Machine Learning approaches in IoT scenarios

It is foreseen that by 2020 the total number of Internet-connected devices being used will be between 25 and 50 billion. As technologies become more mature, the number of connected devices will keep increasing and the consequent amount of data published will keep overwhelming our computing systems. On the other hand, development of innovative hardware, software and communication technologies fostered the emergence of Internet connected sensor devices which observe the physical world and provide data measurements.

This Internet of Things (IoT), thus, keeps on enriching and providing interaction between the cyber and the physical world.

The increased volume of big data produced within the IoT requires intelligent processing and analysis of this data to support smart and scalable IoT applications. Accordingly, machine learning represents an effective tool to deal with the challenges posed by IoT scenarios. Different machine learning techniques and approaches can be introduced to make the network more intelligent and extract relevant information from the big data.

Keeping in mind the need for technological advancements in different enabling domains related to big data processing and filtering in IoT, this special issue provides a platform to the research, academia and industrial technocrats to present their ideas and solutions from various perspectives related to use of machine learning in the challenging IoT scenarios. This special issue will be devoted to both theoretical and practical evaluations related to the design, analysis and implementation of machine learning techniques for IoT. Some of the relevant topics include, but are not limited to the following:

• Machine learning/deep learning techniques for smart systems (smart buildings, smart cities, smart transportation, smart healthcare)
• Supervised, Unsupervised and Reinforcement learning for IoT, drones, WSN networks
• Machine learning/deep learning applied to IoT Applications
• Reasoning/learning and techniques applied IoT Data Management

• Machine learning/deep learning for IoT protocol design and optimization
• Machine learning for energy efficiency in IoT systems
• Self-Learning and adaptive networking protocols and algorithms
• Machine learning in sliced network control & management
• Experimental evaluation of learning systems

Guest Editors:

Gaia Maselli
Sapienza University of Rome, Italy
Email: maselli@di.uniroma1.it

Laura Galluccio
University of Catania, Italy
Email: laura.galluccio@unict.it

Imen Grida Ben Yahia
Orange Labs Networks, France.
Email: imen.gridabenyahia@orange.com

Noura Limam
University of Waterloo
Email: noura.limam@uwaterloo.ca

The schedule for the paper submission is:

Manuscript Submission Deadline: 1 Dec, 2019
Initial Decision: March , 2020
Revised Manuscript Due: May, 2020
Decision Notification: June 2020
Final Manuscript Due: July, 2020
Estimated Publication: As per the journal policy

Submission Guidelines

Please visit https://www.evise.com/profile/#/COMCOM/login to submit your manuscript. To ensure that all manuscripts are correctly identified for inclusion into the special issue, please select “VSI: ML for IoT” when you reach the Article Type step in the submission process. For further information, please contact the guest editors.