CN112800983B - A non-line-of-sight signal recognition method based on random forest - Google Patents

A non-line-of-sight signal recognition method based on random forest Download PDF

Info

Publication number
CN112800983B
CN112800983B CN202110138933.7A CN202110138933A CN112800983B CN 112800983 B CN112800983 B CN 112800983B CN 202110138933 A CN202110138933 A CN 202110138933A CN 112800983 B CN112800983 B CN 112800983B
Authority
CN
China
Prior art keywords
sight
line
training
distance
random forest
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110138933.7A
Other languages
Chinese (zh)
Other versions
CN112800983A (en
Inventor
杨小凤
韦艳芳
王强
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.)
Yulin Normal University
Original Assignee
Yulin Normal University
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 Yulin Normal University filed Critical Yulin Normal University
Priority to CN202110138933.7A priority Critical patent/CN112800983B/en
Publication of CN112800983A publication Critical patent/CN112800983A/en
Application granted granted Critical
Publication of CN112800983B publication Critical patent/CN112800983B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Medical Informatics (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本发明公开了一种基于随机森林的非视距信号识别方法，涉及无线定位技术领域，解决现有定位方法实时性差、精度低的技术问题，所述方法为：构建由若干决策树构成的随机森林模型，依次测量目标节点到各个基站的接收信号r*(t)，将r*(t)的特征参数输入随机森林模型，得到目标节点与各个基站接收信号的视距/非视距识别结果，利用接收信号定位时可将识别为非视距的信号去掉。

The invention discloses a random forest-based non-line-of-sight signal identification method, relates to the field of wireless positioning technology, and solves the technical problems of poor real-time performance and low accuracy of existing positioning methods. The method is: constructing a random algorithm composed of several decision trees. The forest model measures the received signals r * (t) from the target node to each base station in sequence, inputs the characteristic parameters of r * (t) into the random forest model, and obtains the line-of-sight/non-line-of-sight identification results of the signals received by the target node and each base station. , signals identified as non-line-of-sight can be removed when positioning using received signals.

Description

Random forest-based non-line-of-sight signal identification method
Technical Field
The invention relates to the technical field of wireless positioning, in particular to a non-line-of-sight signal identification method based on a random forest.
Background
The wireless positioning (Wireless Localization) is widely applied to the fields of military, logistics, security, medical treatment, searching, rescue and the like. The positioning accuracy of the positioning system in a complex multipath, non-line-of-sight (NLOS) environment is improved, and the positioning accuracy is a research hotspot of wireless positioning based on Time-of-Arrival (TOA), and one of the key problems is non-line-of-sight signal identification.
Non-line-of-sight signal identification refers to identifying and removing non-line-of-sight measurements when there are more range measurements, and locating using only line-of-sight measurements. Currently, there are three main types of methods:
1) Based on the distance measurement method, according to the fact that the variance of the distance measurement value in the non-line-of-sight environment is larger than the variance of the distance measurement value in the line-of-sight environment, the variances of the distance measurement values are compared with a preset threshold value, the variances of the distance measurement values are larger than the threshold value, the non-line-of-sight signal can be judged, the line-of-sight signal can be judged when the variances of the distance measurement values are smaller than the threshold value, the method is suitable for static target positioning, when the target is in a dynamic state, the variance of the distance measurement value is increased, and the line-of-sight signal can be easily misjudged as the non-line-of-sight signal;
2) A method based on channel statistics, identifying non-line-of-sight signals by analyzing a cumulative distribution function of the magnitudes of the channel impulse responses, or by comparing the joint likelihood function values of kurtosis (kurtosis), average delay (mean excess delay) and root mean square delay (root mean square delay) of the channels with threshold values, but the definition of the decision threshold is ambiguous;
3) The channel is identified by the geographic geometry information of the environment, and the non-line-of-sight signal is identified by utilizing a ray tracing algorithm, so that the layout of the environment needs to be known in advance.
The above algorithms all belong to statistical methods, and the common disadvantages are: firstly, the prior distribution of the samples is generally required to be known in advance, and enough sample data needs to be collected, and the requirements are often difficult to achieve in practical application, and the algorithm real-time performance is not high; the feature joint probability distribution required by the algorithm (II) is sometimes difficult to determine and has poor stability.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a non-line-of-sight signal identification method based on a random forest, which has high real-time performance and good stability.
The technical scheme of the invention is as follows: a non-line-of-sight signal identification method based on random forests comprises the following steps:
s1, randomly selecting N training positions in a test area comprising 1 target node and A base stations, sequentially placing training communication nodes at the training positions, and measuring a received signal r of the training communication node from N epsilon N to K base stations at each training position n (t)，K＝1，2，…，A；
Respectively calculating r n 6 characteristic parameters of (t), comprising:
energy parameter e= +|r n (t)| 2 dt、
Maximum amplitude parameter r max ＝max r |r n (t)|、
Rise time parameter t rise ＝min t {t：|r n (t)|≥0.6r max }-min t {t：|r n (t)|≥6σ n }、
Average delay parameter
Root mean square delay parameter
Kurtosis parameter
Combining the 6 characteristic parameters into a characteristic set F= { e, r max ，t rise ，τ m ，τ r ，κ s R obtained by N positions n (t) forming a training input matrixBuilding training output matrix->Wherein y is n R is n The visual distance or non-visual distance identifying mark of (t), if identified as visual distance, y n =1, if it is recognized as non-line of sight, y n =0, resulting in a complete training set +.>
S2, measuring a received signal r from the target node to the base station * (t), and calculating r * 6 characteristic parameters of (t);
s3, constructing a random forest model formed by a plurality of decision trees, wherein for each decision tree: sampling N times from the complete training set D in a put-back sampling mode to form a training set D' of the decision tree, randomly selecting M characteristic parameters from the characteristic set F as the characteristic to be selected of the decision tree, wherein M is less than 6, calculating the Gini index of the characteristic to be selected, sequentially taking the characteristic to be selected as the splitting characteristics of the root node, the middle node and the leaf node of the decision tree according to the sequence from the small Gini index to the large Gini index,
wherein Gini (D ', f) is the classification of training set D' recognition into D according to the feature f to be selected 1 (apparent distance) and D 2 Gini index of two classes (non-line of sight), gini (D) i ) Is of the class D i Gini index, |d, of (i=1, 2) 1 |、|D 2 The I and the I D' I are respectively a set D 1 、D 2 The number of samples in D', p i Is of the class D i The probability of classification correctness and mistakes is identified;
s4, receiving the signal r by the target node * Inputting the feature parameters of (t) into the random forest model, and dividing each decision tree into a feature value area with each nodeComparing the range and outputting the vision distance/non-vision distance recognition category, wherein most of the judgment results of all decision trees are used as the final vision distance/non-vision distance recognition result of the base station;
s5, repeating the steps S1-S4 for the rest base stations in the test area to obtain the sight distance/non-sight distance recognition results of the signals received by the target node and each base station, and removing the signals recognized as non-sight distances when the received signals are used for positioning.
As a further improvement, A is more than or equal to 3.
Advantageous effects
Compared with the prior art, the invention has the advantages that:
the method of the invention uses non-line-of-sight signal recognition as a line-of-sight/non-line-of-sight two-category classification problem to process, adopts a machine learning method, namely a random forest to carry out recognition classification, wherein the random forest is a high-precision classifier comprising a plurality of decision trees, and the output category is determined by most of the categories output by each decision tree.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention will be further described with reference to specific embodiments in the drawings.
Referring to fig. 1, a non-line-of-sight signal identification method based on random forest includes the following steps:
s1, randomly selecting N training positions in a test area comprising 1 target node and A base stations, sequentially placing training communication nodes at the training positions, and measuring a received signal r of the training communication node from N epsilon N to K base stations at each training position n (t)，A≥3，K＝1，2，…，A；
Respectively calculating r n 6 characteristic parameters of (t), comprising:
energy parameter e= +|r n (t)| 2 dt、
Maximum amplitude parameter r max ＝max r |r n (t)|、
Rise time parameter t rise ＝min t {t：|r n (t)|≥0.6r max }-min t {t：|r n (t)|≥6σ n }、
Average delay parameter
Root mean square delay parameter
Kurtosis parameter
Combining 6 characteristic parameters into a characteristic set F= { e, r max ，t rise ，τ m ，τ r ，κ s R obtained by N positions n (t) forming a training input matrixBuilding training output matrix->Wherein y is n R is n The visual distance or non-visual distance identifying mark of (t), if identified as visual distance, y n =1, if it is recognized as non-line of sight, y n =0, resulting in a complete training set +.>
S2, measuring a received signal r from a target node to the base station * (t), and calculating r * 6 characteristic parameters of (t)；
S3, constructing a random forest model formed by a plurality of decision trees, wherein for each decision tree: sampling N times from the complete training set D in a sampling-back mode to form a training set D' of the decision tree, randomly selecting M characteristic parameters from the characteristic set F as the to-be-selected characteristics of the decision tree, wherein M is less than 6, calculating the Gini index of the to-be-selected characteristics, sequentially taking the to-be-selected characteristics as the splitting characteristics of the root node, the middle node and the leaf node of the decision tree according to the sequence from the small Gini index to the large Gini index,
wherein Gini (D ', f) is the classification of training set D' recognition into D according to the feature f to be selected 1 (apparent distance) and D 2 Gini index of two classes (non-line of sight), gini (D) i ) Is of the class D i Gini index, |d, of (i=1, 2) 1 |、|D 2 The I and the I D' I are respectively a set D 1 、D 2 The number of samples in D', p i Is of the class D i The probability of classification correctness and mistakes is identified;
s4, receiving the signal r by the target node * Inputting the characteristic parameters of (t) into a random forest model, comparing each decision tree with the split characteristic value interval range of each node, and outputting the vision distance/non-vision distance identification category of each decision tree, wherein most of the judgment results of all decision trees are used as the final vision distance/non-vision distance identification result of the base station;
s5, repeating the steps S1-S4 for other base stations in the test area to obtain the sight distance/non-sight distance recognition result of the signals received by the target node and each base station, and removing the signals recognized as non-sight distances when the received signals are used for positioning.
The method of the invention uses non-line-of-sight signal recognition as a line-of-sight/non-line-of-sight two-category classification problem to process, adopts a machine learning method, namely a random forest to carry out recognition classification, wherein the random forest is a high-precision classifier comprising a plurality of decision trees, and the output category is determined by most of the categories output by each decision tree.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present invention, and these do not affect the effect of the implementation of the present invention and the utility of the patent.

Claims (2)

1. A non-line-of-sight signal identification method based on random forests is characterized by comprising the following steps:
s1, randomly selecting N training positions in a test area comprising 1 target node and A base stations, sequentially placing training communication nodes at the training positions, and measuring received signals of the training communication nodes at each training position N ∊ N to the Kth base station，K=1,2,…,A；
Respectively calculating to obtainIs included in the set of 6 characteristic parameters:
energy parameter、
Maximum amplitude parameter、
Rise time parameter、
Average delay parameter、
Root mean square delay parameter、
Kurtosis parameter；
Combining the 6 characteristic parameters into a characteristic setN positions are taken +.>Composing training input matrix->Building training output matrix->Wherein->Is->Is a visual distance or non-visual distance identification mark, if the visual distance is identified, the step of +.>If it is recognized as non-line of sight, then +.>Obtaining the finished productWhole training set->；
S2, measuring the received signal from the target node to the base stationAnd calculate +.>Is set to 6 characteristic parameters;
s3, constructing a random forest model formed by a plurality of decision trees, wherein for each decision tree: from a complete training setSampling N times in a manner of put-back sampling to form training set +.>From feature set->Randomly selecting M characteristic parameters as the to-be-selected characteristics of the decision tree, M<6, calculating the Gini index of the feature to be selected, taking the feature to be selected as the splitting features of the root node, the middle node and the leaf node of the decision tree in sequence from small to large according to the Gini index,
，
，
wherein the method comprises the steps ofTo be according to the optional feature->Training set->Identification is divided into sight distance->And non-line of sight->Gini index of two classes, +.>For category->Gini index of->，、、Respectively set->、、The number of samples in>For category->The probability of classification correctness and mistakes is identified;
s4, receiving the signal from the target nodeInputting the characteristic parameters of the random forest model, comparing each decision tree with the split characteristic value interval range of each node, and outputting the sight distance/non-sight distance identification category of each decision tree, wherein most of the judgment results of all decision trees are used as the final sight distance/non-sight distance identification result of the base station;
s5, repeating the steps S1-S4 for the rest base stations in the test area to obtain the sight distance/non-sight distance recognition results of the signals received by the target node and each base station, and removing the signals recognized as non-sight distances when the received signals are used for positioning.
2. The random forest-based non-line-of-sight signal identification method of claim 1, wherein A is not less than 3.
CN202110138933.7A 2021-02-01 2021-02-01 A non-line-of-sight signal recognition method based on random forest Active CN112800983B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110138933.7A CN112800983B (en) 2021-02-01 2021-02-01 A non-line-of-sight signal recognition method based on random forest

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110138933.7A CN112800983B (en) 2021-02-01 2021-02-01 A non-line-of-sight signal recognition method based on random forest

Publications (2)

Publication Number Publication Date
CN112800983A CN112800983A (en) 2021-05-14
CN112800983B true CN112800983B (en) 2024-03-08

Family

ID=75813467

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110138933.7A Active CN112800983B (en) 2021-02-01 2021-02-01 A non-line-of-sight signal recognition method based on random forest

Country Status (1)

Country Link
CN (1) CN112800983B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12082147B2 (en) 2020-09-18 2024-09-03 Samsung Electronics Co., Ltd. Line of sight (LoS)/non-line of sight (NLoS) point identification in wireless communication networks using artificial intelligence
CN113382354B (en) * 2021-06-08 2022-04-22 东南大学 Wireless positioning non-line-of-sight signal discrimination method based on factor graph
CN113625319B (en) * 2021-06-22 2023-12-05 北京邮电大学 Non-line-of-sight signal detection method and device based on ensemble learning
CN115567126A (en) * 2022-09-30 2023-01-03 中国银行股份有限公司 Method and device for determining sight distance
CN116628579A (en) * 2023-03-29 2023-08-22 河海大学 An ECG signal recognition and diagnosis method based on compound machine learning
WO2024197735A1 (en) * 2023-03-30 2024-10-03 Mediatek Singapore Pte. Ltd. Model performance monitor mechanism for ai/ml assisted positioning
CN119575441B (en) * 2025-02-08 2025-04-22 肇庆市金鹏实业有限公司 GPS positioning and 4G communication service system of Internet of things equipment

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107124762A (en) * 2017-04-26 2017-09-01 玉林师范学院 A kind of wireless location method of efficient abatement non-market value
CN107273920A (en) * 2017-05-27 2017-10-20 西安交通大学 A kind of non-intrusion type household electrical appliance recognition methods based on random forest
CN107563437A (en) * 2017-08-31 2018-01-09 广州中海达定位技术有限公司 Ultra wide band non line of sight discrimination method based on random forest
CN107820206A (en) * 2017-11-15 2018-03-20 玉林师范学院 Non line of sight localization method based on signal intensity
KR20190110276A (en) * 2018-03-20 2019-09-30 한양대학교 산학협력단 Multi-sensor based noncontact sleep monitoring method and apparatus using ensemble of deep neural network and random forest
CN111257827A (en) * 2020-01-16 2020-06-09 玉林师范学院 High-precision non-line-of-sight tracking and positioning method
CN111832417A (en) * 2020-06-16 2020-10-27 杭州电子科技大学 Signal modulation pattern recognition method based on CNN-LSTM model and transfer learning
CN111916066A (en) * 2020-08-13 2020-11-10 山东大学 Random forest based voice tone recognition method and system
CN112245728A (en) * 2020-06-03 2021-01-22 北京化工大学 A method and system for recognizing false positive alarm signal of ventilator based on ensemble tree

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8306942B2 (en) * 2008-05-06 2012-11-06 Lawrence Livermore National Security, Llc Discriminant forest classification method and system
US20180260531A1 (en) * 2017-03-10 2018-09-13 Microsoft Technology Licensing, Llc Training random decision trees for sensor data processing

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107124762A (en) * 2017-04-26 2017-09-01 玉林师范学院 A kind of wireless location method of efficient abatement non-market value
CN107273920A (en) * 2017-05-27 2017-10-20 西安交通大学 A kind of non-intrusion type household electrical appliance recognition methods based on random forest
CN107563437A (en) * 2017-08-31 2018-01-09 广州中海达定位技术有限公司 Ultra wide band non line of sight discrimination method based on random forest
CN107820206A (en) * 2017-11-15 2018-03-20 玉林师范学院 Non line of sight localization method based on signal intensity
KR20190110276A (en) * 2018-03-20 2019-09-30 한양대학교 산학협력단 Multi-sensor based noncontact sleep monitoring method and apparatus using ensemble of deep neural network and random forest
CN111257827A (en) * 2020-01-16 2020-06-09 玉林师范学院 High-precision non-line-of-sight tracking and positioning method
CN112245728A (en) * 2020-06-03 2021-01-22 北京化工大学 A method and system for recognizing false positive alarm signal of ventilator based on ensemble tree
CN111832417A (en) * 2020-06-16 2020-10-27 杭州电子科技大学 Signal modulation pattern recognition method based on CNN-LSTM model and transfer learning
CN111916066A (en) * 2020-08-13 2020-11-10 山东大学 Random forest based voice tone recognition method and system

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
基于TOA估计的超宽带快速定位方法;杨小凤;陈铁军;陈宇宁;;现代雷达;20160315(第03期);全文 *
基于超宽带的TOA-DOA联合定位方法;杨小凤;陈铁军;黄志文;李琼;重庆邮电大学学报(自然科学版);20161231(第002期);全文 *
基于随机森林的建筑结构损伤识别方法;周绮凤;杨小青;周青青;雷家艳;振动、测试与诊断;20121231;第32卷(第2期);全文 *
基于随机森林的认知网络主用户信号调制类型识别算法;王鑫;汪晋宽;刘志刚;胡曦;东北大学学报. 自然科学版;20141231;第35卷(第12期);全文 *
基于随机森林的通信信号调制识别算法研究;谭正骄;CNKI;20181231;全文 *
高精度低复杂度的无线定位新方法;杨小凤;陈铁军;刘峰;计算机应用;20141231;第34卷(第002期);全文 *

Also Published As

Publication number Publication date
CN112800983A (en) 2021-05-14

Similar Documents

Publication Publication Date Title
CN112800983B (en) A non-line-of-sight signal recognition method based on random forest
CN111832417B (en) Signal modulation pattern recognition method based on CNN-LSTM model and transfer learning
CN108769969B (en) An RFID Indoor Localization Method Based on Deep Belief Network
US20200374720A1 (en) Method for Detecting Abnormal Data in Sensor Network
CN103413145B (en) Intra-articular irrigation method based on depth image
CN107124762B (en) Wireless positioning method for efficiently eliminating non-line-of-sight errors
CN111079859B (en) A Passive Multi-Site Multi-Target DF Cross-Location and False Point Removal Method
CN104765768A (en) Mass face database rapid and accurate retrieval method
CN111352087B (en) Passive MIMO radar multi-target positioning method based on DBSCAN
CN106851573A (en) Joint weighting k nearest neighbor indoor orientation method based on log path loss model
CN103874200A (en) Floor recognition method and system
CN112135248B (en) WIFI fingerprint positioning method based on K-means optimal estimation
CN106851571A (en) WiFi localization methods in a kind of quick KNN rooms based on decision tree
CN103954935A (en) Radar signal sorting method under minimum L1 bound norm
CN116466314A (en) A radar individual sorting method, device, storage medium and equipment
CN113269825A (en) Forest breast diameter value extraction method based on foundation laser radar technology
CN111405461B (en) Wireless indoor positioning method for optimizing equal-interval fingerprint sampling number
CN115017958B (en) Non-line-of-sight signal identification method based on channel characteristic weighting model
CN110222776A (en) A kind of indoor Passive Location based on CSI finger print information
CN114584497A (en) Passive industrial control system asset identification method and device
CN108663675A (en) The method positioned simultaneously for life detection radar array multiple target
CN111950616B (en) Acoustic signal non-line-of-sight recognition method and device based on unsupervised online learning
CN111310680A (en) Radiation source individual identification method based on deep learning
CN112990125B (en) A method for discriminating whether a radiation source radar belongs to a target platform
Cheng et al. A fingerprint localization method based on weighted KNN algorithm

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
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210514

Assignee: Jingwei Intelligent Technology (Shanghai) Co.,Ltd.

Assignor: Yulin Normal University

Contract record no.: X2024450000003

Denomination of invention: A Non line of sight Signal Recognition Method Based on Random Forest

Granted publication date: 20240308

License type: Common License

Record date: 20240815