at time k, then there is:
wherein,
transmitting signal power P, antenna gain GtAnd signal wavelength λ, which is typically set to a constant value during experimentation, c being a constant, representing the speed of light. t is tkThe time at which time k arrives at the receiver.
As a further optimization, the extraction method of the time delay mean value is as follows:
the extraction mode of the time delay variance is as follows:
where r (n, k) is the actual received signal function at time k.
As a further optimization, the extraction method of the delay spread value is as follows:
where e (t) is the normalized envelope characteristic of the received discrete signal, which is a delay profile formed by different delay signals.
As a further optimization, in step B, the hidden markov model is denoted as λ ═ pi, a, B };
where π is the initial state probability vector, the expression is as follows:
a is a state transition matrix, and the expression is as follows:
b is an observation state probability matrix, and the expression is as follows:
wherein,
denotes from siTo sjThe probability of a state transition of (a),
indicates when in state siWhen o is observedjThe probability of (d);
the specific method for training the stable hidden markov model of the wireless channel aiming at each known scene in the step b is as follows:
and taking the 4-dimensional feature vectors of all known scenes as the input of the hidden Markov model, and solving the model parameters of the hidden Markov model through a Baum-Welch algorithm.
As a further optimization, in step c, the identifying an unknown wireless channel by using the trained hidden markov model specifically includes:
firstly, extracting 4-dimensional feature vectors of unknown wireless channels, then inputting the extracted 4-dimensional feature vectors into various trained hidden Markov models, and calculating an output result by using a Viterbi algorithm, wherein the output result is an output probability P (O | lambda) of an observation sequence O to an HMM model lambda:
and finally, selecting the wireless channel class corresponding to the hidden Markov model with the maximum output probability P (O | lambda) as the identification result of the unknown wireless channel.
As a further optimization, before extracting the 4-dimensional feature vector of the wireless channel, the steps a and c further include: and preprocessing transmission data of the wireless channel, wherein the preprocessing comprises denoising the wireless data according to the data correlation of the plurality of paths of wireless signals.
In another aspect, an embodiment of the present invention provides a system for identifying a wireless channel based on a hidden markov model, including:
the characteristic extraction module is used for extracting 4-dimensional characteristic vectors for expressing different wireless channel characteristics from an actual measurement data packet of a known scene, inputting the 4-dimensional characteristic vectors into the hidden Markov model training module, extracting the 4-dimensional characteristic vectors from the unknown scene and inputting the 4-dimensional characteristic vectors into each trained hidden Markov model;
the hidden Markov model training module is used for training the hidden Markov model by taking the 4-dimensional characteristic vectors extracted from each known scene as input;
the wireless channel classification module is used for classifying the wireless channels according to the training result of the hidden Markov model training module;
and the wireless channel identification module is used for inputting the 4-dimensional feature vector extracted from the unknown scene into the trained hidden Markov model to identify the unknown channel.
As a further optimization, the wireless channel identification module identifies an unknown channel, including:
and identifying the class of the unknown channel according to the calculation result of the hidden Markov model and the classification of the known wireless channel.
The invention has the beneficial effects that:
the channel of a typical wireless environment is characterized, namely mathematically described, and the unknown channel is automatically identified by using the known typical channel, so that the optimization of wireless signal transmission is facilitated, the transmission stability of the wireless signal is improved, and a plurality of adaptive encryption solutions can be generated on the basis.
Drawings
FIG. 1 is a block diagram of a system for identifying a wireless channel based on a hidden Markov model according to the present invention;
FIG. 2 is a flow chart of a method for identifying a wireless channel based on a hidden Markov model according to the present invention;
fig. 3 is a flowchart illustrating training of a hidden markov model and radio channel recognition using the trained model according to an embodiment of the present invention.
Detailed Description
The invention aims to provide a method and a system for identifying a wireless channel based on a hidden Markov model, which can be used for efficiently and accurately identifying an unknown wireless channel so as to improve the stability of wireless signal transmission. In the invention, firstly, the measured data packet of the wireless channel is used for extracting 4 characteristic vectors, then the 4 characteristic vectors are used as the input de-training model of the hidden Markov model to stabilize the model, and finally the hidden Markov model with stable training is used for classifying different wireless channels to achieve the aim of channel recognition.
As shown in fig. 1, the system for identifying a radio channel based on a hidden markov model in the present invention includes:
the characteristic extraction module is used for extracting 4-dimensional characteristic vectors for expressing different wireless channel characteristics from an actual measurement data packet of a known scene, inputting the 4-dimensional characteristic vectors into the hidden Markov model training module, extracting the 4-dimensional characteristic vectors from the unknown scene and inputting the 4-dimensional characteristic vectors into each trained hidden Markov model;
the hidden Markov model training module is used for training the hidden Markov model by taking the 4-dimensional characteristic vectors extracted from each known scene as input;
the wireless channel classification module is used for classifying the wireless channels according to the training result of the hidden Markov model training module;
and the wireless channel identification module is used for inputting the 4-dimensional feature vector extracted from the unknown scene into the trained hidden Markov model to identify the unknown channel.
Based on the above system, the method for identifying a wireless channel based on a hidden markov model proposed by the present invention is shown in fig. 2, and comprises the following implementation steps:
1. extracting 4-dimensional feature vectors for expressing different wireless channel features from a measured data packet of a known scene;
in this step, the extracted 4-dimensional feature vector can well express the features of different wireless channels, and according to the wireless transmission characteristics, the 4-dimensional feature vector determined by the invention comprises: the multipath number, the time delay mean value, the time delay variance and the time delay expansion value of the wireless channel.
The specific extraction process is as follows:
1) in a typical wireless channel, the transmission of electromagnetic waves is not a single path, but is made up of many paths formed by scattering (including reflection and diffraction), i.e., the wireless channel has multipath effects. Under different scenes, the number of the multipath generated by receiving and transmitting is on an order of magnitude, so that the scene changes, the number of the multipath changes, and the number of the multipath is a variable reflecting different wireless channels. The mathematical derivation of the number of multipaths is as follows:
determining the number of multipath signals arriving at the time k according to the relationship between the power of multipath signals received at the time k, the power of single-path multipath signals and the number of multipath signals, and accumulating the number of multipath signals at all the time k
In the formula (1), N represents the number of multipath signals of the wireless channel, and N (k) represents the number of multipath signals arriving at the receiver at the k-th time, and the value is the energy E (k) of all multipath signals arriving at the k-th time and the energy P of single-path multipath signals arriving at the k-th timer(k) To obtain the formula (2)
Substituting the actual received signal function r (n, k) at the moment t into the formulas (1) and (2) to obtain a formula (3)
Wherein,
transmitting signal power P, antenna gain GtAnd signal wavelength λ, which is typically set to a constant value during experimentation, c being a constant. t is tkThe time at which time k arrives at the receiver.
2) The time of arrival at the receiver varies due to the different distances that the electromagnetic wave travels along the various paths. I.e., the delay differences of the multipaths. Therefore, the delay mean and the delay variance are variables representing different wireless channels, and the formulas are expressed as (4) and (5).
Where r (n, k) is a function of the actual received signal at the receiver at time k.
3) When the base station sends a pulse signal, the received signal contains not only the signal but also its respective delay signal. This phenomenon of signal time dispersion due to multipath effects is called multipath time dispersion. The difference between the arrival time of the last distinguishable delay signal and the arrival time of the first delay signal is defined as the delay spread. Therefore, the delay spread is also a variable representing different radio channels, and its mathematical expression is formula (6)
Where e (t) is the normalized envelope characteristic of the received discrete signal, which is a delay profile formed by different delay signals.
Thus, a four-dimensional feature vector is generated based on the four variables, and the feature vector can reflect the features of the wireless channel to the maximum extent, and can be defined as "mathematical description of the wireless channel".
2. Training a stable hidden Markov model aiming at a wireless channel of each known scene by using the extracted 4-dimensional characteristic vector of each known scene as the input of the hidden Markov model, and classifying the wireless channel;
a complete hidden markov model is composed of a number of states N, a number of observations M, and a probability matrix A, B. Once these factors are determined, the hidden markov model is determined. Thus, one HMM model is denoted as λ ═ pi, a, B, where pi is the initial state probability vector, expressed as follows:
a is a state transition matrix, and the expression is as follows:
b is an observation state probability matrix, and the expression is as follows:
wherein,
denotes from siTo sjThe probability of a state transition of (a),
indicates when in state siWhen o is observedjThe probability of (c).
In the step, 4-dimensional feature vectors of each known scene are used as the input of a hidden Markov model, model parameters of the hidden Markov model are solved through a Baum-Welch algorithm, and a stable (namely determined by the model parameters) hidden Markov model aiming at each known scene is obtained; and then classifying the wireless channels of the known scene according to the training result.
3. And identifying the unknown wireless channel by using the trained hidden Markov model.
In the step, when an unknown wireless channel is identified, firstly, 4-dimensional characteristic vectors of the unknown wireless channel are extracted, wherein the 4-dimensional characteristic vectors comprise the multipath number, the time delay mean value, the time delay variance and the time delay expansion value of the wireless channel. Then inputting the characteristics into a trained hidden Markov model and calculating an output result by using a Viterbi algorithm;
the output result is expressed by a probability that the output probability P (O | λ) of the observation sequence O to the HMM model λ is:
and finally, selecting the wireless channel class corresponding to the hidden Markov model with the maximum output probability P (O | lambda) as the identification result of the unknown wireless channel.
Example (b):
in this embodiment, a process of training a hidden markov model and identifying a wireless channel by using the trained model is mainly described, as shown in fig. 3, a data source of a training set for training the hidden markov model is a wireless channel of a plurality of known scenes, a test data packet of the wireless channel is preprocessed first, the purpose of the preprocessing is to reduce noise interference, and a 4-dimensional feature vector is extracted after the preprocessing; and then initializing the HMM model, taking the extracted 4-dimensional feature vector as the input of the HMM model, training the HMM model by adopting a Baum-Welch training algorithm, and solving model parameters for each known scene.
The data source of a test set for carrying out unknown channel identification according to the trained hidden Markov model is a wireless channel of an unknown scene to be tested, similarly, a test data packet of the wireless channel is preprocessed, and 4-dimensional feature vectors are extracted after preprocessing; and then inputting the extracted 4-dimensional feature vector into a training stable HMM model, calculating an output result by adopting a Viterbi algorithm, and finally selecting a wireless channel type corresponding to a hidden Markov model with the maximum output probability P (O | lambda) as a recognition result of the unknown wireless channel and outputting the recognition result.
Claims (9)
1. A method for identifying a radio channel based on a hidden Markov model, comprising the steps of:
a. extracting 4-dimensional feature vectors for expressing different wireless channel features from a measured data packet of a known scene; the 4-dimensional feature vector includes: the multipath number, the time delay mean value, the time delay variance and the time delay expansion value of the wireless channel;
b. training a stable hidden Markov model aiming at a wireless channel of each known scene by using the extracted 4-dimensional characteristic vector of each known scene as the input of the hidden Markov model, and classifying the wireless channel;
c. and identifying the unknown wireless channel by using the trained hidden Markov model.
2. The hidden markov model based method for identifying a wireless channel as claimed in claim 1, wherein the number of multipaths of the wireless channel is extracted by:
determining the number of the multipath signals arriving at the time k according to the relationship among the power of the multipath signals received at the time k, the power of the single-path multipath signals and the multipath number, and accumulating the multipath numbers of all the time k, wherein the method comprises the following steps:
in the formula (1), N represents the number of multipath signals of the wireless channel, and N (k) represents the number of multipath signals arriving at the receiver at the k-th time, and the value is the energy E (k) of all multipath signals arriving at the k-th time and the energy P of single-path multipath signals arriving at the k-th timer(k) The ratio of (a) to (b), namely:
substituting equations (1) and (2) in conjunction with the actual received signal function r (n, k) at time k, then there is:
wherein,
transmitting signal power P, antenna gain GtAnd signal wavelength λ, typically set to a constant value during experimentation; c is a constant, representing the speed of light; t is tkThe time at which time k arrives at the receiver.
3. The hidden markov model based method for identifying a radio channel as claimed in claim 1, wherein the time delay means is extracted by:
the extraction mode of the time delay variance is as follows:
where r (n, k) is the actual received signal function at time k.
4. The hidden markov model based method for identifying a radio channel as claimed in claim 1, wherein the delay spread value is extracted by:
where e (t) is the normalized envelope characteristic of the received discrete signal, which is a delay profile formed by different delay signals.
5. The hidden markov model based radio channel recognition method of claim 1, wherein in step B, the hidden markov model is denoted as λ ═ pi, a, B };
where π is the initial state probability vector, the expression is as follows:
a is a state transition matrix, and the expression is as follows:
b is an observation state probability matrix, and the expression is as follows:
wherein,
denotes from siTo sjThe probability of a state transition of (a),
indicates when in state siWhen o is observedjThe probability of (d);
the specific method for training the stable hidden markov model of the wireless channel aiming at each known scene in the step b is as follows:
and taking the 4-dimensional feature vectors of all known scenes as the input of the hidden Markov model, and solving the model parameters of the hidden Markov model through a Baum-Welch algorithm.
6. The hidden markov model based method for identifying a radio channel as claimed in claim 1, wherein in step c, the identifying an unknown radio channel using the trained hidden markov model specifically comprises:
firstly, extracting a 4-dimensional feature vector of an unknown wireless channel, then extracting the 4-dimensional feature vector in a known scene to train a stable hidden Markov model, namely completing the training process of a training set on a classifier, and finally, calculating an output result in a test set by using a Viterbi algorithm by using the trained hidden Markov model classifier, wherein the output result is the output probability P (O | Lambda) of an observation sequence O on an HMM model Lambda:
and finally, selecting the wireless channel class corresponding to the hidden Markov model with the maximum output probability P (O | lambda) as the identification result of the unknown wireless channel.
7. The hidden markov model-based method for identifying a radio channel according to any one of claims 1 to 6, wherein the steps a and c further comprise, before extracting the 4-dimensional feature vector of the radio channel: and preprocessing transmission data of the wireless channel, wherein the preprocessing comprises denoising the wireless data according to the data correlation of the plurality of paths of wireless signals.
8. A system for identifying a radio channel based on a hidden markov model, comprising:
the characteristic extraction module is used for extracting 4-dimensional characteristic vectors for expressing different wireless channel characteristics from an actual measurement data packet of a known scene, inputting the 4-dimensional characteristic vectors into the hidden Markov model training module, extracting the 4-dimensional characteristic vectors from the unknown scene and inputting the 4-dimensional characteristic vectors into each trained hidden Markov model; the 4-dimensional feature vector includes: the multipath number, the time delay mean value, the time delay variance and the time delay expansion value of the wireless channel;
the hidden Markov model training module is used for training the hidden Markov model by taking the 4-dimensional characteristic vectors extracted from each known scene as input;
the wireless channel classification module is used for classifying the wireless channels according to the training result of the hidden Markov model training module;
and the wireless channel identification module is used for inputting the 4-dimensional feature vector extracted from the unknown scene into the trained hidden Markov model to identify the unknown channel.
9. The hidden markov model based radio channel identification system of claim 8 wherein the radio channel identification module identifies an unknown channel comprising:
and identifying the class of the unknown channel according to the calculation result of the hidden Markov model and the classification of the known wireless channel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710770689.XA CN109428660B (en) | 2017-08-31 | 2017-08-31 | Method and system for identifying wireless channel based on hidden Markov model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710770689.XA CN109428660B (en) | 2017-08-31 | 2017-08-31 | Method and system for identifying wireless channel based on hidden Markov model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109428660A CN109428660A (en) | 2019-03-05 |
| CN109428660B true CN109428660B (en) | 2022-04-22 |
Family
ID=65504702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710770689.XA Active CN109428660B (en) | 2017-08-31 | 2017-08-31 | Method and system for identifying wireless channel based on hidden Markov model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109428660B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111835444B (en) * | 2020-06-17 | 2021-04-27 | 武汉大学 | Wireless channel scene identification method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2309487A1 (en) * | 2009-09-11 | 2011-04-13 | Honda Research Institute Europe GmbH | Automatic speech recognition system integrating multiple sequence alignment for model bootstrapping |
| CN105244038A (en) * | 2015-09-30 | 2016-01-13 | 金陵科技学院 | Ore dressing equipment fault abnormity audio analyzing and identifying method based on HMM |
| CN106548136A (en) * | 2016-10-19 | 2017-03-29 | 中科院成都信息技术股份有限公司 | A kind of wireless channel scene classification method |
-
2017
- 2017-08-31 CN CN201710770689.XA patent/CN109428660B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2309487A1 (en) * | 2009-09-11 | 2011-04-13 | Honda Research Institute Europe GmbH | Automatic speech recognition system integrating multiple sequence alignment for model bootstrapping |
| CN105244038A (en) * | 2015-09-30 | 2016-01-13 | 金陵科技学院 | Ore dressing equipment fault abnormity audio analyzing and identifying method based on HMM |
| CN106548136A (en) * | 2016-10-19 | 2017-03-29 | 中科院成都信息技术股份有限公司 | A kind of wireless channel scene classification method |
Non-Patent Citations (2)
| Title |
|---|
| A configurable fingerprint-based hidden-Markov model for tracking in variable channel conditions;John D. Roth等;《2013, 7th International Conference on Signal Processing and Communication Systems (ICSPCS)》;20140127;第1-9页 * |
| 时变无线信道的小波盲检测算法;方承志等;《电子测量技术》;20070515;第30卷(第5期);第52-55页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109428660A (en) | 2019-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khan et al. | Angle-of-arrival estimation using an adaptive machine learning framework | |
| CN111835444B (en) | Wireless channel scene identification method and system | |
| CN110365612A (en) | A kind of deep learning Beam Domain channel estimation methods based on approximate Message Passing Algorithm | |
| CN108696331B (en) | Signal reconstruction method based on generation countermeasure network | |
| CN105068049B (en) | A kind of Cramér-Rao lower bound computational methods for splitting antenna MIMO radar | |
| CN111050315B (en) | Wireless transmitter identification method based on multi-core two-way network | |
| CN116866129A (en) | Wireless communication signal detection method | |
| CN110808932B (en) | Multi-layer sensor rapid modulation identification method based on multi-distribution test data fusion | |
| Li et al. | Wireless sensing with deep spectrogram network and primitive based autoregressive hybrid channel model | |
| CN113205140B (en) | Semi-supervised specific radiation source individual identification method based on generative countermeasure network | |
| Hsu et al. | An adaptive Wi-Fi indoor localisation scheme using deep learning | |
| Tran et al. | GAN-based data augmentation for UWB NLOS identification using machine learning | |
| CN112749633B (en) | Separate and reconstructed individual radiation source identification method | |
| CN109428660B (en) | Method and system for identifying wireless channel based on hidden Markov model | |
| Seyedsalehi et al. | Propagation channel modeling by deep learning techniques | |
| CN111507299A (en) | Method for identifying STBC (space time Block coding) signal on frequency domain by using convolutional neural network | |
| CN114757224A (en) | Specific radiation source identification method based on continuous learning and combined feature extraction | |
| Wang et al. | Modulation recognition method for underwater acoustic communication signal based on relation network under small sample set | |
| Sonny et al. | Fingerprint Image-Based Multi-Building 3D Indoor Wi-Fi Localization Using Convolutional Neural Networks | |
| CN113242201B (en) | Wireless signal enhanced demodulation method and system based on generation classification network | |
| CN112566129B (en) | Radio frequency fingerprint extraction and identification method capable of resisting multipath interference | |
| CN114611550A (en) | Multi-feature automatic modulation identification method based on complex convolution module | |
| CN110261818B (en) | Method and device for identifying indirect ultra-wideband signal and eliminating error and storage medium | |
| CN110263810B (en) | LoRa signal source identification method | |
| Liu et al. | Individual Intelligent Recognition Method Based on Fingerprint Features of Radar Emitter |
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 |