Computing Systems for Embedded Deep Learning

A special issue of Future Internet (ISSN 1999-5903). This special issue belongs to the section "Smart System Infrastructure and Applications".

Deadline for manuscript submissions: 20 March 2024 | Viewed by 3995

Special Issue Editors

Department of Electronics, Telecommunications and Computer Engineering, Polytechnic of Lisbon, 1500-310 Lisboa, Portugal
Interests: computer architecture; digital system design; reconfigurable computing; embedded computing; machine learning; deep learning; deep neural networks
Special Issues, Collections and Topics in MDPI journals
Electronic and Telecommunications and Computer Engineering Department (DEETC), the High Institute of Engineering of Lisbon (ISEL), Polytechnical Institute of Lisbon (IPL), 1069-035 Lisbon, Portugal
Interests: computer architecture; computer arithmetic; residue number systems

Special Issue Information

Dear Colleagues,

Smart embedded systems have recently been the focus of intensive research and development due to their significant potential to improve the quality of human life in areas such as healthcare, security and safety, home living, city living and many others. Machine learning algorithms can be used to design intelligent embedded devices. Recently, deep neural networks (DNN), such as CNN, RNN, LSTM, GAN and SNN, have achieved superior performances in accuracy when compared to other machine learning algorithms, but they require more computing and memory resources, as well as energy. However, computing platforms of embedded systems have limited computing power, memory and energy. So, the implementation of DNNs in embedded systems is currently a major topic in the scientific community and requires further innovation in its development and application. This Special Issue aims to collect recent research with a focus on deploying DNNs in embedded computing systems. Potential topics include, but are not limited to:

  • DNN models for embedded systems;
  • Optimization of DNN models for embedded computing;
  • Quantization and sparsification of DNN models;
  • Implementation of DNN in embedded GPUs;
  • Implementation of DNN in low-cost computing platforms;
  • Reconfigurable architectures for DNN in embedded systems;
  • Very low-power embedded platforms for DNNs;
  • Coarse-grained reconfigurable architectures for embedded deep learning;
  • Design methodologies for DNN on embedded systems;
  • Design of DNN for IoT devices;
  • Software tools to help design smart embedded systems;
  • Applications of DNN on health, smart homes, smart cities, security, surveillance, etc.;
  • Smart embedded systems for industrial IoT;
  • Designing DNN for robotics.

Dr. Mário Véstias
Dr. Pedro Miguel Florindo Miguens Matutino
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at 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. Future Internet is an international peer-reviewed open access monthly 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.


  • deep learning
  • deep neural network
  • end devices
  • mobile deep learning
  • smart embedded systems
  • smart devices
  • smart IoT
  • smart wireless systems

Published Papers (1 paper)

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


23 pages, 1090 KiB  
Internet Video Delivery Improved by Super-Resolution with GAN
Future Internet 2022, 14(12), 364; - 06 Dec 2022
Cited by 2 | Viewed by 3077
In recent years, image and video super-resolution have gained attention outside the computer vision community due to the outstanding results produced by applying deep-learning models to solve the super-resolution problem. These models have been used to improve the quality of videos and images. [...] Read more.
In recent years, image and video super-resolution have gained attention outside the computer vision community due to the outstanding results produced by applying deep-learning models to solve the super-resolution problem. These models have been used to improve the quality of videos and images. In the last decade, video-streaming applications have also become popular. Consequently, they have generated traffic with an increasing quantity of data in network infrastructures, which continues to grow, e.g., global video traffic is forecast to increase from 75% in 2017 to 82% in 2022. In this paper, we leverage the power of deep-learning-based super-resolution methods and implement a model for video super-resolution, which we call VSRGAN+. We train our model with a dataset proposed to teach systems for high-level visual comprehension tasks. We also test it on a large-scale JND-based coded video quality dataset containing 220 video clips with four different resolutions. Additionally, we propose a cloud video-delivery framework that uses video super-resolution. According to our findings, the VSRGAN+ model can reconstruct videos without perceptual distinction of the ground truth. Using this model with added compression can decrease the quantity of data delivered to surrogate servers in a cloud video-delivery framework. The traffic decrease reaches 98.42% in total. Full article
(This article belongs to the Special Issue Computing Systems for Embedded Deep Learning)
Show Figures

Figure 1

Back to TopTop