Sensors and Machine-Learning Based Signal Processing
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Intelligent Sensors".
Deadline for manuscript submissions: 1 June 2024 | Viewed by 305
Special Issue Editors
Interests: signal processing; time-frequency signal analysis; information theory; coding; image and video processing
Special Issues, Collections and Topics in MDPI journals
Interests: big data; stream processing; machine learning; time series analysis; data warehouses
Special Issues, Collections and Topics in MDPI journals
Interests: heart arrhythmia; electrocardiograph; convolutional neural network; defects; infrared photography; eddy currents; laguerre functions; orthonormal basis; pole
Special Issue Information
Dear Colleagues,
Combined sensors, signal processing, and machine learning can lead to robust solutions for automating decision-making processes in various fields. Traditional digital signal processing (DSP) involves various mathematical operations and algorithms in order to process, filter, modify, and analyze digital signals. It has widespread applications in various fields, such as telecommunications, audio, image and video processing, medical imaging, radar systems, control systems, and many more. Machine learning (ML) has recently significantly impacted DSP, revolutionizing many traditional approaches and creating new possibilities. A key prerequisite for ML implementation is harnessing data from sensors which collect the raw data necessary to analyze and extract meaningful information. By integrating sensors with ML techniques, we can create intelligent systems that can adapt, improve, and make accurate predictions or decisions based on real-time data. The field is dynamic and continually evolving, with new techniques and algorithms being developed to address various signal-related challenges. Some of the ML applications to DSP that are of particular interest to us in this Special Issue include:
- Classification: automatic ML-based classification or categorization of data into predefined classes or categories.
- Signal denoising and enhancement: ML for reconstructing the desired signal from noisy data and improving signal quality.
- Signal reconstruction and synthesis: ML to reconstruct missing or incomplete signal data.
- Time-series prediction and forecasting: ML for nonstationary time-series analysis, allowing for accurate predictions and forecasts.
- Adaptive filtering: ML for adaptive data-driven filtering and parameter optimization for noise cancellation, equalization, echo cancellation, or beamforming, among others.
- Feature extraction: ML for extracting relevant features from complex raw data, reducing the need for manual feature engineering.
- Optimization and parameter tuning: ML to optimize other signal processing algorithms and tuning of parameters.
- Model-driven ML: hybrid learning approaches, such as deep unfolding, that fuse the discipline of ML with model-based signal processing in order to maintain both efficiency and interpretability.
- Sensor fusion: ML with the integration of data from multiple sensors or modalities.
Dr. Jonatan Lerga
Dr. Eftim Zdravevski
Dr. Péter Kovács
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.
Keywords
- artificial intelligence
- machine learning
- deep learning
- model-driven deep learning signal processing
- classification
- signal enhancement
- signal reconstruction
- prediction
- forecasting
- adaptive filtering
- feature extraction
- sensor fusion
