CN109190667A - A kind of Object Threat Evaluation method, model and model building method based on electronic reconnaissance signal - Google Patents
A kind of Object Threat Evaluation method, model and model building method based on electronic reconnaissance signal Download PDFInfo
- Publication number
- CN109190667A CN109190667A CN201810856227.4A CN201810856227A CN109190667A CN 109190667 A CN109190667 A CN 109190667A CN 201810856227 A CN201810856227 A CN 201810856227A CN 109190667 A CN109190667 A CN 109190667A
- Authority
- CN
- China
- Prior art keywords
- threat
- signal
- normalized
- electromagnetic wave
- amplitude
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of Object Threat Evaluation method, model and model building method based on electronic reconnaissance signal, the time of electromagnetic wave signal, frequency, the working condition of amplitude and the affiliated ontology of electromagnetic signal in a direction are obtained；The electromagnetic wave signal of acquisition is normalized；Data distribution after normalized is converted into two-dimension picture；Synthetic threat probability is shown by neural network judgement to the two-dimension picture of input；The neural network is that a series of training study of sensing data progress of the unfinished target identification based on actual acquisition or analogue simulation obtains.Compared with prior art, can be based on the sensing data of unfinished target identification, directly impend assessment, makes up the deficiency of the threat assessment based on target identification.Simultaneously by the study of neural network, expert or old soldier can extract the combat experience that environmental threat judges and be dissolved among equipment.
Description
Technical field
The present invention relates to a kind of Object Threat Evaluation method, model and model building method based on electronic reconnaissance signal,
It is related to the environmental threat evaluation areas based on electronic reconnaissance signal.
Background technique
It is all using target as assessment object in existing radiation source intimidation estimating method.Radiation is had identified first
Source platform, so that the threat degree to target is assessed.Such as: the paper " radiation that IFS-BN is combined that jade-like stone is delivered
Source intimidation estimating method ", as shown in Figure 1, what is proposed in article is assessed based on the radiation source of intuitionistic Fuzzy Sets and Bayesian network
Method, with the proviso that the identification to radiation source platform and radiation source radar.It is platform status, including speed that it, which assesses input parameter,
Degree, distance, attack angle etc..And the information such as radar state, including carrier frequency, repetition, pulsewidth, incoming wave orientation.It is mentioned in article
More bibliography assessment be also premised on target identification.
In article " the target electromagnetic environmental threat degree appraisal procedure based on cloud reasoning " (Dai Qiangwei；Xue Lei；Lee repair and,
Modern defense technology, 01 phase in 2017) and article " application of the cloud Bayesian network in the assessment of target electromagnetic environmental threat "
(Dai Qiangwei；Xue Lei；Lee repair and, marine electronic confrontation, 06 phase in 2016) in mention target electromagnetic environmental threat assessment,
Although not carrying out target identification to electromagnetic environment, its purpose of appraisals is the influence for judging electromagnetic environment to equipment of itself.With
Based on equipment itself running parameter, electromagnetic environment is expressed as several indexs: (with one's own side's reconnaissance equipment signal) time weight
Right, direction registration, frequency coincidency, energy domain coverage etc., are all relevant to specified judge target signature.
And in practical operational environment, since electromagnetic space signal is complicated, such as on sea in addition to there is the thunder of confrontation both sides
Up to signal, there are also the radars that hundreds of fishing boat is also equipped with X, ku wave band.And on ground, then there is a large amount of signal of communication
It is mingled in the electromagnetic signal of confrontation both sides.Therefore, under many scenes, the judgement of threat is depended on whether correctly to know
Not Chu target, rather than depend on impending assessment to target.
Summary of the invention
The present invention provides a kind of Object Threat Evaluation method, model and model construction sides based on electronic reconnaissance signal
Method, can be based on the sensing data of unfinished target identification, and directly impend assessment, makes up the deficiency of target identification.
A kind of Object Threat Evaluation model building method based on electronic reconnaissance signal provided according to the present invention, specific side
Method includes,
A large amount of electronic reconnaissance signals are obtained as analogue data；On the one hand the analogue data is inputted into neural network
It practises, obtains the first threat probabilities；On the other hand marking is carried out to the threat of the analogue data and obtains the second threat probabilities；By
One threat probabilities are compared with the second threat probabilities and obtain error, and error is sent to neural network, obtain updated
First threat probabilities；Updated first threat probabilities are compared with the second threat probabilities and obtains error and then updates the again
One threat probabilities, then compare, it moves in circles, until the first threat probabilities obtained meet setting condition.
The electronic reconnaissance information includes electromagnetic wave signal；The electromagnetic wave signal includes time, frequency, amplitude and electromagnetism
The working condition of the affiliated ontology of signal.
Include by the specific method that learns of analogue data input neural network, by the time of electromagnetic wave signal,
After frequency and amplitude information are normalized, the data distribution after normalized is converted into two-dimension picture；Wherein, it indulges
Coordinate is frequency, and abscissa is the time, with color or depth representing amplitude；The amplitude of electromagnetic wave signal is divided using noise as standard
Cloth is between -13dB ~ 25dB；It is threat signal that a kind of signal is chosen in electromagnetic wave signal, remaining is background signal；Believe when threatening
When number occurring, the working condition of the affiliated ontology of electromagnetic signal is judged, if work specifies the first threat degree in search condition；
If work specifies the second threat degree in tracking mode；When threat signal does not occur, third threat degree is specified；One
All threat signals have been removed in one choosing, finally obtain synthetic threat degree.
The specific method of normalized further includes, and to data quantization, amplitude data is normalized to (- 1,1) section, will
Frequency data normalize to (0,1) section.
The method also includes specifying first to maintain degree is 50%, and the second threat degree is 100%, third threat degree
It is 0%.
A kind of Object Threat Evaluation model based on electronic reconnaissance signal, in above-mentioned Object Threat Evaluation model building method
Upper realization, including,
Electromagnetic environment perception information obtains module, obtains the electromagnetic wave signal of a direction, including time, frequency, amplitude and electricity
The working condition of the affiliated ontology of magnetic signal；
Electromagnetic environment perception information normalized module, the electromagnetic wave signal of acquisition is normalized；
Data distribution after normalized is converted to two-dimension picture by two-dimension picture conversion module；Wherein, ordinate is frequency
Rate, abscissa are the time, with color or depth representing amplitude；
Neural network judgment module carries out judgement to the two-dimension picture of input and obtains synthetic threat probability；
Threat probabilities output module exports the synthetic threat probability obtained.
A kind of Object Threat Evaluation method based on electronic reconnaissance signal, on the basis of above-mentioned Object Threat Evaluation model
It realizes, specific method includes,
S1, the time of electromagnetic wave signal, frequency, the working condition of amplitude and the affiliated ontology of electromagnetic signal in a direction are obtained；
S2, the electromagnetic wave signal of acquisition is normalized；
S3, the data distribution after normalized is converted into two-dimension picture；Wherein, ordinate is frequency, and abscissa is the time,
With color or depth representing amplitude；
S4, synthetic threat probability is shown by neural network judgement to the two-dimension picture of input.
Compared with prior art, can be based on the sensing data of unfinished target identification, directly impend assessment, more
Mend the deficiency of target identification.
Detailed description of the invention
Fig. 1 is schematic diagram in prior art appraisal procedure.
Fig. 2 is the schematic illustration of Object Threat Evaluation model construction of the present invention.
Fig. 3 is Object Threat Evaluation method flow schematic diagram of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
Any feature disclosed in this specification (including abstract and attached drawing) unless specifically stated can be equivalent by other
Or the alternative features with similar purpose are replaced.That is, unless specifically stated, each feature is a series of equivalent or class
Like an example in feature.
A kind of Object Threat Evaluation model building method based on electronic reconnaissance signal, specific method include,
As shown in Fig. 2, obtaining a large amount of electronic reconnaissance signals as analogue data；On the one hand the analogue data is inputted into nerve net
Network is learnt, and obtains the first threat probabilities；On the other hand marking is carried out to the threat of the analogue data and obtains the second threat
Probability；First threat probabilities are compared with the second threat probabilities and obtain error, and error is sent to neural network, are obtained
Updated first threat probabilities；Then updated first threat probabilities are compared with the second threat probabilities obtains error
The first threat probabilities are updated again, then are compared, are moved in circles, until the first threat probabilities obtained meet setting condition.The setting
Condition can be a threat assessment accuracy rate that can reach, such as 90%, be also possible to be cyclically updated the number reached, or
Other conditions.
The electronic reconnaissance information includes electromagnetic wave signal；The electromagnetic wave signal includes time, frequency, amplitude and electromagnetism
The working condition of the affiliated ontology of signal.
Include by the specific method that learns of analogue data input neural network, by the time of electromagnetic wave signal,
After frequency and amplitude information are normalized, the data distribution after normalized is converted into two-dimension picture；Wherein, it indulges
Coordinate is frequency, and abscissa is the time, with color or depth representing amplitude；The amplitude of electromagnetic wave signal is divided using noise as standard
Cloth is between -13dB ~ 25dB；It is threat signal that a kind of signal is chosen in electromagnetic wave signal, remaining is background signal；Believe when threatening
When number occurring, the working condition of the affiliated ontology of electromagnetic signal is judged, if work specifies the first threat degree in search condition；
If work specifies the second threat degree in tracking mode；When threat signal does not occur, third threat degree is specified；One
All threat signals have been removed in one choosing, finally obtain synthetic threat degree.
The specific method of normalized further includes, and to data quantization, amplitude data is normalized to (- 1,1) section, will
Frequency data normalize to (0,1) section.
The method also includes specifying first to maintain degree is 50%, and the second threat degree is 100%, third threat degree
It is 0%.
As a specific embodiment of the invention, 20 kinds of models, 100 kinds of signal pattern (different model/modulation are simulated
The corresponding same pulse pattern of type/frequency combination, 10600 signal data files)；Quantify according to 12,9 effective quantities
Change digit analogue data, amplitude data is normalized into (- 1,1) section；Frequency data normalize to (0,1) section；Signal width
Degree is using noise as standard, i.e., noise is 0dB, is distributed between -13 ~ 25dB；Having a kind of signal in signal is threat signal, remaining
For background signal；When threat signal occurs, when work is in search condition, specifying threat degree is 50%；When threat signal goes out
It is existing, and work in tracking mode, specifying threat degree is 100%.When threat signal does not occur, specified threat degree is
0%.Neural network is established, with analogue data, is trained according to neural network learning shown in Fig. 2, is completed, and generated with analogue data
Data are verified, being substituted into model with verification data and verified further improves model.Object Threat Evaluation mould is constructed
After type, the threat degree in a direction can be judged from sensing data.
A kind of Object Threat Evaluation model based on electronic reconnaissance signal provided according to the present invention, in above-mentioned target threat
It is realized on assessment models construction method, including,
Electromagnetic environment perception information obtains module, obtains the electromagnetic wave signal of a direction, including time, frequency, amplitude and electricity
The working condition of the affiliated ontology of magnetic signal；
Electromagnetic environment perception information normalized module, the electromagnetic wave signal of acquisition is normalized；
Data distribution after normalized is converted to two-dimension picture by two-dimension picture conversion module；Wherein, ordinate is frequency
Rate, abscissa are the time, with color or depth representing amplitude；
Neural network judgment module carries out judgement to the two-dimension picture of input and obtains synthetic threat probability；
Threat probabilities output module exports the synthetic threat probability obtained.
As shown in figure 3, a kind of Object Threat Evaluation method based on electronic reconnaissance signal, in above-mentioned Object Threat Evaluation mould
It is realized on the basis of type, specific method includes,
S1, the time of electromagnetic wave signal, frequency, the working condition of amplitude and the affiliated ontology of electromagnetic signal in a direction are obtained；
S2, the electromagnetic wave signal of acquisition is normalized；
S3, the data distribution after normalized is converted into two-dimension picture；Wherein, ordinate is frequency, and abscissa is the time,
With color or depth representing amplitude；
S4, synthetic threat probability is shown by neural network judgement to the two-dimension picture of input.
Under complex electromagnetic environment, the information between each sensor cannot merge completely, and target identification might have leakage
Alert, bulk information can not all be identified as target.The purpose of the present invention is the sensing data based on unfinished target identification,
Using neural network as core, by there is the study mechanism of supervision, directly impend assessment, makes up the deficiency of target identification.Hair
Bright application value is: the combat experience of other people (expert or old soldiers) being extracted, is dissolved into equipment, to reinforce making
The succession dynamics of war experience improves fight capability.
Technical solution of the present invention threatens assessment in real time based on the battlefield of electronic reconnaissance signal distributions, rather than is detectd by electronics
It examines signal and carries out target identification, gone to judge threat degree by target property；Extraction of the neural network to electronic countermeasure battlefield experience
With application, the experience of manoeuvre, training and simulation study is refined by neural network and is applied on equipment, rather than will be through
It is passed in a manner of teaching again after testing summary.
Claims (6)
1. a kind of Object Threat Evaluation model building method based on electronic reconnaissance signal, specific method include,
A large amount of electronic reconnaissance signals are obtained as analogue data；On the one hand the analogue data is inputted into neural network
It practises, obtains the first threat probabilities；On the other hand marking is carried out to the threat of the analogue data and obtains the second threat probabilities；By
One threat probabilities are compared with the second threat probabilities and obtain error, and error is sent to neural network, obtain updated
First threat probabilities；Updated first threat probabilities are compared with the second threat probabilities and obtains error and then updates the again
One threat probabilities, then compare, it moves in circles, until the first threat probabilities obtained meet setting condition.
2. Object Threat Evaluation model building method according to claim 1, the electronic reconnaissance information includes electromagnetic wave
Signal；The electromagnetic wave signal includes time, frequency, the working condition of amplitude and the affiliated ontology of electromagnetic signal.
3. the analogue data is inputted neural network by Object Threat Evaluation model building method according to claim 2
The specific method learnt includes, and after the time of electromagnetic wave signal, frequency and amplitude information are normalized, will return
One changes that treated that data distribution is converted to two-dimension picture；Wherein, ordinate is frequency, and abscissa is the time, with color or depth
Spend expression amplitude；The amplitude of electromagnetic wave signal is distributed between -13dB ~ 25dB using noise as standard；It is chosen in electromagnetic wave signal
A kind of signal is threat signal, remaining is background signal；When threat signal occurs, the work of the affiliated ontology of electromagnetic signal is judged
State, if work specifies the first threat degree in search condition；If work specifies the second threat degree in tracking mode；
When threat signal does not occur, third threat degree is specified；All threat signals have been removed in choosing one by one, finally obtain comprehensive prestige
Side of body degree.
4. Object Threat Evaluation model building method according to claim 3, the specific method of normalized further include,
To data quantization, amplitude data is normalized into (- 1,1) section, frequency data are normalized into (0,1) section.
5. a kind of Object Threat Evaluation model based on electronic reconnaissance signal, the target threat described in one of claim 2 to 4
It is realized on assessment models construction method, including,
Electromagnetic environment perception information obtains module, obtains the electromagnetic wave signal of a direction, including time, frequency, amplitude and electricity
The working condition of the affiliated ontology of magnetic signal；
Electromagnetic environment perception information normalized module, the electromagnetic wave signal of acquisition is normalized；
Data distribution after normalized is converted to two-dimension picture by two-dimension picture conversion module；Wherein, ordinate is frequency
Rate, abscissa are the time, with color or depth representing amplitude；
Neural network judgment module carries out judgement to the two-dimension picture of input and obtains synthetic threat probability；
Threat probabilities output module exports the synthetic threat probability obtained.
6. a kind of Object Threat Evaluation method based on electronic reconnaissance signal, the Object Threat Evaluation mould described in claim 5
It is realized on the basis of type, specific method includes,
S1, the time of electromagnetic wave signal, frequency, the working condition of amplitude and the affiliated ontology of electromagnetic signal in a direction are obtained；
S2, the electromagnetic wave signal of acquisition is normalized；
S3, the data distribution after normalized is converted into two-dimension picture；Wherein, ordinate is frequency, and abscissa is the time,
With color or depth representing amplitude；
S4, synthetic threat probability is shown by neural network judgement to the two-dimension picture of input.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810856227.4A CN109190667A (en) | 2018-07-31 | 2018-07-31 | A kind of Object Threat Evaluation method, model and model building method based on electronic reconnaissance signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810856227.4A CN109190667A (en) | 2018-07-31 | 2018-07-31 | A kind of Object Threat Evaluation method, model and model building method based on electronic reconnaissance signal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109190667A true CN109190667A (en) | 2019-01-11 |
Family
ID=64937469
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810856227.4A Pending CN109190667A (en) | 2018-07-31 | 2018-07-31 | A kind of Object Threat Evaluation method, model and model building method based on electronic reconnaissance signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190667A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147883A (en) * | 2019-05-28 | 2019-08-20 | 航天科工系统仿真科技（北京）有限公司 | Training method, device, equipment and the storage medium of model for emulation of fighting |
| CN111212067A (en) * | 2019-12-31 | 2020-05-29 | 南京联成科技发展股份有限公司 | Industrial network security risk assessment system based on threat prediction |
| CN111476288A (en) * | 2020-04-03 | 2020-07-31 | 中国人民解放军海军航空大学 | Intelligent perception method for cognitive sensor network to electromagnetic behaviors with unknown threats |
| CN112149818A (en) * | 2019-06-27 | 2020-12-29 | 北京数安鑫云信息技术有限公司 | Threat identification result evaluation method and device |
| CN112904397A (en) * | 2021-01-22 | 2021-06-04 | 中山大学 | Electronic reconnaissance method and system based on sand heap model |
| CN113065808A (en) * | 2021-05-06 | 2021-07-02 | 中国电子科技集团公司第二十九研究所 | Method, equipment and storage medium for simulating reporting rate index of electronic reconnaissance data |
| CN113408805A (en) * | 2021-06-24 | 2021-09-17 | 国网浙江省电力有限公司双创中心 | Lightning ground flashover identification method, device, equipment and readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101214851A (en) * | 2008-01-10 | 2008-07-09 | 黄席樾 | Intelligent all-weather actively safety early warning system and early warning method thereof for ship running |
| CN102298728A (en) * | 2011-08-17 | 2011-12-28 | 电子科技大学 | Method for evaluating target threat degree |
| CN103020452A (en) * | 2012-12-13 | 2013-04-03 | 中国航天科工信息技术研究院 | Method for judging threat level of radar radiation source |
| CN104503425A (en) * | 2014-11-24 | 2015-04-08 | 中国电子科技集团公司第二十九研究所 | Radar countermeasure equipment effectiveness evaluation method based on hardware-in-the-loop simulation |
| CN105144225A (en) * | 2013-03-15 | 2015-12-09 | 珀西斯特发展公司 | Multiple patient EEG monitoring |
| CN105515660A (en) * | 2015-11-30 | 2016-04-20 | 惠州伟志电子有限公司 | Reverse pulse code modulated visible light communication system |
| CN105654232A (en) * | 2015-12-24 | 2016-06-08 | 大连陆海科技股份有限公司 | Coastal monitoring and defense decision-making system based on multi-dimensional space fusion and method thereof |
| CN106388825A (en) * | 2016-10-14 | 2017-02-15 | 广州视源电子科技股份有限公司 | Respiration rate extraction method and device |
| CN107391887A (en) * | 2017-08-30 | 2017-11-24 | 中国电子科技集团公司第二十九研究所 | A kind of electromagnetic space analogue system and emulation mode |
| CN107609601A (en) * | 2017-09-28 | 2018-01-19 | 北京计算机技术及应用研究所 | A kind of ship seakeeping method based on multilayer convolutional neural networks |
| CN108304770A (en) * | 2017-12-18 | 2018-07-20 | 中国计量大学 | A method of the flow pattern of gas-liquid two-phase flow based on time frequency analysis algorithm combination deep learning theory |
-
2018
- 2018-07-31 CN CN201810856227.4A patent/CN109190667A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101214851A (en) * | 2008-01-10 | 2008-07-09 | 黄席樾 | Intelligent all-weather actively safety early warning system and early warning method thereof for ship running |
| CN102298728A (en) * | 2011-08-17 | 2011-12-28 | 电子科技大学 | Method for evaluating target threat degree |
| CN103020452A (en) * | 2012-12-13 | 2013-04-03 | 中国航天科工信息技术研究院 | Method for judging threat level of radar radiation source |
| CN105144225A (en) * | 2013-03-15 | 2015-12-09 | 珀西斯特发展公司 | Multiple patient EEG monitoring |
| CN104503425A (en) * | 2014-11-24 | 2015-04-08 | 中国电子科技集团公司第二十九研究所 | Radar countermeasure equipment effectiveness evaluation method based on hardware-in-the-loop simulation |
| CN105515660A (en) * | 2015-11-30 | 2016-04-20 | 惠州伟志电子有限公司 | Reverse pulse code modulated visible light communication system |
| CN105654232A (en) * | 2015-12-24 | 2016-06-08 | 大连陆海科技股份有限公司 | Coastal monitoring and defense decision-making system based on multi-dimensional space fusion and method thereof |
| CN106388825A (en) * | 2016-10-14 | 2017-02-15 | 广州视源电子科技股份有限公司 | Respiration rate extraction method and device |
| CN107391887A (en) * | 2017-08-30 | 2017-11-24 | 中国电子科技集团公司第二十九研究所 | A kind of electromagnetic space analogue system and emulation mode |
| CN107609601A (en) * | 2017-09-28 | 2018-01-19 | 北京计算机技术及应用研究所 | A kind of ship seakeeping method based on multilayer convolutional neural networks |
| CN108304770A (en) * | 2017-12-18 | 2018-07-20 | 中国计量大学 | A method of the flow pattern of gas-liquid two-phase flow based on time frequency analysis algorithm combination deep learning theory |
Non-Patent Citations (4)
| Title |
|---|
| 代强伟 等: "云贝叶斯网络在目标电磁环境威胁评估中的应用", 《舰船电子对抗》 * |
| 廖羽宇: "统计MIMO雷达检测理论研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
| 张萤 等: "IFS-BN结合的辐射源威胁评估方法", 《空间工程大学学报(自然科学版)》 * |
| 戴幻尧 等: "现代巡航导弹突防中的雷达极化技术", 《航天电子对抗》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147883A (en) * | 2019-05-28 | 2019-08-20 | 航天科工系统仿真科技（北京）有限公司 | Training method, device, equipment and the storage medium of model for emulation of fighting |
| CN112149818A (en) * | 2019-06-27 | 2020-12-29 | 北京数安鑫云信息技术有限公司 | Threat identification result evaluation method and device |
| CN112149818B (en) * | 2019-06-27 | 2024-04-09 | 北京数安鑫云信息技术有限公司 | Threat identification result evaluation method and device |
| CN111212067A (en) * | 2019-12-31 | 2020-05-29 | 南京联成科技发展股份有限公司 | Industrial network security risk assessment system based on threat prediction |
| CN111476288A (en) * | 2020-04-03 | 2020-07-31 | 中国人民解放军海军航空大学 | Intelligent perception method for cognitive sensor network to electromagnetic behaviors with unknown threats |
| CN112904397A (en) * | 2021-01-22 | 2021-06-04 | 中山大学 | Electronic reconnaissance method and system based on sand heap model |
| CN112904397B (en) * | 2021-01-22 | 2022-10-14 | 中山大学 | Electronic reconnaissance method and system based on sand heap model |
| CN113065808A (en) * | 2021-05-06 | 2021-07-02 | 中国电子科技集团公司第二十九研究所 | Method, equipment and storage medium for simulating reporting rate index of electronic reconnaissance data |
| CN113065808B (en) * | 2021-05-06 | 2022-04-12 | 中国电子科技集团公司第二十九研究所 | Method, equipment and storage medium for simulating reporting rate index of electronic reconnaissance data |
| CN113408805A (en) * | 2021-06-24 | 2021-09-17 | 国网浙江省电力有限公司双创中心 | Lightning ground flashover identification method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190667A (en) | A kind of Object Threat Evaluation method, model and model building method based on electronic reconnaissance signal | |
| CN109711087B (en) | UUV dynamic threat situation assessment method | |
| CN107169435B (en) | Convolutional neural network human body action classification method based on radar simulation image | |
| CN103869311B (en) | Real beam scanning radar super-resolution imaging method | |
| CN104297748B (en) | One kind is based on tracking before the enhanced Radar Targets'Detection in track | |
| Li et al. | On the empirical-statistical modeling of SAR images with generalized gamma distribution | |
| CN110133599B (en) | Intelligent radar radiation source signal classification method based on long-time and short-time memory model | |
| CN106842165A (en) | One kind is based on different distance angular resolution radar centralization asynchronous fusion method | |
| Li et al. | Radar signal recognition algorithm based on entropy theory | |
| CN105260524B (en) | Ship-navigation radar two dimension echo sequence is as emulation mode under a kind of scanning mode | |
| CN115061126A (en) | Radar cluster target behavior identification method based on multi-dimensional parameter neural network | |
| Tian et al. | Performance evaluation of deception against synthetic aperture radar based on multifeature fusion | |
| Sehgal et al. | Automatic target recognition using recurrent neural networks | |
| RU2399097C1 (en) | Method for semi-realistic complex statistical modelling of electronic warfare systems of surface ships | |
| CN110991031B (en) | Multi-branch fuze target detection modeling method | |
| CN113627356A (en) | Intelligent sea surface ship identification method | |
| Braga et al. | Estimation of UAV position using LiDAR images for autonomous navigation over the ocean | |
| Sehgal et al. | Automatic Radar Target Identification Using Radar Cross Section Fluctuations and Recurrent Neural Networks | |
| Ye et al. | Realistic scatterer based adversarial attacks on sar image classifiers | |
| CN107610130A (en) | Extra large land clutter Scene Segmentation based on the ratio between amplitude and phase linearity | |
| Song et al. | Underwater terrain-aided navigation based on multibeam bathymetric sonar images | |
| Jie et al. | K distribution sea clutter modeling and simulation based on ZMNL | |
| CN115249322A (en) | Anti-sample generation method based on frequency domain flow field attack | |
| CN113960551A (en) | Clutter image generation method and target detection method for SAR image | |
| Elster et al. | Fundamental design criteria for logical scenarios in simulation-based safety validation of automated driving using sensor model knowledge |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190111 |