CN105550702A - GNSS deception jamming recognition method based on SVM - Google Patents

GNSS deception jamming recognition method based on SVM Download PDF

Info

Publication number
CN105550702A
CN105550702A CN201510907339.4A CN201510907339A CN105550702A CN 105550702 A CN105550702 A CN 105550702A CN 201510907339 A CN201510907339 A CN 201510907339A CN 105550702 A CN105550702 A CN 105550702A
Authority
CN
China
Prior art keywords
svm
gnss
signal
recognition methods
curve
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
Application number
CN201510907339.4A
Other languages
Chinese (zh)
Other versions
CN105550702B (en
Inventor
韩帅
邓雪菲
王学东
孟维晓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Dayi Jiaxing Technology Co.,Ltd.
Original Assignee
Harbin Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Harbin Institute of Technology filed Critical Harbin Institute of Technology
Priority to CN201510907339.4A priority Critical patent/CN105550702B/en
Publication of CN105550702A publication Critical patent/CN105550702A/en
Application granted granted Critical
Publication of CN105550702B publication Critical patent/CN105550702B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/13—Receivers
    • G01S19/21—Interference related issues ; Issues related to cross-correlation, spoofing or other methods of denial of service
    • G01S19/215—Interference related issues ; Issues related to cross-correlation, spoofing or other methods of denial of service issues related to spoofing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention relates to a navigation satellite system and especially relates to a GNSS deception jamming recognition method based on an SVM. The method solves problems that a conventional deception jamming resistance method is higher in algorithm and hardware complexity, the threshold value needs to be set by a user, and the accuracy is not high. The method comprises the following steps: 1, enabling a and b to serve as a training set and enabling c and d to serve as a testing set after a GNSS receiver has already received four satellite signals a, b, c and d; 2, setting the number of sampling points as n, and recording the power values of sampling points as a(n) and b(n); 3, respectively carrying out wavelet transformation of a(n) and b(b), and extracting the characteristic vectors of a(n) and b(b); 4, building an SVM classification model; 5, recording the power values c(n) and d(n) of all sampling points; 6, carrying out the testing of c and d through the model built at step 4, and obtaining a conclusion. The method is suitable for a navigation satellite system.

Description

A kind of GNSS Deceiving interference recognition methods based on SVM
Technical field
The present invention relates to navigational satellite system, particularly relate to a kind of GNSS Deceiving interference recognition methods based on SVM.
Background technology
GNSS (GLONASS (Global Navigation Satellite System)) receives function and provides location, navigation and timing services, has become instrument indispensable in people's daily life, has been widely used in military equipment and with in people's daily life.For the occasion that security, reliability requirement are strict, trustworthy timing location is particularly important.But because satellite-signal when arriving ground is very faint, pickup electrode is vulnerable to interference.Interference is divided into suppress interfere and Deceiving interference.Wherein Deceiving interference can destroy when receiver has no to discover and even control timing positioning result, and thus Deceiving interference threatens larger than suppress interfere.Particularly along with the development of Electronic Warfare Technology and integrated circuit technique, Deceiving interference is more frequently occurred.
The method of existing anti-Deceiving interference mainly contains the anti-Deceiving interference mode based on particle filter, based on the GNSS receiver cross-correlation interference Restrainable algorithms of subspace projection and the cheating interference recognition technology based on Received signal strength DOA (direction of arrival).Algorithm and the hardware complexity of these technology are higher, and need oneself to arrange thresholding, and accuracy rate is not very high.A kind of Deceiving interference recognition methods based on Data classification that this patent proposes, can with almost 100% accuracy rate and zero false alarm rate identification undesired signal, fast operation, complexity is low, and thresholding is intelligent, and application scenarios is more extensive.
Summary of the invention
SVM (support vector machine) is a kind of algorithm of Data classification.Its object is to find a best lineoid to make margin maximization between positive example and counter-example.Due to large about the 3 ~ 7dB of the power ratio actual signal of curve, actual signal and curve can regard positive example and counter-example as respectively, thus the optimal classification lineoid of actual signal and curve can be found out by SVM classifier, then can differentiate unknown signaling, judge which kind of signal it belongs to, thus reach the object identifying curve.
First suppose to have received a curve and an actual signal, using them as training set, use SVM to train it, find the optimal classification lineoid distinguishing curve and actual signal; Then input test satellite-signal, trains the model obtained to test it with training set, judges that it belongs to actual signal or curve.Accuracy rate: the probability correctly identifying curve, false alarm rate: probability actual signal being determined as curve of mistake.
The present invention is that the method solving existing anti-Deceiving interference exists algorithm and hardware complexity is higher, and needs oneself to arrange thresholding, the problem that accuracy rate is not high, and proposes a kind of GNSS Deceiving interference recognition methods based on SVM.
Based on a GNSS Deceiving interference recognition methods of SVM, carry out according to the following steps:
Step one: GNSS receiver has received four satellite-signals a, b, c, d, and using a and b as training set, c and d is as test set.A is actual signal, and b is curve, the large i of power ratio a of b 0doubly, 2≤i 0≤ 5; C and d is signal to be tested;
Step 2: arranging sampling number is n, records actual signal in n-bit Received signal strength and curve performance number a (n), b (n) at each sampled point respectively;
Step 3: respectively wavelet transformation is carried out to data a (n) and b (n), extracts its proper vector, if a (n) extract proper vector be x, b (n) to extract proper vector be y;
Step 4: the proper vector x extracted and y is trained, sets up svm classifier model;
Step 5: record equally in test set, signal c and signal d is at the performance number c (n) of each sampled point and d (n);
Step 6: test test set c and d with step 4 institute Modling model, show that it is actual signal or curve or sends false-alarm alarm.
The present invention includes following beneficial effect:
1, the present invention proposes a kind of Deceiving interference recognition methods based on Data classification, can with almost 100% accuracy rate and zero false alarm rate identification undesired signal, fast operation, complexity is low, and thresholding is intelligent, and application scenarios is more extensive;
2, the present invention only need receive an actual signal and curve in advance, carries out modeling to it, namely can identify the satellite-signal of the unknown, judges whether it belongs to Deceiving interference signal, method simple practical.
Accompanying drawing explanation
Fig. 1 be experiment in different capacity than under recognition accuracy and false alarm rate schematic diagram.
Embodiment
For enabling above-mentioned purpose of the present invention, feature and advantage become apparent more, and below in conjunction with Fig. 1 and embodiment, the present invention is further detailed explanation.
A kind of GNSS Deceiving interference recognition methods based on SVM described in embodiment one, present embodiment, carry out according to the following steps:
Step one: GNSS receiver receives four satellite-signals a, b, c, d, and using a and b as training set, c and d is as test set.A is actual signal, and b is curve, the large i of power ratio a of b 0doubly, 2≤i 0≤ 5; C and d is signal to be tested;
Step 2: arranging sampling number is n, records actual signal in n-bit Received signal strength and curve respectively at the performance number a (n) of each sampled point and b (n);
Step 3: respectively wavelet transformation is carried out to data a (n) and b (n), extracts its proper vector, if a (n) extract proper vector be x, b (n) to extract proper vector be y;
Step 4: the proper vector x extracted and y is trained, sets up svm classifier model;
Step 5: record equally in test set, signal c and signal d is at the performance number c (n) of each sampled point and d (n);
Step 6: test test set c and d with step 4 institute Modling model, show that it is actual signal or curve or sends false-alarm alarm.
Present embodiment comprises following beneficial effect:
1, present embodiment proposes a kind of Deceiving interference recognition methods based on Data classification, can with almost 100% accuracy rate and zero false alarm rate identification undesired signal, fast operation, complexity is low, and thresholding is intelligent, and application scenarios is more extensive;
2, present embodiment only need receive an actual signal and curve in advance, carries out modeling to it, namely can identify the satellite-signal of the unknown, judges whether it belongs to Deceiving interference signal, method simple practical.
Embodiment two, present embodiment and embodiment one is unlike 2≤i described in step one 0≤ 4, other step and parameter identical with embodiment one.
Embodiment three, present embodiment and embodiment one or two are unlike i described in step one 0=2, other step and parameter identical with embodiment one.
Embodiment four, present embodiment and embodiment one or two are unlike i described in step one 0=3, other step and parameter identical with embodiment one.
Embodiment five, present embodiment and embodiment one or two are unlike i described in step one 0=4, other step and parameter identical with embodiment one.
Embodiment six, present embodiment are further illustrating a kind of GNSS Deceiving interference recognition methods based on SVM described in embodiment one, set up svm classifier model described in step 4, obtain optimal classification lineoid equation with training set exactly.
For verifying accuracy rate of the present invention and false alarm rate, test as follows.
Step one: GNSS receiver receives four satellite-signals a, b, c, d, and using a and b as training set, c and d is as test set.A is actual signal, and b is curve, the large i of power ratio a of b 0doubly, i 0=2; C is actual signal, and d is curve, larger than c j times of d, j=2;
Step 2: arranging sampling number is n=1000, records actual signal in 1000 bit reception signals and curve respectively at the performance number a (n) of each sampled point and b (n);
Step 3: respectively wavelet transformation is carried out to data a (n) and b (n), extracts its proper vector, if a (n) extract proper vector be x, b (n) to extract proper vector be y;
Step 4: the proper vector x extracted and y is trained, sets up svm classifier model;
Step 5: record equally in test set, actual signal c and curve d is at the performance number c (n) of each sampled point and d (n);
Step 6: with step 4 institute Modling model, test set c and d is tested, draw the accuracy rate of prediction;
Step 7: for improving accuracy rate, repeats step one and arrives step 6 1000 times, draw consensus forecast accuracy rate and false alarm rate;
Step 8: respectively with regard to the accuracy rate of test set classification under different j (j=2,3,4,5), and carry out analysis contrast.
Criterion wherein in step 6: be greater than 500 if having in 1000 of signal c sampled points and be classified as actual signal, be judged to actual signal, otherwise there is false-alarm; If 1000 sampled points of same d have and are greater than 500 points and are classified as curve, be judged to curve;
Fig. 1 be experiment in different capacity than under recognition accuracy and false alarm rate schematic diagram.As can be seen from the figure, along with curve is than the increase of actual signal power increase multiple, curve recognition accuracy is 100%, and false alarm rate is zero.Illustrate that the method can fast with higher accuracy rate identification curve.

Claims (6)

1., based on a GNSS Deceiving interference recognition methods of SVM, it is characterized in that it carries out according to the following steps:
Step one: GNSS receiver has received four satellite-signals a, b, c, d, and using a and b as training set, c and d is as test set; A is actual signal, and b is curve, the large i of power ratio a of b 0doubly, 2≤i 0≤ 5; C and d is signal to be tested;
Step 2: arranging sampling number is n, records actual signal in n-bit Received signal strength and curve performance number a (n), b (n) at each sampled point respectively;
Step 3: respectively wavelet transformation is carried out to data a (n) and b (n), extracts its proper vector, if a (n) extract proper vector be x, b (n) to extract proper vector be y;
Step 4: the proper vector x extracted and y is trained, sets up svm classifier model;
Step 5: record equally in test set, signal c and signal d is at the performance number c (n) of each sampled point and d (n);
Step 6: test test set c and d with step 4 institute Modling model, show that it is actual signal or curve or sends false-alarm alarm.
2. a kind of GNSS Deceiving interference recognition methods based on SVM as claimed in claim 1, is characterized in that 2≤i described in step one 0≤ 4.
3. a kind of GNSS Deceiving interference recognition methods based on SVM as claimed in claim 1 or 2, is characterized in that i described in step one 0=2.
4. a kind of GNSS Deceiving interference recognition methods based on SVM as claimed in claim 1 or 2, is characterized in that i described in step one 0=3.
5. a kind of GNSS Deceiving interference recognition methods based on SVM as claimed in claim 1 or 2, is characterized in that i described in step one 0=4.
6. a kind of GNSS Deceiving interference recognition methods based on SVM as claimed in claim 1 or 2, is characterized in that setting up svm classifier model described in step 4, obtains optimal classification lineoid equation exactly with training set.
CN201510907339.4A 2015-12-09 2015-12-09 A kind of GNSS Deceiving interference recognition methods based on SVM Active CN105550702B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510907339.4A CN105550702B (en) 2015-12-09 2015-12-09 A kind of GNSS Deceiving interference recognition methods based on SVM

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510907339.4A CN105550702B (en) 2015-12-09 2015-12-09 A kind of GNSS Deceiving interference recognition methods based on SVM

Publications (2)

Publication Number Publication Date
CN105550702A true CN105550702A (en) 2016-05-04
CN105550702B CN105550702B (en) 2019-07-02

Family

ID=55829885

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510907339.4A Active CN105550702B (en) 2015-12-09 2015-12-09 A kind of GNSS Deceiving interference recognition methods based on SVM

Country Status (1)

Country Link
CN (1) CN105550702B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107247273A (en) * 2017-05-05 2017-10-13 西安电子科技大学 A kind of GPS separate types dynamical feedback interference method
CN113359158A (en) * 2021-06-15 2021-09-07 东南大学 GNSS generated deception jamming detection method based on SVM
CN113376659A (en) * 2021-06-15 2021-09-10 东南大学 GNSS (Global navigation satellite System) generated deception jamming detection method based on BP (Back propagation) neural network
CN115494526A (en) * 2022-08-29 2022-12-20 中山大学 GNSS deception jamming detection method and device, electronic equipment and storage medium
US20230035856A1 (en) * 2021-07-20 2023-02-02 Cambridge Mobile Telematics Inc. Identifying unreliable global navigation satellite system (gnss) data

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1996190A (en) * 2006-11-23 2007-07-11 浙江大学 Industrial process fault diagnosis system and method based on wavelet analysis
CN101833671A (en) * 2010-03-30 2010-09-15 西安理工大学 Support vector machine-based surface electromyogram signal multi-class pattern recognition method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1996190A (en) * 2006-11-23 2007-07-11 浙江大学 Industrial process fault diagnosis system and method based on wavelet analysis
CN101833671A (en) * 2010-03-30 2010-09-15 西安理工大学 Support vector machine-based surface electromyogram signal multi-class pattern recognition method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
吴昊等: "一种面向卫星频谱监测的复合式干扰自动识别算法", 《系统仿真学报》 *
张婧等: "基于神经网络和SVM的GPS干扰类型识别", 《信息与电子工程》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107247273A (en) * 2017-05-05 2017-10-13 西安电子科技大学 A kind of GPS separate types dynamical feedback interference method
CN113359158A (en) * 2021-06-15 2021-09-07 东南大学 GNSS generated deception jamming detection method based on SVM
CN113376659A (en) * 2021-06-15 2021-09-10 东南大学 GNSS (Global navigation satellite System) generated deception jamming detection method based on BP (Back propagation) neural network
US20230035856A1 (en) * 2021-07-20 2023-02-02 Cambridge Mobile Telematics Inc. Identifying unreliable global navigation satellite system (gnss) data
CN115494526A (en) * 2022-08-29 2022-12-20 中山大学 GNSS deception jamming detection method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN105550702B (en) 2019-07-02

Similar Documents

Publication Publication Date Title
CN105550702A (en) GNSS deception jamming recognition method based on SVM
CN108924736B (en) PCA-Kalman-based passive indoor personnel state detection method
CN105678273B (en) The starting point detection algorithm of radio-frequency fingerprint identification technology transient signal
CN106446877B (en) A kind of radio-frequency fingerprint feature extraction and recognition methods based on signal amplitude sequence
US11081126B2 (en) Processing of sound data for separating sound sources in a multichannel signal
CN111175718A (en) Time-frequency domain combined ground radar automatic target identification method and system
CN113376659B (en) GNSS (global navigation satellite system) generated deception jamming detection method based on BP (back propagation) neural network
CN105979485A (en) Personnel detection method in indoor environment based on channel state information (CSI)
CN106452716A (en) Unmanned aerial vehicle signal recognition and detection algorithm based on Hash fingerprint
CN105429719A (en) Strong interference signal detection method based on power spectrum and multiple dimensioned wavelet transformation analysis
CN108549078A (en) A kind of radar pulse signal is across combining channel and detection method
CN108197581A (en) A kind of unmanned plane signal identification detection algorithm based on improvement AC-WGANs
CN105678263A (en) Method and system for object recognition
CN113359158A (en) GNSS generated deception jamming detection method based on SVM
CN110764152B (en) Device and method for rapid detection and identification of unmanned aerial vehicle
CN115661869A (en) Radio frequency signal fingerprint identification method and system based on multi-dimensional feature intelligent fusion
Cui et al. Spatio-temporal synchrophasor data characterization for mitigating false data injection in smart grids
CN103116740A (en) Method and device for identifying underwater targets
Miao et al. Application of one-class classification in NLOS identification of UWB positioning
Liu et al. Unsupervised clustering method to discriminate dense deception jamming for surveillance radar
CN114067614A (en) Method, device and equipment for extracting characteristics of air traffic control monitoring response signal and storage medium
Won et al. Wiparkfind: Finding empty parking slots using wifi
CN113572555B (en) Black broadcast monitoring method based on zero sample learning
CN115575992A (en) ADS-B deception jamming detection method, medium and device based on deep learning
CN112016539B (en) Signal identification method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20240401

Address after: Room 1107, 11 / F, National University Science Park, Harbin Institute of technology, No. 434, youyou street, Nangang District, Harbin City, Heilongjiang Province

Patentee after: Harbin Institute of Technology Asset Management Co.,Ltd.

Country or region after: China

Patentee after: Han Shuai

Address before: 150001 No. 92 West straight street, Nangang District, Heilongjiang, Harbin

Patentee before: HARBIN INSTITUTE OF TECHNOLOGY

Country or region before: China

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20240416

Address after: 518000, Building 9, A3101, Zone 2, Shenzhen Bay Science and Technology Ecological Park, No. 3609 Baishi Road, High tech Zone Community, Yuehai Street, Nanshan District, Shenzhen City, Guangdong Province

Patentee after: Shenzhen Dayi Jiaxing Technology Co.,Ltd.

Country or region after: China

Address before: Room 1107, 11 / F, National University Science Park, Harbin Institute of technology, No. 434, youyou street, Nangang District, Harbin City, Heilongjiang Province

Patentee before: Harbin Institute of Technology Asset Management Co.,Ltd.

Country or region before: China

Patentee before: Han Shuai