CN108776817A - The type prediction method and system of the attack of terrorism - Google Patents
The type prediction method and system of the attack of terrorism Download PDFInfo
- Publication number
- CN108776817A CN108776817A CN201810564043.0A CN201810564043A CN108776817A CN 108776817 A CN108776817 A CN 108776817A CN 201810564043 A CN201810564043 A CN 201810564043A CN 108776817 A CN108776817 A CN 108776817A
- Authority
- CN
- China
- Prior art keywords
- attack
- terrorism
- type
- attribute
- algorithm
- 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
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Abstract
Present disclose provides a kind of type prediction method and system of attack of terrorism, wherein this method includes:Obtain the attribute of the attack of terrorism;Multiple sort operations are executed to the attack of terrorism based on the attribute of the attack of terrorism, to obtain multiple classification results;And multiple classification results are combined, to determine the type of the attack of terrorism.
Description
Technical field
This disclosure relates to a kind of type prediction method and system of attack of terrorism.
Background technology
After " 911 " event, the gloom whole world of the attack of terrorism.Although each state all increases prevention and control dynamics, terrified
Attack is not far from people's lives.Largely with the pass that implies various profound levels in the relevant data of the attack of terrorism
Connection and rule, these hiding phenomenons can effectively instruct the building-up work of anti-terrorism early warning system, help to solve anti-terrorism decision
In knotty problem, carry out rule identification and prediction.However, during predicting attack of terrorism big data, there is classification
The problem that False Rate is high, precision of prediction is low is operated, it is inefficient so as to cause anti-terrorism early warning system.
Invention content
In order to solve at least one above-mentioned technical problem, in the first aspect, present disclose provides a kind of attack of terrorism things
The type prediction method of part comprising:
Obtain the attribute of the attack of terrorism;
Multiple sort operations are executed to the attack of terrorism based on the attribute of the attack of terrorism, are tied with obtaining multiple classification
Fruit;And
Multiple classification results are combined, to determine the type of the attack of terrorism.
In some embodiments, multiple sort operations are executed to the attribute of the attack of terrorism, to obtain multiple classification
As a result the step of includes:Pass through K nearest neighbour classifications algorithm, decision tree C4.5 sorting algorithm, bootstrapping convergence method sorting algorithm and branch
It holds vector machine sorting algorithm and multiple sort operations is executed to the attribute of the attack of terrorism respectively, to obtain multiple classification results.
In some embodiments, multiple classification results are combined, to determine the type of the attack of terrorism
Step includes:
Multiple classification results are combined with predefined weight, and the attack type with maximum probability is determined as terror
The type of attack.
In some embodiments, this method further includes:
Training data set is provided;
Multiple sort operations are executed to training data set, to obtain training type;And
Based on obtained training type, the weight of multiple sort operations is determined respectively by genetic algorithm.
In some embodiments, this method further includes:The operator of genetic algorithm is selected using roulette mode.
In some embodiments, this method further includes:The two-point crossover probability that genetic algorithm is arranged is 0.7.
In some embodiments, this method further includes:The single-point mutation probability that genetic algorithm is arranged is 0.1.
In some embodiments, the type of the attack of terrorism is selected from following one:Assassination, kidnapping, armed attack, misfortune
It holds, the destruction of roadblock, infrastructure, manually attack, exploding and is unknown.
In some embodiments, the attribute of the attack of terrorism includes:The city of the attack of terrorism occurs, generation terror is attacked
The area hit terroristic organization's title, weapon type, causes damages, whether generates ransom money.
In second aspect, present disclose provides a kind of type prediction systems of attack of terrorism, including:
Processor;
Memory is stored with the computer-readable instruction that can be executed by processor, and is performed in computer-readable instruction
When, processor executes following operation:
Obtain the attribute of the attack of terrorism;
Multiple sort operations are executed to the attack of terrorism based on the attribute of the attack of terrorism, are tied with obtaining multiple classification
Fruit;And
Multiple classification results are combined, to determine the type of the attack of terrorism.
Description of the drawings
Attached drawing shows the illustrative embodiments of the disclosure, and it is bright together for explaining the principles of this disclosure,
Which includes these attached drawings to provide further understanding of the disclosure, and attached drawing is included in the description and constitutes this
Part of specification.
Fig. 1 shows the schematic stream of the type prediction method of the attack of terrorism according to the disclosure some embodiments
Cheng Tu.
Fig. 2 shows the processes according to the weight of the determination sort operation of disclosure embodiment.
Fig. 3 shows the weight for determining sort operation by genetic algorithm according to the disclosure at least one embodiment
Schematic flow chart.
Fig. 4 shows the type prediction method for being adapted for carrying out the attack of terrorism according to the disclosure some embodiments
The structural schematic diagram of computer system.
Specific implementation mode
The disclosure is described in further detail with embodiment below in conjunction with the accompanying drawings.It is understood that this place
The specific implementation mode of description is only used for explaining related content, rather than the restriction to the disclosure.It also should be noted that being
Convenient for description, illustrated only and the relevant part of the disclosure in attached drawing.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the disclosure can
To be combined with each other.The disclosure is described in detail below with reference to the accompanying drawings and in conjunction with embodiment.
Fig. 1 shows the signal of the type prediction method 100 of the attack of terrorism according to the disclosure some embodiments
Property flow chart.As shown in Figure 1, method 100 includes:
S101 obtains the attribute of the attack of terrorism;
S102 executes multiple sort operations based on the attribute of the attack of terrorism to the attack of terrorism, multiple to obtain
Classification results;And
S103 is combined multiple classification results, to determine the type of the attack of terrorism.
The attribute for the attack of terrorism being previously mentioned in step S101 may include but be not limited to:City (attacking spot),
Specific area (class variable represents the specific area for probably attacking generation), terroristic organization's title (to probably attacking responsible tissue), weapon
Type causes damages, whether generates ransom money.
In step s 102, attribute of each sort operation based on the attack of terrorism determines the attack of terrorism
Type is with the probability of one of Types Below:Assassination, kidnapping, armed attack, abduction, roadblock, infrastructure destroy, manually attack,
Explosion is unknown.Each sort operation can determine that the type of the attack of terrorism is the probability of one of the above-mentioned type.
In the disclosure, above-mentioned sort operation can classify (K-nearest Neighbor, K-NN) based on k nearest neighbor
The sort operation of algorithm, is based on the sort operation based on support vector machines (Support Vector Machine, SVM) algorithm
Naive Bayesian (Bayesian) sort operation of algorithm, the sort operation based on decision tree C4.5 algorithm, be based on two
The sort operation of secondary discriminant analysis (Quadratic Discriminant Analysis, QAD) algorithm is divided based on linear discriminant
Analyse the sort operation of (Linear Discriminant Analysis, LDA) algorithm, based on reconstruct discriminant analysis
The sort operation of (Reconstructive Discriminant Analysis, RDA) algorithm is based on Bagging
The sort operation of (Bootstrap aggregating) algorithm.In an illustrative embodiments of the disclosure, step S102
In can pass through K nearest neighbour classifications algorithm, decision tree C4.5 sorting algorithm, bootstrapping convergence method sorting algorithm and support vector cassification
Algorithm executes sort operation to the attribute of the attack of terrorism respectively, to obtain four classification results, wherein each sort operation
The type that obtained classification results indicate the attack of terrorism is with the probability of one of Types Below:Assassination, kidnapping, force
Fill attack, abduction, roadblock, infrastructure destruction, manually attack, explosion or unknown.
In step s 103, it obtained classification results will be combined in step s 102, to determine that the terror is attacked
Hit the type of event.In some embodiments of the disclosure, step S103 may include:By multiple classification results with predefined weight
It is combined, and the attack type with maximum probability is determined as to the type of the attack of terrorism.
The process of the weight of determination sort operation according to disclosure embodiment is described below in conjunction with Fig. 2.Such as Fig. 2
It is shown, it may include according to the process 200 of the weight of the determination sort operation of disclosure embodiment:
S201 provides training data set;
S202 executes multiple sort operations to training data set, to obtain training type;And
S203 determines the weight of multiple sort operation by genetic algorithm respectively based on obtained training type.
Process 200 is carried out explanation is explained in greater detail with reference to a specific example.
In step s 201, training data set D, D={ (an x is providedi,yi), i=1,2 ... I }, training herein
Data acquisition system D refer to built from University of Maryland global terrorism database (Global Terrorism Database,
GTD by the data of data prediction (that is, 45221 with complete 7 attributes are probably attacked record) in), x represents mentioned above
Arrive 7 kinds input attributes, including city, area, attack type, terroristic organization's title, weapon type, cause damages, whether produce
Raw ransom money.Y indicates corresponding output attribute (prediction attribute), i.e. attack of terrorism type (Attack Type), and I is trained
Data count (I=45221).
In step S202, K nearest neighbour classifications algorithm, decision tree C4.5 sorting algorithm, bootstrapping convergence method classification can be passed through
Algorithm and support vector cassification algorithm execute sort operation to training data set respectively.Optionally, from training data set D
In isolate a part of sample, and handled using four kinds of above-mentioned sort operations.The sample data only separated is used
Learn in the distribution of each sort operation weight, can effectively reduce the time of genetic algorithm training optimization weight in this way.
The combination of sort operation is represented byWherein, AkIndicate kth kind sort operation, feature vector wkTable
Show the weight of distribution.Distribution weight is optimized using genetic algorithm in step S203, n node is given by probability assignments
The mathematical model formula 1 that different classifications operation is classified indicates as follows, whereinIt indicates using classification behaviour
Make the probability that i is trained sample data set, wkIndicate the weight of corresponding probability assignments,
The syncretizing mechanism that hybrid classification operates learning outcome is established with genetic algorithm, generates point with highest prediction precision
Generic operation combines.As shown in figure 3, genetic algorithm is related to the setting of multiple object functions, including population definition, Population Size,
Intersect and the rule etc. that makes a variation.In this research, population defines the weight vector that each chromosome includes each sort operation, and summation
It is 1;Population Size (popsize=20%) simultaneously uses roulette mode selection opertor;Using two-point crossover rule, crossover probability
It is 0.7;It is made a variation using single-point, mutation probability 0.1.
By determining that the process 200 of the weight of sort operation determines that the weight of each sort operation is as shown in table 2 below:
Sort operation | Weight |
SVM | 0.138577600742077 |
BAGGING | 0.439491309912032 |
C4.5 | 0.39946895924973 |
KNN | 0.02246213009616 |
Weight distribution in the combination of 2 sort operation of table
Lower section table 3 illustrates type prediction method and single classification according to the attack of terrorism of disclosure embodiment
The precision of prediction of operation compares.It can be seen that the type prediction method precision of prediction of the attack of terrorism is best (94%).For
Single sort operation, Bagging (91.5%) and C4.5 (90.5%) performance are close, and SVM (88.5%) effect is slightly worse, and KNN
(83%) then worst.
Prediction technique | Precision of prediction (%) |
SVM | 88.5 |
BAGGING | 91.5 |
C4.5 | 90.5 |
KNN | 83 |
Sort operation combines | 94 |
The precision of prediction comparison that 3 independent sort operation of table is combined with sort operation
Below with reference to Fig. 4, it illustrates suitable for for realizing that the type of the attack of terrorism of disclosure embodiment is pre-
The structural schematic diagram of the computer system 400 of survey method.
As shown in figure 4, computer system 400 includes central processing unit (CPU) 401, it can be read-only according to being stored in
Program in memory (ROM) 402 or be loaded into the program in random access storage device (RAM) 403 from storage section 408 and
Execute various actions appropriate and processing.In RAM 403, also it is stored with system 400 and operates required various programs and data.
CPU 401, ROM 402 and RAM 403 are connected with each other by bus 404.Input/output (I/O) interface 405 is also connected to always
Line 404.
It is connected to I/O interfaces 405 with lower component:Importation 406 including keyboard, mouse etc.;It is penetrated including such as cathode
The output par, c 407 of spool (CRT), liquid crystal display (LCD) etc. and loud speaker etc.;Storage section 408 including hard disk etc.;
And the communications portion 409 of the network interface card including LAN card, modem etc..Communications portion 409 via such as because
The network of spy's net executes communication process.Driver 410 is also according to needing to be connected to I/O interfaces 405.Detachable media 411, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on driver 410, as needed in order to be read from thereon
Computer program be mounted into storage section 408 as needed.
Particularly, according to embodiment of the present disclosure, it is soft to may be implemented as computer above with reference to Fig. 1 processes described
Part program.For example, embodiment of the present disclosure includes a kind of computer program product comprising be tangibly embodied in machine readable
Computer program on medium, the computer program include the program code of the method for executing Fig. 1.In such embodiment party
In formula, which can be downloaded and installed by communications portion 409 from network, and/or from detachable media 411
It is mounted.
Flow chart in attached drawing and block diagram, it is illustrated that according to system, method and the computer of the various embodiments of the present invention
The architecture, function and operation in the cards of program product.In this regard, each box in flowchart or block diagram can be with
Represent a part for a module, program segment, or code, the part of above-mentioned module, program segment, or code include one or
Multiple executable instructions for implementing the specified logical function.It should also be noted that in some implementations as replacements, box
Middle marked function can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated
It can essentially be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.
It is also noted that the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart, it can
It is realized with the dedicated hardware based systems of the functions or operations as defined in execution, or specialized hardware can be used and calculated
The combination of machine instruction is realized.
As on the other hand, the disclosure additionally provides a kind of computer readable storage medium, the computer-readable storage medium
Matter can be computer readable storage medium included in server in the above embodiment;Can also be individualism, not
The computer readable storage medium being fitted into equipment.There are one computer-readable recording medium storages or more than one journey
Sequence, the type which is used for executing the attack of terrorism for being described in the disclosure by one or more than one processor are pre-
Survey method.
It will be understood by those of skill in the art that the above embodiment is used for the purpose of clearly demonstrating the disclosure, and simultaneously
Non- be defined to the scope of the present disclosure.For those skilled in the art, may be used also on the basis of disclosed above
To make other variations or modification, and these variations or modification are still in the scope of the present disclosure.
Claims (10)
1. a kind of type prediction method of attack of terrorism, which is characterized in that the method includes:
Obtain the attribute of the attack of terrorism;
Attribute based on the attack of terrorism executes multiple sort operations to the attack of terrorism, to obtain multiple points
Class result;And
The multiple classification results are combined, to determine the type of the attack of terrorism.
2. according to the method described in claim 1, it is characterized in that, the attribute to the attack of terrorism executes multiple classification
Operation, to obtain multiple classification results the step of include:Pass through K nearest neighbour classifications algorithm, decision tree C4.5 sorting algorithm, bootstrapping
Convergence method sorting algorithm and support vector cassification algorithm execute multiple classification to the attribute of the attack of terrorism respectively and grasp
Make, to obtain the multiple classification results.
3. according to the method described in claim 1, it is characterized in that, being combined to the multiple classification results, to determine
The step of type of the attack of terrorism includes:
The multiple classification results are combined with predefined weight, and the attack type with maximum probability are determined as described
The type of the attack of terrorism.
4. according to the method described in claim 1, it is characterized in that, the method further includes:
Training data set is provided;
The multiple sort operation is executed to the training data set, to obtain training type;And
Based on the obtained trained type, the weight of the multiple sort operation is determined respectively by genetic algorithm.
5. according to the method described in claim 4, it is characterized in that, the method further includes:Institute is selected using roulette mode
State the operator of genetic algorithm.
6. according to the method described in claim 4, it is characterized in that, the method further includes:It is arranged the two of the genetic algorithm
Point crossover probability is 0.7.
7. according to the method described in claim 4, it is characterized in that, the method further includes:The list of the genetic algorithm is set
Point mutation probability is 0.1.
8. according to the method described in claim 1, it is characterized in that, the type of the attack of terrorism is selected from following one:
Assassination, kidnapping, armed attack, abduction, roadblock, infrastructure destroy, manually attack, explosion and it is unknown.
9. according to the method described in claim 1, it is characterized in that, the attribute of the attack of terrorism includes:Occur terrified
The city of attack, terroristic organization's title, weapon type, causes damages, whether generates ransom money at the area that the attack of terrorism occurs.
10. a kind of type prediction system of attack of terrorism, including:
Processor;
Memory is stored with the computer-readable instruction that can be executed by the processor, in the computer-readable instruction quilt
When execution, the processor executes following operation:
Obtain the attribute of the attack of terrorism;
Attribute based on the attack of terrorism executes multiple sort operations to the attack of terrorism, to obtain multiple points
Class result;And
The multiple classification results are combined, to determine the type of the attack of terrorism.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810564043.0A CN108776817A (en) | 2018-06-04 | 2018-06-04 | The type prediction method and system of the attack of terrorism |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810564043.0A CN108776817A (en) | 2018-06-04 | 2018-06-04 | The type prediction method and system of the attack of terrorism |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108776817A true CN108776817A (en) | 2018-11-09 |
Family
ID=64025685
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810564043.0A Pending CN108776817A (en) | 2018-06-04 | 2018-06-04 | The type prediction method and system of the attack of terrorism |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108776817A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109685321A (en) * | 2018-11-26 | 2019-04-26 | 山东师范大学 | Event risk method for early warning, electronic equipment and medium based on data mining |
CN109784525A (en) * | 2018-11-13 | 2019-05-21 | 北京码牛科技有限公司 | Method for early warning and device based on day vacant lot integration data |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101673280A (en) * | 2009-07-20 | 2010-03-17 | 浙江大学 | Method for determining terror attack organization based on feature mining of terror attack event |
US20130070976A1 (en) * | 2005-09-28 | 2013-03-21 | Facedouble, Inc. | Image Classification And Information Retrieval Over Wireless Digital Networks And The Internet |
CN105608460A (en) * | 2014-11-24 | 2016-05-25 | 中国电信股份有限公司 | Method and system for fusing multiple classifiers |
CN105956982A (en) * | 2016-05-04 | 2016-09-21 | 江苏大学 | Method of predicting act of terror based on background change |
CN106776884A (en) * | 2016-11-30 | 2017-05-31 | 江苏大学 | A kind of act of terrorism Forecasting Methodology that multi-categorizer is combined based on multi-tag |
CN106973038A (en) * | 2017-02-27 | 2017-07-21 | 同济大学 | Network inbreak detection method based on genetic algorithm over-sampling SVMs |
CN107704952A (en) * | 2017-09-19 | 2018-02-16 | 中国电子科技集团公司第二十八研究所 | A kind of attack of terrorism Forecasting Methodology based on stochastic subspace |
-
2018
- 2018-06-04 CN CN201810564043.0A patent/CN108776817A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130070976A1 (en) * | 2005-09-28 | 2013-03-21 | Facedouble, Inc. | Image Classification And Information Retrieval Over Wireless Digital Networks And The Internet |
CN101673280A (en) * | 2009-07-20 | 2010-03-17 | 浙江大学 | Method for determining terror attack organization based on feature mining of terror attack event |
CN105608460A (en) * | 2014-11-24 | 2016-05-25 | 中国电信股份有限公司 | Method and system for fusing multiple classifiers |
CN105956982A (en) * | 2016-05-04 | 2016-09-21 | 江苏大学 | Method of predicting act of terror based on background change |
CN106776884A (en) * | 2016-11-30 | 2017-05-31 | 江苏大学 | A kind of act of terrorism Forecasting Methodology that multi-categorizer is combined based on multi-tag |
CN106973038A (en) * | 2017-02-27 | 2017-07-21 | 同济大学 | Network inbreak detection method based on genetic algorithm over-sampling SVMs |
CN107704952A (en) * | 2017-09-19 | 2018-02-16 | 中国电子科技集团公司第二十八研究所 | A kind of attack of terrorism Forecasting Methodology based on stochastic subspace |
Non-Patent Citations (3)
Title |
---|
HAOWEN MO 等: "Terrorist Event Prediction Based on Revealing Data", 《2017 IEEE 2ND INTERNATIONAL CONFERENCE ON BIG DATA ANALYSIS 》 * |
王锂达: "恐怖组织行为挖掘与预测", 《中国优秀硕士学位论文全文数据库 社会科技I辑》 * |
陈泉浈: "基于迁移学习的恐怖行为预测算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109784525A (en) * | 2018-11-13 | 2019-05-21 | 北京码牛科技有限公司 | Method for early warning and device based on day vacant lot integration data |
CN109685321A (en) * | 2018-11-26 | 2019-04-26 | 山东师范大学 | Event risk method for early warning, electronic equipment and medium based on data mining |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200167466A1 (en) | Data type recognition, model training and risk recognition methods, apparatuses and devices | |
Ramos et al. | New insights on nontechnical losses characterization through evolutionary-based feature selection | |
US11790237B2 (en) | Methods and apparatus to defend against adversarial machine learning | |
Alsheref et al. | Automated prediction of employee attrition using ensemble model based on machine learning algorithms | |
CN109190379A (en) | A kind of leak detection method and device of deep learning system | |
Shi et al. | Active deep learning attacks under strict rate limitations for online API calls | |
Aljanabi et al. | Improved TLBO-JAYA algorithm for subset feature selection and parameter optimisation in intrusion detection system | |
CN112149609A (en) | Black box anti-sample attack method for electric energy quality signal neural network classification model | |
CN109840413A (en) | A kind of detection method for phishing site and device | |
CN115563610B (en) | Training method, recognition method and device for intrusion detection model | |
CN108776817A (en) | The type prediction method and system of the attack of terrorism | |
Yin et al. | An empirical study on the performance of cost-sensitive boosting algorithms with different levels of class imbalance | |
CN110020868B (en) | Anti-fraud module decision fusion method based on online transaction characteristics | |
Pristyanto et al. | The effect of feature selection on classification algorithms in credit approval | |
US8301584B2 (en) | System and method for adaptive pruning | |
Niranjan et al. | EBJRV: an ensemble of Bagging, J48 and random committee by voting for efficient classification of intrusions | |
US20220129789A1 (en) | Code generation for deployment of a machine learning model | |
Chkirbene et al. | Data augmentation for intrusion detection and classification in cloud networks | |
de Melo et al. | Using complexity measures to evolve synthetic classification datasets | |
Ghomeshi et al. | RED-GENE: An evolutionary game theoretic approach to adaptive data stream classification | |
Herrera-Semenets et al. | A framework for intrusion detection based on frequent subgraph mining | |
Younas | Anomaly Detection using Data Mining Techniques: A Review | |
Sanguanmak et al. | Auto-tuning of parameters in hybrid sampling method for class imbalance problem | |
He et al. | A novel multi-stage ensemble model for credit scoring based on synthetic sampling and feature transformation | |
Liang et al. | ASE: Anomaly scoring based ensemble learning for highly imbalanced datasets |
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: 20181109 |