Identifying Hidden Influences of Traffic Incidents’ effect in Smart Cities

Full text

Identifying Hidden Influences of Traffic Incidents’
Effect in Smart Cities
Attila M. Nagy
Department of Networked Systems and Services
Budapest University of Technology and Economics
Magyar Tudósok krt 2., Budapest, Hungary
Email: anagy@hit.bme.hu
Vilmos Simon
Department of Networked Systems and Services
Budapest University of Technology and Economics
Magyar Tudósok krt 2., Budapest, Hungary
Email: svilmos@hit.bme.hu
Abstract—The road network of big cities is a complex and
hardly analyzable system in which the accurate quantification
of interactions between nonadjacent road segments is a serious
challenge. In this paper we would like to present a novel method
able to determine the effects (the time delay and the level of
the correlation) of distinct road segments on each other of a
smart city’s road network. To reveal these relationships, we are
investigating unexpected events such as traffic jams or accidents.
This novel analysis can give a significant insight to improve the
operation of currently widespread traffic prediction algorithms.
I. INT ROD UC TI ON
NOWADAYS smart city services are becoming more
widespread than ever as cities are growing and becoming
more and more crowded as a result of urbanization and growth
of the world population. The rapid progress of urbanization
improved life of many people, but also brought remarkable
challenges, like traffic congestions that can lead to increased
energy/fuel consumption and enormous emission of pollutants
[1]. These phenomena heavily and directly impact the health,
the life quality and expectancy of city dwellers. According
to [2], laboratory studies indicated that transport-related air
pollution may increase the risk of developing allergies and can
exacerbate symptoms, particularly in susceptible subgroups,
while [3] showed that traffic jams increase the risk of heart
attacks.
Intelligent management systems, such as Advanced Traffic
Management System (ATMS) and Intelligent Transportation
System (ITS) can help overcome or significantly reduce the
impact of such negative effects on city dwellers. Forecasts of
these systems can support traffic control centers in managing
the road network and allocating resources systematically, for
example opening/closing lanes, pricing dynamically parking
places or adapting the traffic lights to the current traffic trends.
In vehicle navigation the knowledge of traffic forecasts for
different routes during the route planning is advantageous, as
the devices will be able to calculate more efficient routes and
reduce travel time. Insight into vehicular flows of smart cities
could make searching for parking spaces much easier and
faster. It could also provide added value for emerging V2X
based traffic control systems, which can play an important
role in route planning of self-driving cars.
In the literature, there are numerous prediction models
utilized for traffic flow prediction, however the road network of
big cities is a complex and hardly analyzable system in which
unexpected events could significantly decrease the correctness
of the result of the prediction models.
Every predicted value is composed of a predictable compo-
nent and an error [4], which includes both prediction error and
unpredictability of uncertainty. Thus the predictable value is
derived from the deterministic part and the predictable part of
uncertainty. Therefore it follows, that the predictability of the
traffic flow depends on whether the model is able to predict the
uncertainty part or not. Fortunately, lots of prediction models
can be prepared for handling the uncertainty part by integrating
different external data sources. The uncertainty is influenced
by many factors, like weather condition, mass events, road
constructions, road closures, accidents etc. By considering
these external environmental factors, the error of prediction
models can be decreased.
In this paper, a new method will be presented, which aims to
reduce the previously mentioned uncertainties. The algorithm
focuses on unexpected events, such as traffic accidents, which
can have a negative impact on the traffic prediction. By
investigating the effect of these phenomena, the algorithm is
able to:
•identify neighboring road segments that could be affected
by the event
•to determine the level of correlation between the road
segment affected by the accident and its neigboring road
segments,
•to quantify the time delay: the time needed for the
effects of the accident to propagate to neighboring road
segments.
By fusing this information with real-time traffic information,
the prediction models will be able to provide more accurate
predictions even in the case of an unexpected event happening
nearby.
The paper is organized as follows. In Section II., various
prediction techniques are introduced aimed at reducing the
error of prediction models. This section also contains a short
summary of usable data sources. In Section III, the algorithm
is presented in detail, which is followed by a case study
simulation in Section IV. Section V concludes the paper and
points out the current weaknesses and future improvements of
the algorithm.
Proceedings of the Federated Conference on
Computer Science and Information Systems pp. 651–658
DOI: 10.15439/2018F194
ISSN 2300-5963 ACSIS, Vol. 15
IEEE Catalog Number: CFP1885N-ART c
2018, PTI 651

(a) A road network with control points
fe1,2 cp1
cp2
cp3
cp4
cp5cp7
cp6
fe2,1
fe3,2
fe2,3
fe2,4
fe4,5
fe5,7
fe7,5
fe6,5
fe5,6
(b) The flow graph model of the road network
Fig. 1: An example of the traffic graph model interpretation. On Figure 1a, the original road network is depicted with control
points, while Figure 1b shows the road network’s graph representation.
II. TR AFFI C PRE DI CT IO N METHODS IN SMART CITIES
A. Prediction Techniques
There are several proposed prediction models [5], which
perform well for regular conditions, however an unexpected
event could significantly decrease the quality of their traffic
forecasts. The reason is that the predictability of the traffic
flow depends on whether the model is able to predict the
uncertainty part of the traffic flow with the required precision.
The uncertainty is influenced by many factors, like weather,
events, road constructions, lighting conditions etc. Incorporat-
ing external environmental factors and fused data [6] to the
model is crucial to decrease the error of the prediction and
increase the predictable part of uncertainty.
Traffic is predictable in the sense that it does not vary
significantly during weekdays and during most months of
the year [7]. In [8] similar results were obtained as well as
they have found a relatively high daily predictability of traffic
conditions despite the absence of any apriori knowledge of
drivers’ origins and destinations and the quite different travel
patterns between weekdays and weekends.
A neurowavelet prediction algorithm was proposed [9] to
forecast the hourly traffic flow considering the effect of
rainfall. In the article, the authors use a stationary wavelet
transform to reveal correlation between different weather con-
ditions and changes in the traffic flow. An examination was
carried out [10] whether or not road usage on a particular
location determines the impacts of various weather conditions.
The study showed that the precipitation, cloudiness and wind
speed reduce traffic intensity, while high temperatures and hail
significantly increase traffic intensity.
Other papers contentrated on the spatio-temporal property
of the traffic flow, by using different Autoregressive Integrated
Moving Average (ARIMA) model variants [11]–[13], applying
K-Nearest Neighbors (KNN) models [14], [15] while others
employed Convolutional Neural Network (CNN) for this pur-
pose [16]–[18]. Deep learning based prediction model was
also presented for spatio-temporal data [17]. The prediction
model uses spatial and temporal relations and integrates global
information (such as day of week, meteorological conditions,
etc.) to decrease the uncertainty.
Relation between traffic predictability and prediction time
horizon was investigated [4] by examining spatio-temporal
traffic relationship using Cross-correlation function (CFF).
The time lag calculated by CFF can be used to determine
prediction time horizon, and the cross-correlation coefficient
can be utilized to identify the spatial relations that can be used
in prediction.
Solutions enumerated in this section aim to handle the pre-
viously listed uncertainties of traffic flows. However, we have
not found significant work aimed at increasing the predictabil-
ity of traffic flow through the investigation of unexpected
events like accidents or traffic congestions of uncontrolled
traffic flow. In this paper, we will present a novel method,
which can exploit these events to measure the time delay and
calculate the level of influence between distinct road segments.
B. Data sources
In the first generation of ATMSs and ITSs [19] the utilized
data sources were various presence sensors in fixed positions,
able to detect the presence of nearby vehicles. Initially in-
ductive loop detectors were the most popular, but nowadays a
wide variety of sensors became available [20].
Recently, the advent of GPS equipped smartphones and
vehicles has given rise to a relatively new type of data source
that could supplement presence type sensors to gather more
detailed information or get data about roads, which have not
been covered with presence sensors yet.
Our method can leverage both types of data sources, but
in the case of GPS traces, a preprocess step is needed to be
inserted before the data model building.
652 PROCEEDINGS OF THE FEDCSIS. POZNA ´
N, 2018

III. MET HO DO LO GY
The road network of big cities is a complex and hard to ana-
lyze system in which the accurate quantification of interactions
between nonadjacent road segments is almost an insolvable
objective, because of the unique decisions of thousands of
drivers which makes the interactions invisible. However an
unexpected event could be used to reveal hidden connections
between road segments, because they always appear as an
outlier in the timeseries of the investigated data type (traffic
speed, traffic flow count, travel time, etc.). It follows, that if
the emergence of an unexpected event is known, the ripple
of that event can be observed through the network, thus the
hidden correlations will become observable. As an analogy,
we suppose that one can think of a road network as a huge
black box system, which has one input and numerous outputs.
If the system is fed with an unusual input, the inner behavior
of the system can be inferred through the outputs.
In this section, the Algorithm for Identifying Hidden In-
fluences (AIHI) will be introduced in detail, which targets
to exploit unexpected traffic events to reveal the previously
mentioned connections. In Subsection III-A, the graph based
data model will be presented which is suitable for the analysis
of unexpected events, then the distinct steps of the algorithm
will be explained in Subsection III-B.
A. Data model
In our solution, the road network is modeled with a F G =
(CP , F E)directed flow graph. Each cp ∈CP node represents
a control point, which is a special point of the road network,
where the traffic measurement is feasible by different type of
traffic sensors (such as inductive loop detectors, radar sensors,
audio sensors, etc.). A cp control point itself does not store any
traffic data, they just measure the traffic flow at their position.
The fe ∈F E directed flow edges represent a link between
two adjacent control points (cpsrc,cpdst ), where there is at
least one lane between the two control points in the spreading
direction of the traffic. To every f e directed flow edge, a ts
time series is assigned, which stores historical traffic flow
data. The ts time series of fe flow edge will contain those
measurements, which are provided by the cpdst destination
control point of fe. For instance, if there is a directed
flow edge between cp1(source) and cp2(destination) control
points denoted by fe1,2, then the f e1,2edge will contain the
measurements of cp2control point.
Besides the data from fixed position sensors, the data model
is also able to utilize GPS traces, if virtual control points are
defined and trace data is aggregated in these points.
On Figure 1, an example of the traffic graph interpretation
is depicted, it shows how the data model have to be interpreted
on a simple road structure. Figure 1a illustrates a simple
road network with control points, which are marked by cpi
identifiers. On Figure 1b, the directed flow graph of the
previous road network is visualized. The cpiidentifiers on this
figure are identical with the identifiers of the ones on Figure
1a, and there are fex,y directed flow edges in the graph, if
cpxand cpycontrol points are connected in the road network
in the spreading direction of the traffic.
We also have to deal with the timeliness of our model. The
different fixed position or GPS sensors sample the measured
data type with different frequences based on their settings.
Consequently the traffic analysis requires a homogeneous
sampling frequency. Different aggregating time intervals are
used in the literature for this purpose, which mainly depend
on the task at hand.
Generally, narrow intervals, for example 10 seconds, are
meaningless and really noisy. We have found that the most
common time intervals are in minutes (5-10 minutes) [21],
[22], but there are also many papers claiming that longer time
intervals would be more effective, like quarter or half an hour
[16], [23]. For our model, we chose a 30 seconds time interval
because too long time intervals could hide important features
of an unexpected event and the noisiness of the 30 seconds
scale does not affect the correctness of the AIHI.
B. The steps of the algorithm
1) Initialization: Let us denote a time series of f esrc,dst
flow edge by tssrc,dst in which data can be described as an
ordered sequence of discrete measurements:
tssrc,dst ={mt}t= 1,2,...T (1)
where mtis the measured traffic count value at time tat the
cpdst control point.
The entry point of the algorithm will be an fe directed
flow edge, for which the associated ts time series shows
unexpected event between an arbitrary (tstart,tend) time
interval. The (tstart,tend ) time interval contains an unexpected
event, if a statistically significant change can be detected in the
behavior/shape of the ts time series between tstart and tend
compared to the tshist historical average, or in other words, ts
time series contains an anomalous part compared to the tshist
historical average.
Fig. 2: Visualization of anomaly behavior compared to Pre-
dicted flow
ATTILA NAGY, VILMOS SIMON: IDENTIFYING HIDDEN INFLUENCES OF TRAFFIC INCIDENTS’ EFFECT IN SMART CITIES 653

Input :
•F G: Directed flow graph of the road network
•fe: The investigated directed edge
•tstart: The start time of the unexpected event
Output: The effects of the event organized in a tree
structure
1job_pool ←[];
2visited_edges ←[];
3tsan =findAnomaly(fe.ts,tstart );
4addJob({fe,tsan,tstar t,f orward});
5while job_pool is not empty do
6j=getNext(job_pool);
7addVisitedEdge(j.fe);
8(b, i) = bestFitLag(j.tsan ,j.f e.ts,j.tstart ,
j.dir);
9is_anomaly, next_tsan =
findAnomaly(j.ts,nj.tstart +b);
10 if is_anomaly then
11 s_neighs =getEdges(j.f e.cpsrc );
12 foreach edge in s_neighs do
13 if j.fe.cpsrc is edge.cpdst and edge not
in visited_edges then
14 addJob({edge,next_tsan ,
tstart +b,backward});
15 end
16 end
17 d_neighs =getEdges(j.f e.cpdst );
18 foreach edge in d_neighs do
19 if j.fe.cpdst is edge.cpsrc and edge not
in visited_edges then
20 addJob({edge,next_tsan ,
tstart +b,f orward});
21 end
22 end
23 end
24 end
Algorithm 1: AIHI algorithm
There are two methods to discover such time intervals.
The easiest way when we have apriori knowledge about the
occured unexpected events like accidents or road closures as
these can be used directly as the input of the AIHI algorithm.
The other possible approach is to execute an extensive search
in the raw historical dataset for unexpected events. This
approach requires a classification model that is able to decide
whether a tssrc,dst time series contains an unexpected event
or not.
The AIHI algorithm needs the following three inputs:
•The F G flow graph of the road network
•The fe flow edge, which was the source of the unex-
pected event
•The tstart time of the emergence of the unexpected event
on fe
Utilizing these three inputs, the algorithm will follow the
effect of the unexpected event through the traffic flow graph
and determining those flow edges that could be affected by
the input event.
2) Processing of a job: AIHI algorithm 1 uses a job
pool based approach in which the whole investigation task
is separated to smaller independent subtasks. In this case,
a subtask is responsible for the investigation of whether the
currently examined fe flow edge’s ts time series is affected by
the source unexpected event or not. To run a job, the following
elements are necessary:
•An fe flow edge
•The tsan time series, which contains the whole anomaly
part identified by the source job
•The tstart emergence time of the anomaly in the source
job
•The dir direction of the spread of the event (forward
or backward), because the unexpected events of the road
network can have an effect in both directions.
To start the algorithm, the first job will be created from
the entry point. The entry point contains all necessary job
input parameters, except the tsan time series, thus by using
the findAnomaly function (in Section III-B4), the anomalous
part of the ts time series of fe flow edge have to be calculated.
After that, the execution of the algorithm can be started and
the processing of jobs will be continued until the pool has
been emptied.
A job will execute these steps:
1) Find the best fitting best_lag time lag between the
ts time series of fe flow edge and tsan anomalous
time series from tstart in the chosen dir direction (see
Algorithm 2)
2) Check that an anomalous event can be identified from
best_lag or not (see Algorithm 3)
3) If an anomalous event is detected during the second step,
then the adjacent flow edges of the investigated fe flow
edge are put into the job pool as new jobs in which the
source job will be the current job
3) Find best lag: The BestFitLag function is responsible
for determining the start of an anomalous event in the ts time
series of the current job.f e flow edge.
We can assume that the shape of the anomalous time series
tsan is quite similar to the anomaly observed in the actual
ts time series of job.f e. To measure this similarity we de-
fined a new distance function, called shape_dist (Equation 2).
Contrary to other distance function like Manhattan, Euclidean
or DynamicTimeWarping [24], it measures the similarity the
time series’ shape by differentiating changes in the different
time series:
shape_dist(x, y) = v
u
u
t
n
X
i=1
((xi−xi−1)−(yi−yi−1))2(2)
The shape_dist function is calculated with increasing lag =
0,1,2, ... between ts time series and tsan time series. It can
654 PROCEEDINGS OF THE FEDCSIS. POZNA ´
N, 2018

Input :
•tsan: The time series containing the whole
anomaly part
•ts: The time series of the fe flow edge
•tstart: The emergence time of the anomaly
in the time series
•dir: The direction of the spread of the event
(forward or backward)
Output:
•bestlag: The best fitting time lag
•influence: The level of influence
1last ←dist(tsan,shift(ts,tstar t));
2if dir is forward then
3i←1;
4end
5if dir is backward then
6i← −1;
7end
8lastlag ←0;
9while dist(tsanom,shift(ts,tstart +i))
≤last do
10 lastlag ←lastlag +i;
11 end
12 bestlag =i;
13 length =len(tsan);
14 influence =1
1+exp(1
length ∗last);
Algorithm 2: BestFitLag
be assumed, that while the delay is increasing, the distance
between the two time series will decrease until the best fit
is reached. Thus if the calculated distance values start to
increase, the possible best delay has been reached, because
the adjacent road segments show high correlation in general.
However sometimes the calculated delay can be just a local
minimum, thus a simulate annealing is applied to find the
global optimum.
Furthermore, the best distance value can be used to express
the influence between the two flow edges, however a transfor-
mation is required, converting the shape_dist function’s [0,inf )
domain to [1,0] domain. Higher values mean a stronger influ-
ence, while lower values mean a weaker influence. Equation
4 is designed for this purpose:
distance =shape_dist(tsan, shif t(ts, lastlag)) (3)
influence =1
1 + exp(1
length ∗distance)(4)
, where the length parameter equals with the length of tsan .
4) Find anomaly: The findAnomaly function (Algorithm
3) is responsible for determining whether an anomalous part
starting from tstart can be identified. If an anomalous part is
found, the function also returns its length.
The findAnomaly function exploits the observation, that
the error of a prediction model significantly increases when
Input :
•ts: The time series of the fe flow edge
•tshist: The historical average time series of the
fe flow edge
•tstart: The emergence time of the anomaly in
the time series
Output:
•is_anomaly: The input ts time series contains
anomaly from tstart or not
•next_tsan: The anomaly part in the input ts time
series if it exists
1model ←exp_smooth(tshist);
2error ←measure_error(model, tshist);
3error_dist ←norm_dist(error)
4length ←0;
5while ts[tstart +length]from error_dist do
6length ←length + 1;
7end
8if length is 0then
9is_anomaly ←f alse;
10 else
11 is_anomaly ←true;
12 next_tsan ←ts[tstart, tstart +length]
Algorithm 3: findAnomaly
anomalous behavior can be observed. The error of prediction
was analyzed and we could conclude, that the prediction error
has a normal distribution in case of normal behavior (depicted
on Figure 3), while the distribution of the error significantly
differs in case of anomalous behavior. Thus the operating
principle of findAnomaly is:
1) Fitting a prediction model on tshist
2) Running until the prediction error of the model returns
to a normal distribution
Fig. 3: Histogram of different prediction errors
Therefore for findAnomaly, a prediction model is con-
structed by applying a simple moving average on tshist, then
ATTILA NAGY, VILMOS SIMON: IDENTIFYING HIDDEN INFLUENCES OF TRAFFIC INCIDENTS’ EFFECT IN SMART CITIES 655

Fig. 4: The simulation map with location of traffic accident and control points
based on that model the distribution of the prediction error is
determined. The algorithm starts from tstart and runs until the
prediction error of the model returns to a normal distribution.
This point in the time series is length apart from tstar t,
therefore the length of the anomaly can be calculated. If the
length equals with zero, it means that ts does not contain an
anomaly.
IV. CAS E ST UDY
After the implementation of the AIHI, in this section we
will demonstrate its ability to follow the spread of the effect
of a traffic accident through a traffic flow graph.
At first, we searched for datasets containing traffic flow
data and traffic accidents as well, but unfortunately there was
no such publicly available traffic flow dataset at the time of
writing. Because of this, a simulation framework was used for
the evaluation.
As the simulation framework, we chose Simulation of Urban
Mobility (SUMO), a free and open traffic simulation suite,
which is available since 2001. SUMO allows modeling of
intermodal traffic systems, including roads, vehicles, public
transport and pedestrians. Included with SUMO is a wealth
of supporting tools, which handle tasks such as route finding,
visualization, road network import from open street maps and
emission calculation.
In our scenario, besides the real traffic flow data, a traffic
accident had to be generated. The authors of [25] used traffic
lights for this purpose, thus this approach had been applied in
our simulation as well. The accident is simulated by opening
only one of the four available lanes on a road.
In the simulation, high rank roads of Budapest’s suburb
are examined. Seven control points (using inductive loop
detectors) were placed on the map as depicted on Figure 4.
We simulated five hours of traffic flow, which was similar
to afternoon rush hours. The vehicles are simulated with
speedF actor =normc(1,0.1,0.2,2), which means that 95%
of the vehicles drove between 80% and 120% of the legal
speed limit. In the beginning we simulated normal traffic flow,
then an one hour long traffic accident had been inserted after
two and a half hours near to cp2, so the effect of the accident
could be identified first on fe1,2flow edge (Figure 2).
As mentioned in Subsection III-B1, the entry point of AIHI
was fe1,2flow edge with tstart start time of the simulated
traffic accident. The result of AIHI, is displayed on Figure
5. The spreading tree of the accident shows that the farther
control points were, the bigger the detected time lags became,
while the influences were decreasing as expected. The change
of the pattern of the anomalous part was also visualised
between cp4and cp5on Figure 6.
V. CO NC LU SI ON
The road network of big cities is a complex and hard
to analyze system in which the accurate quantification of
interactions between nonadjacent road segments is almost
an insolvable objective, because of the unique decisions of
thousands of drivers which makes the interactions invisible.
In this paper a novel algorithm (AIHI) has been presented,
that is able to exploit unexpected traffic events to reveal the
hidden connections between nonadjacent road segments and
provides the following information:
•identify nearby road segments that could be affected by
the event
•if a road segment is affected, the exact level of influence
between the affected and accident road segments,
•the time delay: the time between the event and its
detection on the affected road segments
Combining these new information sources with real-time traf-
fic information, the accuracy of prediction models able to
integrate external environmental variables can be increased.
We have demonstrated the capabilities of AIHI with simu-
lations on a real road network which results can be depicted
as spreading tree of the accident.
656 PROCEEDINGS OF THE FEDCSIS. POZNA ´
N, 2018

cp2
cp3cp4cp5
cp7
cp6
timelag:30 sec, influence:0.94
timelag:0 sec, influence:1.00
timelag:30 sec, influence:0.93
timelag: 60 sec, influence:0.87
timelag:90 sec, influence:0.80
timelag:90 sec, influence:0.78
Fig. 5: Visualization of the AIHI’s result. The examined control point was cp2(red dot), where the time lag is zero and the
influence is 1.0. Other influenced control points in the road network identified by AIHI are marked with blue dots.
(a) Traffic flow of FlowEdge(2, 4) (b) Traffic flow of FlowEdge(4, 5)
Fig. 6: On Figure 6a and Figure 6b the measured traffic flows are depicted at cp4and cp5, respectively. On Figure 6b the effect
of other connected roads can be seen, where the anomalous part starts to differ compared to the anomalous part of Figure 6a
.
In the future, we are planning to extend prediction models
like Neural Networks (NN) and KNN to utilize the result of
AIHI. We also want to develop a classification model able to
decide whether a time series contains an unexpected event or
not, because the input of parameters of AIHI are currently
determined manually. Applying the classification model, the
determination of AIHI’s input parameters will be automated.
VI. ACK NOWLEDGMENT
The research reported in this paper was supported by the
BME- Artificial Intelligence FIKP grant of EMMI (BME
FIKP-MI/SC).
REF ER EN CE S
[1] J. He, S. Gong, Y. Yu, L. Yu, L. Wu, H. Mao, C. Song, S. Zhao,
H. Liu, X. Li, et al., Air pollution characteristics and their relation to
meteorological conditions during 2014–2015 in major chinese cities,
Environmental pollution 223 (2017) 484–496.
[2] M. Krzy ˙
zanowski, B. Kuna-Dibbert, J. Schneider, Health effects of
transport-related air pollution, WHO Regional Office Europe, 2005.
[3] A. Peters, S. Von Klot, M. Heier, I. Trentinaglia, A. Hörmann, H. E.
Wichmann, H. Löwel, Exposure to traffic and the onset of myocardial
infarction, New England Journal of Medicine 351 (17) (2004) 1721–
1730.
[4] Y. Yue, A. G. Yeh, Y. Zhuang, Prediction time horizon and effectiveness
of real-time data on short-term traffic predictability, in: Intelligent
Transportation Systems Conference, 2007. ITSC 2007. IEEE, IEEE,
2007, pp. 962–967.
[5] A. Ermagun, D. Levinson, Spatiotemporal traffic forecasting: review and
proposed directions, Transport Reviews (2018) 1–29.
[6] N.-E. El Faouzi, H. Leung, A. Kurian, Data fusion in intelligent
transportation systems: Progress and challenges–a survey, Information
Fusion 12 (1) (2011) 4–10.
[7] A. Stathopoulos, M. Karlaftis, Temporal and spatial variations of real-
time traffic data in urban areas, Transportation Research Record: Journal
of the Transportation Research Board (1768) (2001) 135–140.
[8] J. Wang, Y. Mao, J. Li, Z. Xiong, W.-X. Wang, Predictability of road
traffic and congestion in urban areas, PloS one 10 (4) (2015) e0121825.
[9] S. Dunne, B. Ghosh, Weather adaptive traffic prediction using neu-
ATTILA NAGY, VILMOS SIMON: IDENTIFYING HIDDEN INFLUENCES OF TRAFFIC INCIDENTS’ EFFECT IN SMART CITIES 657

rowavelet models, IEEE Transactions on Intelligent Transportation Sys-
tems 14 (1) (2013) 370–379.
[10] M. Cools, E. Moons, G. Wets, Assessing the impact of weather on traffic
intensity, Weather, Climate, and Society 2 (1) (2010) 60–68.
[11] Q. T. Tran, Z. Ma, H. Li, L. Hao, Q. K. Trinh, A multiplicative seasonal
arima/garch model in evn traffic prediction, International Journal of
Communications, Network and System Sciences 8 (04) (2015) 43.
[12] W. Min, L. Wynter, Real-time road traffic prediction with spatio-
temporal correlations, Transportation Research Part C: Emerging Tech-
nologies 19 (4) (2011) 606–616.
[13] S. V. Kumar, L. Vanajakshi, Short-term traffic flow prediction using
seasonal arima model with limited input data, European Transport
Research Review 7 (3) (2015) 21.
[14] P. Cai, Y. Wang, G. Lu, P. Chen, C. Ding, J. Sun, A spatiotemporal
correlative k-nearest neighbor model for short-term traffic multistep
forecasting, Transportation Research Part C: Emerging Technologies 62
(2016) 21–34.
[15] B. Yu, X. Song, F. Guan, Z. Yang, B. Yao, k-nearest neighbor model
for multiple-time-step prediction of short-term traffic condition, Journal
of Transportation Engineering 142 (6) (2016) 04016018.
[16] X. Ma, Z. Dai, Z. He, J. Ma, Y. Wang, Y. Wang, Learning traffic as im-
ages: a deep convolutional neural network for large-scale transportation
network speed prediction, Sensors 17 (4) (2017) 818.
[17] J. Zhang, Y. Zheng, D. Qi, R. Li, X. Yi, Dnn-based prediction model
for spatio-temporal data, in: Proceedings of the 24th ACM SIGSPA-
TIAL International Conference on Advances in Geographic Information
Systems, ACM, 2016, p. 92.
[18] Y. Li, R. Yu, C. Shahabi, Y. Liu, Graph convolutional recur-
rent neural network: Data-driven traffic forecasting, arXiv preprint
arXiv:1707.01926.
[19] B. Singh, A. Gupta, Recent trends in intelligent transportation systems:
a review, Journal of Transport Literature 9 (2) (2015) 30–34.
[20] Y. Yue, Traffic sensors, International Encyclopedia of Geography:
People, the Earth, Environment and Technology: People, the Earth,
Environment and Technology (2016) 1–7.
[21] R. Fu, Z. Zhang, L. Li, Using lstm and gru neural network methods for
traffic flow prediction, in: Chinese Association of Automation (YAC),
Youth Academic Annual Conference of, IEEE, 2016, pp. 324–328.
[22] D. Xia, B. Wang, H. Li, Y. Li, Z. Zhang, A distributed spatial–temporal
weighted model on mapreduce for short-term traffic flow forecasting,
Neurocomputing 179 (2016) 246–263.
[23] Y. Tian, L. Pan, Predicting short-term traffic flow by long short-term
memory recurrent neural network, in: Smart City/SocialCom/Sustain-
Com (SmartCity), 2015 IEEE International Conference on, IEEE, 2015,
pp. 153–158.
[24] M. Müller, Dynamic time warping, Information retrieval for music and
motion (2007) 69–84.
[25] J. Q. Shi, L. Cheng, Simulation and analysis of highway traffic accident
based on vissim, in: Applied Mechanics and Materials, Vol. 253, Trans
Tech Publ, 2013, pp. 1682–1685.
658 PROCEEDINGS OF THE FEDCSIS. POZNA ´
N, 2018