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 passenger transportation by public transport.
Today one of the most important problems in smart city developing is public transportation, 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. 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 vehicles.
The object of the study is the process of creating an intelligent system of visual simulation of passenger flows in the field of public transport. 2 2.1
The author in [
In order to improve the organization of passenger service on the route, the authors
of [
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 [
The authors [
To predict passenger traffic in [
In [
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.
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 accordance 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 accordance with the international standard GTFS.
To facilitate the understanding of the main parts of the intellectual system, a description 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, displaying all passengers who are waiting for or are already in transit and are moving between stops.
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. 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 manually.
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 passenger 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 features. This is done to make the program interface as intuitive as possible without reading the documentation shown in Fig. 9.
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. 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, dynamically 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 template 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). 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 optimization 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.