Context-Aware Location Recommendations for Smart Cities
Machine learning (ML) helps to optimize the quality of service for citizens with low expenses and quick responses on urgent issues. ML techniques have been known for many years and are now capable of helping with the development of solutions to several common issues found in smart cities, including network infrastructure and Internet of Things (IoT) data (Huang et al. Social friend recommendation based on multiple network correlation, 2015). ML provides intelligent network infrastructures with smarter data management and cognitive applications.
Smart city projects address several issues affecting highly inhabited areas and cities. As such, state institutions and private organizations are exploring their potential benefits. In technical terms, smart city projects have a complex set of requirements, including multiple users with extremely different needs.
Recommendation systems have recently gained popularity with researchers because of their versatility with integrating different research areas. A recommendation system generally interacts with its users in the most user-friendly way possible and recommends something based its user’s preferences. Recommendations for news, videos, retail items, or personalized travel can be dealt with by comparative ML algorithms. Moreover, in the recommendation requests, ML algorithms can be adjusted with the help of special query language.
ML provides an attainable approach to resolve multiple demands and objectives while keeping computations on an inexpensive level of difficulty and providing the necessary process capabilities. This permits, for example, the ability to develop “on-the-fly” solutions for issues with decision variables. An ML recommendation system can be created, which can help in the formation of smart cities.
The adoptions of software-defined networking and ML are innovative approaches for smart city project development and preparation. Big data are also considered to be an inherent component of smart city projects that must be tackled. It has been argued that the complexity of smart city projects requires new and innovative approaches that can result in more efficient and intelligent systems. A broad framework is proposed in this chapter, with a discussion about the impacts of software-defined networking and ML on innovation. In addition, a use case is presented to demonstrate the potential benefits of cognitive learning for smart cities.
Internet of Things
Location-Based Social Networks
- 1.Guo, L., Zhang, C., & Fang, Y. (2013). A trust-based privacy-preserving friend recommendation scheme for online social networks. Piscataway, NJ: IEEE.Google Scholar
- 2.Kacchi, T. R., & Deoranker, A. V. (2016). Friend recommendation system based on lifestyles of users. In International Conference on Advances in Electrical, Electronics, Information, Communication and Bioinformatics (AEEICB16) (pp. 01–04).Google Scholar
- 4.Bian, L., & Holtzman, H. (2011). Online friend recommendation through personality matching and collaborative filtering. In Proceedings of the 5th International Conference on Mobile Ubiquitous Compute, Systems, Services and Technologies (pp. 230–235).Google Scholar
- 5.Amazon. (2014). [Online]. Available: http://www.amazon.com/
- 6.Netflix. (2014). [Online]. Available: https://signup.netflix.com/
- 7.Kwon, J., & Kim, S. (2010). Friend recommendation method using physical and social context. International Journal of Computer Science and Network Security, 10(11), 116–120.Google Scholar
- 11.Raghuwanshi, R., & Prajapati, G. L. (2017). An approach for friend recommendation based on selected attributes. In Proceedings of the World Congress on Engineering 2017, Vol. II WCE 2017, July 5–7, 2017, London, UK.Google Scholar
- 13.Farikha, M., Mhiri, M., & Gargouri, F. An user interest ontology based on trusted friend preferences for personalized recommendation. In EMCIS 2017, LNBIP 299 (pp. 54–67). Cham: Springer.Google Scholar
- 14.Fei, Y., Che, N., Li, Z., Li, K., & Jiang, S. Friend recommendation considering preference coverage in location-based social networks. In PAKDD 2017, Part II, LNAI 10235 (pp. 91–105). Cham: Springer.Google Scholar
- 15.Zhang, Z., Zhao, X., & Wang, G. (2017). FE-ELM: A new friend recommendation model with extreme learning machine. New York: Springer.Google Scholar
- 16.Zhang, Z., Liu, Y., Ding, W., & Huang, W. W. (2015). A friend recommendation system using users’ information of total attributes. In ICDS 2015, LNCS 9208 (pp. 34–41). Cham: Springer.Google Scholar
- 18.Alabady, S. A., AI-Turjman, F., & Din, S. (2018). A novel security model for cooperative virtual networks in the IoT era. Springer International Journal of Parallel Programming, 1–16.Google Scholar
- 19.Nguyen, T. L. T., & Cao, T. H. (2014). Multi-group-based user perceptions for friend recommendation in social networks. In PAKDD 2014, LNAI 8643 (pp. 525–534). Cham: Springer.Google Scholar