https://doi.org/10.31449/inf.v48i5.5393 Informatica 48 (2024) 23 –28 23 
Statistical Analysis of Urban Traffic Flow Using Deep Learning 
Quanzhi Liu,
1, *
 Shuang Wu,
2
 Peng Zhang
3
 
1
Department of Mathematics and Statistics, Cangzhou Normal University, Cangzhou, Hebei 061001, China  
2
Department of Planning and Finance, Cangzhou Normal University, Cangzhou, Hebei 061001, China  
3
Department of Marxism, Cangzhou Normal University, Cangzhou, Hebei 061001, China 
E-mail: xunzhi05qhcjo@yeah.net 
*
Corresponding author 
Keywords: graph convolutional network model, long short-term memory network model, urban road condition, traffic 
flow 
Received: October 31, 2023 
In recent years, urbanization has brought about challenges such as population growth, increased demand 
for traffic, and traffic congestion. To address the need for accurate traffic condition statistics, this paper 
proposed an improved method that combines graph convolutional network (GCN) and long short-term 
memory network (LSTM) model for forecasting and statistics of traffic conditions. Through the modeling 
and analysis of urban road conditions and traffic flow, the combination of GCN model and LSTM model 
enabled more precise prediction of traffic flow trends. Experiments were carried out on the actual traffic 
data set of Cangzhou, Hebei. The results demonstrated that the proposed method achieved high accuracy 
and reliability in predicting traffic flow. By using the LSTM model to improve the GCN model, it effectively 
adapts to changes in urban traffic conditions while providing dependable predictions. 
Povzetek: Članek predlaga izboljšano metodo, ki združuje grafično konvolucijsko mrežo (GCN) in 
dolgoročno kratkoročni model spominskega omrežja (LSTM) za napovedovanje in statistiko prometnih 
razmer. 
 
 
1 Introduction 
In the field of transportation, there has been notable 
advancements in deep learning technology in recent times, 
among which graph convolutional network (GCN) has 
attracted much attention as an effective graph data 
modeling method. However, the traditional GCN model 
encounters challenges such as low accuracy and 
substantial prediction errors when dealing with traffic 
prediction. Consequently, research focused on enhancing 
the prediction accuracy of the GCN model has emerged as 
a prominent topic within the current academic community. 
In order to improve the traditional GCN model and 
improve the accuracy of urban traffic flow statistics, this 
paper introduced the long short-term memory (LSTM) 
model into the GCN model. By integrating urban road 
conditions and traffic flow data, this approach achieves 
more precise and reliable traffic flow prediction. 
Furthermore, empirical evaluation using real-world traffic 
dataset from Cangzhou, Hebei Province demonstrates that 
the proposed GCN-LSTM model outperforms other 
models in terms of prediction accuracy and precision. 
2 Related works 
Table 1: A summary of related works 
Literatur
e 
Model type Recognition 
method 
Finding 
Peng et 
al. [1] 
A memory 
augmented graph 
Predict 
traffic 
It solved the 
problem of 
convolutional 
network (MA-
GCN) model  
networks by 
combining 
graph 
convolutiona
l network 
(GCN) and 
differential 
neural 
computer 
(DNC)  
long-term 
dependence and 
spatial 
dependence in 
traffic 
prediction. 
Bao et al. 
[2] 
Prior knowledge 
enhanced time-
varying graph 
convolutional 
network (PKET-
GCN) 
Considering 
dynamic and 
static 
features and 
using prior 
knowledge 
to improve 
the 
correlation 
of nodes, 
combined 
with 
convolution 
and a time-
varying 
feature 
extraction 
module 
PKET-GCN 
showed 
superior results 
over existing 
methods on 
multiple real 
datasets.  
Diao et 
al. [3] 
A novel deep 
learning 
Using a 
graph with 
specific local 
EC-GCN 
outperformed 
the state-of-the-

24 Informatica 48 (2024) 23 –28 Q. Liu et al.  
framework called 
EC-GCN 
structure to 
represent 
each 
encrypted 
traffic type, 
and 
introducing a 
lightweight 
layer and a 
graph pool 
learning 
layer 
art methods on 
three real data 
sets, improving 
the 
classification 
accuracy by 
5%-20%. 
 
Zhang et 
al. [4] 
Combine fuzzy C-
means (FCM) and 
GCN to create a 
hybrid model 
FCM was 
used to 
cluster the 
trajectory 
data to 
generate the 
air traffic 
flow network 
graph 
structure, 
and GCN 
was used to 
detect 
trajectory 
deviation 
and delay.  
FCM-GCN was 
superior to 
other models in 
medium and 
long-term 
traffic 
prediction 
tasks, which is 
helpful to 
optimize the 
highly 
interconnected 
and 
interdependent 
air traffic flow 
network. 
3 Traffic flow and GCN model 
improvement 
3.1 Traffic flow 
The term “traffic flow ” refers to the density and flow 
degree of moving objects within a transportation network 
during a specific time period. It serves as an important 
indicator for measuring the traffic congestion levels and 
road utilization. Traffic flow exhibits spatio-temporal 
correlation, periodicity, and uncertainty. It is possible to 
achieve data processing and feature engineering with 
appropriate model algorithms and evaluate and optimize 
predictive models by using historical traffic flow data as 
training samples in conjunction with on-site observation 
data, environmental factors, and road network structure 
information [5]. These models can analyze historical data 
and train models using statistical methods, machine 
learning, artificial intelligence, and other technologies for 
predicting future traffic flow indicators. They assist 
transportation management departments in formulating 
effective traffic strategies for improving traffic mobility 
and reduce congestion issues. 
3.2 GCN model 
The GCN model is a deep learning model designed for the 
modeling and analysis of graph structure data. By 
considering the interconnections between nodes and their 
neighbor nodes, it realizes the feature extraction and 
information dissemination propagation within the graph 
data. It applies convolutional operations on the graph to 
capture structural information among nodes, which in turn 
enables representation and inference of node features. 
Through multi-layer graph convolution operations, the 
GCN model can learn more advanced features, thus 
enhancing robustness in tasks such as edge prediction, 
node identification, and network analysis of graph data. 
The GCN model can be applied to various graph 
structures, including social networks, recommendation 
systems, bioinformatics, and other fields. 
The GCN model has been widely used in traffic-
related tasks, including flow prediction, road condition 
analysis, and road network modeling. By modeling the 
topology structure and node characteristics of the traffic 
network, it offer more accurate traffic prediction and  
analysis results for road network. Through iterative 
updates to node representations, the direct neighbors of the 
node are considered in each iteration, and their feature 
information is aggregated and updated. The way of 
neighbor aggregation and multi-layer stacking enables 
nodes to use their location relationships within the graph 
to acquire richer information.  Consequently, it becomes 
possible to capture contextual relationships among nodes 
within the graph structure while effectively addressing 
data analysis tasks involving graph structures [7]. The 
update formula for each node and layer of the model is as 
follows: 
𝐻 𝑙 +1
=σ (𝐷 ̃
1
2
𝐴 ̃
𝐷 ̃
1
2
𝐻 𝑙 𝑊 𝑙 ), 
𝐴 ̃
= A + 𝐼 𝑁 , 
𝐷 ̃
= D + 𝐼 𝑁 , 
where 𝐻 𝑙 +1
 is the node representation of the l+1-th 
layer, 𝐻 （𝑙 )
 is the node representation after the processing 
of layer l, and 𝑊 𝑙 represents the weight matrix of the l-th 
layer. 𝐴 ̃
 represents the sum of the adjacent matrix and unit 
matrix, i.e., 𝐴 ̃
=A+I. 𝐷 ̃
 stands for the degree matrix of 𝐴 ̃
. 
This way of information transmission employed by 
the GCN model facilitates the comprehensive analysis of 
traffic data patterns and characteristics from both a global 
and local perspective, taking into account the topological 
structure of the traffic network as well as node 
relationships [8]. However, it falls short in effectively 
capturing long-term time dependencies when dealing with 
time series data. However, the LSTM model is very good 
at processing time series data and can effectively capture 
long-term time dependencies, enabling retention of past 
information for accurate future predictions. Therefore, the 
LSTM model is incorporated into the GCN model to 
effectively capture and retain historical traffic flow 
information, enabling consideration of previous states and 
trends in prediction. This comprehensive modeling of 
spatio-temporal relationships allows for better adaptation 
to dynamic changes and complexity in traffic flow data, 
resulting in accurate predictions of traffic flow and road 
conditions. Ultimately, this improves traffic efficiency 
and reduces congestion. 
3.3 LSTM model 
The LSTM is a variant of temporal RNN that solves the 
issues of gradient explosion and vanishing in traditional 
RNNs by introducing input gates, forget gates, and output 

Statistical Analysis of Urban Traffic Flow Using Deep …                                                          Informatica 48 (2024) 23 –28   25 
gates [9]. LSTM adjusts the degree of information storage 
and forgetting in both long-term memory and short-term 
memory by setting a threshold, while introducing cell state 
to save long-term memory information [10]. This method 
effectively overcomes the gradient problem encountered 
in RNN and improves the stability of the training model. 
The forget gate filters the cell information of the 
previous time step and determines which information 
needs to be discarded. The formula is: 
𝑓 𝑖 = 𝛿 (𝑊 𝑓 . [ℎ
𝑡 −1
, 𝑥 𝑖 ] + 𝑏 𝑓 ). 
This gate integrates information ℎ
𝑡 −1
 transmitted in 
the previous stage and input data 𝑥 𝑖 at the current moment, 
so as to fuse them together in the calculation process, 
control whether the input information at the current time 
step enters the memory unit, and thus affect the memory 
and information flow of the network when processing 
sequence data. The input gate controls what information 
from the current input and the hidden state at the previous 
time step should be added to the cell state, and the 
corresponding formulas are:  
𝑖 𝑡 = 𝜎 (𝑊 𝑖 . [ℎ
𝑡 −1
, 𝑥 𝑡 ] + 𝑏 𝑖 ), 
𝐶 ̅ 𝑡 = 𝑡 ℎ𝑎 ℎ(𝑤 𝐶 . [ℎ
𝑡 −1
, 𝑥 𝑡 ] + 𝑏 𝑖 ), 
𝐶 𝑡 = 𝑓 𝑡 ∗ 𝐶 𝑡 −1
+ 𝑖 𝑡 ∗ 𝐶 ̅ 𝑡 . 
By filtering the forgotten information, the input gate 
combines the input data of the current time step with the 
hidden state of the previous time step at time step t to 
obtain candidate cell state 𝐶 𝑡 . The output of the input gate 
is then multiplied by the candidate cell state, and the 
obtained result is added to the previous memory state to 
update the memory state at the current time step. The 
output gate controls the flow of information between the 
input at the current time step and the memory at the 
previous time step, and between the input at the current 
time step and the output at the current time step. The 
corresponding formulas are: 
𝑂 𝑡 = 𝜎 (𝑤 𝑜 . [ℎ
𝑡 −1
, 𝑥 𝑒 + 𝑏 𝑜 ), 
ℎ
𝑡 = 𝑂 𝑒 ∗ tanh (𝐶 𝑒 ), 
where 𝜎 and tanh are both activation functions, 𝑥 𝑡 
represents the input data at time t, ℎ
𝑡 −1
 is the hidden state 
at time step t-1, 𝐶 𝑡 is the cell state at time t, and 𝐶 ̅ 𝑡 is the 
cell state value at time step t-1. The forget gate, input gate, 
output gate, and neuron state all have parameter matrices 
with values between 0 and 1, which are denoted by 𝑊 𝑓 , 
𝑊 𝑖 , 𝑊 𝑐 , and 𝑊 𝑒 , respectively.  b
f
, b
i
, b
o
, and b
e
 are bias 
vectors corresponding to matrices. f
t
, i
t
, and O
t
 represent 
threshold values corresponding to the three gates [11]. 
3.4 Improved GCN model 
The GCN model performs well in handling nonlinear data 
and capturing complex dependencies between nodes, 
while the LSTM model is good at capturing long-term 
dependencies in time series data. These two models are 
integrated to form a new approach known as the GCN-
LSTM model. This model operates by iteratively 
alternating between the GCN and LSTM models, 
continuously updating node representations and time-
dependent information. By calculating the gradient of the 
parameters to the loss function and updating the model 
parameters according to the gradient, the model 
progressively adapts to training data and improves 
performance [12]. The steps are as follows. 
(1) The GCN model is used for conducting 
representation learning on graph data, and the 
representation of each node is updated by the adjacency 
matrix and node features. 
(2) The spatial feature representation extracted by the 
GCN model is fed into the LSTM model, which uses its 
memory unit and gating mechanism to capture the time 
dependence in sequence data, thereby further extracting 
crucial time-related information. 
(3) The GCN-LSTM model undergoes training with 
temporal data across multiple time steps. At each step, the 
hidden state is updated and adjusted to make predictions 
regarding future traffic flow or other relevant information. 
4 Experimental analysis 
4.1 Data acquisition 
In order to evaluate the GCN-LSTM traffic flow 
prediction model constructed in this paper, experimental 
verification was conducted. Data on vehicle flow from 
Qinxue Road, Wenlan Street, and Fengfan Road in the 
central urban district of Cangzhou City were collected 
from the website of the Ministry of Communications of 
the People's Republic of China during October 1 to 
October 31, 2021. The statistical time period ranged from 
00:00 to 24:00, with a time interval of every 10 min. 
Finally, 1,500 records were obtained as the data set. The 
actual road images were collected from several angles and 
time periods, and the resulting images were subjected to 
frame-splitting and  data cleaning, and manually labeled 
with automobiles, pedestrians, and non-motorized 
vehicles. The GCU and GCN models were selected as 
control objects, and the mean absolute percentage error 
(MAPE) was used to evaluate the prediction performance 
of the test models. 
4.2 Evaluation indicators 
Due to the complexity of the traffic system, the MAPE can 
be used as the evaluation indicator for assessing the 
performance of the GCN-LSTM prediction model. MAPE 
represents the average degree of deviation between 
predicted and actual vehicle flow, with a smaller value 
indicating a stronger correlation [13]. The formula is: 
MAPE =
1
𝑛 ∑
|𝑦 𝑖 −𝑦 ̂
𝑖 |
𝑦 𝑖 𝑛 𝑖 =1
∗ 100%, 
where n is the number of observations, 𝑦 ̂
𝑖 is the 
predicted value of the model, and 𝑦 𝑖 is the true data value. 
4.3 Experimental results 
By comparing the MAPE of the GRU, GCN and GCN-
LSTM models as illustrated in Figure 1, it is evident that 
the improved GCN-LSTM model exhibited exceptional 
prediction performance for Cangzhou's traffic flow dataset 
with a significantly low MAPE value. 
 

26 Informatica 48 (2024) 23 –28 Q. Liu et al.  
 
Figure 1: Performance comparison results of various 
models. 
As shown in Figure 2, the vehicle flow in the central 
urban area showed obvious periodic changes. With the 
exception of holidays, this cycle occurred consistently 
throughout all seven days of the week, and each cycle 
displayed similar characteristics regarding vehicle flow. 
Notably, weekdays witnessed a substantial volume of 
vehicles, while non-weekdays experienced relatively 
lower traffic levels. 
 
 
Figure 2: The change trend of traffic flow in Cangzhou 
City in October. 
After analyzing the monthly change characteristics of 
vehicle flow in the central urban area, it can be found that 
the change of the vehicle flow in the central urban area 
was periodic from Monday to Sunday. The vehicle flow 
data of the central urban area of Cangzhou City from 
October 18 to 24, 2021, which represents a complete week 
excluding holidays, were selected to analyze the variation 
distribution characteristics of vehicle flow in the central 
urban area within a week (from 00:00 to 24:00) (Table 2).  
The data in Table 2 reveals that during the period from 
October 18 to 22, there was a low traffic flow in the early 
morning hours, which remained relatively stable at around 
2,000 PUC/D. However, it experienced a significant surge 
after 06:00 and reached its peak between 06:00 and 08:00. 
Subsequently, there was a decrease in traffic flow from 
10:00 to 16:00 followed by an increase reaching its 
maximum at 18:00. On October 23 and 24, compared to 
regular working days, the peak traffic volume was delayed 
by two hours. Consequently, it can be concluded that there 
were two distinct peaks of traffic flow in the central area. 
The periods of 06:00-08:00 and 16:00-18:00 exhibited the 
highest traffic flow on weekdays, while the peak traffic 
flow on non-weekdays occurred between 08:00-10:00 and 
18:00-20:00. Generally speaking, weekdays witnessed a 
relatively substantial volume of vehicle flow. 
 
Table 2: The seven-day change distribution of the vehicle 
flow in the central urban area of Cangzhou City 
Date  
Time slot 
10/
18 
10/
19 
10/
20 
10/
21 
10/
22 
10/
23 
10/
24 
00:00-
02:00 
11
08 
10
91 
11
95 
10
67 
11
52 
98
5 
99
6 
04:00-
06:00 
23
59 
24
60 
14
27 
23
96 
24
05 
24
56 
23
90 
06:00-
08:00 
94
59 
96
30 
96
48 
96
33 
97
16 
75
11 
76
08 
08:00-
10:00 
86
48 
87
51 
87
06 
88
00 
86
04 
87
15 
86
12 
10:00-
12:00 
75
49 
78
36 
80
61 
83
02 
82
87 
89
60 
88
95 
12:00-
14:00 
72
23 
73
65 
71
62 
75
71 
76
00 
72
93 
72
47 
14:00-
16:00 
78
75 
77
58 
76
89 
82
01 
84
30 
72
23 
73
16 
16:00-
18:00 
97
42 
98
97 
98
00 
99
15 
96
75 
79
87 
80
02 
18:00-
20:00 
81
71 
81
00 
83
65 
80
09 
84
12 
86
50 
88
32 
20:00-
22:00 
77
12 
80
91 
83
21 
82
09 
84
12 
61
53 
62
21 
22:00-
24:00 
31
12 
32
08 
33
69 
36
1 
32
19 
22
01 
21
17 
 
Because there is a time-dependent relationship 
between vehicle flow, vehicle flow on weekdays and non-
weekdays by extracting time features [14]. Therefore, 
when the GCN-LSTM model makes a prediction, it is 
necessary to determine the input and output
 
of the model 
beforehand [15]. The input data is mainly composed of the 
following features: historical traffic flow, month, specific 
date, travel time period, working day indicator, and legal 
holidays (0 means yes, 1 means no). The known traffic 
data for historical dates was selected as the input, and the 
date to be predicted was input. For example, the traffic 
flow related characteristics of Qinxue Road from January 
1, 2023 to July 31, 2023 was selected as input to predict 
the vehicle flow between 6:00 and 20:00 on this road 
section on August 1, 2023. Subsequently, the predicted 
vehicle flow value was compared with the actual value 
(Figure 3). 
 

Statistical Analysis of Urban Traffic Flow Using Deep …                                                          Informatica 48 (2024) 23 –28   27 
 
Figure 3: Predicted and actual traffic flow values of 
Qinxue Road in Cangzhou on August 1. 
The predicted vehicle flow of Qinxue Road in 
Cangzhou City during the morning peak hours of 06:00-
08:00 on August 1, as depicted in Figure 3, exhibited a 
significant deviation from the actual value. It is worth 
noting that this time period typically experiences heavy 
traffic volume with an average of approximately 9,600 
PCU/D based on historical data. However, it can be seen 
from Figure 3 that the actual traffic flow on August 1 was 
7,539 PCU/D, which exhibited a decrease compared to the 
previous flow, and the morning peak time was also 
postponed. Consequently, it can be inferred that 
congestion occurred on Qinxue Road between 06:00 and 
08:00 on August 1st. 
 
5 Discussion 
Urban transportation is easily affected by various 
factors such as human intervention and traffic control. To 
cope with congestion caused by peak travel and traffic 
restrictions, it is essential to have real-time monitoring of 
traffic flow and predictions for future time periods. 
Traditional GCN models have several limitations in the 
field of transportation. For instance, these models can only 
extract spatial features in a transportation network and 
may not effectively consider the temporal changes in 
feature processing for spatiotemporal data. Traditional 
GCN models tend to provide deterministic predictions, 
which limits their robustness in practical applications due 
to the existence of uncertainties in real traffic networks. 
However, the experimental results showed that by 
leveraging the temporal characteristics of LSTM, it 
effectively modeled the time dimension data and reduced 
the average absolute percentage error between predicted 
and actual traffic flow. This approach better captures the 
temporal variations in traffic volume, comprehensively 
considers both spatial and temporal features, enhances 
understanding of dynamic patterns in traffic data, and 
ultimately improves the accuracy of traffic flow 
prediction. In actual urban traffic flow prediction, by 
comparing with historical data, we can more accurately 
assess the future changes in city road conditions. By 
comparing historical data, future changes in city road 
conditions can be more accurately assessed in actual urban 
traffic flow prediction. Therefore, the GCN-LSTM model 
was used to predict the traffic flow in real time, and the 
result was compared with the historical data. The change 
of road conditions was judged by analyzing the difference 
between the predicted results and the actual observation 
values. If the difference between the predicted value and 
the actual value is large, it may mean that there is 
congestion or other abnormal conditions. Based on these 
prediction results and difference analysis, traffic 
management departments can take timely measures to 
optimize road traffic safety and efficiency and maximize 
the utilization of road resources. According to the 
predicted traffic conditions, people can adjust the 
appropriate means of transportation and formulate more 
reasonable travel routes at any time, so as to avoid 
congestion and improve travel efficiency. 
 
6 Conclusion 
In this paper, the LSTM model was introduced to improve 
the GCN model. An experimental application was carried 
out using real traffic data of Cangzhou, Hebei Province. 
By training and verifying the GCN-LSTM model, the 
traffic flow in different time periods was successfully 
predicted, and the statistical analysis was carried out. The 
results showed that the improved GCN-LSTM model 
significantly improved the prediction accuracy and 
precision, enabling more accurate forecasting of traffic 
flow fluctuations and providing valuable support for travel 
route and mode planning. Furthermore, it can also assist 
traffic management departments in conducting traffic 
dispatch and monitoring more effectively, thereby 
reducing congestion and improving road efficiency. 
Additionally, it provides valuable reference data for urban 
transportation planning and management. In the future, we 
will further optimize and improve the GCN-LSTM model 
to verify its applicability in a wider range of scenarios, 
aiming to continuously enhance the efficiency and safety 
of urban traffic. 
References 
[1] Peng D, Zhang Y (2023). MA-GCN: A Memory 
Augmented Graph Convolutional Network for traffic 
prediction. Engineering Applications of Artificial 
Intelligence, 121. 
https://doi.org/10.1109/TITS.2019.2935152 
[2] Bao Y, Liu J, Shen Q, Cao Y, Ding W, Shi Q (2023). 
PKET-GCN: Prior knowledge enhanced time-
varying graph convolution network for traffic flow 
prediction. Information Sciences, 634, pp. 359-381. 
https://doi.org/10.1016/j.ins.2023.03.093 
[3] Diao ZL, Xie GG, Wang GX, Ren R, Meng XY, 
Zhang GX, Xie K, Qiao M (2023). EC-GCN: A 
encrypted traffic classification framework based on 
multi-scale graph convolution networks. Computer 
Networks, 224. 
https://doi.org/10.1016/j.comnet.2023.109614 
[4] Zhang YN, Lu Z, Wang J, Chen L (2023). FCM-
GCN-based upstream and downstream dependence 
model for air traffic flow networks. Knowledge-
Based Systems, 260. 
https://doi.org/10.1016/j.knosys.2022.110135 

28 Informatica 48 (2024) 23 –28 Q. Liu et al.  
[5] Wei G, He S, Ma J (2012). Review on Traffic Flow 
Phenomena and Theory. Journal of Transportation 
Systems Engineering and Information Technology, 
12, pp. 90-97. https://doi.org/10.1016/S1570-
6672(11)60205-5 
[6] Lee K, Rhee W (2022). DDP-GCN: Multi-graph 
convolutional network for spatiotemporal traffic 
forecasting. Transportation Research Part C: 
Emerging Technologies, 134. 
https://doi.org/10.48550/arXiv.1905.12256 
[7] Yu B, Lee Y, Sohn K (2020). Forecasting road traffic 
speeds by considering area-wide spatio-temporal 
dependencies based on a graph convolutional neural 
network (GCN). Transportation Research Part C: 
Emerging Technologies, 114, pp. 189-204. 
https://doi.org/10.1016/j.trc.2020.02.013 
[8] Zheng Y, Wang S, Dong C, Li W, Zheng W, Yu J 
(2022). Urban road traffic flow prediction: A graph 
convolutional network embedded with wavelet 
decomposition and attention mechanism. Physica A: 
Statistical Mechanics and its Applications, 608. 
https://doi.org/10.1016/j.physa.2022.128274 
[9] Li Z, Xu H, Gao X, Wang Z, Xu W (2023). Fusion 
attention mechanism bidirectional LSTM for short-
term traffic flow prediction. Journal of Intelligent 
Transportation Systems Technology Planning and 
Operations. 
https://doi.org/10.1080/15472450.2022.2142049 
[10] Narmadha S, Vijayakumar V (2023). Spatio-
Temporal vehicle traffic flow prediction using 
multivariate CNN and LSTM model. Materials 
Today: Proceedings, 81, pp. 826-833. 
https://doi.org/10.1016/j.matpr.2021.04.249 
[11]  Yang BL, Sun SL, Zhang KL, Li JY, Tian Y (2019). 
Traffic flow prediction using LSTM with feature 
enhancement. Neurocomputing, 332, pp. 320-327. 
https://doi.org/10.1007/978-981-10-0451-3_1 
[12] Wang S, Zhang Y, Hu Y, Yin B (2023). Knowledge 
fusion enhanced graph neural network for traffic 
flow prediction. Physica A: Statistical Mechanics 
and its Applications, 623. 
https://doi.org/10.1016/j.physa.2023.128842 
[13] Song J, Kang H, Hyun S, Jee E, Bae DH (2022). 
Continuous verification of system of systems with 
collaborative MAPE-K pattern and probability 
model slicing. Information and Software 
Technology, 147. 
https://doi.org/10.1016/j.infsof.2022.106904 
[14] Hou R, Wang Z, Ren R, Cao Y, Wang Z (2023). 
Multi-channel network: Constructing efficient GCN 
baselines for skeleton-based action recognition. 
Computers & Graphics, 110, pp. 111-117. 
https://doi.org/10.1016/j.cag.2022.12.008 
[15] Wang G, Zhang Z, Bian Z, Xu Z (2021). A short-
term voltage stability online prediction method 
based on graph convolutional networks and long 
short-term memory networks. International Journal 
of Electrical Power & Energy Systems, 127, pp. 1-9. 
https://doi.org/10.1016/j.ijepes.2020.106647