Artificial intelligence-based sensors for next generation IoT applications: a review

Subhas Chandra Mukhopadhyay, Sumarga Kumar Sah Tyagi, Nagender Kumar Suryadevara, Vincenzo Piuri, Fabio Scotti, Sherali Zeadally

Research output: Contribution to journalReview articlepeer-review

95 Citations (Scopus)

Abstract

Sensors play a vital role in our daily lives and are an essential component for Internet of Things (IoT) based systems as they enable the IoT to collect data to take smart and intelligent decisions. Recent advances in IoT systems, applications, and technologies, including industrial Cyber-Physical Systems (CPSs), are being supported by a wide range of different types of sensors based on artificial intelligence (AI). These smart AI-based sensors are typically characterized by onboard intelligence and have the ability to communicate collaboratively or through the Internet. To achieve the high level of automation required in today's smart IoT applications, sensors incorporated into nodes must be efficient, intelligent, context-aware, reliable, accurate, and connected. Such sensors must also be robust, safety- and privacy-aware for users interacting with them. Sensors leveraging advanced AI technologies, new capabilities have recently emerged which have the potential to detect, identify, and avoid performance degradation and discover new patterns. Along with knowledge from complex sensor datasets, they can promote product innovation, improve operation level, and open up novel business models. We review sensors, smart data processing, communication protocol, and artificial intelligence which will enable the deployment of AI-based sensors for next-generation IoT applications.

Original languageEnglish
Pages (from-to)24920-24932
Number of pages13
JournalIEEE Sensors Journal
Volume21
Issue number22
Early online date29 Jan 2021
DOIs
Publication statusPublished - 15 Nov 2021

Fingerprint

Dive into the research topics of 'Artificial intelligence-based sensors for next generation IoT applications: a review'. Together they form a unique fingerprint.

Cite this