CN103310248A - Optimized RFID (Radio Frequency Identification) network system based on particle swarm algorithm - Google Patents

Optimized RFID (Radio Frequency Identification) network system based on particle swarm algorithm Download PDF

Info

Publication number
CN103310248A
CN103310248A CN2013101718838A CN201310171883A CN103310248A CN 103310248 A CN103310248 A CN 103310248A CN 2013101718838 A CN2013101718838 A CN 2013101718838A CN 201310171883 A CN201310171883 A CN 201310171883A CN 103310248 A CN103310248 A CN 103310248A
Authority
CN
China
Prior art keywords
read write
particle
network
write line
rfid
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
Application number
CN2013101718838A
Other languages
Chinese (zh)
Inventor
张军
龚月姣
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.)
Sun Yat Sen University
National Sun Yat Sen University
Original Assignee
National Sun Yat Sen 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 National Sun Yat Sen University filed Critical National Sun Yat Sen University
Priority to CN2013101718838A priority Critical patent/CN103310248A/en
Publication of CN103310248A publication Critical patent/CN103310248A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • Y02B60/50—

Landscapes

  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)

Abstract

The invention discloses an RFID (Radio Frequency Identification) network system based on a particle swarm optimization algorithm. The RFID network system based on the particle swarm optimization algorithm is used for providing an intelligent solution for the needs on monitoring and positioning in applications, such as logistics and supply management, production manufacturing and assembly and document tracking/library management. The RFID network system has the advantages that the problem in the past that network blind spots may exist in an artificially-designed network is solved, the coverage and identification efficiency of an RFID network are increased, and the cost is decreased. According to the RFID network system based on the particle swarm optimization algorithm, a redundant node elimination mechanism is introduced based on a standard particle swarm optimization algorithm, so that the number of readers/writers configured for the network can be adjusted dynamically during optimization, and then, the maximized coverage of the network is achieved by adopting minimal readers/writers; meanwhile, the positions of mobile readers/writers in a monitoring environment and the transmitting power of the mobile readers/writers are adjusted dynamically through an algorithm coding strategy so as to reduce interference caused by reader/writer signal overlapping and save energy; and through embedded variation operation, the global optimum characteristics of the system are further improved so as to strive to construct a complete RFID system.

Description

Optimization RFID network system based on particle cluster algorithm
Technical field:
The present invention relates to intelligence computation and radio frequency identification (RFID) two big fields, a kind of particle swarm optimization algorithm of eliminating mechanism with redundant node of main use is arranged by the node in the RFID network and the power emission problem is optimized, thereby forms the intelligentized RFID network system of a cover.
Background technology:
Radio RF recognition technology (RFID) is an automatic identification technology that develops rapidly in recent years, has attracted the concern from industry member and industrial community.Be accredited as one of technology of big tool contribution of 21st century ten, the RFID technology is expected to be widely used in every field, as logistics, supply chain management, asset management, false proof etc.A typical rfid system is made up of three parts: (1) RF label, and it is a kind of miniature electric data load bearing equipment, is pasted and pays on the article of needs monitoring and identification; (2) read write line, it transmits and receive data by the direction of signal label of radio frequency; (3) host computer system, it is responsible for handling and distributing data.
Because the limited query scope of communicating by letter between read write line and the label, a RFID network system need be arranged a plurality of read write lines.This has caused some problems when disposing the RFID network, for example, should arrange where what read write lines, these read write lines be placed on respectively, the emissive power of each read write line should be set to much.RFID network planning problem is the major issue that RFID uses, and also is a difficult task, because it must satisfy many requirements, and for example coverage, service quality (QoS) and cost efficiency.The way of manual test debug expended time in and manpower very much repeatedly in the past.In addition, be that human eye is sightless because radio signal is propagated, the performance of RFID network system is difficult to quantitatively and qualitative evaluation.Along with the development of computer technology and automatic technology, loaded down with trivial details manual method certainly will will be calculated replacement by science.In addition, because the network system design problem of RFID has comprised the minimal set covering problem of NP difficulty as subproblem, it also is the NP difficulty, because its problem complexity, traditional mathematical method and deterministic computerized algorithm can't solve large-scale RFID network system deployment issue in the practical application in acceptable time.
Summary of the invention:
Covering the defective that aspects such as efficient, service quality and cost consumption exist in order to overcome existing network design, the present invention proposes a kind of optimization RFID network system based on particle swarm optimization algorithm, use intelligentized method, successively consider the maximization network coverage rate, minimize the read write line interstitial content, reduce signal interference and four important goals of energy efficient, realize the intelligentized RFID network system of a cover, satisfy various application demands.
The technical solution adopted for the present invention to solve the technical problems is:
(1) adopt the particle swarm optimization algorithm with global optimization characteristic to carry out node deployment in the RFID network.The group behavior of this algorithm simulation flock of birds or the shoal of fish, each particle have a dynamic speed flies in problem space, and according to self prior imformation and the historical experience of the colony size and Orientation of regulating the speed.In this way, particle colony gathers the optimal region in the search volume gradually, and constantly near global optimum's point, and have the algorithm clear concept, advantages such as iterative process is simple, search efficiency is high, strong robustness.
(2) position and the emissive power with each read write line is encoded in the particle position information as control variable.Suppose to have N read write line, each particle position is a 3N dimension real number vector so, wherein 2N dimension element is used for representing the coordinate position of N read write line in the 2D working environment, and N dimension element is used for representing the emissive power of each read write line in addition, and it determines the query scope of read write line.
(3) embed a kind of " node is interim to be eliminated and recovery " mechanism (TRE), dynamically adjust the read write line quantity in the network.Under the prerequisite of current network coverage rate arrival 100%, from network, delete this read write line after the archival of information of that read write line that TRE is minimum with covering number of tags in the network.This moment, the coverage rate of network may reduce.By position and the emissive power of particle swarm optimization algorithm dynamic adjustments residue read write line, if the network coverage can reach 100% at short notice again, so current read write line node is eliminated operation and is considered to be permanent; Otherwise TRE will recover the deleted read write line that falls.Simultaneously, in particle swarm optimization algorithm, embed mutation operator to prevent the precocious convergence of population body.
(4) adopt a kind of mechanism of hierarchical priority to handle maximization network coverage rate in the network, minimize the read write line interstitial content, reduce signal interference and four targets of energy efficient.When carrying out the individual optimal location of particle and the position renewal of global optimum of colony, above four targets are compared successively according to priority, win in certain target up to the current location of particle.In this way, both guarantee network quality, saved cost and energy consumption again.
The invention has the beneficial effects as follows: (1) is disposed the RFID network all sidedly, dynamically regulates quantity, coordinate and the emission parameter of read write line in optimizing process; (2) consider covering efficient, cost efficiency, service indication and the energy consumption index of rfid system simultaneously, build optimized intelligent RFID network system.
Description of drawings:
Figure disposes process flow diagram based on the optimization RFID network system of particle cluster algorithm
Embodiment:
Accompanying drawing has provided the process flow diagram that system disposes.The embodiment of whole algorithm is described below:
1. particle is encoded
Each particle position is described to a D=3N MaxThe real number vector of dimension, wherein N MaxIt is the sum that can be arranged all read write lines in the network.In this description, 2N MaxDimension represents N MaxThe coordinate position of individual read write line in two-dimentional work space, N in addition MaxThe emissive power of each read write line of dimension expression is determining the query scope.Therefore, i particle position in the colony turned to by form:
X i = [ x i 1 , y i 1 , p i 1 , x i 2 , y i 2 , p i 2 , . . . , x i N max , y i N max , p i N max ] - - - ( 1 )
Wherein
Figure BSA00000892911500032
With
Figure BSA00000892911500033
Coordinate and the emissive power of representing k read write line respectively.
Notice the read write line number N of actual arrangement in network rBe not encoded in each particle position.The substitute is whole particle colony and safeguarding a N MaxBoolean's switch vector of dimension
Figure BSA00000892911500034
Each on wherein k∈ 0,1} (k=1,2 ..., N Max) whether k read write line of expression actual is arranged to (whether it is redundant node) in the network.So, we obtain
Figure BSA00000892911500035
Upgrade in the TRE operation that this boolean's switch vector ON will describe in the back.
2. initialization
In initialization procedure, all particle position all generate at random, namely each
Figure BSA00000892911500036
Be in the work space a random point, each
Figure BSA00000892911500037
It is a random value in the read write line emissive power scope.Simultaneously, boolean's switch vector is set to ON=[1, and 1 ..., 1], all N when it is illustrated in init state MaxIndividual read write line all will be arranged in the network.In addition, the historical optimal location of each particle is set to its current location, and the optimal location of whole colony is configured to best that in current all particle positions.
3. adaptive value assessment
Considering four indexs when the adaptive value of particle is assessed, is respectively maximization label coverage rate COV, minimizes the read write line number N r, the overlapping interference of minimum signal ITF, and minimize total emissive power POW, they are defined by following formula:
COV＝∑ t∈TSCv(t)/N t×100％，
Figure BSA00000892911500041
N r＝|RS|＝N max-N red. (3)
ITF＝∑ t∈TSγ(t)，γ(t)＝∑PT r，t-max{PT r，t}，r∈RS∧PT r，t≥T t (4)
POW＝∑ r∈RSPS r (5)
Wherein TS is the set of label in the network, N t=| TS| is number of tags in the network; RS is the set of the read write line that using in the network; PT represents the power from read write line that label receives, and PR represents the reflective power from label that read write line receives, T tAnd T rIt is respectively the signal sensitivity threshold value of label and read write line; N RedIt is the redundant read write line number of finding in the network; PS is the emissive power of read write line.
The evaluation process of each particle is as follows:
The first step: calculate the label coverage rate COV of each particle current location correspondence, read write line number N according to formula (2)-(5) r, signal overlap disturbs ITF and total emissive power POW.
Second step: if current C OV jumped to for the 6th step greater than the historical optimum COV of particle; If two values equate, continued for the 3rd step; Otherwise, finish evaluation process.
The 3rd step: if current N rLess than the historical optimal N of particle r, jumped to for the 6th step; If two values equate, continued for the 4th step; Otherwise, finish evaluation process.
The 4th step: if current I TF jumped to for the 6th step less than the historical optimum ITF of particle; If two values equate, continued for the 5th step; Otherwise, finish evaluation process.
The 5th step: if current POW jumped to for the 6th step less than the historical optimum POW of particle; Otherwise, finish evaluation process.
The 6th step: the historical optimal location of particle is set to the current location of particle.
The 7th step: the global optimum position of upgrading whole colony according to similar step.
4. particle rapidity and position are upgraded
Each particle i upgrades its speed according to following formula
Figure BSA00000892911500051
And position
X i = [ X i 1 , X i 2 , . . . , X i D ] :
V i d = ω × V i d + c 1 × rand 1 d × ( pBest i d - X i d ) + c 2 × rand 2 d × ( gBest d - X i d ) - - - ( 6 )
X i d = X i d + V i d - - - ( 7 )
Wherein, pBest i = [ pBest i 1 , pBest i 2 , . . . , pBest i D ] The individual optimal location of expression particle i, gBest=[gBest 1, gBest 2..., gBest D] the global optimum position found of the whole particle population of expression; ω is the inertia weight, c 1And c 2It is speedup factor;
Figure BSA00000892911500056
With
Figure BSA00000892911500057
It is two [0,1] interval random number.
5. node is interim eliminates and Restoration Mechanism (TRE)
The interim elimination with Restoration Mechanism (TRE) of node is used for controlling the read write line switch vector that colony safeguards
Figure BSA00000892911500058
In order to reduce read write line number and don't the loss label coverage rate of arranging as much as possible, TRE deletes a read write line in every trial property ground of taking turns from the set of current active read write line.When particle swarm optimization algorithm is carried out every maxRG iteration by judging that current 100% coverage rate that whether reaches determines whether to activate the TRE operation, if satisfy 100% coverage rate, TRE is activated so, and it will be deleted and cover minimum that read write line k of number of tags in current all movable read write lines.Therefore, corresponding among the read write line switch vector ON kBe set to 0, and movable read write line number N rSubtract 1.At this moment, the coverage rate of network may be lowered.If in following maxRG iteration, along with the optimization of particle swarm optimization algorithm to read write line position and emissive power, the network coverage can reach 100% again, and the deletion to read write line k is considered to permanent so; Otherwise, recover read write line k in network, carry out on k=1 and N rAdd 1.
Simultaneously, read write line switch vector ON controls the renewal of each particle, for all among the ON k=0 dimension k, particle is corresponding
Figure BSA00000892911500059
With Can not upgrade, this expression corresponding position of read write line k and power can not be changed.This helps to keep on-the-spot on the one hand, makes particle can recover the read write line k that is temporarily deleted smoothly, also prevents particle on the other hand to invalid information study and the waste computational resource.
6. mutation operator
Mutation operator is an operations necessary in native system.This be because, at the initial stage of algorithm, very Duo read write line all is disposed in the network, this makes each read write line only need launch the covering quality that less power just can guarantee network.Convergence along with particle, may lose " gene " of the big emissive power of representative in the colony, because need read write line that bigger emissive power is arranged when using relatively small number of read write lines to realize bigger coverage rate, the disappearance of this gene can cause redundant node to eliminate the activation difficulty of mechanism.Therefore, must in system, embed mutation operator to store the gene of losing again.On the other hand, embed the global search performance that mutation operator also helps further to improve particle swarm optimization algorithm.
The flow process of mutation operator is very simple, in each generation that particle swarm optimization algorithm is carried out, selects certain the one dimension k on the particle i at random, and it is carried out following change:
X i d = X i d + random ( - Δα , Δα ) - - - ( 8 )
Wherein, Δ α is the range of variation parameter, and it is set to 20% of variable range.In addition, if the variation after
Figure BSA00000892911500062
Exceeded the span of variable d, it will be limited on the border.

Claims (4)

1. monitoring and location requirement in using at logistics and supplies management, the manufacturing and assembling, document tracking/library management etc., designed the optimization RFID network system of a cover based on particle cluster algorithm, it is characterized in that: use the particle swarm optimization algorithm main frame, consider position and the emissive power of read write line in the coding, and the embedding redundant node is eliminated the read write line that mechanism reduces use, network arrangement problem to RFID is found the solution, and the algorithm that the present invention proposes may further comprise the steps and operates:
(1) particle coding: each particle position is described to a D=3N MaxThe real number vector of dimension, wherein N MaxBe the sum that can be arranged all read write lines in the network, in this description, 2N MaxDimension represents N MaxThe coordinate position of individual read write line in two-dimentional work space, N in addition MaxThe emissive power of each read write line of dimension expression is determining the query scope;
(2) initialization: in initialization procedure, all particle position all generate at random, namely each
Figure FSA00000892911400011
Be in the work space a random point, each
Figure FSA00000892911400012
It is a random value in the read write line emissive power scope;
(3) adaptive value assessment: considering four indexs when the adaptive value of particle is assessed, is respectively maximization label coverage rate COV, minimizes the read write line number N rThe overlapping interference of minimum signal ITF, and minimize total emissive power and consume POW is carrying out the particle individuality when having most position and global optimum position to upgrade, above four targets are compared successively according to priority, win in certain target up to the current location of particle;
(4) particle rapidity and position are upgraded: each particle upgrades its speed and position according to following formula
Figure FSA00000892911400013
Figure FSA00000892911400014
(5) node is interim eliminates and Restoration Mechanism (TRE): particle swarm optimization algorithm is carried out after every maxRG iteration by judging that current 100% coverage rate that whether reaches determines whether to activate the TRE operation, if satisfy 100% coverage rate, TRE is activated so, it will delete and cover minimum that read write line k of number of tags in current all movable read write lines, if in following maxRG iteration, along with the optimization of particle swarm optimization algorithm to read write line position and emissive power, the network coverage can reach 100% again, and the deletion to read write line k is considered to permanent so; Otherwise, recover read write line k in network;
(6) mutation operator: in each generation that particle swarm optimization algorithm is carried out, select certain the one dimension k on the particle i at random, it is carried out following change:
Figure FSA00000892911400021
。
2. the particle swarm optimization algorithm for RFID peak optimizating network layout according to claim 1 is characterized in that: position and the emissive power of each read write line are encoded in the particle position information as control variable.
3. the particle swarm optimization algorithm for RFID peak optimizating network layout according to claim 1 is characterized in that: embed a kind of " node is interim to be eliminated and recovery " machine-processed (TRE), dynamically adjust the read write line quantity in the network.
4. the particle swarm optimization algorithm for RFID peak optimizating network layout according to claim 1 is characterized in that: adopt a kind of hierarchical priority mechanism to handle maximization network coverage rate in the network simultaneously, minimize the read write line interstitial content, reduce signal interference and four targets of energy efficient.
CN2013101718838A 2013-04-25 2013-04-25 Optimized RFID (Radio Frequency Identification) network system based on particle swarm algorithm Pending CN103310248A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2013101718838A CN103310248A (en) 2013-04-25 2013-04-25 Optimized RFID (Radio Frequency Identification) network system based on particle swarm algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2013101718838A CN103310248A (en) 2013-04-25 2013-04-25 Optimized RFID (Radio Frequency Identification) network system based on particle swarm algorithm

Publications (1)

Publication Number Publication Date
CN103310248A true CN103310248A (en) 2013-09-18

Family

ID=49135439

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2013101718838A Pending CN103310248A (en) 2013-04-25 2013-04-25 Optimized RFID (Radio Frequency Identification) network system based on particle swarm algorithm

Country Status (1)

Country Link
CN (1) CN103310248A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103996086A (en) * 2014-06-06 2014-08-20 中山大学 Intelligent reader planning method for RFID system
CN104517141A (en) * 2014-12-27 2015-04-15 西安电子科技大学 Radio frequency recognition network layout method based on load balance and particle swarm optimization
CN105243348A (en) * 2015-11-10 2016-01-13 天津工业大学 Reader optimal deployment method based on passive ultrahigh frequency RFID positioning system
CN105242238A (en) * 2015-09-01 2016-01-13 西南交通大学 Wireless network positioning technology based on particle auxiliary random search
CN110365390A (en) * 2019-08-21 2019-10-22 杭州立宸科技有限公司 Low-power consumption Internet of Things wireless power distributed MIMO antenna cloth optimization method
CN111225367A (en) * 2020-01-08 2020-06-02 西安电子科技大学 RFID network planning method based on hybrid particle swarm optimization
CN111241648A (en) * 2020-01-20 2020-06-05 广西大学 RFID network dynamic optimization deployment method based on hyena capture model
CN114372543A (en) * 2022-01-11 2022-04-19 重庆邮电大学 RFID (radio frequency identification device) indoor multi-target 3D (three-dimensional) positioning system and method based on carrier phase

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080106386A1 (en) * 2006-10-17 2008-05-08 International Business Machines Corporation Methods, systems, and computer program products for providing mutual authentication for radio frequency identification (rfid) security
CN102034123A (en) * 2010-10-27 2011-04-27 北京航空航天大学 RFID (Radio Frequency Identification) triple safety certification method based on label ID (Identification) random division
CN102238024A (en) * 2010-04-28 2011-11-09 上海互惠信息技术有限公司 Radio frequency identification (RFID)-based intelligent network system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080106386A1 (en) * 2006-10-17 2008-05-08 International Business Machines Corporation Methods, systems, and computer program products for providing mutual authentication for radio frequency identification (rfid) security
CN102238024A (en) * 2010-04-28 2011-11-09 上海互惠信息技术有限公司 Radio frequency identification (RFID)-based intelligent network system
CN102034123A (en) * 2010-10-27 2011-04-27 北京航空航天大学 RFID (Radio Frequency Identification) triple safety certification method based on label ID (Identification) random division

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103996086A (en) * 2014-06-06 2014-08-20 中山大学 Intelligent reader planning method for RFID system
CN104517141B (en) * 2014-12-27 2017-06-13 西安电子科技大学 Radio frequency identification network topology method based on load balance Yu particle cluster algorithm
CN104517141A (en) * 2014-12-27 2015-04-15 西安电子科技大学 Radio frequency recognition network layout method based on load balance and particle swarm optimization
CN105242238B (en) * 2015-09-01 2017-10-24 西南交通大学 A kind of wireless network location technology based on particle auxiliary random search
CN105242238A (en) * 2015-09-01 2016-01-13 西南交通大学 Wireless network positioning technology based on particle auxiliary random search
CN105243348B (en) * 2015-11-10 2017-09-19 天津工业大学 Reader optimal deployment method based on passive ultrahigh frequency RFID positioning system
CN105243348A (en) * 2015-11-10 2016-01-13 天津工业大学 Reader optimal deployment method based on passive ultrahigh frequency RFID positioning system
CN110365390A (en) * 2019-08-21 2019-10-22 杭州立宸科技有限公司 Low-power consumption Internet of Things wireless power distributed MIMO antenna cloth optimization method
CN110365390B (en) * 2019-08-21 2022-04-19 杭州智爱时刻科技有限公司 Low-power-consumption Internet of things wireless power supply distributed MIMO antenna network arrangement optimization method
CN111225367A (en) * 2020-01-08 2020-06-02 西安电子科技大学 RFID network planning method based on hybrid particle swarm optimization
CN111241648A (en) * 2020-01-20 2020-06-05 广西大学 RFID network dynamic optimization deployment method based on hyena capture model
CN111241648B (en) * 2020-01-20 2023-09-01 广西大学 RFID network dynamic optimization deployment method based on hyena capture model
CN114372543A (en) * 2022-01-11 2022-04-19 重庆邮电大学 RFID (radio frequency identification device) indoor multi-target 3D (three-dimensional) positioning system and method based on carrier phase
CN114372543B (en) * 2022-01-11 2023-12-19 东莞市宇讯电子科技有限公司 RFID indoor multi-target 3D positioning system and method based on carrier phase

Similar Documents

Publication Publication Date Title
CN103310248A (en) Optimized RFID (Radio Frequency Identification) network system based on particle swarm algorithm
Vázquez-Canteli et al. CityLearn v1. 0: An OpenAI gym environment for demand response with deep reinforcement learning
Zhang et al. A return-cost-based binary firefly algorithm for feature selection
Gong et al. Optimizing RFID network planning by using a particle swarm optimization algorithm with redundant reader elimination
Tilahun et al. Continuous versions of firefly algorithm: a review
Castello et al. Adaptive foraging for simulated and real robotic swarms: the dynamical response threshold approach
CN103116762B (en) A kind of image classification method based on self-modulation dictionary learning
Soares et al. Distributed energy resource short-term scheduling using Signaled Particle Swarm Optimization
Bredeche et al. Environment-driven embodied evolution in a population of autonomous agents
Yu et al. Enhancing firefly algorithm using generalized opposition-based learning
Tao et al. SA-PSO based optimizing reader deployment in large-scale RFID Systems
Chen et al. Beetle swarm optimisation for solving investment portfolio problems
Moayedikia et al. Weighted bee colony algorithm for discrete optimization problems with application to feature selection
CN101464831A (en) Reduction technology for test use cases
CN110502976A (en) The training method and Related product of text identification model
Abdechiri et al. Adaptive imperialist competitive algorithm (AICA)
Tang et al. Variable predictive model class discrimination using novel predictive models and adaptive feature selection for bearing fault identification
CN103729680A (en) RFID network topology method based on multi-agent evolutionary algorithm
Hajizadeh et al. Node deployment in wireless sensor networks using the new multi‐objective Levy flight bee algorithm
Wang et al. Improving economic values of day‐ahead load forecasts to real‐time power system operations
CN103246924A (en) Genetic algorithm based RFID system
Ren et al. Online multi-fault power system dynamic security assessment driven by hybrid information of anticipated faults and pre-fault power flow
Zhang et al. Research on fault diagnosis of diesel engine based on PSO-SVM
Gao et al. Multiobjective estimation of distribution algorithm combined with PSO for RFID network optimization
Iscan et al. A novel candidate solution generation strategy for fruit fly optimizer

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20130918