The Use of Artificial Intelligence in the Assessment of User Routes in Shared Mobility Systems in Smart Cities
The use of artificial intelligence in solutions used in smart cities is becoming more and more popular. An example of the use of machine learning is the improvement of the management of shared mobility systems in terms of assessing the accuracy of user journeys. Due to the fact that vehicle-sharing...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Smart Cities |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-6511/6/4/86 |
| _version_ | 1797583193540395008 |
|---|---|
| author | Andrzej Kubik |
| author_facet | Andrzej Kubik |
| author_sort | Andrzej Kubik |
| collection | DOAJ |
| description | The use of artificial intelligence in solutions used in smart cities is becoming more and more popular. An example of the use of machine learning is the improvement of the management of shared mobility systems in terms of assessing the accuracy of user journeys. Due to the fact that vehicle-sharing systems are appearing in increasing numbers in city centers and outskirts, and the way vehicles are used is not controlled by operators in real mode, there is a need to fill this research gap. The article presents a built machine learning model, which is a supplement to existing research and is updated with new data from the existing system. The developed model is used to determine and assess the accuracy of trips made by users of shared mobility systems. In addition, an application was also created showing an example of using the model in practice. The aim of the article is therefore to indicate the possibility of correct identification of journeys with vehicles from shared mobility systems. Studies have shown that the prediction efficiency of the data generated by the model reached the level of 95% agreement. In addition, the research results indicate that it is possible to automate the process of evaluating journeys made in shared mobility systems. The application of the model in practice will facilitate management and, above all, it is open to further updates. The use of many machine learning models will allow solving many problems that will occur in an increasing number of smart cities. |
| first_indexed | 2024-03-10T23:35:23Z |
| format | Article |
| id | doaj.art-1ffdcf2c289f49c9bb0b2d82f310d9a9 |
| institution | Directory Open Access Journal |
| issn | 2624-6511 |
| language | English |
| last_indexed | 2024-03-10T23:35:23Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Smart Cities |
| spelling | doaj.art-1ffdcf2c289f49c9bb0b2d82f310d9a92023-11-19T03:00:28ZengMDPI AGSmart Cities2624-65112023-08-01641858187810.3390/smartcities6040086The Use of Artificial Intelligence in the Assessment of User Routes in Shared Mobility Systems in Smart CitiesAndrzej Kubik0Department of Road Transport, Faculty of Transport and Aviation Engineering, Silesian University of Technology, Krasińskiego 8 Street, 40-019 Katowice, PolandThe use of artificial intelligence in solutions used in smart cities is becoming more and more popular. An example of the use of machine learning is the improvement of the management of shared mobility systems in terms of assessing the accuracy of user journeys. Due to the fact that vehicle-sharing systems are appearing in increasing numbers in city centers and outskirts, and the way vehicles are used is not controlled by operators in real mode, there is a need to fill this research gap. The article presents a built machine learning model, which is a supplement to existing research and is updated with new data from the existing system. The developed model is used to determine and assess the accuracy of trips made by users of shared mobility systems. In addition, an application was also created showing an example of using the model in practice. The aim of the article is therefore to indicate the possibility of correct identification of journeys with vehicles from shared mobility systems. Studies have shown that the prediction efficiency of the data generated by the model reached the level of 95% agreement. In addition, the research results indicate that it is possible to automate the process of evaluating journeys made in shared mobility systems. The application of the model in practice will facilitate management and, above all, it is open to further updates. The use of many machine learning models will allow solving many problems that will occur in an increasing number of smart cities.https://www.mdpi.com/2624-6511/6/4/86smart citiesshared mobilitymachine learningartificial intelligencemobility modeling |
| spellingShingle | Andrzej Kubik The Use of Artificial Intelligence in the Assessment of User Routes in Shared Mobility Systems in Smart Cities Smart Cities smart cities shared mobility machine learning artificial intelligence mobility modeling |
| title | The Use of Artificial Intelligence in the Assessment of User Routes in Shared Mobility Systems in Smart Cities |
| title_full | The Use of Artificial Intelligence in the Assessment of User Routes in Shared Mobility Systems in Smart Cities |
| title_fullStr | The Use of Artificial Intelligence in the Assessment of User Routes in Shared Mobility Systems in Smart Cities |
| title_full_unstemmed | The Use of Artificial Intelligence in the Assessment of User Routes in Shared Mobility Systems in Smart Cities |
| title_short | The Use of Artificial Intelligence in the Assessment of User Routes in Shared Mobility Systems in Smart Cities |
| title_sort | use of artificial intelligence in the assessment of user routes in shared mobility systems in smart cities |
| topic | smart cities shared mobility machine learning artificial intelligence mobility modeling |
| url | https://www.mdpi.com/2624-6511/6/4/86 |
| work_keys_str_mv | AT andrzejkubik theuseofartificialintelligenceintheassessmentofuserroutesinsharedmobilitysystemsinsmartcities AT andrzejkubik useofartificialintelligenceintheassessmentofuserroutesinsharedmobilitysystemsinsmartcities |