Computational Intelligence-Based Sensors

Dear Colleagues,

Frequently, smart sensors operate in a well-defined hierarchical structure. Sensor intelligence in the lower layer improves selectivity, suppressing the influence of undesired variables. Intelligence in the middle layer generates intermediate output by combining the outputs of the lower layer. Intermediate outputs are sent to the upper layer intelligence, which recognizes the situation. The lower layer uses to be implemented in low-capability microcontrollers, often with energy constraints, and hence it is the higher layer where computationally heavy tasks use to take place. There is a compromise between the amount of information that is passed to the higher layers and the amount of processing at the lowest levels. Cooperative processing, data-driven feature extraction, model-based and indirect measurements, among other techniques, are leveraged to balance computational power, energy consumption and information flow at the lowest layer. Data fusion, parameter tuning and model-based synthesis of variables are performed at the middle layer. Intelligent data analysis and certain data-driven decision systems are deployed at the higher layer. In this respect, Computational Intelligence (CI) and Soft Computing-based sensors build on fuzzy logic, artificial neural networks, evolutionary computing, learning theory and probabilistic methods to solve the mentioned tasks at each level of the architecture. The application of CI to sensor systems is a hot topic, as shown by the following (non-exhaustive) list of problems, that is comprised of different applications of CI to sensor systems reported during the first half of 2018:

• Computational efficiency (power control)
• Cooperative processing (swarm intelligence, fog computing, etc.) in sensor networks
• Cyber Physical Systems (CPS) and Internet of Things
• Data analytics and cloud computing
• Data-driven feature extraction (time series, 2D and 3D imaging)
• Human activity recognition (wearable sensors)
• Hyper-parameter learning (learning and tuning of sensor parameters, automatic calibration)
• Indirect measurements (soft sensors)
• Information fusion in sensor networks
• Management of uncertain, incomplete and/or noisy data
• Privacy-preserving data aggregation
• Sensitivity and robustness analysis
• Social sensing (humans as “sensors” to report observations about the physical world)

The Special Issue will publish original research, reviews and applications in the field of Computational Intelligence techniques (fuzzy logic, artificial neural networks, evolutionary computing, learning theory and probabilistic methods) applied to sensor systems.

Prof. Dr. Luciano Sánchez
Dr. David Anseán
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.