Abstract
The traditional Internet of Things (IoT) paradigm has evolved towards intelligent IoT applications which exploit knowledge produced by IoT devices using artificial intelligence techniques. Knowledge sharing between IoT devices is a challenging issue in this trend. In this paper, we propose a Knowledge of Things (KoT) framework which enables sharing self-taught knowledge between IoT devices which require similar or identical knowledge without help from the cloud. The proposed KoT framework allows an IoT device to effectively produce, cumulate, and share its self-taught knowledge with other devices at the edge in the vicinity. This framework can alleviate behavioral repetition in users and computational redundancy in systems in intelligent IoT applications. To demonstrate the feasibility of the proposed concept, we examine a smart home case study and build a prototype of the KoT framework-based smart home system. Experimental results show that the proposed KoT framework reduces the response time to use intelligent IoT devices from a user’s perspective and the power consumption for compuation from a system’s perspective.
Highlights
Recent advances in the Internet of Things (IoT) have changed the lifestyle of people in various environments in which many of electronic devices around us, such as smart appliances, mobile devices, sensors, and wearables, are connected to the network
The smart mirror contributes its face Self-taught knowledge (STK) element into the Knowledge of Things (KoT) repository of the home gateway, and the smart doorbell catches the face STK element stored in the KoT repository
We propose a Knowledge of Things (KoT) framework which enables sharing self-taught knowledge between IoT devices which require similar or identical knowledge at the edge
Summary
Recent advances in the Internet of Things (IoT) have changed the lifestyle of people in various environments in which many of electronic devices around us, such as smart appliances, mobile devices, sensors, and wearables, are connected to the network. Since a wide range of practical applications has absorbed enormous amounts of sensors and devices, the number of IoT devices connected to the Internet has increased more rapidly. More than 5 million new IoT devices are getting connected to the Internet every day and the number of connected devices will reach more than 20 billion by 2020 [1]. To provide intelligent services to customers, IoT devices need informative models trained from data. IoT devices will be able to produce self-taught knowledge by training models locally from their acquisition of sensing data in order to perform real-time inference
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
