ABSTRACT
This paper describes the development of a prototype website for traffic, parking and transport in a smart city. Machine Learning (ML) tools are applied to open datasets from the City of Melbourne, Australia to develop a set of Application Programming Interfaces (APIs) that provide useful information for the city's managers and citizens. The APIs accessed from this website enable users to query the ML models and obtain answers to questions such as: which parts of the city have the greatest pedestrian traffic, or the availability and cost of parking spots. The freeware tool RStudio was used for Big Data analytics while Machine Learning with Plumber was used to wrap the R code into APIs and Swagger to specify and document them. Postman and Swagger were used for testing while Docker was employed to package the APIs into standard containers for cloud deployment. The prototype website was developed using Wix and deployed on the Nectar cloud. The resulting website provides predictive models for COM traffic, parking, and transport and demonstrates the application of online smart city services for city planners and managers.
- Nikitas, A., Michalakopoulou, K., Njoya, E. T. and Karampatzakis, D. (2020) Artificial intelligence, transport and the smart city: Definitions and dimensions of a new mobility era. Sustainability 12 (7) 2789Google ScholarCross Ref
- Mualla, Y., Najjar, A., Galland, S., Nicolle, C., Haman Tchappi, I., Yasar, A.-U.-H. and Främling, K. (2019) Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent SystemsGoogle Scholar
- Al-Turjman, F. and Malekloo, A. (2019) Smart parking in IoT-enabled cities: A survey. Sustainable Cities and Society 49 2019/08/01/ 101608Google ScholarCross Ref
- Mudaliar, S., Agali, S., Mudhol, S. and Jambotkar, C. (2019) IoT based smart car parking system. Int J Sci Adv Res Technol 5 (1) 270-272Google Scholar
- Gopal, D. G., Jerlin, M. A. and Abirami, M. (2019) A smart parking system using IoT. World Review of Entrepreneurship, Management and Sustainable Development 15 (3) 335-345Google ScholarCross Ref
- NSW Department of Transport. Car Park API. [Accessed 28 September 2020]; Available from: https://opendata.transport.nsw.gov.au/dataset/car-park-api.Google Scholar
- ACT Government Open Data Portal dataACT. SmartParking API. [Accessed 20 September 2020]; Available from: https://www.data.act.gov.au/Transport/SmartParking-API/2xfc-29mw.Google Scholar
- Zheng, Y., Elefteriadou, L., Chase, T., Schroeder, B. and Sisiopiku, V. (2016) Pedestrian Traffic Operations in Urban Networks. Transportation Research Procedia 15 2016/01/01/ 137-149Google Scholar
- Galanis, A., Botzoris, G. and Eliou, N. (2017) Pedestrian road safety in relation to urban road type and traffic flow. Transportation Research Procedia 24 2017/01/01/ 220-227Google Scholar
- Feliciani, C., Gorrini, A., Crociani, L., Vizzari, G., Nishinari, K. and Bandini, S. (2019) Calibration and validation of a simulation model for predicting pedestrian fatalities at unsignalized crosswalks by means of statistical traffic data. Journal of Traffic and Transportation Engineering (English Edition) 7 (1) 2019/07/27/ 1-18Google ScholarCross Ref
- Akhter, F., Khadivizand, S., Siddiquei, H. R., Alahi, M. E. E. and Mukhopadhyay, S. (2019) IoT enabled intelligent sensor node for smart city: pedestrian counting and ambient monitoring. Sensors 19 (15) 3374Google ScholarCross Ref
- Vitello, P., Capponi, A., Fiandrino, C., Giaccone, P., Kliazovich, D. and Bouvry, P. (2018) High-precision design of pedestrian mobility for smart city simulators. In: 2018 IEEE International Conference on Communications (ICC), IEEEGoogle ScholarCross Ref
- City of Melbourne. City of Melbourne Open Data. (2020) [Accessed 9 September 2020]; Available from: https://data.melbourne.vic.gov.au.Google Scholar
- Cross, B. Comparing Machine Learning as a Service: Amazon, Microsoft Azure, Google Cloud AI, IBM Watson. (2018) [Accessed 7 April 2020]; Available from: https://www.altexsoft.com/blog/datascience/comparing-machine-learning-as-a-service-amazon-microsoft-azure-google-cloud-ai-ibm-watson/.Google Scholar
- Rstudio. Open Source & Professional Software for Data Science Teams 2020. (2020) Updated 16 January 2020 [Accessed 2 September 2020]; Available from: https://rstudio.com.Google Scholar
- Rutqvist, D., Kleyko, D. and Blomstedt, F. (2019) An Automated Machine Learning Approach for Smart Waste Management Systems. IEEE Transactions on Industrial Informatics 16 (1) 1-9Google Scholar
- Detective, T. D. The 80/20 Split Intuition and an Alternative Split Method. (2020) [Accessed 16 October 2020]; Available from: https://towardsdatascience.com/finally-why-we-use-an-80-20-split-for-training-and-test-data-plus-an-alternative-method-oh-yes-edc77e96295d.Google Scholar
- Gour, R. Train and Test Set in Python Machine Learning — How to Split. (2020) [Accessed 16 October 2020]; Available from: https://medium.com/@rinu.gour123/train-and-test-set-in-python-machine-learning-how-to-split-58029a0d657b.Google Scholar
- Plumber. Plumber: An API Generator for R. [Accessed 2 September 2020]; Available from: www.rplumber.io.Google Scholar
- Swagger. Swagger: API Development for Everyone. Updated 9 September 2020 [Accessed 20 September 2020]; Available from: www.swagger.io.Google Scholar
- Postman. Postman, The Collaboration Platform for API Development. [Accessed 2 September 2020]; Available from: https://www.postman.com.Google Scholar
- Docker. What is a Container? A standardized unit of software. (2020) Updated 3 June 2020 [Accessed; Available from: https://www.docker.com/resources/what-container.Google Scholar
- Wix. Wix - Create Your Website. [Accessed 20 September 2020]; Available from: www.wix.com.Google Scholar
Recommendations
Visualization and Waste Collection Route Heuristics of Smart Bins Data using Python Big Data Analytics
ICSIM '21: Proceedings of the 2021 4th International Conference on Software Engineering and Information ManagementThis paper describes a set of waste management Application Programming Interfaces (APIs) written in the python language and using the Pandas, NumPy, Matplotlib, Basemap, Haversine and other big data analytics libraries. These access open datasets ...
Can a small city be considered a smart city?
The term smart cities has been widely used over the last years. The main goal of the smart cities initiative is to enable cities to manage their assets efficiently, investing in innovation and creativity as a way to promote sustainable and inclusive ...
Smart Cities as Hubs: Navigating the Smart City Data Providers Landscape
Information Integration and Web IntelligenceAbstractSmart Cities produce a wealth of data from the network of sensors and devices that are deployed at metropolitan scale. These data are managed by Smart City platforms that may provide APIs for enabling access them. The compatibility of these APIs ...
Comments