CN112949742A - Method and electronic device for enhancing constellation data by using hidden Markov model - Google Patents
Method and electronic device for enhancing constellation data by using hidden Markov model Download PDFInfo
- Publication number
- CN112949742A CN112949742A CN202110300662.0A CN202110300662A CN112949742A CN 112949742 A CN112949742 A CN 112949742A CN 202110300662 A CN202110300662 A CN 202110300662A CN 112949742 A CN112949742 A CN 112949742A
- Authority
- CN
- China
- Prior art keywords
- data
- constellation
- constellation diagram
- hidden markov
- state
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000002708 enhancing effect Effects 0.000 title claims abstract description 20
- 238000010586 diagram Methods 0.000 claims abstract description 110
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims description 19
- 238000013139 quantization Methods 0.000 claims description 14
- 230000007704 transition Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 6
- 230000006698 induction Effects 0.000 claims description 5
- 238000013506 data mapping Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 description 10
- 238000010276 construction Methods 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
- G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Evolutionary Biology (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Digital Transmission Methods That Use Modulated Carrier Waves (AREA)
Abstract
The invention discloses a method for enhancing constellation data by using a hidden Markov model, which comprises the following steps: s1, collecting an original data stream, and obtaining an original constellation diagram data stream; s2, preprocessing the original constellation diagram data stream and constructing a standard constellation diagram database; s4, generating a hidden Markov triple by using a hidden Markov model according to initial data in the standard constellation database; and S6, generating constellation diagram data, namely an observation sequence according to the hidden Markov ternary group set. The invention solves the problem of data non-intercommunication by constructing a standardized constellation diagram database, and completes constellation diagram data expansion by using a hidden Markov model for the standardized constellation diagram data. The invention also provides corresponding electronic equipment.
Description
Technical Field
The invention belongs to the technical field of optical communication, and particularly relates to a method for enhancing constellation data by using a hidden Markov model and electronic equipment.
Background
The existing constellation data is mainly extracted through manual operation, specifically, the existing constellation data is connected with a network element master control panel through SSH (Secure Shell, Secure Shell protocol), and then a command line issues a Telnet command to a line side single panel to obtain a constellation. The main problems involved in the above method are: the constellation diagram data acquisition mode is complex and the operation is complex; the constellation diagram data accumulation rate in the same state is low, and the manual operation efficiency under repeated instruction circulation is low; the data storage format of the constellation diagram is not standard, and data of different module code types are not communicated with each other; less constellation diagram data are acquired within a limited time, and the training quality of an artificial intelligence model related to subsequent constellation diagram data is influenced. Therefore, the prior constellation diagram collection adopts a manual collection scheme, the collection efficiency is low, the time is consumed, and the constellation diagram data of different modules and code patterns can not be communicated.
Disclosure of Invention
Aiming at the defects or improvement requirements in the prior art, the invention provides a method for enhancing constellation data by using a hidden Markov model, which solves the problem of data non-intercommunication by constructing a standardized constellation database and completes constellation data expansion by using the hidden Markov model for the standardized constellation data.
To achieve the above object, according to an aspect of the present invention, there is provided a method of enhancing constellation data using a hidden markov model, comprising:
s1, collecting an original data stream, and obtaining an original constellation diagram data stream;
s2, preprocessing the original constellation diagram data stream and constructing a standard constellation diagram database;
s4, generating a hidden Markov triple by using a hidden Markov model according to initial data in the standard constellation database;
and S6, generating constellation diagram data, namely an observation sequence according to the hidden Markov ternary group set.
In an embodiment of the present invention, the step S1 includes:
the original data flow is connected with a main control panel of the network element by using an SSH protocol through a network element server, and then the main control panel sends a Telnet instruction to a line panel to obtain the data flow; and extracting the original constellation diagram data stream by using characteristic character positioning in the obtained original data stream.
In an embodiment of the present invention, the step S2 includes:
s21, preprocessing data: the data stream of the original constellation diagram is normalized, so that the data projection of the constellation diagram can be conveniently finished in a unified coordinate system;
and S22, constructing a standard constellation map database according to the original constellation map data stream after normalization processing.
In an embodiment of the present invention, the step S22 includes:
s221, constellation diagram data normalization: taking an absolute value of the constellation diagram data, unifying the data to the same quadrant, and reducing the complexity of subsequent processing;
s222, uniformly standardizing data of the multi-module constellation diagram: standardizing the constellation diagram data of modules of different manufacturers, namely zooming the data into the same coordinate system;
s223, tensorial representation: and combining the normalized constellation diagram data with the corresponding code pattern to form a tensor quantization representation format, so that the code pattern is not perceived, and realizing multi-code pattern data mapping in the same tensor space.
In an embodiment of the present invention, the step S4 includes: and carrying out statistical induction on the constellation diagram data in the standard constellation diagram database to generate a state transition probability matrix and an observation state probability matrix, selecting a random initial state from the constellation diagram sequence, and carrying out statistics on the initial state probability distribution to obtain a hidden Markov triple.
In an embodiment of the present invention, the statistical induction of the constellation data in the standard constellation map database includes:
the representation mode of the preprocessed constellation diagram data is a tensor matrix, and the hidden state set of the constellation diagram data is counted to be Q ═ Q { (Q)1，q2，q3…qNV ═ V for observation state set1，v2，v3...vMAnd the hidden state refers to coordinates of points of a constellation diagram which may appear in a three-dimensional space mapped by the standard constellation diagram database T, and the observation state refers to coordinates of points corresponding to data in the three-dimensional space in the standard constellation diagram database T at present, wherein N is the number of all possible hidden states, and M is the number of all possible observation states.
In one embodiment of the present invention, for a sequence of length S, I is concealmentState sequence, O is observation sequence, I ═ I1，i2，i3...iS}，O＝{O1，O2，O3...OSThe state transition probability matrix is A ═ a }ij]N×NWherein a is from time t to time t +1ij＝P(it+1＝qj|it＝qi)。
In one embodiment of the present invention, the observed state probability matrix is B ═ Bjk]N×MWherein at time t i, based on the observation independence assumptiont＝qj，Ot＝vkAt that moment observe the state vkIn a hidden state qjThe generation probability ofj(k)＝P(Ot＝vk|it＝qj)。
In an embodiment of the present invention, the step S6 includes:
s61, a group of hidden Markov triples lambda (A, B, pi) with observation sequence length S is taken to generate hidden states i according to the initial state probability distribution pi1；
S62, according to the hidden state itDistribution of observed states of
Generating an observed State Ot；
S63, according to the hidden state itState transition probability distribution of
Generating a hidden state it+1；
S64, repeating the steps S62-S63 for a total of S times;
s65, all OtTogether forming the observation sequence O ═ { O ═ O1，O2，...，OtAnd (4) constellation diagram enhancement data in the system state corresponding to the hidden markov triple.
According to another aspect of the present invention, there is also provided an electronic apparatus including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the above-described method of enhancing constellation data using hidden markov models.
Generally, compared with the prior art, the technical scheme of the invention has the following beneficial effects:
(1) the constellation diagram data is used as important data for evaluating the performance of the optical network, contains a large amount of original signal information, and is an important component for building the intelligent optical network. The invention greatly shortens the time spent on the data accumulation of the constellation diagram and greatly saves the cost of manpower and material resources; a new quantization data representation mode is introduced to construct a standard constellation diagram database, the problem of intercommunication among constellation diagram data of modules and code patterns of different manufacturers is solved, and a machine learning algorithm is used for a small amount of original data to achieve the purpose of data expansion. The enhanced data set can optimize the existing intelligent algorithm model or support the subsequent model training with higher precision and complexity;
(2) the invention adopts a hidden Markov model as a basic algorithm model of data increment for the first time, wherein algorithms such as a homogeneous Markov chain, an observation independence hypothesis and the like are all applied to an optical network for the first time. Aiming at the time sequence accumulation characteristic of the optical signal constellation diagram, analyzing the state sequence of the optical signal constellation diagram by pertinently applying a Markov model, and concluding a hidden Markov triple set lambda which is respectively suitable for optical modules with different models and different physical environments (such as transmission distance, fiber-entering power and the like), thereby laying a solid foundation for the on-demand expansion of subsequent constellation diagram data;
(3) the constellation diagram data enhancement scheme is proposed for the first time, and meanwhile, as a basic general data enhancement method, the constellation diagram data enhancement method can be expanded to other data types with the same property, the large data platform construction can be enhanced, and under the large environment of artificial intelligence construction mainly based on data, the constellation diagram data enhancement method is a crucial step for breaking the foundation of problems of data isolated islands, data fusion difficulty and the like in the field of optical communication.
Drawings
FIG. 1 is a schematic diagram illustrating a method for enhancing constellation data using a hidden Markov model according to an embodiment of the present invention;
fig. 2 is a schematic diagram of the principle of collecting original constellation data in the embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a principle of probability interval quantization on constellation data according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating the principle of generating a state transition matrix and an observation state matrix according to a standard constellation database in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The technical scheme for solving the technical problem is as follows: and the problem of data non-intercommunication is solved by constructing a standardized constellation diagram database, and the constellation diagram data expansion is completed by using a hidden Markov model for the standardized constellation diagram data.
The constellation diagram is essentially a characterization quantity of the system state, and data of the constellation diagram has the characteristic of being accumulated along with the time sequence when the constellation diagram is observed, so that when the system is in a stable state, the hidden Markov model can be used for completing the prediction and sampling of the state sequence of the constellation diagram through the observation of the dominant sequence of the constellation diagram.
As shown in fig. 1, the present invention provides a method for enhancing constellation data using hidden markov models, comprising:
s1, collecting an original data stream, and obtaining an original constellation diagram data stream;
fig. 2 is a schematic diagram illustrating a principle of collecting original constellation data according to an embodiment of the present invention; specifically, the method comprises the following steps: the original data flow is connected with a main control panel of the network element by using an SSH protocol through a network element server, and then the main control panel sends a Telnet instruction to a line panel to obtain the data flow; and extracting the original constellation diagram data stream by using characteristic character positioning in the obtained original data stream.
S2, preprocessing the original constellation diagram data stream, and constructing a standard constellation diagram database, including:
s21, preprocessing data: the data stream of the original constellation diagram is normalized, so that the data projection of the constellation diagram can be conveniently finished in a unified coordinate system;
s22, constructing a standard constellation map database according to the original constellation map data stream after normalization processing, wherein the standard constellation map database comprises the following steps:
s221, constellation diagram data normalization: since the constellation diagram data is symmetrical about the coordinate axis in the coordinate system, the absolute value of the constellation diagram data is taken, the data are unified to the same quadrant, and the complexity of subsequent processing is reduced;
specifically, the constellation original data S is { x ═ xi1，yi1，xq1，yq1，...，xin,yin,xqn,yqnOrthogonalizing, i.e. taking S ═ abs (S), and projecting constellation points into a uniform quadrant, where x isin、xqnRepresenting the coordinates, y, of the first signal point of the n-th group of modulated signals projected on the I-axis and the Q-axis, respectivelyin、yqnAnd the coordinates of the second signal point of the nth group modulation signal projected on the I axis and the Q axis respectively are shown.
S222, uniformly standardizing data of the multi-module constellation diagram: the factory-leaving representation modes of the constellation diagrams corresponding to the modulation signals of the DSP modules of different models are different, and the factory-leaving representation modes are mainly represented by that the data of different manufacturers are mapped on coordinate axes of different lengths, so that the data of the constellation diagrams of the modules of different manufacturers need to be standardized, namely the data are zoomed into the same coordinate system, and the standardized data can realize no perception on the model numbers of the modules;
specifically, because the constellation diagrams corresponding to the signals modulated by the DSPs with different models have different factory-leaving expression modes, in order to facilitate subsequent unified data processing, module model no-perception data standardization based on different code patterns is adoptedAnd (6) processing. Namely, the normalized constellation data S' is standardized, specifically
Wherein
S223, tensorial representation: and combining the normalized constellation diagram data with the corresponding code pattern m to form a tensorial representation format T, so that the code pattern is not perceived, and multi-code data mapping is realized in the same tensor space.
Specifically, the normalized constellation data S ″ and the corresponding code pattern are combined to form a final standard constellation database T [ { x ]) expressed by a tensori1,yi1，m1}，{xq1,yq1,m1}，...，{xit,yit，mt}，{xqt,yqt,mt}...，{xin,yin，mn}，{xqn，yqn，mn}]Wherein m istThe modulation code pattern is corresponding to the t-th set of IQ modulation signals.
S3, projecting the standard constellation diagram data T expressed by tensor in a three-dimensional space, carrying out sampling precision quantization grading on a mapping space according to requirements, using coarse precision quantization when the requirement on the constellation diagram data is not high, effectively improving the efficiency of subsequent data generation, using high precision quantization when the requirement on the data quality is high, and exchanging enhanced data with higher degree of similarity with the original constellation diagram data distribution at the cost of the data generation efficiency. Fig. 3 is a schematic diagram illustrating a principle of probability interval quantization on constellation data according to an embodiment of the present invention. The method comprises the following steps:
s31, formulating a quantization accuracy level table R ═ { R0, R1, R2,. a, ri,. a, rn }, ri being a constant, which can be set as required;
s32, performing quantization sampling division on the mapping space as required, namely T' ═ T/ri;
and S33, after the quantization subspaces are formed in the mapping space, carrying out statistical induction on the constellation points in each single subspace.
It should be noted that step S3 is an optional step.
S4, generating hidden Markov triples (A, B, Π) according to the initial data in the standard constellation database T by using a hidden Markov model.
As shown in fig. 4, a schematic diagram of generating a state transition matrix and an observation state matrix according to a standard constellation database in the embodiment of the present invention is shown; the method comprises the following steps:
s41, carrying out statistical induction on the constellation diagram data in the standard constellation diagram database T to generate a state transition probability matrix and an observation state probability matrix, selecting a random initial state from the constellation diagram sequence, and carrying out statistics on the initial state probability distribution;
s411, preprocessing the data of the constellation diagram, wherein the representation mode is a tensor matrix.
Counting the hidden state set as Q ═ Q1，q2，q3…qNV ═ V for observation state set1，v2，v3…vMIn the method, a hidden state refers to coordinates of all possible constellation points of a constellation diagram in a three-dimensional space mapped by a standard constellation diagram database T, namely a complete set of position points in a quantization space, and an observation state refers to coordinates of corresponding points of existing data in the standard constellation diagram database T in the three-dimensional space before the current time, wherein N is the number of all possible hidden states, specifically the number of all position points in the quantization space, M is the number of all observation states, specifically the total number of unrepeated position points of all points in the standard constellation diagram database T in the quantization space;
s412, for a sequence with the length of S, I is a hidden state sequence, and O is an observation sequence;
wherein I ═ { I ═ I1，i2，i3...iS}，is∈Q；O＝{O1，O2，O3...OS}，Os∈V；
Based on the homogeneous Markov chain hypothesis, the state transition probability a from time t to time t +1ij＝P(it+1＝qj|it＝qi)；
So its Markov chain's state transition probability matrix A ═ aij]N×N；
Based on the assumption of observation independence, i at time tt＝qj，Ot＝vk；
Then the state v is observed at that momentkIn a hidden state qjThe generation probability ofj(k)＝P(Ot＝vk|it＝qj)；
Therefore, the probability matrix of the observed state is B ═ Bjk]N×M；
Initial state hidden probability distribution pi ═ pi (i)]NWherein pi (i) ═ P (i)1＝qi)
Finally, the hidden markov triplet λ of the data is obtained as (a, B, Π).
S42, calculating hidden Markov triples (A, B, Π) by using a Bowmember algorithm (optional, if the initial data volume is small, the step S41 can be skipped directly);
s5, enriching the constellation diagram data under different physical scenes, changing the physical environment of the original constellation diagram data acquisition, such as changing parameters of transmission distance, modulation code type or transmission power, repeating the steps S1-S4 under different test environments, and obtaining a plurality of groups of hidden Markov triples under different system states.
And S6, generating corresponding constellation diagram data, namely corresponding observation sequences according to the hidden Markov triad sets in different system states. The specific process is as follows:
s61, a group of hidden Markov triples lambda (A, B, pi) with observation sequence length S is taken to generate hidden states i according to the initial state probability distribution pi1；
S62, according to the hidden state itDistribution of observed states of
Generating an observed State Ot；
S63, according to the hidden state itState transition probability distribution of
Generating a hidden state it+1；
S64, repeating the steps S62-S63 for a total of S times;
s65, all OtTogether forming the observation sequence O ═ { O ═ O1，O2，...，OtAnd (4) constellation diagram enhancement data in the system state corresponding to the hidden markov triple.
Further, the present invention also provides an electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the above-described method of enhancing constellation data using hidden markov models.
The technical scheme of the invention can be applied to the situation that constellation data is required to be used as model training original data in the construction process of the intelligent optical network, and the constellation data set is enriched in the construction process of the intelligent optical network by using the technical scheme, so that a solid data basis is laid for the model construction work related to the constellation data in the future.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for enhancing constellation data using a hidden markov model, comprising:
s1, collecting an original data stream, and obtaining an original constellation diagram data stream;
s2, preprocessing the original constellation diagram data stream and constructing a standard constellation diagram database;
s4, generating a hidden Markov triple by using a hidden Markov model according to initial data in the standard constellation database;
and S6, generating constellation diagram data, namely an observation sequence according to the hidden Markov ternary group set.
2. The method for enhancing constellation data using hidden markov models as recited in claim 1 wherein said step S1 comprises:
the original data flow is connected with a main control panel of the network element by using an SSH protocol through a network element server, and then the main control panel sends a Telnet instruction to a line panel to obtain the data flow; and extracting the original constellation diagram data stream by using characteristic character positioning in the obtained original data stream.
3. The method for enhancing constellation data using hidden markov models as claimed in claim 1 or 2 wherein said step S2 comprises:
s21, preprocessing data: the data stream of the original constellation diagram is normalized, so that the data projection of the constellation diagram can be conveniently finished in a unified coordinate system;
and S22, constructing a standard constellation map database according to the original constellation map data stream after normalization processing.
4. The method for enhancing constellation data using hidden markov models as recited in claim 3 wherein said step S22 comprises:
s221, constellation diagram data normalization: taking an absolute value of the constellation diagram data, unifying the data to the same quadrant, and reducing the complexity of subsequent processing;
s222, uniformly standardizing data of the multi-module constellation diagram: standardizing the constellation diagram data of modules of different manufacturers, namely zooming the data into the same coordinate system;
s223, tensorial representation: and combining the normalized constellation diagram data with the corresponding code pattern to form a tensor quantization representation format, so that the code pattern is not perceived, and realizing multi-code pattern data mapping in the same tensor space.
5. The method for enhancing constellation data using hidden markov models as claimed in claim 1 or 2 wherein said step S4 comprises: and carrying out statistical induction on the constellation diagram data in the standard constellation diagram database to generate a state transition probability matrix and an observation state probability matrix, selecting a random initial state from the constellation diagram sequence, and carrying out statistics on the initial state probability distribution to obtain a hidden Markov triple.
6. The method for enhancing constellation data using hidden markov models as recited in claim 5 wherein said statistically generalizing constellation data in a standard constellation database comprises:
the representation mode of the preprocessed constellation diagram data is a tensor matrix, and the hidden state set of the constellation diagram data is counted to be Q ═ Q { (Q)1，q2，q3…qNV ═ V for observation state set1，v2，v3…vMAnd the hidden state refers to coordinates of points of a constellation diagram which may appear in a three-dimensional space mapped by the standard constellation diagram database T, and the observation state refers to coordinates of points corresponding to data in the three-dimensional space in the standard constellation diagram database T at present, wherein N is the number of all possible hidden states, and M is the number of all possible observation states.
7. The method of enhancing constellation data using hidden markov models as claimed in claim 6 wherein for a sequence of length S, I is the hidden state sequence, O is the observation sequence, and I ═ { I ═ I1，i2，i3...iS}，O＝{O1，O2，O3...OSThe state transition probability matrix is A ═ a }ij]N×NWherein a is from time t to time t +1ij＝P(it+1＝qj|it＝qi)。
8. The method for enhancing constellation data using hidden markov models as recited in claim 7 wherein the observed state probability matrix is B ═ Bjk]N×MWherein at time t i, based on the observation independence assumptiont＝qj，Ot＝vkAt that moment observe the state vkIn a hidden state qjThe generation probability ofj(k)＝P(Ot＝vk|it＝qj)。
9. The method for enhancing constellation data using hidden markov models as claimed in claim 1 or 2 wherein said step S6 comprises:
s61, a group of hidden Markov triples lambda (A, B, pi) with observation sequence length S is taken to generate hidden states i according to the initial state probability distribution pi1；
S62, according to the hidden state itDistribution of observed states of
Generating an observed State Ot；
S63, according to the hidden state itState transition probability distribution of
Generating a hidden state it+1；
S64, repeating the steps S62-S63 for a total of S times;
s65, all OtTogether forming the observation sequence O ═ { O ═ O1，O2，...，OtAnd (4) constellation diagram enhancement data in the system state corresponding to the hidden markov triple.
10. An electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of enhancing constellation data using hidden markov models of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110300662.0A CN112949742B (en) | 2021-03-22 | 2021-03-22 | Method and electronic device for enhancing constellation data by using hidden Markov model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110300662.0A CN112949742B (en) | 2021-03-22 | 2021-03-22 | Method and electronic device for enhancing constellation data by using hidden Markov model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112949742A true CN112949742A (en) | 2021-06-11 |
| CN112949742B CN112949742B (en) | 2022-04-08 |
Family
ID=76227815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110300662.0A Active CN112949742B (en) | 2021-03-22 | 2021-03-22 | Method and electronic device for enhancing constellation data by using hidden Markov model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949742B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130238543A1 (en) * | 2010-11-10 | 2013-09-12 | Commissariat A L'energie Atomique Et Aux Ene Alt | Sensor detection device, corresponding detection method and computer program |
| CN104699606A (en) * | 2015-03-06 | 2015-06-10 | 国网四川省电力公司电力科学研究院 | Method for predicting state of software system based on hidden Markov model |
| US20200125978A1 (en) * | 2018-10-22 | 2020-04-23 | General Electric Company | Detection and protection against mode switching attacks in cyber-physical systems |
| CN112069045A (en) * | 2020-08-14 | 2020-12-11 | 西安理工大学 | Cloud platform software performance prediction method based on hidden Markov |
-
2021
- 2021-03-22 CN CN202110300662.0A patent/CN112949742B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130238543A1 (en) * | 2010-11-10 | 2013-09-12 | Commissariat A L'energie Atomique Et Aux Ene Alt | Sensor detection device, corresponding detection method and computer program |
| CN104699606A (en) * | 2015-03-06 | 2015-06-10 | 国网四川省电力公司电力科学研究院 | Method for predicting state of software system based on hidden Markov model |
| US20200125978A1 (en) * | 2018-10-22 | 2020-04-23 | General Electric Company | Detection and protection against mode switching attacks in cyber-physical systems |
| CN112069045A (en) * | 2020-08-14 | 2020-12-11 | 西安理工大学 | Cloud platform software performance prediction method based on hidden Markov |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112949742B (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111242282B (en) | Deep learning model training acceleration method based on end edge cloud cooperation | |
| CN109783910B (en) | Structure optimization design method for accelerating by using generation countermeasure network | |
| CN112132197A (en) | Model training method, image processing method, device, computer equipment and storage medium | |
| CN115147545A (en) | Scene three-dimensional intelligent reconstruction system and method based on BIM and deep learning | |
| KR20170101455A (en) | Training method of robot with 3d camera using artificial intelligence deep learning network based big data platform | |
| CN114462509A (en) | Distributed Internet of things equipment anomaly detection method | |
| CN112949742B (en) | Method and electronic device for enhancing constellation data by using hidden Markov model | |
| CN113505465B (en) | Fully unsupervised non-invasive electrical appliance state model self-adaptive construction method | |
| CN116503296B (en) | Surgical scene image conversion method | |
| CN112199154A (en) | Distributed collaborative sampling central optimization-based reinforcement learning training system and method | |
| CN115600494A (en) | Low-voltage distribution area topology automatic identification method and device | |
| CN107122472A (en) | Extensive unstructured data extracting method, its system, DDM platform | |
| CN106780722B (en) | A kind of differential mode scale Forest Scene construction method of the same race and system | |
| CN112987606B (en) | Visual programming tool system based on artificial intelligence and Internet of things | |
| CN115664005A (en) | Rapid communication point establishing method and system based on new energy electrical equipment model | |
| CN112329799A (en) | Point cloud colorization algorithm | |
| CN112202861A (en) | Hydropower engineering method management application system based on BIM | |
| CN111401141B (en) | 3D gesture estimation method based on skeleton | |
| CN118193628A (en) | Semantic enhancement graph contrast learning method and system for road network representation | |
| CN116662903A (en) | Power grid terminal equipment identification method and system based on graphic neural network | |
| CN118502761A (en) | Three-dimensional visual editing system based on digital twin | |
| CN117827992A (en) | Dynamic map generation method and system based on multidimensional data processing | |
| CN117787386A (en) | Mixed privacy data-oriented end-edge cloud collaborative training and task reasoning method | |
| CN118505564A (en) | Yun Bianduan coordinated biological intelligent manufacturing process behavior analysis image preprocessing system | |
| CN115345857A (en) | Method, apparatus, device, medium, and program product for acquiring augmented sample image |
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 |