(Self)-Sensing Systems and Diagnostics of Complex (Technology) Environment

Dear Colleagues,

We are currently running a Special Issue titled "(Self)-Sensing Systems and Diagnostics of Complex (Technology) Environment", on the open access journal Sensors (IF 4-35, ISSN 1424-8220) belonging to the section Intelligent Sensors. The submission deadline is 29 December 2023, and authors may submit papers immediately or at any time until the deadline, as papers will be published on an ongoing basis.

The main aim of this special issue is to disseminate research focusing on intelligent sensor concepts and explainable AI. Making AI results understandable is one possible way to turn a black box into a comprehensible methodology, e.g., extracting a decision tree from a neural network (NN), using intelligent sensing. Stakeholders are coming from various application areas and use enabling technologies, e.g., cognitive computing platforms, emerging technologies related to artificial intelligence, machine learning, as well as big data processing and analytics, advanced data visualization, and interaction in augmented/virtual reality and immersive environments. Intelligent sensors provide data in standardized quality in a scope and format tailored to user’ expectations. Different users require various formats and ways of explanations depending on the context. Therefore, stakeholders should provide an appropriate validation and verification assessment (V&VA) based on quality criteria and metrics, e.g., usability is assessed via survey evaluation based on a user experience scale; other quality criteria such as accuracy, completeness and reliability and their metrics are also important.  

Intelligent sensors are monitoring NN data processing using machine and deep learning enhancement. They record changes in network weights during training to improve the result quality. Using AI-technologies, a collaborative, fault-tolerant, and adaptive sensing middleware provides data acquisition with quality-of-service requirements.

Another typical example from smart manufacturing and inspection concerns data--driven based classification via graph based soft-sensing neural networks (GraSSNet): industrial time-series data collected by soft sensors are mostly nonlinear, nonstationary, imbalanced, and noisy and require soft-sensing machine learning models. Data analytics helps to detect temporal dependencies or inter-series correlations, without ignoring the correlations in time-series multiply labeled instances. In consequence, combined with AI methods, NN or deep learning non-intelligent sensors can become intelligent.

Performance and accuracy of AI/machine learning as preprocessing method together with micro-electro-mechanical-system (MEMS) technology, i.e. high-precision inertial sensors were recently examined in a special issue “Artificial intelligence in sensors” running 2022 in MDPI micro machines. Using MEMS may serve a wide variety of industry applications, but comes with some problems: there are cost impacts of storing, processing and transmitting AI data. The reliability of AI-MEMS describes how the sensor construct maintains its level of quality over time, experiencing various loading conditions.

In view of the wide and challenging variety of topics, we invite investigators to contribute both original research and review articles, covering the research and development in the following areas—and this list is by no means exhaustive.

• Adaptive sensing middleware;
• Advanced motion sensing;
• AI-enabled sensing;
• Deep sensing with AI;
• Graph based soft-sensing neural networks;
• High-frequency sensing and AI services/technologies;
• Intelligent crowd-sensing;
• ML-enabled smart sensor systems;
• (Non) intelligent sensory augmentation;
• Quality criteria and metrics of sensory systems;
• Self-monitoring/sensing for self-diagnostics;
• Sensory extension;
• Sensory substitution;
• Smart depth sensing.

Prof. Dr. Wolfram Luther
Prof. Dr. Gregor Schiele
Dr. Ashot N. Harutyunyan
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 100 words) can be sent to the Editorial Office for announcement on this website.

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.

• adaptive sensing
• advanced motion sensing
• AI-enabled sensing
• deep sensing
• graph based soft-sensing neural networks
• high-frequency sensing
• intelligent crowd-sensing
• (non) intelligent sensory augmentation
• self diagnostics
• self-monitoring/sensing
• sensory extension
• sensory substitution
• smart sensor systems
• verification and validation assessment