Virtual Sensors with Neurocomputing and Machine Learning Techniques

in Special Issue   Posted on December 31, 2020 

Information for the Special Issue

Submission Deadline: Tue 31 Aug 2021
Journal Impact Factor : 3.275
Journal Name : Sensors
Journal Publisher:
Website for the Special Issue:
Journal & Submission Website:

Special Issue Call for Papers:

Dear Colleagues,

The idea of a virtual sensor is to extract information or parameter values that cannot be measured directly, or at least would require very costly sensors, by only using and appropriately processing the available information. Virtual sensing does therefore inherently help overcoming/alleviating a series of limitations of “physical sensors” through context related abstraction, modelling and either mathematical or machine learning related processing. Those limitations are cost, energy consumption, special accessibility of some part of the physical context, time-related latency of physical sensors, low resolution, low accuracy, etc.

Virtual sensors also have the potential of significantly enhancing accuracy. Indeed, virtual sensors takes into account all data that real sensors measure (e.g., temperature, pression, position, etc.). A virtual sensor now takes all available data from the real/physical sensors and calculates the exact parameters.

The complexity of virtual models significantly increases with the complexity of the process that they describe, and thus new methods for their development are constantly evaluated. Among many others, data-driven techniques and machine learning offer promising results, creating, for example, deep neural networks that are capable to map complex input-output relations.

Selected keywords (not limited to):

Theoretical foundations of virtual sensors
State-of-the-art review of virtual sensors, related challenges and technical solutions
Sensor clouds
Autonomous virtual actors in relation to virtual sensors
Virtual sensors for diagnosis and fault detection
Neurocomputing technologies for virtual sensors
Machine learning techniques for virtual sensors
Bayesian models for virtual sensors
Creating virtual sensors using learning based super resolution and data fusion
Stacked auto-encoder techniques for data-driven virtual sensing of relevant variables
Virtual sensors for predicting fuel consumption (for automobiles or aircrafts)
Virtual sensors in intelligent transportation systems
Virtual sensors in body sensor networks
Virtual sensors in video surveillance systems
Virtual sensors for semiconductor manufacturing
Mobile virtual sensors
Virtual sensing for autonomous vehicles
Sensor aggregation and virtual sensors
Virtual sensors for service oriented virtual environments
Virtual sensors to support model calibration
Cost-benefit analysis of virtual sensors
Forecasting product quality in industrial processes with virtual sensors

Prof. Dr. Kyandoghere Kyamakya
Dr. Fadi Al-Machot
Dr. Ahmad Haj Mosa
Dr. Jean Chamberlain Chedjou
Prof. Dr. Zhong Li
Prof. Dr. Antoine Bagula
Guest Editors

Other Special Issues on this journal

Closed Special Issues