Artificial Intelligence and Machine Learning for Intelligent Sensing and Signal Processing in Smart-X Technologies

A special issue of AI (ISSN 2673-2688).

Deadline for manuscript submissions: closed (30 September 2021) | Viewed by 5434

Special Issue Editor


E-Mail Website
Guest Editor
Institute for microelectronics and microsystems (IMM), National Research Council of Italy (CNR), Lecce, Italy
Interests: smart multi-sensor systems; decision support systems; intelligent sensing algorithms; human behavior monitoring; physiological signal monitoring/detection/prediction; abnormal event detection/prediction; kinematic and physiological sensing; ambient-assisted living; active and healthy aging; smart living technologies; radar signal processing; biomedical signal processing; 3D vision systems; computer vision; machine learning; deep learning; pattern recognition; computational intelligence; intelligent sensing; ambient intelligence
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

The pervasive use of sensors, portable or worn by the user and incorporated in the surrounding environment, generates increasingly large and diversified data flows, big sensor data, which are ill suited to be processed using only traditional signal processing techniques. The application of machine learning in the signal and image processing area has proven very useful in addressing this growing complexity. The systematic use of machine learning and artificial intelligence, with particular focus on the emerging areas of autoML (automatic machine learning) and deep learning (deep artificial neural networks), is receiving much attention in industry and academia for modeling, design, and development of smart technological solutions.

In this context, intelligent sensing and advanced signal processing techniques, well suited to treat a large amount of multi-sensor and multi-channel data, generated at a constant rate by the ever-growing number of permanently connected smart devices (according to the Internet of Things paradigm), are the main focus of this Special Issue, aiming at the same time to highlight their great impact in different smart-x sectors, such as smart home, smart building, smart city, smart healthcare, smart transportation, and smart industry, just to name a few.

The purpose of this Special Issue is to reflect the most recent advances, present representative applications, and define future research directions related to the application of AI for intelligent sensing and advanced signal processing in smart-x technology, through machine learning, deep learning, computational intelligence, cognitive computing, and other emerging areas of AI. Prospective authors are invited to submit original and high-quality papers that are related, but not limited, to one or more of the following topics:

  • Machine learning techniques for multi-sensor time series analysis, classification, clustering, and forecasting in smart-x applications;
  • Pattern recognition and predictions using multi-sensor time series data;
  • Multi-sensor fusion strategies and their application in smart-x areas;
  • Synthetic long-term multi-sensor time series simulation and generation;
  • Change point detection in multi-sensor time series data;
  • Intelligent sensing-based decision support system for diagnosis, maintenance planning, and operation scheduling in smart-x applications;
  • Machine learning-based critical event detection, diagnosis, and prediction using multi-sensor time series signals;
  • Long-term multi-sensor time series signal processing.

Dr. Giovanni Diraco
Guest Editor

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. AI is an international peer-reviewed open access quarterly 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 1600 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.

Keywords

  • multi-sensor time series
  • abnormal event detection and prediction
  • anomaly detection and prediction
  • time series classification
  • time series clustering
  • long-term time series forecasting
  • change point detection
  • decision support systems
  • decision-making techniques
  • synthetic multi-sensor time series
  • long-term multi-sensor time series signal processing
  • predictive analytics
  • predictive maintenance
  • hazard detection/prediction
  • machining monitoring
  • structural health monitoring
  • personal health monitoring

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

20 pages, 1785 KiB  
Article
RIANN—A Robust Neural Network Outperforms Attitude Estimation Filters
by Daniel Weber, Clemens Gühmann and Thomas Seel
AI 2021, 2(3), 444-463; https://doi.org/10.3390/ai2030028 - 17 Sep 2021
Cited by 23 | Viewed by 4455
Abstract
Inertial-sensor-based attitude estimation is a crucial technology in various applications, from human motion tracking to autonomous aerial and ground vehicles. Application scenarios differ in characteristics of the performed motion, presence of disturbances, and environmental conditions. Since state-of-the-art attitude estimators do not generalize well [...] Read more.
Inertial-sensor-based attitude estimation is a crucial technology in various applications, from human motion tracking to autonomous aerial and ground vehicles. Application scenarios differ in characteristics of the performed motion, presence of disturbances, and environmental conditions. Since state-of-the-art attitude estimators do not generalize well over these characteristics, their parameters must be tuned for the individual motion characteristics and circumstances. We propose RIANN, a ready-to-use, neural network-based, parameter-free, real-time-capable inertial attitude estimator, which generalizes well across different motion dynamics, environments, and sampling rates, without the need for application-specific adaptations. We gather six publicly available datasets of which we exploit two datasets for the method development and the training, and we use four datasets for evaluation of the trained estimator in three different test scenarios with varying practical relevance. Results show that RIANN outperforms state-of-the-art attitude estimation filters in the sense that it generalizes much better across a variety of motions and conditions in different applications, with different sensor hardware and different sampling frequencies. This is true even if the filters are tuned on each individual test dataset, whereas RIANN was trained on completely separate data and has never seen any of these test datasets. RIANN can be applied directly without adaptations or training and is therefore expected to enable plug-and-play solutions in numerous applications, especially when accuracy is crucial but no ground-truth data is available for tuning or when motion and disturbance characteristics are uncertain. We made RIANN publicly available. Full article
Show Figures

Graphical abstract

Back to TopTop