Traffic decision‐making system, as known as intelligent transportation system (ITS), aims to detect traffic flow within a smart city and offer optimal solutions using proper big data analytics [48]. Assessing and analyzing this big data plays a pivot role in decision making systems that makes the process time‐ and cost‐efficient [37]. Researchers addressed some case studies within traffic decision‐making systems, such as road traffic accidents analysis [49, 50], public transportation management and control, and road traffic flow prediction.
Additionally, big data analysis algorithms facilitate and boost the process of handling large amount of data to provide enough information for making decisions. Traffic decision‐making systems using big data algorithms and technologies help associate offices and the people in charge to get to learn drivers' journey patterns within the transportation network that reports whole network trends or better understanding of similar drivers [37]. Considering this feature, the systems provide the best path to drivers to reach their destination through the minimum time possible. Furthermore, the systems help the city to relay the traffic by controlling traffic light, the best timing to decide which light should be on or off and for what period.
Furthermore, traffic decision‐making systems predicts the probability of traffic accident occurrence using big data algorithms [37]. This requires to have smart healthcare systems, which is nominated as one of smart cities features discussed in Figure 2.1, to help emergency centers to facilitate the process of emergency rescue.
2.3.3.2 Safe and Smart Environment
Researchers in [5] leveraged DL algorithms and advanced communication technologies to link vehicles, roads, and drivers to facilitate and enhance various traffic‐related tasks and improve air pollution [6]. The scientists focused on different initiatives with the goal of creating a safe and smart environment and transportation. Further, Zhu et al. [37] developed an approach to use two algorithms: Bayesian inference and Random forest to execute in real time to predict the probability of crash occurrence to decrease crash risks in smart cities. Moreover, researchers [38] have established a combination of supervised and regression algorithms such as multivariate adaptive regression splines, classification and regression trees, and logistic regression to study the dataset of motor vehicle accident injury.
To have a safe environment, air pollution prediction in smart cities plays an imperative role. There have been a significant amount of work tried to enhance the prediction using several machine learning algorithms. The usage of machine learning algorithms to make environment safe has increased consistently, stating that how important this prediction would be for smart cities [6]. We examined the most relevant research studies [4, 6, 23, 38] but not limited to these, applying different evaluation based on several metrics. The evaluation of those research leads us to the following common observations: first, the rate of applying of the advanced (DL) machine learning algorithms has proliferated rather than typical machine learning algorithms; second, among the prediction elements for air pollution prediction, PM2.5 is considered as the most popular element; third, the data used for air pollution prediction had already generated hourly rather than daily; and in the final observation, efficient prediction occurs when air‐quality captured data merged with other relevant data of other networks like healthcare network within the smart cities.
2.4 Conclusion
We highlight smart cities' research branches and technology advancement regarding different complex domains. We propose a solution, namely, universal smart cities' decision making, which has three main sections: data capturing, data analysis, and decision making. We provide an abstract review of the fundamental concepts of big data, ML, and DL algorithms being applied to smart cities. We explore the essential role of the aforementioned algorithms on making decision within smart cities. The goal of this study is to provide a comprehensive survey of data analytics in smart cities, more specifically the role of big data algorithms and other advanced technologies like ML and DL for making decision in smart mobility within smart cities.
References
1 1 Amini, M.H., Mohammadi, J., and Kar, S. (2020). Promises of fully distributed optimization for IoT‐based smart city infrastructures. In: Optimization, Learning, and Control for Interdependent Complex Networks, ( M Hadi Amini), 15–35. Springer.
2 2 Montori, F., Bedogni, L., and Bononi, L. (2017). A collaborative internet of things architecture for smart cities and environmental monitoring. IEEE Internet of Things Journal 5 (2): 592–605.
3 3 Bibri, S.E. and Krogstie, J. (2017). Smart sustainable cities of the future: an extensive interdisciplinary literature review. Sustainable Cities and Society 31: 183–212.
4 4 Amini, M.H., Imteaj, A., and Pardalos, P.M. (2020). Interdependent networks: a data science perspective. Patterns 1 100003.
5 5 An, C. and Wu, C. (2020). Traffic big data assisted V2X communications toward smart transportation. Wireless Networks 26 (3): 1601–1610.
6 6 Iskandaryan, D., Ramos, F., and Trilles, S. (2020). Air quality prediction in smart cities using machine learning technologies based on sensor data: a review. Applied Sciences 10 (7): 2401.
7 7 Mohammadi, F.G., Amini, M.H., and Arabnia, H.R. (2020). An introduction to advanced machine learning: meta‐learning algorithms, applications, and promises. In: Optimization, Learning, and Control for Interdependent Complex Networks, ( M Hadi Amini), 129–144. Springer.
8 8 Neves, F.T., de Castro Neto M., and Aparicio, M. (2020). The impacts of open data initiatives on smart cities: a framework for evaluation and monitoring. Cities 106: 102860.
9 9 Amini, M.H., Arasteh, H., and Siano, P. (2019). Sustainable smart cities through the lens of complex interdependent infrastructures: panorama and state‐of‐the‐art. In: Sustainable Interdependent Networks II, ( M Hadi Amini), 45–68. Springer.
