期刊名称：International Journal of Computer Network and Information Security
印刷版ISSN：2074-9090
电子版ISSN：2231-4946
出版年度：2021
卷号：13
期号：3
页码：1-14
DOI：10.5815/ijcnis.2021.03.01
出版社：MECS Publisher
摘要：Increasing the implication of IoT data puts a focus on extracting the knowledge from sensors’ raw data. The management of sensors’ data is inefficient with current solutions, as studies have generally focused on either providing cloud-based IoT solutions or inefficient predefined rules. Cloud-based IoT solutions have problems with latency, availability, security and privacy, and power consumption. Therefore, Providing IoT gateways with relevant intelligence is essential for gaining knowledge from raw data to make the decision of whether to actuate or offload tasks to the cloud. This work proposes a model that provides an IoT gateway with the intelligence needed to extract the knowledge from sensors’ data in order to make the decision locally without needing to send all raw data to the cloud over the Internet. This speeds up decisions and actions for real-time data and overcomes the limitations of cloud-based IoT solutions. When the gateway is unable to process a task locally, the data and task are offloaded to the cloud.
关键词：Internet of Things;Distributed Intelligence;IoT Gateway;Machine Learning;and Neural Networks
