Intelligent Transportation Systems Solutions for Buses Mobility Scheduling
To build intelligent transport systems in road traffic, first of all, it is required to organize the collection of information about the state of traffic. One way to do this is to ensure that data is received directly from users. Almost every person has a smartphone with GPS and other useful sensors that allow to transmit up-to-date information about the transport system (Wan et al., 2020). To collect information, an application can be developed where the user will indicate his route, helping the system collect data on speed, delays in certain sections, altitude and many other factors that can be used to analyze the traffic situation.
The second way of collecting information does not require the direct participation of a person: it involves the use of modern Big Data analytics. Already today, there are programs and entire systems that help analyze the movement of people through SIM-cards in phones, collecting large amounts of anonymous data (Zhu et al., 2019). The information collected using smartphones makes it possible to obtain and use real information about the situation and dynamics of population movement in any part of the road network (Fatemidokht et al., 2021). Using such solutions, it is possible to start building modern urban passenger transport management systems, as well as entire “smart cities”.
In addition to the above, traffic monitoring on the road can be organized using high-quality cameras and traffic radars. These technologies provide the necessary information about speed, distance between vehicles, routes, traffic through intersections, delays and distribution between individual traffic lanes (Guevara and Cheein, 2020). Settlements should have the most accurate information about the situation on transport routes in order to properly plan and build urban road infrastructure, optimize it, taking into account the needs of citizens and current conditions.
Internet of Things
Intelligent transport systems on the roads are a whole range of functional equipment that collects information, manages traffic flow and informs road users. Only if the system is equipped with the necessary equipment and its integrated work can a significant improvement in the situation on the roads in megacities be achieved (Lana et al., 2021). It is important to analyze the most vitl aspects of the whole system:
Road Cameras
Traffic cameras act as the “eyes” of modern intelligent transport systems. These are high-resolution cameras, which are widely used by the developers of ITS and complexes for video recording of traffic violations (Brincat et al., 2019). The systems use industrial cameras that allow you to effectively monitor the traffic flow, highlight and trace moving objects, capture frames with state registration plates of vehicles, and recognize alphanumeric images on license plates.
Smart Traffic Lights
It is customary to call a traffic light smart, which is controlled by a special program that allows the device to make decisions independently, including on the basis of incoming traffic information from other similar devices. In cities where such systems are already used, a situational center is required to function, which also helps to pass emergency vehicles to calls.
Traffic Detectors
These are special measuring devices that work with the help of sensitive elements, an amplifier-converter and an output device. The device captures the fact of the passage or presence of a vehicle in the controlled area, generates a primary signal, which is subsequently amplified, processed and converted into a form convenient for registration.
Electronic Means of Fare Payment
The need to pay for travel contributes to the formation of congestion on the roads. To reduce traffic jams, so-called electronic means of fare payment – transponders are used. These are transceivers that allow you to move non-stop through paid checkpoints (Pan et al., 2021). They are installed on the windshield of a car, have unique personal accounts and identification numbers. To pay the fare, the driver only needs to slow down to 30 km/h and the money will be automatically debited from the account.
Parking Meters
To simplify and secure the city’s road system, it is necessary to think over parking. Parking meters, devices that are located in places of automated paid parking, do an excellent job with this. With their help, the motorist can independently pay for parking in accordance with the specified tariffs (Mollah et al., 2020). The devices not only make life easier for drivers, but also make parking more economical by reducing employee costs.
Automated Lighting Control
The lighting control system makes it possible to fully automate street and road lighting. It is able to independently make a decision on the need to turn on or off the light in accordance with the situation on the road, time of day and other factors (Sobral et al., 2019). The system works according to a set algorithm, receiving information from various sensors that record the load and illumination of the road zone.
Artificial Intelligence, Data Analytics, and Deep Learning
Transportation systems already under construction, as well as those under development, have a number of advantages that make government and business representatives in cities around the world think about the possibility of implementing the technology. For example, Intelligent Transport System is being developed, aimed simultaneously at:
- Reduction of traffic hazards, reduction in the number of accidents and deaths on the roads;
- Ensuring unhindered movement of special services and special vehicles to respond to calls (Guerrero-Ibanez et al., 2018);
- Prompt and accurate communication of information to special services about the situation on the roads;
- Informing drivers about traffic violations;
- Fixation of any facts of traffic violations by the driver;
- Increasing the driver’s attention while driving and preventing falling asleep at the wheel;
- Creating the necessary conditions to reduce the time that passengers have to spend to get to work or to any other place in the city (Camacho et al., 2018);
- Ensuring the possibility of choosing the optimal route in terms of convenience and speed;
- Optimization of traffic, taking into account the situation on the roads.
At the same time, more globally, the introduction of AI technologies in transport has two main advantages: convenience for passengers and integration with road transport services.
Examples of Implementation of Transport Management Systems
Smart public transport is extremely relevant today, therefore, in different countries and cities, individual technical and software solutions are being developed and implemented to make road traffic safer and more convenient. In Singapore, traffic detectors and video cameras are installed on most roads – every 500 and 1000 meters, respectively (Hirtan et al., 2020, p. 791). They are also equipped with traffic lights and city buses. All data is sent to a single control center, where it is analyzed and used to improve the situation on the roads. The country has a trip planner that uses information from taxi dispatch services (Zhou et al., 2019). Using this data, the average speed of movement along the main highways is calculated, and the planner adjusts the issued route (Haydari and Yilmaz, 2022). Radio channels are actively used, through which reports on the congestion of key roads and interchanges are transmitted. During peak hours, informing citizens becomes more frequent.
Japan’s ITS is based on the automotive information and communications system, which is used as a basis for making navigators for cars and through which GPS data on traffic congestion and detours can be obtained. Information is transmitted from roadside transmitters and beacons installed back in 1995 to a single information center (Ganin et al., 2019). Information about road accidents, pavement repairs and traffic jams goes directly to drivers’ navigators. In the country, transport management systems use the DSRC standard – a wireless communication channel (Manogaran and Alazab, 2021). With this solution, road users can receive notifications and warnings about emergency situations (Lv et al., 2021). In addition, the American transport system allows you to monitor the performance of cars remotely in real time, collect tolls electronically, warn about the possibility of a frontal collision or car overturn.
Synthesis of Findings
Many companies are thinking over the architecture of intelligent transport systems, offering more and more modern and technological solutions to control the situation on the road, but not all of them are being implemented today. The task of modernizing the transport system of even one city is enormous (Zichihi et al., 2020). Projects require sometimes crazy investments – what does it cost to install cameras every 500 meters on all roads, as is done today in Singapore (Ferdowsi et al., 2019, p. 67). Projects are not limited to cameras alone: their work requires incredible resources, so smart systems can be developed and built only if there is an appropriate institutional capacity, which is not available in most states. A lot is being done in the state to modernize the outdated system.
For example, geolocation is being introduced, which allows you to find out the location of buses, trains and other traffic participants. It helps not only the passengers and travelers themselves, but also business owners who want to control the current location of their vehicles (Veres and Moussa, 2020). The work of smart transport with geolocation is implemented through the Internet of things, where the elements of the system exchange information with each other (Dain et al., 2018). Data from sensors from buses and on the road is sent to a specially created application that informs passengers about the position of the vehicle. In addition, many cities are introducing a system of unified non-cash fares, which makes all financial transactions completely transparent.
References
Brincat, A. A., Pacifici, F., Matrinaglia, S., & Mazzola, F. (2019). The Internet of Things for intelligent transportation systems in real smart cities scenarios.2019 IEEE 5th World Forum on Internet of Things (WF-IoT), 1(1).
Camacho, F., Cardenas, C., & Munoz, D. (2018). Emerging technologies and research challenges for intelligent transportation systems: 5G, HetNets, and SDN. International Journal on Interactive Design and Manufacturing (IJIDeM), 12, 327-335.
Dain, A., Harrou, F., Sun, Y., & Senouci, M. (2018). Obstacle detection for intelligent transportation systems using deep stacked autoencoder and k-nearest neighbor scheme. IEEE Sensors Journal, 18(2), 5122-5132.
Fatemidokht, H., Rafsanjani, M. K., Gupta, B. B., & Hsu, C. H. (2021). Efficient and secure routing protocol based on artificial intelligence algorithms with UAV-Assisted for vehicular ad hoc networks in intelligent transportation systems. IEEE Transactions on Intelligent Transportation Systems, 22(7), 4757-4769.
Ferdowsi, A., Challita, U. & Saad, W. (2019). Deep learning for reliable mobile edge analytics in intelligent transportation systems: An overview. IEEE Vehicular Technology Magazine, 14(1), 62-70.
Ganin, A. A., Mersky, A. C., Jin, A. S., Kitsak, M., Keisler, J. M., & Linkov, I. (2019). Resilience in intelligent transportation systems (ITS).Transportation Research Part C: Emerging Technologies, 100, 318-329.
Guerrero-Ibanez, J., Zeadally, S., & Conteras-Castillo, J. (2018). Sensor technologies for intelligent transportation systems.Sensors, 18(4), 1212.
Guevara, L., & Cheein, F. A. (2020). The role of 5G technologies: Challenges in smart cities and intelligent transportation systems. Sustainability, 12(16), 6469.
Haydari, A., & Yilmaz, Y. (2022). Deep reinforcement learning for intelligent transportation systems: A survey. IEEE Transactions on Intelligent Transportation System, 23(1), 11-32.
Hirtan, L. A., Dobre, C., & Gonzalez-Velez, H. (2020). Blockchain-based reputation for intelligent transportation systems. Sensors, 20(3), 791.
Lana, I., Sanchez-Medina, J. J., Viahogianni, E. I., & Del Ser, J. (2021). From data to actions in intelligent transportation systems: A prescription of functional requirements for model actionability. Sensors, 21(4), 1121.
Lv, Z., Rou, R., & Singh, A. K. (2021). AI empowered communication systems for intelligent transportation systems. IEEE Transactions on Intelligent Transportation Systems, 22(7), 4579-4587.
Manogaran, G. & Alazab, M. (2021). Ant-inspired recurrent deep learning model for improving the service flow of intelligent transportation systems. IEEE Transactions on Intelligent Transportation Systems, 22(6), 3654-3663.
Mollah, M. B., Zhao, J., Niyato, D., Guan, L. Y., Yuen, C., Sun, S., & Lam, K. Y. (2020). Blockchain for the Internet of vehicles towards intelligent transportation systems: A survey.IEEE Internet of Things Journal, 8(6), 4157-4185.
Pan, S., Yan, H., He, J., & He, Z. (2021). Vulnerability and resilience of transportation systems: A recent literature review. Physica A: Statistical Mechanics and its Applications, 581, 126235.
Sobral, T., Galvao, T., & Borges, J. (2019). Visualization of urban mobility data from intelligent transportation systems. Sensors, 19(2), 332. Web.
Veres, M. & Moussa, M. (2020). Deep learning for intelligent transportation systems: A survey of emerging trends. IEEE Transactions on Intelligent Transportation Systems, 21(8), 3152-3168.
Wan, S., Xu, X., Wang, T., & Gu, Z. (2020). An intelligent video analysis method for abnormal event detection in intelligent transportation systems. IEEE Transactions on Intelligent Transportation Systems, 22(7), 4487-4495.
Zhou, Y., Wang, J., & Yang, H. (2019). Resilience of transportation systems: Concepts and comprehensive review. IEEE Transactions on Intelligent Transportation Systems, 20(12), 4262-4276.
Zhu, L., Yu, F., Wang, B., Ning, B. & Tang, T. (2019). Big data analytics in intelligent transportation systems: A survey. IEEE Transactions on Intelligent Transportation Systems, 20(1), 383-398.
Zichihi, M., Ferreti, S., & D’Angelo, G. (2020). A framework based on distributed ledger technologies for data management and services in intelligent transportation systems. IEEE Access, 8, 100384-100402.