Urban Traffic Flow Prediction Model with CPSO/SSVM Algorithm under the Edge Computing Framework

Abstract

Urban traffic flow prediction has always been an important realm for smart city build-up. With the development of edge computing technology in recent years, the network edge nodes of smart cities are able to collect and process various types of urban traffic data in real time, which leads to the possibility of deploying intelligent traffic prediction technology with real-time analysis and timely feedback on the edge. In view of the strong nonlinear characteristics of urban traffic flow, multiple dynamic and static influencing factors involved, and increasing difficulty of short-term traffic flow prediction in a metropolitan area, this paper proposes an urban traffic flow prediction model based on chaotic particle swarm optimization algorithm-smooth support vector machine (CPSO/SSVM). The prediction model has built a new second-order smooth function to achieve better approximation and regression effects and has further improved the computational efficiency of the smooth support vector machine algorithm through chaotic particle swarm optimization. Simulation experiment results show that this model can accurately predict urban traffic flow.

Full text

Research Article
Urban Traffic Flow Prediction Model with CPSO/SSVM
Algorithm under the Edge Computing Framework
Fengkai Liu ,
1,2
Xingmin Ma,
2
Xingshuo An,
2
and Guangnan Liang
2
1
College of Computer Science and Technology, Zhejiang University, 310027 Hangzhou, China
2
North China Institute of Computing Technology, NCI, 100083 Beijing, China
Correspondence should be addressed to Fengkai Liu; 11821127@zju.edu.cn
Received 23 April 2020; Revised 28 June 2020; Accepted 3 August 2020; Published 1 September 2020
Academic Editor: Ke Xiong
Copyright © 2020 Fengkai Liu et al. This is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Urban trafficflow prediction has always been an important realm for smart city build-up. With the development of edge computing
technology in recent years, the network edge nodes of smart cities are able to collect and process various types of urban traffic data
in real time, which leads to the possibility of deploying intelligent traffic prediction technology with real-time analysis and timely
feedback on the edge. In view of the strong nonlinear characteristics of urban trafficflow, multiple dynamic and static influencing
factors involved, and increasing difficulty of short-term trafficflow prediction in a metropolitan area, this paper proposes an urban
trafficflow prediction model based on chaotic particle swarm optimization algorithm-smooth support vector machine
(CPSO/SSVM). The prediction model has built a new second-order smooth function to achieve better approximation and
regression effects and has further improved the computational efficiency of the smooth support vector machine algorithm
through chaotic particle swarm optimization. Simulation experiment results show that this model can accurately predict urban
trafficflow.
1. Introduction
The concept of a smart city has been quite popular in recent
years as it demonstrates great potential for improving urban
management and people’s life [1]. Various sensing and com-
puting technologies have gradually outlined the future of a
smart city. In the smart city scenario, the combined applica-
tion of multiple technologies has generated a huge amount of
data, which has laid the basic foundation of a smart city.
With the surge of data volume, cloud computing has
encountered unforeseen challenges [2]. Firstly, due to the
huge amounts of data instantly acquired from multiple
sources, the sensing layer of a smart city has shown special
characteristics such as strong redundancy, inner and inter-
connectivity, sensitivity to transmission delay, and heteroge-
neous. Therefore, it is difficult for cloud-centralized service to
handle such large-scale data under high pressure [3]. Sec-
ondly, cloud computing is a cohesion model; it will lead to
network delay and waste of bandwidth once data is sent from
edge to cloud through a remote network. Finally, the data
security and privacy protection of a smart city during long-
distance transmission are facing great challenge [4], since a
centralized cloud-computing model makes it difficult to
ensure security and privacy of data transmitted from distrib-
uted edges.
The paradigm to handle the aforementioned issues is
edge computing. “Edge”indicates proximity to the user or
the sources which generate data. Therefore, edge computing
mainly provides computation, data storage, and network
support from the edge. The tasks of storage and computation
have been transferred to the edge instead of servers from the
cloud, as indicated in Figure 1.
Edge computing has demonstrated great advantages
from the perspectives of wide connection, distributed com-
putation, proximity to a data source, and low latency. Edge
computing can provide better capability in the areas of data
Hindawi
Wireless Communications and Mobile Computing
Volume 2020, Article ID 8871998, 11 pages
https://doi.org/10.1155/2020/8871998

filtering and compression, situational awareness, and data
classification, which has laid a strong technical foundation
for the application of big data analysis, traffic management,
and urban environmental monitoring [5].
There are some differences between edge data processing
and traditional data processing techniques. Firstly, the core
of smart city data is heterogeneous in nature. Smart city data
normally come from areas of governance, public security,
environment, transportation, internet, and IOT, all of which
generate data from multiple sources in different modalities.
Secondly, restriction on the access of the edge node should
be taken into consideration during the process of edge pro-
cessing. Lastly, the cooperation between edge and cloud
needs to be taken into consideration [6].
Therefore, the paper focuses on the urban data process-
ing on the edge side, particular small-scale urban data though
not huge but significant in daily urban governance operation,
and successful application of these data would eventually lead
to the informed decision during urban governance and plan-
ning. The contribution of the article includes the following:
(1) proposed a data application framework for urban edge
computing based on the research of requirements of urban
data processing and (2) proposed a new CPSO/SSVM algo-
rithm, which has built a new 2
nd
-order smooth function to
achieve a better effect on approximation and regression.
Meanwhile, CPSO optimization has further improved the
efficiency of SVM. The prediction result is satisfactory on
accuracy and stability when processing trafficflow data from
the edge. The remaining structure of the paper is as follows:
part 2 has introduced related work on edge computing and
trafficflow prediction, part 3 designed the urban traffic pre-
diction model under the edge computing framework, part 4
has tested the model, and part 5 has given the conclusion.
2. Related Works
Big data and edge computing are both hotspots in the acade-
mia, and some scholars have begun to pay attention to big
data processing at the edge. Yang and Liu [7] discussed the
advantages of edge computing. To maximize the application
of edge computing, data fusion is used in the framework of
edge computing. The authors have proposed a Gaussian
process-based temporal data fusion (GPTDF) method aimed
for the issue of sequential online forecasting at the edge. This
approach provides an effective data fusion tool for data cap-
ture and privacy protection of edge computing. Big data
applications operating under an edge computing environ-
ment have their own unique characteristics. Ndikumana
et al. [8] put forward the concept of joint 4C (computing,
caching, communication, and control) to describe this fea-
ture. Joint 4C is transformed into an optimization problem
and solved in the research. Considering the complexity and
difference of mobile big data, Xu et al. [9] propose a compu-
tation offloading method, named COM, for IoT-enabled
cloud-edge computing. In order to solve the issue of data
sharing and collaboration in edge computing, Zhang et al.
[10] propose a new computing paradigm named Firework.
Firework provides a balanced environment where data can
be shared, distributed, and processed for big data application;
in the meantime, computing power is kept within stake-
holder’s information infrastructure.
The application of data processing in smart cities has also
received considerable attention in recent years. Lau et al. [11]
introduce a multiperspective classification of the data pro-
cessing to evaluate the smart city applications in their over-
view article on smart cities. Then, the aforementioned
method has been applied to evaluate a group of selective
applications in each domain of the smart city. Jara et al.
[12] fused traffic and temperature data in their study. They
also proposed a temperature-traffic prediction model that
obeys the Poisson distribution.
The prediction algorithm for urban traffic has also
received considerable attentions in recent years. Jiang and
Adeli [13] have proposed a novel nonparametric dynamic
time-delay recurrent wavelet neural network model to pre-
dict trafficflow. Lv et al. [14] have proposed a novel method
to predict a trafficflow-based deep-learning algorithm, which
considers the correlation within the spatiotemporal traffic
network. The test result has shown a superior outcome in
trafficflow prediction. Zhang et al. [15] has put forward an
algorithm framework based on deep learning; the algorithm
predicts the traffic network’s node flow and edge flow con-
currently under a spatiotemporal scenario. Test results have
demonstrated the advantages of methodologies with an out-
come above 11 baselines, such as ConvLSTM, CNN, and
Markov random field. Yuan et al. [16] have put forward a
novel method to analyze Shanghai urban traffic by designing
a key mode of urban traffic and predicting transition between
different modes. Experimental results have demonstrated the
proposed method to predict that traffic mode is more accu-
rate and comprehensive.
3. Materials and Methods
3.1. Urban Traffic Data Application Architecture under the
Edge Computing Framework. Based on the inherent proper-
ties of trafficflow in the urban area as well as factors
Edge
computing
layer
Core network
Cloud
computing
layer
Figure 1: Technical architecture for smart city edge computing.
2 Wireless Communications and Mobile Computing

influencing the efficiency of the intelligent transportation sys-
tem (ITS), such as proximity to the edge, flowability, and het-
erogeneous, the paper proposed an application architecture of
urban traffic data and designed a trafficpredictionmodelto
better handle trafficflow data from the edge. The overall archi-
tecture includes five layers including edge data collection, edge
computation, data storage, data processing and computing,
and data analysis and visualization, as illustrated in Figure 2.
Edge data collection layer is the “entrance”of data for the
overall technical architecture; it is mainly responsible for the
collection of data from road traffic network. Real-time traffic
data are mainly generated by ring induction coils, toll bayo-
net, car GPS, etc. The amount of data is on a large scale with
heterogeneous in nature. At this layer, it is necessary to build
a channel for data acquisition, so that traffic big data can con-
verge to the edge nodes.
Edge computation layer will provide a timely response
from close proximity at the edge of the network; data fusion
methodologies are normally applied at this layer to deal with
heterogeneous traffic information collected from multiple
sources. At the same time, preliminary data preprocessing
is also required at the edge computing layer for data quality
control. The edge node is responsible for processing data in
a larger area of the local area network and provides extensible
data processing capabilities. The edge computing layer
mainly performs tasks such as data cleaning, data integration,
and data deduplication.
The data storage layer will store the data extracted from
the edge data collection layer, and the extracted data will be
temporarily or permanently stored in the edge device. In
the urban traffic big data scenario, the data stored at this layer
is divided into three categories, including trafficflow data,
weather data, and street view data from different POIs. His-
torical trafficflow data is used to train trafficflow prediction
models, and real-time trafficflow data is used to evaluate pre-
diction effects; improvements on the model will be made
Multi sourc e
trac data
Edge data collection
Data storage
Data processing and
computing service
Spatial
data
Geographical
information
Road network
data
Trac ow
data
Wea t he r
condition
data
Trac
management
data
Real-time data
database
Basic information
database Trac database Data warehouse
Data analysis and
visualization service
Analytical interface for intelligent transportation system
Result feedback Algorithm deployment
Trac cameras’ data
Edge node-server Edge node-smart gateway Edge node-smart trac lights
Data cleaning Data
deduplication Data integration Data
transformation ……
Edge comput ation
Vehicle dataMobile data
Data acquire Data acquire
Data acquire
Multisource trac data
fusion
Classication and
prediction algorithm
Model interpretation
and evaluation
Hadoop cluster NoSQL database Flow-data real-time
computation
Figure 2: Technical architecture for urban traffic big data.
3Wireless Communications and Mobile Computing

accordingly based on evaluation results. This layer provides
data support for the computing service layer. The data
required by the computing service layer comes from this layer.
The data processing and computing service layer is the
core functional layer of the architecture. The purpose of this
architecture is to provide users with accurate trafficflow pre-
diction. This layer provides trafficflow preprocessing func-
tion and trafficflow prediction algorithm library. The
preprocessing function is mainly realized by the system auto-
matically. A variety of prediction algorithms will be provided
including SVM smoothing algorithm, traditional support
vector regression (SVR) algorithm, SVR with Chaotic
Genetic Algorithm (CGA-SVR), Back Propagation Neural
Network (BPNN), Autoregressive Integrated Moving Aver-
age model (ARIMA), and other trafficflow prediction
models; users can apply the corresponding algorithm for traf-
ficflow prediction based on different scenarios.
Data analysis and visualization service layer will inter-
act with the analytical interface for ITS. With the support
of the data processing and computing service layer, predic-
tion results can be obtained in a more efficient way.
Meanwhile, analytical methods and visualization methods
enhance users’ability to acquire in-depth information.
The RESTful architecture is used between the computing
service layer and the visualization service layer, which
can achieve loosely coupled connections between modules.
Through the data analysis and visualization service layer, a
more flexible and comprehensive interaction between the
user and the data is achieved.
The combination of edge computing and data analytics is
powerful as it can provide edge users a timely and accurate
decision support when it comes to traffic management dur-
ing rush hours. By deploying intelligent algorithms close to
the edge computing layer, analytical results can be quickly
shared across edge networks, which is vital to ITS as traffic
flow management is highly related to efficient information
sharing, and safety on the road can be guaranteed by provid-
ing accurate and timely road traffic feedback to the drivers.
The urban trafficflow prediction model can be applied in
the urban traffic data application architecture in two ways.
Firstly, it can be deployed in the edge computing layer to con-
duct some instant analytical tasks in order to predict fluctu-
ating trafficflow; the results can be shared with drivers
through edge networks in a timely manner. Secondly, the
model can be applied in the data analysis and visualization
service layer in ITS’s enterprise cloud in order to conduct
analysis over heterogeneous traffic data from multiple
sources and put forward informed suggestions to key stake-
holders who have overseen the entire metropolitan traffic
network.
3.2. Design of Urban Traffic Indicators. Urban trafficflow is a
crucial part of smart city management with multiple
influencing factors involved. When it comes to the metropol-
itan area, the issue can be even more complex. The factors
influencing urban trafficflow normally include flow from
adjacent traffic nodes, weather condition, and point of inter-
est (POI), such as nearby school, hospital, and shopping mall,
thanks to the multiple traffic data acquired from the edge
node, which includes spatial data, geographical information,
road network data, trafficflow data, weather condition data,
and traffic management data. The paper is based on traffic
flow data from Guiyang City, with a spatial span of 717 inter-
sections and a temporal span of 6 months; the experimental
data type is shown in Table 1. A group of urban traffic indi-
cators is built to evaluate factors that are influencing urban
trafficflow.
The indicators of weather data are as follows:
(1) Fog: the level of fog can be graded as minor fog, fog,
heavy fog, dense fog, and heavy dense fog
(2) Haze: the level of haze can be graded as light haze,
haze, and heavy haze
(3) Rain: the level of rain can be graded as light rain,
medium rain, heavy rain, storm rain, and heavy
storm rain
(4) Snow: the level of snow can be graded as light snow,
medium snow, and heavy snow
3.3. Methodology for the CPSO/SSVM Urban Traffic Flow
Prediction Model. The urban traffic prediction model based
on various kinds of machine learning methodologies is
key to the construction of ITS. It is able to provide tech-
nical support for urban traffic management especially flow
control of busy traffic nodes in the metropolitan area.
Urban traffic is a complex system with high dynamic,
which makes it difficult to analyze in a short-time manner.
Increasing randomness within the urban intelligent system
makes it difficult for trafficflow prediction. Short-time
trafficflow is the key part of urban traffic big data; the
basic characteristics of short-time trafficflow include non-
linearity, randomness, and uncertainty.
Currently, urban traffic control and route guidance is
mostly applied on a preset manner; only a few cities apply
self-adaptive control mode during trafficflow detection. In
Table 1: Experimental data type.
Data source Data type No. of indicators Content of indicators
Trafficflow data Continuous variable 1 Trafficflow
Weather data Discrete variable 4 Fog, haze, rain, snow
POI data Discrete variable 10
Adjacent traffic nodes with 500 meters, no. of shopping malls,
no. of schools, no. of hospitals, no. of tourist sites,
no. of bus stations, no. of restaurants, no. of hotels, no. of supermarkets
4 Wireless Communications and Mobile Computing

order to make up for the inefficiency, various machine learn-
ing methodologies have been introduced to build up related
prediction techniques. SVM has been widely applied in the
area of trafficflow prediction. With the method of structural
risk minimization, SVM has great advantages on overcoming
problems such as a small sample, nonlinearity, curse of
dimensionality, oversimulation, and local minimization,
which simplifies the problem of classification and regression
during trafficflow analysis. Therefore, SVM has shown a
promising future in intelligent traffic control and guidance,
which can ease the issue of traffic congestion in the metropol-
itan area.
The paper has proposed an urban traffic prediction
model based on CPSO/SSVM, which is able to predict
short-time trafficflow at city intersection by considering
multiple factors including POI and weather condition and
acquire better prediction result compared to tradition SVM
algorithm.
The standard SVM algorithm is as follows [17]:
min
w,b,C
w
kk
2
2+CeTy
s:t:D⋅Aw +eb
ðÞ
≥e
y≥0:
ð1Þ
In 2005, Lee et al. from Taiwan University introduced the
concept of smooth function to improve SVM by introducing
nondifferentiable function [18]; the formula is as follows:
min
w,b,C
1
2∗Ce−DAw−eb
ðÞðÞ
+



2
2+1
2∗wTw+b2

:ð2Þ
There is a nondifferentiable function in the objective
function, which has shown a strong rotundity and unique
solution; however, its nondifferentiable function is not
smooth; therefore, a smooth function is required to infinitely
approach a nondifferentiable function. Lee et al. have per-
formed integral processing over a sigmoid function [18]
and acquire
px,k
ðÞ
=x+1
k∗lg 1 + e−kx

:ð3Þ
By taking an integral function of Sfunction as smooth
function, smooth processing has been performed over a non-
differentiable part in formula (2), which therefore acquired
initial SSVM.
min
w,b,C
1
2∗Cpe−DAw−eb
ðÞ
,k
ðÞ
kk
2
2+1
2∗wTw+b2

:ð4Þ
With the introduction of SSVM, it can replace nondiffer-
entiable function by introducing a different smooth function
to achieve the effect of smooth processing, which resulted to
lots of smooth functions with a good approximation effect,
which in turn resulted to several SSVM algorithms.
In 2005, Yuan et al. from UESTC has proposed a function
as follows [19]:
Tx,k
ðÞ
=
0, x<−1
k,
k2
6x3+k
2x2+1
2x+1
6k,−1
k<x<0,
−k2
6x3+k
2x2+1
2x+1
6k,0≤x≤1
k,
x,x>1
k:
8
>
>
>
>
>
>
>
>
>
>
>
>
<
>
>
>
>
>
>
>
>
>
>
>
>
:
ð5Þ
In 2013, Wu et al. from XUPT has proposed two 2
nd
-
order smooth functions as follows [20, 21]:
φx,k
ðÞ
=
0, x<−1
3k,
3
2k21
3k+x

3
,−1
3k≤x<0,
x+3
2k21
3k−x

3
,0≤x≤1
3k,
x,x>1
3k,
8
>
>
>
>
>
>
>
>
>
>
>
>
>
<
>
>
>
>
>
>
>
>
>
>
>
>
>
:
ð6Þ
Gx,k
ðÞ
=
0, x<−1
4k,
8
3k2x3+2kx2+1
2x+1
24k,−1
4k≤x<0,
−8
3k2x3+2kx2+1
2x+1
24k,0≤x≤1
4k,
x,x>1
4k:
8
>
>
>
>
>
>
>
>
>
>
>
<
>
>
>
>
>
>
>
>
>
>
>
:ð7Þ
By a piecewise smooth function from formula (6) and (7)
to an approximate nondifferentiable part in formula (2), the
approximation effect and final regression effect of the func-
tion have shown that the accuracy of formula (7) is more
superior than formula (6) and (7). The paper proposed a
new type of 2
nd
smooth function; the approximation effect
and final regression effect of the function are more superior
than formula (6) and (7); the proposed smooth function is
as follows:
Mx,k
ðÞ
=
0, x<−1
7k,
49
6k2x3+7
2kx2+1
2x+1
42k,−1
7k≤x<0,
−49
6k2x3+7
2kx2+1
2x+1
42k,0≤x≤1
7k,
x,x>1
7k:
8
>
>
>
>
>
>
>
>
>
>
>
<
>
>
>
>
>
>
>
>
>
>
>
:ð8Þ
5Wireless Communications and Mobile Computing

The paper has set up a new SSVM algorithm (Ma-Liu
Piecewise Smooth Support Vector Machine, MLSSVM) as
follows:
min
w,b,C
1
2∗CMe−DAw−eb
ðÞ
,k
ðÞ
kk
2
2+1
2∗wTw+b2

:
ð9Þ
Theorem 1. The smooth function Mðx,kÞis as formula (8);
x+= max f0,xgindicates the nondifferentiable function, and
smooth function Mðx,kÞsatisfies the following:
(1) Mðx,kÞis about x2
nd
-order smooth
(2) Mðx,kÞ≥x+
(3) For x∈R,Mðx,kÞ2−x2
+≤1/821k2
Proof.
(1) When x= ±1/7kand x=0, condition holds true for
function Mðx,kÞas follows: Mð−1/7k,kÞ=0,lim
x→0−
Mðx,kÞ= lim
x→0+Mðx,kÞ,Mð1/7k,kÞ= 1/7k,M′ð−1/7
k,kÞ=0,lim
x→0−M′ðx,kÞ= lim
x→0+M′ðx,kÞ,M′ð1/7k,kÞ=1,
M′′ð−1/7k,kÞ=0,lim
x→0−M′′ðx,kÞ= lim
x→0+M′′ðx,kÞ,
M′′ð1/7k,kÞ=0. Therefore, Mðx,kÞis 2
nd
-order
smooth about x
(2) When x≥1/7kand x≤−1/7k,Mðx,kÞ≥x+holds
true obviously x∈ð0, 1/7kÞ;Mðx,kÞ−x+shows
decremental properties, Mðx,kÞ−x+≥Mð1/7k,kÞ−
x+=0;x∈ð−1/7k,0Þ,Mðx,kÞ−x+shows incremen-
tal properties, Mðx,kÞ−x+≥Mð−1/7k,kÞ=0;there-
fore, Mðx,kÞ≥x+
(3) When x≥1/7kand x≤−1/7k,Mðx,kÞ2−x2
+≤1/
821k2holds true obviously x∈ð−1/7k,0Þ,Mðx,kÞ2
−x2
+=Mðx,kÞ2≤Mð0, kÞ2< 1/821k2;x∈ð0, 1/7kÞ,
let fðxÞ=Mðx,kÞ2−x2
+=Mðx,kÞ2−x2,t=7kx ∈ð0, 1Þ;
by transformation, we are able to acquire
fðtÞ=ð−ð1/49Þt3+ð1/28Þt2+ð1/14Þt+ð1/14ÞÞ2−ð1/49Þt2;
under t∈ð0, 1Þ, the maximum value of fðtÞis t=
0:1705; plug that value into fðtÞ, we are able to
acquire fð0:1705Þ=0:0012/k2< 1/821k2. Therefore,
for any given x∈R,Mðx,kÞ2−x2
+≤1/821k2; the
theorem is proved
The smooth function in this paper has a good degree of
approximation under the same kvalue. The paper compared
the result of functions from formula (5), (6), and (7) on the
approximation effect over the nondifferentiable function.
The comparison result is as in Figure 3. Figure 3 shows that
the smooth function proposed by this paper has a better
degree of approximation.
In order to further improve the computing efficiency of
the SSVM algorithm, the chaotic particle swarm algorithm
with good optimization characteristics has been introduced
for the optimization of parameters over penalty coefficient,
insensitive parameters, and relaxation variable [22].
Chaotic characteristic itself is a pattern and possesses the
property of pseudorandomness. The paper will take advan-
tage of the two characteristics to track any state without rep-
etition. The paper applies the logistic equation to build a
chaotic optimization sequence, which is as formula (10)
[23, 24].
xt+1
ðÞ
=μxt
ðÞ1−xt
ðÞðÞ
, t=0,1,2,⋯n:ð10Þ
In formula (10), μis the overall control parameter.
When 0<xð0Þ<1,μ=4, formula (10) is in a complete
chaotic state [23, 24].
This paper applies two characteristics of chaos to initial-
ize the position and velocity of particles in the system, which
is pseudorandomness of chaos theory and its own law to
enhance search capability for the swarm. Assume formulas
hold true as follows:
ωi+1
ðÞ
=4:0ωi
ðÞ⋅1−ωi
ðÞðÞ
,ð11Þ
ωi
ðÞ=α+β−α
ðÞ
⋅ωi
ðÞ
:ð12Þ
In formula (12), when α=0:4,β=0:9, the system is in a
perfect state of chaos. Two constants r1,r2have been intro-
duced to update the logistic mapping, which is as follows:
rit+1
ðÞ
=4:0rit
ðÞ
⋅1−rit
ðÞðÞ
,ð13Þ
where riðtÞ∈ð0, 1Þ,i=1,2.
Assume objective function is as follows:
min fx
1,x2,⋯,xn
ðÞ
s:t:ai≤xi≤bi, i=1,2,⋯,n:
ð14Þ
–
0.0 2
–
0.015 -0.01 -0.005 0 0.005 0.01 0.015 0.02
0
0.005
0.01
0.015
0.02
0.025
0.03
X
Y
TPSSVM
TSSSVM
PWSSVM
MLSSVM
Figure 3: Approximation accuracy of four smooth functions.
6 Wireless Communications and Mobile Computing

The optimized process for the particle swarm algorithm
is shown in Figure 4.
The specific procedures of the adaptive optimization
algorithm are as follows [23, 24]:
(1) Chaos initialization of corresponding parameters of a
particle swarm algorithm
(2) Comparison and optimization of the fitness level
obtained from step (1)
(3) Comparison between optimal fitness pbestiwithin the
swarm and gbestiof all the particles and acquire the
particle’s optimal position and state
(4) Update the particle’s position and velocity
(5) Chaotic optimization of the optimal position
(6) In the original solution space, obtain a feasible solu-
tion PðmÞ
g, calculate the level of fitness, obtain the opti-
mal feasible solution p∗, and replace other particle
positions
(7) Through the operations of steps (1)-(7), and satisfy-
ing the set optimization conditions, the search is
stopped, the optimal solution is given, and the best
position is obtained, otherwise, return to step (2)
and repeat the operation
3.4. Framework for the CPSO/SSVM-Based Urban Traffic
Flow Prediction Model. The SVM prediction method is
applied to predict multisource urban trafficflow data. It
inherits the relevant ideas of machine learning. Through con-
tinuous training and learning of the prediction model, the
goal of effective prediction is finally achieved. The process
mainly includes two parts, the training process and the test-
ing process. Figure 5 shows the basic framework of the urban
trafficflow prediction model.
In this paper, multisource urban trafficflow data is used
as a model input, which needs to go through five stages: data
collection, data preprocessing, data normalization process-
ing, SSVM construction, and optimization problem solving.
Among them, the preprocessed data consisted of training
data and test data. The training data set is used to train the
CPSO/SSVM model, and then, the test data set is used to test
the performance of the established prediction model. The
model’s performance is improved by constant learning and
adjusting, which will eventually lead to an automatic predic-
tion of urban trafficflow. The execution steps of the urban
trafficflow prediction model based on CPSO/SSVM are as
follows.
(1) Data collection stage: collect trafficflow data, weather
condition data, and POI (points of interest) data
from various sources
(2) Data preprocessing stage:the collected multisource
urban intersection trafficflow data went through data
cleaning and preprocessing procedures, considering
the universality of the algorithm application scenario.
Firstly, prepossessed all 9,577,708 pieces of traffic
information from 717 intersections on a Python 3.8
platform, all the invalid records have been removed,
and a descriptive statistical analysis was carried out
to filter out key urban intersections with higher aver-
age flow rate, ones with a higher average flow rate and
a larger number of surrounding POIs is used as the
model input
Chaos initialization particle position and
velocity
Calculate tness for each
particle
If tness (x)>tness(pbest) then pbest=x
If tness(x )>tness(gbest)then gbest=x
Chaos optimization
optimal position
Optimize particle speed
Meet termination
conditions
Ye s
No, form the next
generation group
gbest parameter is optimal
parameter
Figure 4: Diagram of the particle swarm algorithm.
7Wireless Communications and Mobile Computing

(3) Data normalization processing: normalize the multi-
source urban trafficflow data, including quantifying
the collected POI information of the city intersection
and the weather information of the day and apply the
normalization algorithm to process all model vari-
ables to form a unified metric
(4) Construct a smooth support vector machine: con-
struct a smooth support vector machine algorithm
model
(5) Optimization problem solving: construct a second-
order smooth kernel function and solve the optimiza-
tion problem with the SSVM algorithm model to
generated prediction results
4. Results and Discussion
Based on the Matlab_R2014a platform, this paper has built
up a trafficflow prediction algorithm by applying the
Trac ow data Weather
condition data
Data prepossessing
Build smooth kernel
function
Choose penalty
coecient
Build decision
function
Test set
Prediction
model
Test result
Training set Te st se t
POI data
Training set
or test set
Propose optimization
problem
Solve optimization
problem
Training set
Figure 5: Framework for the CPSO/SSVM-based urban trafficflow prediction model.
1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000
0
50
100
150
200
250
300
350
Test samp le dat a
Trac ow
Actual data
Paper algorithm
GA-BP algorithm
LS-SVM algorithm
Figure 6: Analysis of prediction results.
1994 1996 1998 1999
35
40
45
50
55
60
Test sample data
Trac ow
Actual data
Paper algorithm
GA-BP algorithm
LS-SVM algorithm
Figure 7: Comparison of sample data under the same dimension.
8 Wireless Communications and Mobile Computing

optimized parameter results from part 3 and uses particle
swarm optimization-smooth support vector regression to
predict trafficflow. The experimental data set is the
cross-section flow data of Guiyang City, Guizhou Province
(5 min interval). 200 intersections with high average traffic
flow were selected with 10 flow records per intersection,
which is a total of 2000 flow records for model testing.
Among them, 1989 records are the training set, and the
last 11 records are the test set. In order to verify the pre-
diction effect of the algorithm in this paper, this paper
uses a genetic-BP neural network [25] and LS-SVM algo-
rithm [26] for comparative analysis. The specific results
are shown in Figure 6.
It can be concluded from Figure 6 that the proposed algo-
rithm has higher prediction accuracy than other algorithms.
Due to the large span of trafficflow in Figure 6, 1994
th
,
1996
th
, 1998
th
, and 1999
th
sample data have selected for com-
parison under the same dimension. The comparison result is
as in Figure 7.
From Figure 7, it can be concluded that proposed algo-
rithm is the best match with actual data. GA-BP algorithm
have shown large deviation at 1998
th
and 1999
th
sample data,
LS-SVM algorithm has shown large deviation at 1996
th
sam-
ple data. Therefore, the algorithm put forward by the paper
has a better performance in prediction.
In order to facilitate the analysis, the relative error is
introduced for analysis. The relative error data is shown in
Table 2, its comparative analysis is shown in Figure 7.
As can be concluded from Figure 8 and Table 2, com-
pared with the genetic-BP neural network and the minimum
support vector machine regression algorithm, the relative
error of this algorithm is lower, the prediction error is within
5%, and the accuracy and stability of the algorithm both meet
the forecasting needs of actual trafficflow. Among three algo-
rithms predicting fluctuating trafficflow, the genetic BP neu-
ral network still demonstrates the issue of overfitting, which
leads to a higher prediction error. The minimum SVM per-
forms well for the less fluctuated data but has a weak gener-
alization ability when dealing with fluctuating traffic with
high intensity. In comparison, CPSO/SSVM proposed in
the paper has shown a stronger level of robustness and gen-
eralization ability.
In order to further analyze the characteristics of these
three algorithms, the time cost of the three algorithms under
different sample data in the prediction process is counted.
The specific results are shown in Table 3.
Table 2: Relative error of prediction results of three algorithms.
Algorithm 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000
GA-BP 11.91 7.97 1.92 3.95 4.11 4.06 4.14 24.50 16.75 7.28 5.25
LS-SVM 5.95 6.00 4.88 2.73 4.18 1.49 5.70 19.00 15.38 2.89 9.75
MLSSVM 2.59 3.95 0.22 0.95 2.32 1.11 1.77 2.00 4.85 0.32 0.25
1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000
0
5
10
15
20
25
Test sample data
Mean square error (%)
Paper algorithm
GA-BP algorithm
LS-SVM algorithm
Figure 8: Analysis of relative error.
Table 3: Comparison of three algorithms time overhead.
Algorithm No. of sample (500)
time overhead (S)
No. of samples (1000)
time overhead (S)
No. of samples (2000)
time overhead (S)
GA-BP 0.0158 0.0276 0.0394
LS-SVM 0.0162 0.0287 0.0299
Paper algorithm 0.0147 0.0196 0.0255
9Wireless Communications and Mobile Computing

It can be known from Table 3 that although all three algo-
rithms can achieve trafficflow prediction under low time
overhead, the algorithm in this paper has faster processing
speed and higher adaptability. Therefore, based on the com-
prehensive analysis of the experimental results and the theo-
retical basis, the algorithm in this paper has a good prediction
effect.
In conclusion, the SSVM algorithm put forward in this
paper has better prediction accuracy in the area of trafficflow
management and possesses better robustness and rapid
adaptability. The algorithm can meet the requirements of
low latency during the processing of heterogeneous data at
the edge side, which can benefit prospective research that
combines edge computing and big data analytics.
5. Conclusions
In this paper, a CPSO/SSVM model is constructed to predict
trafficflow at the intersection of Guiyang City. The
CPSO/SSVM model achieves better approximation and
regression effects by constructing a new second-order
smooth function, and at the same time, further improves
the computational efficiency of the SSVM regression algo-
rithm through particle swarm optimization. Based on exper-
imental results, it is proved that CPSO/SSVM model is able to
output more accurate result compared with the GA-BP algo-
rithm and LS-SVM algorithm. The model has powerful
information processing and prediction capabilities and can
be applied to deal with complex nonlinear problems, espe-
cially the problem of trafficflow prediction at urban intersec-
tion, the location of which normally comes with complex
scenes and various disturbance factors. The model provides
an alternative solution for the research of data-driven urban
trafficflow forecasting, and extends the application of SVM
algorithm in the area of short-term urban trafficflow predic-
tion at the same time. The output accuracy of the model is
high and can be deployed in ITS to achieve short-term traffic
flow prediction, which has a high application value for smart
city development and real-time traffic management in edge
computing scenarios.
Data Availability
The paper is based on trafficflow data from Guiyang City,
with a spatial span of 717 intersections and a temporal span
of 6 months. The experimental data set is the cross-section
flow data of Guiyang City, Guizhou Province (5 min interval).
Conflicts of Interest
The authors declare that there is no conflict of interest
regarding the publication of this paper.
Acknowledgments
The research is part of the author’s employment to explore
potential applications of big data analytics in smart city
development and urban traffic planning. The employer is
Zhejiang University.
References
[1] K. Su, J. Li, and H. Fu, “Smart city and the applications,”in
2011 International Conference on Electronics, Communica-
tions and Control (ICECC), pp. 1028–1031, Ningbo, China,
September 2011.
[2] Z. Khan, A. Anjum, K. Soomro, and M. A. Tahir, “Towards
cloud based big data analytics for smart future cities,”Journal
of Cloud Computing, vol. 4, no. 1, p. 2, 2015.
[3] F. Lin, Y. Zhou, X. An, I. You, and K.-K. R. Choo, “Fair
resource allocation in an intrusion-detection system for edge
computing: ensuring the security of internet of things devices,”
IEEE Consumer Electronics Magazine, vol. 7, no. 6, pp. 45–50,
2018.
[4] H. Hui, C. Zhou, S. Xu, and F. Lin, “A novel secure data trans-
mission scheme in industrial internet of things,”China Com-
munications, vol. 17, no. 1, pp. 73–88, 2020.
[5] W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, “Edge computing:
vision and challenges,”IEEE Internet of Things Journal,
vol. 3, no. 5, pp. 637–646, 2016.
[6] C. Gong, F. Lin, X. Gong, and Y. Lu, “Intelligent cooperative
edge computing in the internet of things,”IEEE Internet of
Things Journal, p. 1, 2020.
[7] L. Yang and B. Liu, “Temporal data fusion at the edge,”in 2019
IEEE International Conferences on Ubiquitous Computing &
Communications (IUCC) and Data Science and Computational
Intelligence (DSCI) and Smart Computing, Networking and
Services (SmartCNS), Shenyang, China, October 2019.
[8] A. Ndikumana, N. H. Tran, T. M. Ho et al., “Joint communica-
tion, computation, caching, and control in big data multi-
access edge computing,”IEEE Transactions on Mobile Com-
puting, vol. 19, no. 6, pp. 1359–1374, 2020.
[9] X. Xu, Q. Liu, Y. Luo et al., “A computation offloading method
over big data for IoT-enabled cloud-edge computing,”Future
Generation Computer Systems, vol. 95, pp. 522–533, 2019.
[10] Q. Zhang, X. Zhang, Q. Zhang, W. Shi, and H. Zhong, “Fire-
work: big data sharing and processing in collaborative edge
environment,”in 2016 Fourth IEEE Workshop on Hot Topics
in Web Systems and Technologies (HotWeb), pp. 20–25, Wash-
ington, DC, USA, October 2016.
[11] B. P. L. Lau, S. H. Marakkalage, Y. Zhou et al., “A survey of
data fusion in smart city applications,”Information Fusion,
vol. 52, pp. 357–374, 2019.
[12] A. J. Jara, D. Genoud, and Y. Bocchi, “Short paper: sensors data
fusion for smart cities with KNIME: a real experience in the
smartsantander testbed,”in 2014 IEEE World Forum on Inter-
net of Things (WF-IoT), Seoul, South Korea, March 2014.
[13] X. Jiang and H. Adeli, “Dynamic wavelet neural network
model for trafficflow forecasting,”Journal of Transportation
Engineering, vol. 131, no. 10, pp. 771–779, 2005.
[14] Y. Lv, Y. Duan, W. Kang, Z. Li, and F.-Y. Wang, “Trafficflow
prediction with big data: a deep learning approach,”IEEE
Transactions on Intelligent Transportation Systems, vol. 16,
no. 2, pp. 865–873, 2014.
[15] J. Zhang, Y. Zheng, J. Sun, and D. Qi, “Flow prediction in
spatio-temporal networks based on multitask deep learning,”
IEEE Transactions on Knowledge and Data Engineering,
vol. 32, no. 3, pp. 468–478, 2020.
[16] C. Yuan, D. Li, and Y. Xi, “Short term urban traffic mode pre-
diction based on VOMM,”in 2016 Chinese Control and Deci-
sion Conference (CCDC), Yinchuan, China, May 2016.
10 Wireless Communications and Mobile Computing

[17] C. J. C. Burges, “A tutorial on support vector machines for pat-
tern recognition,”Data Mining and Knowledge Discovery,
vol. 2, no. 2, pp. 121–167, 1998.
[18] Y.-J. Lee, W.-F. Hsieh, and C.-M. Huang, “Epsilon-SSVR: A
smooth support vector machine for epsilon insensitive regres-
sion,”IEEE Transactions on Knowledge and Data Engineering,
vol. 17, no. 5, pp. 678–685, 2005.
[19] Y. B. Yuan, J. Yan, and C. X. Xu, “Polynomial smooth support
vector machine,”Chinese Journal of Computers, vol. 28, no. 1,
pp. 9–17, 2005.
[20] Q. Wu, “A new class of ε-piecewise smooth support vector
regressions,”Journal of Information Science & Engineering,
vol. 31, no. 5, pp. 1813–1828, 2015.
[21] W. U. Qing, L. Bo, W. Wan, and W. En, “Face recognition
method based on multi-class classification of smooth support
vector machine,”Journal of Computer Applications, vol. 19,
no. 5, pp. 688–696, 2015.
[22] M. Clerc, Particle swarm optimization, John Wiley & Sons,
New Jersey, 2010.
[23] F.-P. An, “Image feature extraction algorithm based on bi-
dimensional local mean decomposition,”Optical Review,
vol. 26, no. 1, pp. 43–64, 2019.
[24] F.-P. An and Z.-W. Liu, “Bi-dimensional empirical mode
decomposition (BEMD) algorithm based on particle swarm
optimization-fractal interpolation,”Multimedia Tools and
Applications, vol. 78, no. 12, pp. 17239–17264, 2019.
[25] G. D. Sun, L. A. Qin, Z. H. Hou et al., “Feasibility analysis for
acquiring visibility based on lidar signal using genetic
algorithm-optimized back propagation algorithm,”Chinese
Physics B, vol. 28, no. 2, article 024213, 2019.
[26] J. Zhu, “Probability least squares support vector machine with
L1 norm for remote sensing image retrieval,”International
Journal of Information and Communication Technology,
vol. 13, no. 2, p. 208, 2018.
11Wireless Communications and Mobile Computing