=Paper=
{{Paper
|id=Vol-2604/paper60
|storemode=property
|title=Intelligent System of Visual Simulation of Passenger Flows
|pdfUrl=https://ceur-ws.org/Vol-2604/paper60.pdf
|volume=Vol-2604
|authors=Yurii Matseliukh,Victoria Vysotska,Myroslava Bublyk
|dblpUrl=https://dblp.org/rec/conf/colins/MatseliukhVB20
}}
==Intelligent System of Visual Simulation of Passenger Flows==
https://ceur-ws.org/Vol-2604/paper60.pdf
Intelligent System of Visual Simulation of Passenger
Flows
Yurii Matseliukh [0000-0002-1721-7703], Victoria Vysotska [0000-0001-6417-3689],
Myroslava Bublyk [0000-0003-2403-0784]
Lviv Polytechnic National University, Lviv, Ukraine
indeed.post@gmail.com1, Victoria.A.Vysotska@lpnu.ua2,
my.bublyk@gmail.com3
Abstract. Existing information systems in the field of passenger transportation
are investigated, where the key task is to evaluate passenger flows. Possibilities,
accessibility, principles and principles of optimization of information systems of
passenger transportation of public transport are analyzed. It is established that the
visualization of passenger flows is one of the important tasks of optimizing routes
and improving the quality of passenger transportation by public transport. An
intelligent system of visual simulation of passenger traffic is proposed, which,
based on the operation of the neural network, allows optimizing the work of pas-
senger transportation by public transport.
Keywords: intelligent system, passenger flow, visualization, simulation, public
transportation
1 Introduction
Today one of the most important problems in smart city developing is public transpor-
tation, which in turn is not sufficiently guided by modern intelligent systems. The main
and most important unit in the field of public transportation is a passenger who needs
urban or long-distance transportation. The large number of passengers who use public
transport and make their own movements with it help to form the concept of passenger
flows. Passenger flows depend not only on the features of the route, but also on certain
major points of the largest passenger flows in the city. Passenger flows are the most
important aspect that must be discouraged when creating new routes and connections,
updating or modifying existing ones.
At the moment, it is precisely this problem of research and visualization of passenger
flows that has not been resolved, indicating its relevance.
The aim is to create intelligent system for visual simulation of passenger flows in
order to solve the current problems in the study and analysis of passenger flows by
using visualization.
Visual simulation of passenger flows will help solve the following tasks:
1. Visually see problem areas on routes.
Copyright © 2020 for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
2. Clearly identify major stops with the highest passenger flows.
3. Decide quickly on the need for route upgrades.
4. Obtain passenger flows forecasts for the quantitative and qualitative change of vehi-
cles.
The object of the study is the process of creating an intelligent system of visual simu-
lation of passenger flows in the field of public transport.
2 Analytical Review of Sources
2.1 Analysis of Recent Research and Publications
The author in [1] analyzes scientific developments in the field of information support
to optimize networks of public transport routes in large and very large cities, where he
developed a method of obtaining a matrix of correspondences containing all kinds of
urban displacements to the purposes with precision detailing to a specific stop. The
identified goals and directions can be used for further research of information support
of optimization tasks of public transit routes in large and very large cities.
In order to improve the organization of passenger service on the route, the authors
of [2] proposed to use a rational distribution of vehicles to take into account their pas-
senger capacity during the period during which the transportation is carried out. When
using rolling stock with a small number of seats in [2] considered that such an increase
in the number of transport leads to congestion of urban transport system and increasing
excess emissions of harmful gases into the atmosphere. The research has also developed
measures to increase the efficiency of rolling stock use to improve passenger service.
The problem of assessing the quality of passenger transportation by public transport
within the city with different numbers of vehicles on the route is devoted to work [3].
The authors [3] analyzed the existing methods of assessing the quality of urban
transport and identified among the criteria quality indicators: pedestrian movement,
waiting time, travel time and dynamic transport capacity factor. The simulation model
of change of the complex indicator of quality of public transport in the city developed
in [3] established a stable dependence of this indicator on the number of vehicles on the
route. This made it possible to determine such a rational number of rolling stock that
would maximize the efficiency of urban transport for a given quality level.
To predict passenger traffic in [4], the authors used the smart city principle for public
transport management, which was realized through the use of long-term short-term
memory (LSTM) based on a recurrent neural network architecture. The proposed hy-
brid optimized network model gives additional performance improvements of 4% -
20% compared to non-hybrid models, indicating the feasibility of using the proposed
hybrid optimized LSTM network based on the estimation of the accelerated Nester ad-
aptation moment (Nadam) and the stochastic gradient descent algorithm SGD when
modeling passenger flows.
In [5], the authors proposed a simulation model of the distribution of passenger traf-
fic on transport networks, taking into account the timetable and delay of trains. As a
result of modeling, the authors of [5] formulate statistical indicators, including the vol-
ume of passenger traffic of each vehicle and the stops that are animated by the software
of the software. The model proposed in [5] provides a quantitative example to illustrate
developed software. The authors [6-31] estimate man-made damage in the passenger
transportation, and modeling the fuzzy knowledge base for IT evaluation.
2.2 Analysis of Existing Software Products
Possibilities of visualization of passenger traffic in the sphere of public transport are
provided by the company "A + C Ukraine", as well as a three-month visualization of
data on the sale of electronic ticket in the city of Zhytomyr from the site
http://texty.org.ua/. A + C Ukraine does not disclose its methods and concentrates on
individual cities or routes, does not cooperate with international standards for route
reporting, and prefers to develop solutions individually for each situation. The greater
concentration of this company is focused on the organization of information gathering
and to a lesser extent on visual simulation, the only one presented by this company in
open access, an example of the work is shown in Fig. 1.
Fig. 1. Software from A + C Ukraine
As for the visualization of data from the electronic ticket from the site
http://texty.org.ua/, it has not been updated since January 2019 and provides visualiza-
tion only for a period of three months. It is worth noting that the e-ticket data is already
partially distorted, because not all passengers buy a ticket immediately after entering
the transport for various reasons, and not all passengers buy the ticket at all. This system
does not use data from real passenger traffic and provides only a schematic picture of
the tickets paid, without taking into account the current traffic load on the race.
Fig. 2. Website texty.org.ua
3 Systematic Analysis of the Proposed Intelligent System for
Visual Simulation of Passenger Flows
The developed intelligent system works with the most up-to-date data, downloading it
at the user's request from the servers of the city. From the diagrams in Fig. 3 and fig. 4
shows that the proposed intelligent system is very flexible to use and does not require
a long wait for updating and downloading of data for visual simulation or analysis.
Most processes with large datasets are performed only once at initial startup or forced
upgrade. In the future, this data is cached and does not require further updating. The
creation of additional files for filling occurs in a fully automatic mode, where the user
needs to fill in the data either in accordance with a specified template, which is created
specifically to unify the process of interaction between different systems, or in accord-
ance with the international standard GTFS.
The developed intelligent system works with the most up-to-date data, downloading
it at the user's request from the servers of the city. From the diagrams in Fig. 3 and fig.
4 shows that the proposed intelligent system is very flexible to use and does not require
a long wait for updating and downloading of data for visual simulation or analysis.
Most processes with large datasets are only performed once at initial startup or forced
upgrade. In the future, this data is cached and does not require further updating. The
creation of additional files for filling occurs in a fully automatic mode, where the user
needs to fill in the data either in accordance with a specified template, which is created
specifically to unify the process of interaction between different systems, or in accord-
ance with the international standard GTFS.
To facilitate the understanding of the main parts of the intellectual system, a descrip-
tion of the behavior of the projected system is presented in the form of an activity graph,
which is depicted using the activity diagram, which is shown in Fig. 3 and the state
diagrams in Figs. 4.
Fig. 3. Diagram of activity of the intelligent system
The neural network can be trained and retrained at the request of the user, which reduces
the running of calculations for the next visual simulations. There are also two different
modes of visual simulation: 1. With schematic representation of the route and stops on
it. 2. Real image of the route with real scale on the map.
Map mode also displays a simulation of moving traffic throughout the day, display-
ing all passengers who are waiting for or are already in transit and are moving between
stops.
Fig. 4. State diagram
To understand the interaction of the user, the intelligent system and other components
in Fig. Figure 5 shows a diagram showing that the system is constantly accessible and
can be updated from the servers of the city where the most up-to-date information about
all routes is located.
Fig. 5. Deployment chart
3.1 Description of the finished software
The main screen of the software is the interface shown in Fig. 6. The whole interface
is made according to the CE (Chain Elements) principle, which indicates this type of
interface when the user cannot click on buttons that are responsible for processing data
that does not yet exist, instead the user only has access to the buttons that are currently
available to use. And only after using the active buttons the user will gradually be able
to access the following buttons. That is, the user at any time can be sure that if the
button is active, then the action it describes will be executed exactly, of course, unless
there is some unforeseen situation, which will be reported separately. According to this
principle, in the presence of data, we can only update the data and choose the route and
its type. Also, the application interface is made in the dark mode, which is now very
popular for all software products or websites, which, in turn, is more pleasing to the
human eye and not too bright.
Fig. 6. The main interface
And in the absence of data, it will only be available to download the new data shown
in Fig. 7.
Fig. 7. Main interface without GTFS data
After selecting the route and its type, all other buttons and fields will be activated, and
the type of download will be "fast" or "slow", that is, whether the program already has
cached data, or whether to create a new cache for future runs. Immediately displays
whether there are downloaded maps or not. In general, the application does not require
maps, if the user does not have an API key for Google Maps, or does not want to use
maps, the mode will be displayed without a card in the background, but with all pro-
portions and scales. The main program window showing all the new features is pre-
sented in fig. 8.
Fig. 8. Main interface with all active buttons
The Create Excel buttons create a file to fill with passenger traffic for each transport on
the route. An Excel file is selected based on several factors, such as:
1. Passenger traffic data can only be collected by people who stop and count it man-
ually.
2. With the help of special sensors mounted on the doors of vehicles, which in turn
will be able to export the collected data to an Excel spreadsheet.
After successfully filling the Excel file with the number of passengers at stops, you can
choose any mode, either schematic or on the map.
In schematic mode, stops are marked one by one according to their location on the
route in the forward and reverse directions, there is a scroll up and down mouse to view
all stops and arrow navigation to select the next or previous time intervals.
If you use the D key, you can get to see the general information all day, not hourly.
Each stop is signed by the name and number used at the actual stops in the city on
the respective signs. The following is a summary of how many passengers went in and
out at a stop over a given period, the sum of all flow passengers at a stop. The size and
segments of a circle are dynamically determined. The larger circle indicates the greater
number of people who came in and left at this stop. The segments are highlighted in
different colors to reflect the attitude of those who have entered and those who have
left.
Between the stops, the dynamic width of the line and the number indicate the pas-
senger flow, that is, how many people were transported during this hour on this race
between stops.
This mode's interface uses different colors to indicate different meanings and fea-
tures. This is done to make the program interface as intuitive as possible without read-
ing the documentation shown in Fig. 9.
Fig. 9. Schematic mode
In this mode, you can also click on the stop and get more information, an example of a
window is shown in fig. 10.
The races also support the function of an additional data window, which shows the
maximum capacity of the race for several parameters, and of course all overloads are
depicted clearly by the color change, which is shown in Fig. 11.
General information about the route is displayed by clicking on the button "General
information" and an example of the window is shown in fig. 12.
Fig. 10. Stop data window
Fig. 11. The distillation data window
Fig. 12. General information window
Another available mode is the visual simulation mode on the map (Fig. 13), where ac-
cording to the received data on the time of transport and passengers accurate simulation
of traffic during the day with stops and picking up and disembarking of passengers.
This mode is best suited to understanding where real congestion can be found on the
map, or certain places that attract people to the city. Since the screen shows the exact
time of day, you can also see how much traffic is currently on the route, what is hap-
pening to them, perhaps the vehicle at lunch, or moving too slowly than expected.
Fig. 13. Map mode
This mode also supports zoom in and out, slowing down the simulation 2 and 3 times
(Fig. 14, 15) from normal. You can pause the simulation on the space key and examine
this point in time. Red is indicated by the active vehicle on the route, yellow - if at
lunch. At each stop, the number of passengers waiting for transport is indicated and the
size of the circle that indicates the stop, the more people, the larger the circle, dynami-
cally depends. The size of the circle increases dynamically between arrivals of
transport, also at landing and disembarkation.
Movement in all directions is by arrows, zoom - mouse wheel. The standard animation
speed is that 1 minute of virtual time is simulated in 1 second of real time, the speed
can be reduced 2 and 3 times by the PageDown key, and the speed increase by the
PageUP key.
Fig. 14. The smallest zoom
Fig. 15. The greatest zoom
Regarding the interaction with transport forecasting, there is a separate block on the
right side of the main menu (Fig. 8), in which you can train the neural network, after
which it will be saved and will not require retraining. The program also creates a tem-
plate file for the submission of information in GTFS format, which should fill the user
with a new additional transport schedule. Pressing the "Scheme Visualize" key asks for
the capacity of the added transport in the window in fig. 16, the passenger traffic data
is recalculated and it is displayed in the schematic display mode (Fig. 17).
Fig. 16. Window for entering capacity
Fig. 17. Changed passenger flows
4 Conclusions
The paper investigates a number of existing passenger software products on the market.
It is established that the key task of public transport information systems is to evaluate
passenger traffic. Their possibilities, accessibility, principles and principles of optimi-
zation of passenger transportation are analyzed. It is established that the visualization
of passenger flows is one of the important tasks of optimizing routes and improving the
quality of passenger transportation by public transport. An intelligent system of visual
simulation of passenger traffic is proposed, which, based on the operation of the neural
network, allows optimizing the work of passenger transportation by public transport.
References
1. Kohleber, Yu.A.: Informational support of optimization tasks for the public passenger
transport route network of major and major cities: relevance and approaches. In: Sibadi Ga-
zette, 15(2), 218-228. (2018)
2. Ryabov, I.M., Kashmanov, R.Ya.: Improving the organization of passenger service on the
route by using buses of different capacity. In: Sibadi Gazette, 16(3), 264-275. (2019)
3. Chumachenko, I.V., Davidich, Yu. A., Galkin, A.S., Davidich, N.V.: Evaluation of the qual-
ity of passenger transportation by public transport at different number of vehicles operating
on the route. In: Science and technology, 16(5), 415-421. (2017)
4. Han, Y., Wang, C., Ren, Y., Wang, S., Zheng, H., Chen, G.: Short-term prediction of bus
passenger flow based on hybrid optimized LSTM network. In: ISPRS International Journal
of Geo-Information, 8(9), 366. (2019) https://doi.org/10.3390/ijgi8090366.
5. Li, W., Zhu, W.: A dynamic simulation model of passenger flow distribution on a schedule-
based rail transit network with train delays. In: Journal of Traffic and Transportation Engi-
neering, 3(4), 364-373. (2016)
6. Kuzmin, O., Bublyk, M.: Economic evaluation and government regulation of technogenic
(man-made) damage in the national economy. In: Computer sciences and in-formation tech-
nologies. Proceedings of the XIth International Scientific and Technical Conference (CSIT
2016), 37–39. (2016). DOI: 10.1109/STC-CSIT.2016.7589863
7. Bublyk, M.I., Rybytska, O. M.: The model of fuzzy expert system for establish-ing the pol-
lution impact on the mortality rate in Ukraine. In: Computer sciences and in-formation tech-
nologies: Proceedings of the 2017 12th International Scientific and Tech-nical Conference
(CSIT 2017), 1, 253–256. (2017) DOI: 10.1109/STC-CSIT.2017.8098781.
8. Bublyk, M., Rybytska, O., Karpiak, A., Matseliukh, Y. Structuring the fuzzy knowledge
base of the IT industry impact factors. In: Computer sciences and information technologies
: Proceed. of the 2018 IEEE 13th International Scientific and Technical Conference (CSIT
2018), (Lviv, Ukraine, September, 11–14, 2018). (2018). DOI: 10.1109/STC-
CSIT.2018.8526760.
9. Su, J., Sachenko, A., Lytvyn, V., Vysotska, V., Dosyn, D.: Model of Touristic Infor-mation
Resources Integration According to User Needs, 2018 IEEE 13th International Scientific
and Technical Conference on Computer Sciences and Information Technolo-gies, CSIT
2018 – Proceedings 2, 113-116 (2018)
10. Lytvyn, V., Peleshchak, I., Vysotska, V., Peleshchak, R.: Satellite spectral information
recognition based on the synthesis of modified dynamic neural networks and holographic
data processing techniques, 2018 IEEE 13th International Scientific and Technical Con-fer-
ence on Computer Sciences and Information Technologies, CSIT 2018 – Proceedings 1,
330-334 (2018)
11. Vysotsky A., Lytvyn V., Vysotska V., Dosyn D., Lyudkevych I., Antonyuk N., Naum O.,
Vysotskyi A., Chyrun L., Slyusarchuk O.: Online Tourism System for Proposals For-mation
to User Based on Data Integration from Various Sources. In: 2019 IEEE 14th International
Scientific and Technical Conference on Computer Science and Information Nechnologies
(CSIT’2019), 92-97. (2019)
12. Antonyuk N., Vysotsky A., Vysotska V., Lytvyn V., Burov Y., Demchuk A., Lyudkevych
I., Chyrun L., Chyrun S., Bobyk І.: Consolidated Information Web Re-source for Online
Tourism Based on Data Integration and Geolocation. In: 2019 IEEE 14th International Sci-
entific and Technical Conference on Computer Science and Information Nechnologies
(CSIT’2019), 15-20. (2019)
13. Babichev, S.: An Evaluation of the Information Technology of Gene Expression Profiles
Processing Stability for Different Levels of Noise Components. In: Data, 3 (4), art. no. 48.
(2018)
14. Babichev, S., Durnyak, B., Pikh, I., Senkivskyy, V.: An Evaluation of the Objective Clus-
tering Inductive Technology Effectiveness Implemented Using Density-Based and Agglom-
erative Hierarchical Clustering Algorithms. In: Advances in Intelligent Systems and Com-
puting, 1020, 532-553. (2020)
15. Boreiko, O. Y., Teslyuk, V. M., Zelinskyy, A., Berezsky, О.: Development of models and
means of the server part of the system for passenger traffic registration of public transport
in the "smart" city. In: Eastern-European Journal of Enterprise Technologies, 1(2-85), 40-
47. (2017)
16. Kazarian, A., Teslyuk, V., Tsmots, I., Tykhan, M.: Implementation of the Face Recognition
Module for the “Smart” Home Using Remote Server. In: Advances in Intelligent Systems
and Computing III, AISC 871, Springer, 17–27. (2019)
17. Rusyn, I. B., Valko, B. T.: Container landscaping with Festuca arundinaceae as а mini bio-
electrical systems in a modern buildings. In: International Journal of Energy for a Clean
Environment, 20(3), 211-219. (2019).
18. Rusyn, I. B., Hamkalo, Кh. R.: Bioelectricity production in an indoor plant-microbial bio-
technological system with Alisma plantago-aquatica. In: Acta Biologica Szegediensis, 62
(2), 170-179. (2018).
19. Berko, A.Y., Aliekseyeva, K.A.: Quality evaluation of information resources in web-pro-
jects. In: Actual Problems of Economics 136(10), 226-234. (2012)
20. Kanishcheva, O., Cherednichenko, O., Sharonova, N.: Image Tag Core Generation. In:
CEUR Workshop Proceedings, Vol-2533, 35-44. (2019)
21. Tkachenko, V., Cherednichenko, O., Godlevskyi, M.: The Concept of Device Meta-Model
for Real-Time Communication in the Transboundary Environment Monitoring System. In:
International Scientific-Practical Conference, PIC S&T, 64-70. (2018)
22. Anisimova, O., Vasylenko, V., Fedushko, S.: Social Networks as a Tool for a Higher Edu-
cation Institution Image Creation. In: CEUR Workshop Proceedings, Vol-2392, 54–65.
(2019)
23. Fedushko, S., Davidekova, M.: Analytical service for processing behavioral, psychological
and communicative features in the online communication. In: The International Workshop
on Digitalization and Servitization within Factory-Free Economy (D&SwFFE), 160, 509-
514. (2019)
24. Fedushko, S., Trach, O., Kunch, Z., Turchyn, Y., Yarka, U.: Modelling the Behavior Clas-
sification of Social News Aggregations Users. In: CEUR Workshop Proceedings, Vol 2392.
95–110. (2019)
25. Fedushko, S., Ustyianovych, T.: Predicting Pupil’s Successfulness Factors Using Machine
Learning Algorithms and Mathematical Modelling Methods. In: Advances in Intelligent
Systems and Computing, 938. Springer, Cham, 625-636. (2020)
26. Lozynska, O., Savchuk, V., Pasichnyk, V.: Individual Sign Translator Component of Tourist
Information System. In: Advances in Intelligent Systems and Computing IV, Springer Na-
ture Switzerland AG 2020, Springer, Cham, 1080, 593-601. (2020)
27. Rzheuskyi, A., Kutyuk, O., Voloshyn, O., Kowalska-Styczen, A., Voloshyn, V., Chyrun, L.,
Chyrun, S., Peleshko, D., Rak, T.: The Intellectual System Development of Distant Compe-
tencies Analyzing for IT Recruitment. In: Advances in Intelligent Systems and Computing
IV, Springer, Cham, 1080, 696-720. (2020)
28. Rusyn, B., Pohreliuk, L., Rzheuskyi, A., Kubik, R., Ryshkovets Y., Chyrun, L., Chyrun, S.,
Vysotskyi, A., Fernandes, V. B.: The Mobile Application Development Based on Online
Music Library for Socializing in the World of Bard Songs and Scouts’ Bonfires. In: Ad-
vances in Intelligent Systems and Computing IV, Springer, 1080, 734-756. (2020)
29. Veres, O., Rusyn, B. Sachenko, A., Rishnyak, I.: Choosing the method of finding similar
images in the resverse seach system. In: CEUR WorkshopProceedings, 2136, 99-107. (2018)
30. Varetskyy, Y., Rusyn, B., Molga, A., Ignatovych, A.: A new method of fingerprint key pro-
tection of grid credential. In: Advances in Intelligent and Soft Computing, 84, 99-103.
(2010)
31. Antonyuk, N., Medykovskyy, M., Chyrun, L., Dverii, M., Oborska, O., Krylyshyn, M.,
Vysotsky, A., Tsiura, N., Naum, O.: Online Tourism System Development for Searching
and Planning Trips with User’s Requirements. In: Advances in Intelligent Systems and
Computing IV, Springer Nature Switzerland AG 2020, 1080, 831-863. (2020)