Application of Deep Neural Network in Electrical and Electronic Engineering

Dear Colleagues,

The widespread use of Deep Neural Networks (DNNs) has revolutionized various domains by providing powerful tools for pattern recognition, data analysis, and predictive modeling. Indeed, in the field of Electrical and Electronic Engineering, DNNs offer transformative potential across a wide spectrum of applications. For example, in signal processing applications, DNNs are employed in noise reduction for audio signals, image enhancement in medical imaging, and even real-time speech recognition systems, thanks to their capability to handle non-linear and high-dimensional data, which makes them particularly effective in these applications. 

Control systems and robotics also benefit greatly from the integration of DNNs. Traditional control algorithms often require the precise mathematical modeling of the system, which can be challenging for complex or dynamic environments. Through reinforcement learning, DNNs can learn control policies directly from data, providing more robust and adaptive control solutions. In robotics, DNNs enhance vision-based navigation, object recognition, and motion planning capabilities, enabling more intelligent and autonomous robotic systems. 

DNNs have also proven useful in the design and optimization of electronic circuits. They assist in automating the design process, predicting the performances of circuit components, and optimizing design parameters to meet specific requirements. DNNs can model the behavior of electronic devices under various conditions, leading to better design choices and reducing the time and cost associated with prototyping and testing. 

Another, no less important area in which DNNs have found great development is computer vision. Indeed, in this field, the development and diffusion of DNNs have made it possible to overcome obstacles that have prevented the improvement of these techniques for years. In this field, therefore, methodologies such as object detection and segmentation are being used in numerous other fields, such as automotive and industry 4.0.

A final area often overlooked by researchers working with DNNs is Electronic Measurements. In this field, efforts are being made to employ DNNs as measurement tools. This new approach necessarily requires that the uncertainty of the measurements produced by these instruments be evaluated to clearly show the quality of these measurements. It is necessary, in this regard, to improve the robustness of DNNs, as they are often used in mission-critical applications. These will be mandatory in the European Union in the coming years as part of the Artificial Intelligence Act, which requires DNN-based applications and methodologies to be accompanied by a “datasheet” with their metrological characteristics.

Recommended topics include, but are not limited to, the application of DNNs in the following Electrical and Electronic Engineering areas:

• Metrology:
  • Aleatoric uncertainty assessment;
  • Epistemic uncertainty assessment;
  • Calibration;
  • Robustness evaluation.
• Computer vision for automotive and industry 4.0.
• Control systems and robotics.
• Circuit design and optimization.
• Power system optimization.
• Microelectronics and nanoelectronics devices modeling and improvement.
• Novel signal processing techniques.
• Novel techniques for telecommunications.
• Applications and novelties in optics and photonics.
• Novel methodologies for explainability.

Other topics are welcome as long as they fall within the applied case studies of the Electrical and Electronic Engineering area. 

Original work highlighting the latest research and technical development is encouraged, but review papers and comparative studies are also welcome.

Dr. Vincenzo Gallo
Prof. Dr. Piotr A. Kowalski
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. Applied Sciences 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 2400 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.

• deep neural networks
• electronic measurements
• computer vision
• circuit design
• microelectronics
• nanoelectronics
• explainability
• signal processing
• control systems and robotics