You are on page 1of 7

Coastal Education & Research Foundation, Inc.

Benefit Distribution Method of Coastal Port Intelligent Logistics Supply Chain under Cloud
Computing
Author(s): Shunhui Li, Qiubi Sun and Wulin Wu
Source: Journal of Coastal Research, Special Issue No. 93: Advances in Water Resources and
Exploration (FALL 2019), pp. 1041-1046
Published by: Coastal Education & Research Foundation, Inc.
Stable URL: https://www.jstor.org/stable/26853394
Accessed: 01-04-2024 20:52 +00:00

REFERENCES
Linked references are available on JSTOR for this article:
https://www.jstor.org/stable/26853394?seq=1&cid=pdf-reference#references_tab_contents
You may need to log in to JSTOR to access the linked references.

JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide
range of content in a trusted digital archive. We use information technology and tools to increase productivity and
facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org.

Your use of the JSTOR archive indicates your acceptance of the Terms & Conditions of Use, available at
https://about.jstor.org/terms

Coastal Education & Research Foundation, Inc. is collaborating with JSTOR to digitize,
preserve and extend access to Journal of Coastal Research

This content downloaded from 213.55.83.51 on Mon, 01 Apr 2024 20:52:51 +00:00
All use subject to https://about.jstor.org/terms
Journal of Coastal Research SI 93 1041–1046 Coconut Creek, Florida 2019

Benefit Distribution Method of Coastal Port Intelligent Logistics


Supply Chain under Cloud Computing
Shunhui Li†, Qiubi Sun†, and Wulin Wu‡*


School of Economics and Management ‡
School of Economics
Fuzhou University Fujian Normal University
Fuzhou 350108, China Fuzhou 350108, China www.cerf-jcr.org

ABSTRACT

Li, S.; Sun, Q., and Wu, W., 2019. Benefit distribution method of coastal port intelligent logistics supply
chain under cloud computing. In: Guido-Aldana, P.A. and Mulahasan, S. (eds.), Advances in Water
Resources and Exploration. Journal of Coastal Research, Special Issue No. 93, pp. 1041–1046. Coconut
Creek (Florida), ISSN 0749-0208.

www.JCRonline.org In order to improve the benefit distribution planning ability of coastal port intelligent logistics supply chain
under cloud computing, a benefit distribution model of coastal port intelligent logistics supply chain based
on intelligent bionic group evolutionary optimization control is proposed. The distributed node deployment
model of coastal port intelligent logistics supply chain under cloud computing is constructed, and the optimal
path planning and design of coastal port intelligent logistics supply chain network is carried out by using the
least square programming method. The fuzzy decision statistical characteristics of coastal port intelligent
logistics supply chain path output under cloud computing are extracted, and the benefit distribution model of
coastal port intelligent logistics supply chain under cloud computing is constructed by combining adaptive
decision optimization control method. The intelligent bionic group evolutionary optimization algorithm is
used to realize the adaptive planning and design of coastal port intelligent logistics supply chain under cloud
computing, and the optimal benefit distribution and control of coastal port intelligent logistics supply chain
under cloud computing are realized. The simulation results show that the resource consumption of coastal
port intelligent logistics supply chain planning under cloud computing is small and the spatial planning ability
is strong, which improves the scheduling path optimization and intelligent control ability of coastal port
intelligent logistics supply chain.

ADDITIONAL INDEX WORDS: Cloud computing, coastal port, intelligent logistics, supply chain, benefit
distribution.

INTRODUCTION deployment design of logistics coastal port intelligent logistics


With the continuous expansion of the scale of intelligent logistics supply chain network, and adopts fuzzy association scheduling
supply chain in coastal ports, it is necessary to distribute the method. The benefit distribution model of coastal port intelligent
benefits of intelligent logistics supply chain in coastal ports at the logistics supply chain under cloud computing is designed to
back end to improve the efficiency of intelligent logistics supply promote supply chain optimization (Yan and Gao, 2019).
chain scheduling in coastal ports. In the process of optimizing In the coastal port intelligent logistics supply chain network
logistics scheduling and supply chain benefit distribution (Mao system, the research on the benefit distribution model of coastal
et al., 2016), it is necessary to study an efficient planning model port intelligent logistics supply chain under cloud computing has
of coastal port intelligent logistics supply chain, and to realize attracted great attention, through the optimization design of coastal
the spatial optimization planning and design of coastal port port intelligent logistics supply chain under cloud computing (Ma
intelligent logistics supply chain network. To improve the ability and Yu, 2018). Combined with intelligent logistics technology to
of organization, command and collaborative control of supply realize the optimal scheduling and intelligent control of coastal
chain, to study the benefit distribution model of coastal port port intelligent logistics supply chain under cloud computing, in
intelligent logistics supply chain under cloud computing, and to the traditional methods. The benefit distribution model of coastal
optimize the scheduling of coastal port intelligent logistics supply port intelligent logistics supply chain under cloud computing is
chain. It is of great significance to improve the intelligent level of mainly designed by fuzzy benefit distribution algorithm, control
logistics supply chain (Lu and You, 2018). The research on benefit benefit distribution model and least square programming model,
distribution model of coastal port intelligent logistics supply and the optimization intelligent algorithm is adopted. The central
chain under cloud computing is based on the intelligent node network model of intelligent logistics supply chain scheduling in
coastal ports under cloud computing is constructed. The electronic
logistics control method is used to optimize the supply chain
DOI: 10.2112/SI93-150.1 received 15 October 2018; accepted in scheduling and benefit distribution model of coastal port intelligent
revision 2 June 2019. logistics under cloud computing (Chao, Wang, and Wang, 2018).
*Corresponding author: haliyo2020@163.com The shortest path optimization method is based on the irregular
©
Coastal Education and Research Foundation, Inc. 2019

This content downloaded from 213.55.83.51 on Mon, 01 Apr 2024 20:52:51 +00:00
All use subject to https://about.jstor.org/terms
1042 Li, Sun, and Wu

triangular network model. With the adaptive path planning NInter


= i ( n) NInteri (n) + 1, if j ∉ N i ∪ tij ≥ Th (1)
and design of coastal port intelligent logistics supply chain
network, the benefit distribution model of coastal port intelligent wherein, CInteri (n) represents the maximum transmission delay
logistics supply chain under cloud computing is realized, but the of the coastal port intelligent logistics supply chain scheduling
redundancy of this method is large and the adaptive planning node i under cloud computing, and carries on the node automatic
ability is not good. The benefit distribution model of coastal port deployment design through the additional bus scheduling method.
intelligent logistics supply chain based on intelligent ant colony To realize the security assessment of benefit distribution in coastal
algorithm is to realize the benefit distribution and planning design port intelligent logistics supply chain under cloud computing
of coastal port intelligent logistics supply chain network by ant (Bao et al., 2018), the balanced scheduling output of the node
colony optimization (Szala, 2016). However, the computational center of coastal port intelligent logistics supply chain under
overhead of this method is large and the adaptive convergence cloud computing is as follows:
performance is not good. In view of the disadvantages of
traditional methods, a benefit distribution model of coastal port NIntrai (n) NInteri (n)
intelligent logistics supply chain based on intelligent bionic CIntrai (n)
= = , CInteri (n) (2)
T T 
group evolutionary optimization control is proposed. The
distributed node deployment model of coastal port intelligent Combined with rough set theory, the dynamic constraint control
logistics supply chain under cloud computing is constructed, model of benefit distribution in coastal port intelligent logistics
and the adaptive planning and design of coastal port intelligent supply chain under cloud computing is constructed, and the multi-
logistics supply chain under cloud computing is realized by using frequency and multi-format RFID identification technology is
intelligent bionic group evolutionary optimization algorithm. The adopted (Wu et al., 2015). The intelligent information collection
optimal benefit distribution and control of coastal port intelligent of benefit distribution in coastal port intelligent logistics supply
logistics supply chain under cloud computing are realized, and the chain under cloud computing is carried out (Liu and Luo, 2012).
performance test is carried out through simulation experiments, The optimal deployment and path adaptive search model of
and the effective conclusion is drawn (Gu et al., 2012). coastal port intelligent logistics supply chain node under cloud
computing is obtained as follows:
MATERIAL AND METHODS
Node Deployment Model of Coastal Port Intelligent Logistics
 NI
Supply Chain under Cloud Computing  ∑ s (i, t )
NI
In order to realize the benefit distribution and deployment  ρtI =
= 1

of coastal port intelligent logistics supply chain under cloud  V V



computing, it is necessary to design the node optimization NR

 R ∑
 s (i, t )
deployment model of coastal port intelligent logistics supply chain 1 NR (3)
under cloud computing. Combined with the optimal distribution = tρ =
 V V
route control protocol (Guo et al., 2018), the scheduling

evaluation of coastal port intelligent logistics supply chain under 
cloud computing is carried out. The distribution model of coastal  N
 ρtS = S
port intelligent logistics supply chain is shown in Figure 1. V

Combined with link equilibrium control protocol, the  
information fusion of intelligent logistics supply chain scheduling
and evaluation of coastal ports under cloud computing is realized The multi-objective evolution method is used to optimize the
(Guo et al., 2016). The clustering node path scheduling model shortest path of coastal port intelligent logistics supply chain
of coastal port intelligent logistics supply chain scheduling under under cloud computing, and the optimal search path of redundant
cloud computing is constructed. NInteri (n) is used to represent supply chain= is pi ( pi1 , pi 2 ,…, piD ) . In the path search of coastal
the clustering path of coastal port intelligent logistics supply port intelligent logistics supply chain scheduling under cloud
chain under cloud computing. computing, 0 is used to represent the location pheromone, and
the fuzzy dynamic weighting method is combined with the fuzzy
dynamic weighting method (Wang et al., 2012). The fuzzy search
and fusion of each coastal port intelligent logistics supply chain
node under cloud computing is carried out, and the distributed
node deployment model of coastal port intelligent logistics supply
chain under cloud computing is constructed. The least square
programming method is used to design the optimal path planning
of coastal port intelligent logistics supply chain network (Yi,
Peng, and Luan, 2015).

Optimal Path Planning of Intelligent Logistics Supply Chain


Network in Coastal Ports
The smart card reader based on Radio Frequency Identification
(RFID) is used to collect the intelligent information of coastal port
Figure 1. Distribution model of intelligent logistics supply chain in coastal intelligent logistics supply chain under cloud computing (Pan et
ports.

Journal of Coastal Research, Special Issue No. 93, 2019

This content downloaded from 213.55.83.51 on Mon, 01 Apr 2024 20:52:51 +00:00
All use subject to https://about.jstor.org/terms
Benefit Distribution Method of Coastal Port Intelligent Logistics Supply Chain under Cloud Computing1043

al., 2015), and the collected benefit distribution information of of coastal port intelligent logistics supply chain scheduling
supply chain is converged and grouped. Based on the shortest path information under cloud computing is extracted. The label reader
optimization algorithm, the control equation of the optimal path is used for information sampling to realize the optimal planning
planning for the intelligent logistics supply chain of coastal ports design and balanced scheduling of the path (Cui, Xiong, and He,
under cloud computing is as follows: 2015).

f (i ) dS (i ) + d T (i ) (4)
= Feature Extraction of Benefit Distribution in Supply Chain
The routing graph topology is used for adaptive balanced
wherein, dS ( i ) is the equivalent constraint of benefit distribution scheduling of coastal port intelligent logistics supply chain under
in coastal port intelligent logistics supply chain under cloud cloud computing (Sun et al., 2016). For the coastal port intelligent
computing. Under the control of intelligent constraint, the logistics supply chain scheduling section under cloud computing,
related dimension feature vector of benefit distribution in coastal RFID smart card reader is used to sample the coastal port
port intelligent logistics supply chain under cloud computing is intelligent logistics supply chain scheduling information under
expressed as follows: cloud computing. Combined with fuzzy control method (Liu, Liu,
and Liu, 2013), the central information processing of intelligent
x ( k ) = [ x1( k ) , x2( k ) ,...xN( kk)−1 ]T (5) logistics supply chain scheduling in coastal ports under cloud
computing, the ARM information processing unit is constructed
The load balancing scheduling method is used to realize the to realize the intelligent scheduling of coastal port intelligent
fuzzy benefit distribution and balanced scheduling of coastal port logistics supply chain scheduling under cloud computing, at the
intelligent logistics supply chain under cloud computing (Wang cost of minimizing the load of node distribution. The adaptability
et al., 2015), and the minimum variance criterion is adopted. variance of intelligent logistics supply chain scheduling evaluation
The statistical characteristic data set of path planning of coastal in coastal ports under cloud computing is obtained.
port intelligent logistics supply chain under cloud computing is
2
obtained as a matrix of n × n , which is expressed as follows:  f −f 
n
σ = −∑  i avg 
2
(9)
i =1  f  
 0 d (1, 2) d (1,3)  d (1, 4 ) 
 
 d ( 2,1) 0 d ( 2,3)  d ( 2, n )  wherein, n is the number of link center points in coastal port
D =  d ( 3,1) d ( 3, 2 ) 0  d ( 3, n )  (6) intelligent logistics supply chain scheduling under cloud
  computing, and f i is the adaptability value of coastal port
    0  
intelligent logistics supply chain node under cloud computing.
 d (n,1) d ( n, 2 ) d ( n,3)  0  
 f avg is the average fitness of the optimal configuration of coastal
port intelligent logistics supply chain scheduling and evaluation
The similarity feature quantity s (i, j ) between the central data center under cloud computing. When σ < m , m is a certain
2

points xi and x j of the coastal port intelligent logistics supply threshold (Noël and Kerschen, 2017). Assuming that the RFID
chain under cloud computing is automatically reorganized, and information acquisition model for intelligent logistics supply chain
the autocorrelation matching and path automatic planning method scheduling evaluation in coastal ports under cloud computing is
is adopted. The correlation eigenvalues of coastal port intelligent represented as follows:
logistics supply chain under cloud computing are constructed.
=
when d ( i, j ) d=
( j, i ) , d ( i, i ) 0 , the shortest path planning  ∂v1 ( x) ∂v1 ( x) ∂v1 ( x) 
criterion of coastal port intelligent logistics supply chain under  ∂x 
 ∂x2 ∂xn 
cloud computing is obtained, it is described as follows: 1
 ∂v2 ( x) ∂v2 ( x) ∂v2 ( x) 
  
m n J ( x) =  ∂x1 ∂x2 ∂xn  (10)
min( f ) = ∑∑ Cij X ij  
(7)    
=i 1 =j 1
 
 ∂vN ( x) ∂vN ( x) ∂vN ( x) 
 ∂x 
m ∂x2 ∂xn  
∑ X = ij i ,i
a= 1, 2 m  1

 j =1
 m The second-order gradient ∇ 2 F ( x) is used to describe the
∑ = X ij b=i, j 1, 2 n (8) fuzzy constraint of coastal port intelligent logistics supply chain
 i =1 scheduling evaluation under cloud computing. The total number
 X ij =
≥ 0, i 1, 2= m, j 1, 2 n
 of control nodes V is constant. When t < δ , the statistical
s.t   characteristics of intelligent logistics supply chain scheduling
evaluation in coastal ports under cloud computing are described
Suppose the number of RFID nodes sampled by coastal port by the following equations:
intelligent logistics supply chain scheduling information under
cloud computing is N, where N1 ,, N n . The correlation statistical ds (t ) di (t )
= − β i (t ) s (t ) = β i (t ) s (t ) (11)
analysis method is used to realize the information evaluation and dt , dt 
intelligent scheduling of coastal port intelligent logistics supply
chain under cloud computing, and the characteristic quantity

Journal of Coastal Research, Special Issue No. 93, 2019

This content downloaded from 213.55.83.51 on Mon, 01 Apr 2024 20:52:51 +00:00
All use subject to https://about.jstor.org/terms
1044 Li, Sun, and Wu

When t > δ is used, the fuzzy feature extraction of benefit N

distribution in coastal port intelligent logistics supply chain under MdistFg = ∑ dist (i, Fg ) / N (17)
i =1 
cloud computing can be described as follows:
According to the intersection and variation and convergence
 ds (t ) conditions in the process of particle swarm optimization, the
 dt = − β i (t ) s (t ) + α r (t )
global optimal value is updated, and the benefit distribution and

 di (t ) particle adaptive optimization of redundant supply chain are
=
 β i (t ) s (t ) − µi (t ) (12)
realized (Amirat and Münch, 2019).
 dt
 dr (t )
 = µi (t ) − α r (t ) 
RESULTS
 dt
In order to test the application performance of this algorithm
in realizing the benefit distribution of coastal port intelligent
Thus, the network structure model of coastal port intelligent
logistics supply chain under cloud computing, the experimental
logistics supply chain scheduling evaluation under cloud
analysis is carried out. Matlab is used for algorithm design, and
computing is constructed, and the fuzzy decision statistical
particle swarm optimization is used for adaptive optimization
characteristics of coastal port intelligent logistics supply chain
(Weaver et al., 2016). The number of particle population N is
path output under cloud computing are extracted. Combined
set to 120000, the fuzzy PN sequence of coastal port intelligent
with adaptive decision optimization control method, the benefit
logistics supply chain scheduling is 01001000, and the sampling
distribution model of coastal port intelligent logistics supply chain
under cloud computing is constructed (Cao, Li, and Liu, 2019).

Benefit Distribution Output of Coastal Port Intelligent Logistics 10

Supply Chain under Cloud Computing 5


The intelligent control method is used to optimize the node
deployment design and fuzzy constraint control of the coastal port 0
Logarithm of the optimal solution of a

intelligent logistics supply chain scheduling and evaluation center -5


under cloud computing, and the particle swarm optimization
-10
method is adopted. The optimal benefit distribution model
function(log)

of coastal port intelligent logistics supply chain under cloud -15


computing is obtained as:
-20

1 2 -25
min Q −PΩ +µ Q (13) SFLA
Q 2 Ω F *  -30 MSFLA1
MSFLA2
In the distribution of benefits in the supply chain, the position of -35 LMSFLA
particle i at k + 1 time is as follows: -40
0 50 100 150 200 250 300 350 400 450 500
Number of evolutionary iterations
x j (k ) − xi (k )
xi (k + 1)
= xi (k ) + s ( ) (14) Figure 2. Results of cost optimization and benefit distribution in supply
x j (k ) − xi (k )  chain.

With the initial weight sensitive adjustment method of the


output layer, it is found that the link overhead of the optimal
benefit distribution of the coastal port intelligent logistics supply 100
chain under cloud computing is µ . Under the optimal benefit
0
distribution deployment, the selection of µ value should be
Logarithm of the optimal solution of a function(log)

satisfied:
-100

2
QΩ −PΩ ≈ F (Ω)σˆ 2 (15) -200
F

=
Set µ ( n1 + n2 ) pσˆ , the ambiguity function of optimal -300

benefit distribution in supply chain is as follows:


-400

SFLA
d
-500
dist (i, j=
) ∑ ( xik − x jk )2 + ( f ( X i ) − f ( X j ))2
k =1 
(16)
MSFLA1
MSFLA2
-600 LMSFLA

Considering the global optimization problem min{f(x)}, the


-700
benefit distribution of coastal port intelligent logistics supply chain 0 50 100 150 200 250 300 350 400 450 500
Number of evolutionary iterations
under cloud computing is obtained, and the optimal adaptability
value is expressed as follows: Figure 3. Path optimization benefit distribution results of supply chain.

Journal of Coastal Research, Special Issue No. 93, 2019

This content downloaded from 213.55.83.51 on Mon, 01 Apr 2024 20:52:51 +00:00
All use subject to https://about.jstor.org/terms
Benefit Distribution Method of Coastal Port Intelligent Logistics Supply Chain under Cloud Computing1045

frequency of redundant supply chain benefit distribution is 300 chain planning under cloud computing is small and the spatial
KHz. The scale of feature distribution set in coastal port intelligent planning ability is strong. The scheduling path optimization and
logistics supply chain network is 2000, the training sample set is intelligent control ability of coastal port intelligent logistics supply
120, the function dimension is set to 30, the number of iterations chain are improved. The statistical results of product distribution
in supply chain benefit distribution is 2000, and the related factor in the supply chain are tested in Table 1.
ALR=2.2, The number of logistics distributor (L) are 4, 6, 8, Taking the above statistical analysis as the data input, the
8, 9, respectively, and the training parameters ω1 ,ω2 ,ω3 ,ω4 ,ω5 intelligent bionic group evolutionary optimization algorithm is
are 0.34, 0.65, 0.30, 0.21 and 0.05, respectively, according to used to realize the adaptive planning and design of the coastal
the above simulation environment and parameters. The benefit port intelligent logistics supply chain under cloud computing.
distribution simulation of coastal port intelligent logistics supply To realize the optimal benefit distribution and control of coastal
chain under cloud computing is carried out, and the benefit port intelligent logistics supply chain under cloud computing, the
distribution of centralized redundant supply chain is optimized relationship between the minimum cost and the optimal individual
under the minimum cost constraint. The cost optimization and in the coastal port intelligent logistics supply chain network is
path optimization benefit distribution results of supply chain are shown in Table 2.
shown in Figures 2 and 3.
CONCLUSION
DISCUSSION In this paper, an efficient planning model of logistics supply
By analyzing the above simulation results, it is found that the chain is studied to realize the spatial optimization planning and
resource consumption of coastal port intelligent logistics supply design of coastal port intelligent logistics supply chain network,
and to improve the organization, command and collaborative
Table 1. Product distribution statistics in the supply chain. control ability of supply chain. In this paper, a benefit distribution
model of coastal port intelligent logistics supply chain based
Distribution
Distribution on intelligent bionic group evolutionary optimization control is
Path proposed, and the distributed node deployment model of coastal
Supply Chain System
16 25 port intelligent logistics supply chain under cloud computing is
0 1.54 constructed. The least square programming method is used to
1.47 0
design the optimal path of coastal port intelligent logistics supply
Statistical
chain network, and the benefit distribution model of coastal
cycle 1 0 1.50
port intelligent logistics supply chain under cloud computing is
1.67 0 constructed by combining adaptive decision optimization control
0 1.43 method. The intelligent bionic group evolutionary optimization
Statistical 1.89 0 algorithm is used to realize the adaptive planning and design
cycle 2 0 1.45 of coastal port intelligent logistics supply chain under cloud
The Distribution
Center of Coastal computing, and the optimal benefit distribution and control
0.86 0
Port Intelligent of coastal port intelligent logistics supply chain under cloud
Logistics Supply 0 1.67 computing are realized. It is found that the resource consumption
Chain Network Statistical 1.45 0 of coastal port intelligent logistics supply chain planning under
cycle 3 0 1.65 cloud computing is small and the ability of adaptive optimization
1.70 0 is strong, which improves the scheduling path optimization and
0 1.43
intelligent control ability of coastal port intelligent logistics
supply chain. It has good application value in supply chain benefit
Statistical 1.65 0
distribution.
cycle 4 0 1.35
1.69 0 ACKNOWLEDGEMENT
This research was supported by The National Social Science
Table 2. Relationship between the minimum cost and the optimal individual Foundation of China [Grant number 18BGL106].
in the intelligent logistics supply chain network of coastal ports.
LITERATURE CITED
Minimum Cost
Particle Swarm Amirat, Y. and Münch, A., 2019. On the controllability of an
Optimal advection-diffusion equation with respect to the diffusion
(10,000 yuan)
Individual
parameter: asymptotic analysis and numerical simulations.
Reduce 50% 545.06 1010
Acta Mathematicae Applicatae Sinica (English Serie), 35(1),
Reduce 40% 546.8 0111 54-110.
Requirement
Increase 30% 433.1 1010 Bao, S.T.; Sun, L.P.; Zheng, X.Y., and Guo, L.M., 2018. Density
Increase 50% 432.3 1011 peaks clustering algorithm based on shared near neighbors
similarity. Journal of Computer Applications, 38(6), 1601-
Reduce 40% 35.6 1110
1607.
Reduce 30% 43.3 0101 Cao, S.T.; Li, Z.S., and Liu, B., 2019. Nonlinear time history
Distance
Increase 50% 43 1010 analysis of a large-scale complex connected structure base
Increase 30% 45.8 1100

Journal of Coastal Research, Special Issue No. 93, 2019

This content downloaded from 213.55.83.51 on Mon, 01 Apr 2024 20:52:51 +00:00
All use subject to https://about.jstor.org/terms
1046 Li, Sun, and Wu

on an explicit friction pendulum element. Engineering Noël, J.P. and Kerschen, G., 2017. Nonlinear system identification
Mechanics, 36(6), 128-137. in structural dynamics, 10 more years of progress. Mechanical
Chao, Y.; Wang, S.B., and Wang, H.L., 2018. Image watermarking Systems and Signal Processing, 83, 2-35.
algorithm based on SVD and PSO. Journal of Jilin University Pan, J.L.; Xiong, Z.; Wang, L.N.; Yu, F.; Zhao, H., and Lin, A.J.,
(Science Edition), 56(05), 1163-1169. 2015. A simplified UKF algorithm for SINS/GPS/CNS
Cui, Y.Q.; Xiong, W., and He, Y., 2015. Height compensation for integrated navigation system in launch inertial coordinate
3-D target state estimation using 2-D warning radar based system. Acta Armamentarii, 36(3), 484-491.
on target indication. Chinese Journal of Electronics, 43(3), Sun, S.Z.; Li, H., and Sun, H., 2016. Measurement and analysis
475-482. of coastal waves along the north sea area of China. Polish
Gu, Q.; Yuan, L.; Ning, B.; Hua, L, and Li, W., 2012. A noval Maritime Research, 23, 72-78.
classification algorithm for imbalanced datasets based on Szala, G., 2016. Application of two-parameter fatigue
hybrid resampling strategy. Computer Engineering and charactersitics in fatigue persistence calculations of structural
Science, 34(10), 128-134. components under conditions of a broad spectrum of loads.
Guo, H.P.; Dong, Y.D.; Mao, H.T.; Wu, C.A., and Fan, M., Polish Maritime Research, 23, 138-145.
2016. Logistic discrimination based rare-class classification Wang, L.; Liu, H.T.; Liang, T.; Ma, X., and Zhao, W., 2015.
method. Journal of Chinese Computer Systems, 37(1), 140- Modeling and analysis of dynamic response of servo
145. feed system under low frequency excitation. Journal of
Guo, H.P.; Zhou, J.; Wu, C.A., and Fan, M., 2018. K-nearest Mechanical Engineering, 51(3), 18-28.
neighbor classification method for class-imbalanced Wang, Y.Q.; Zhou, J.Z.; Mo, L.; Zhang, R., and Zhang, Y.C.,
problem. Journal of Computer Applications, 38(4), 955-959. 2012. Precise scheduling method for daily generation plan
Liu, J. and Luo, X.J., 2012. Short-term optimal environmental of large-scale hydropower station based on comprehensive
economic hydrothermal scheduling based on handling state evaluation strategy for generating units. Power System
complicated constraints of multi-chain cascaded hydropower Technology, 36(7), 94-99.
station. Proceedings of the CSEE, 32(14), 27-35. Weaver, R.J.; Johnson, J.E., and Ridler, M., 2016. Wind-driven
Liu, Y.L.; Liu, J., and Liu, J.N., 2013. Research on composite circulation in a shallow microtidal estuary: The Indian River
inversion of dynamic loads and structural parameters based lagoon. Journal of Coastal Research, 32, 1333-1343.
on sub-structure analysis. Journal of Mechanical Strength, Wu, H.J.; Shen, J.J.; Cheng, C.T.; Lu, J.Y., and Li, G., 2015.
35(5), 553-558. Coordination method of regional and provincial grids for
Lu, A.N. and You, M.Y., 2018. Statistical analysis of direction short-term peak shaving operation among hybrid energy
finding blur and error of phase interferometer. Journal of sources. Proceedings of the CSEE, 35(11), 2743-2755.
China Academy of Electronics and Information Technology, Yan, L. and Gao, T., 2019. Heterogeneous wireless network
13(1), 42-46. vertical switching algorithm for improving Markov process.
Ma, K. and Yu, J.L., 2018. Design and experimental research Journal of Jilin University (Scientific Edition), 57(03), 633-
method of mmc control system based on TMS28035. Journal 639.
of Power Supply, 16(4), 133-142. Yi, X.L.; Peng, S.L., and Luan, S.C., 2015. An approach of adaptive
Mao, W.T.; Tian, Y.Y.; Wang, J.W., and He, L., 2016. Granular signal separation based on operator and locally orthogonal
extreme learning machine for sequential imbalanced data. constraint. Journal of Electronics and Information, 37(11),
Control and Decision, 31(12), 2147-2154. 2613-2620.

Journal of Coastal Research, Special Issue No. 93, 2019

This content downloaded from 213.55.83.51 on Mon, 01 Apr 2024 20:52:51 +00:00
All use subject to https://about.jstor.org/terms

You might also like