Deep Learning-Based Decision-Making with WoT for Smart City Development
S P Vimal, V. Jeyabalaraja, P. Subbulakshmi, A. Suresh, M. Kaliappan, S. Koteeswaran · 2020
The advancements in modern wireless communications enhances the internet access to a connected network, the Internet of Things (IOT), which in turn explores the data from IOT with a connectivity service and applications through Web of Things (WoT). The WoT has occupied a major role in smart city development with resource sharing and energy management. The challenges in handling the huge volume of data, the incompatibility of platforms and proper supportive decision-making enhance the smart city integration with WoT. The huge volume of data can be handled efficiently with the support of Machine Learning (ML) algorithms that enhances the smart building intelligence and application [ 23 ][24]. Many researchers are attracted towards handling the big data from various connected devices and smart energy conservation with the allocated resources. Smart city development has data integrated from various sources to enhance the operational feasibility in smart home, healthcare assistance, smart transportation, environmental conditions monitoring, logistics and supply chain management and secure surveillance systems. Apart from various smart infrastructure smart energy management is a good option to develop a smart city. The data collected from the sensor network for planning the smart city development needs a structural assembling of data that has been done with a deep learning algorithm. The deep learning algorithm gives the decision-makers a pattern for the big data stream. Deep learning supports the representational state transfer (RESTful) Web of Things (WoT) to enhance network performance and energy management. This chapter proposes the integration of WoT in smart buildings for energy management using a deep learning dashboard for the decision-making from sensor data.