Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.1
2.8
Journals
Future Internet
Special Issues
Deep Neural Networks on Reconfigurable Embedded Systems
share announcement

Deep Neural Networks on Reconfigurable Embedded Systems

A special issue of Future Internet (ISSN 1999-5903). This special issue belongs to the section "Big Data and Augmented Intelligence".

Deadline for manuscript submissions: closed (20 June 2022) | Viewed by 12135

Special Issue Editor

Dr. Mário Véstias

E-Mail Website
Guest Editor
INESC-ID/ISEL/IPL, Portugal
Interests: computer architecture; digital systems design; reconfigurable computing; embedded computing; deep learning; deep neural networks
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Smart systems are a topic of intensive research due to its many contributions which improve the quality of human life in healthcare, security and safety, home-living, and many others. Recently, deep neural networks (DNN) have boosted the accuracy and quality of these applications, improving the results of previous machine learning algorithms. DNN are computationally intensive, so cloud computing has been the preferred platform. However, many smart user-centered applications have latency, privacy, and energy constraints not compatible with cloud computing. So, new high-performance embedded systems are needed to run deep neural networks on end devices. These systems must be performance and energy-efficient, and flexible enough to adapt to the fast evolution of DNN. Reconfigurable computing fulfills these requirements by allowing the computing architecture to be tailored for each particular model with high performance and low energy.

This Special Issue aims to collect recent innovations to deploy DNNs on embedded systems with reconfigurable devices. Potential topics include, but are not limited to:

  • DNN for embedded systems
  • Architectures to run DNN on embedded systems
  • FPGA accelerators for DNN on end devices
  • Hardware-oriented optimizations of DNNs on FPGA for embedded systems
  • Coarse-grained reconfigurable architectures for embedded deep learning
  • Design methodologies for DNN on embedded reconfigurable devices
  • Design of DNN for IoT devices with reconfigurable computing
  • Reconfigurable embedded devices for DNN applied to health, smart-home, etc.
  • Embedded DNN for industrial IoT
  • DNN for mobile embedded systems and robotics
  • Smart wireless sensor networks with DNN
  • Reconfigurable embedded systems for smart-city architectures

Dr. Mário Véstias
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. 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.

Keywords

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

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

17 pages, 1614 KiB  
Article
Smart Embedded System for Skin Cancer Classification
by Pedro F. Durães and Mário P. Véstias
Future Internet 2023, 15(2), 52; https://doi.org/10.3390/fi15020052 - 29 Jan 2023
Cited by 6 | Viewed by 2230
Abstract
The very good results achieved with recent algorithms for image classification based on deep learning have enabled new applications in many domains. The medical field is one that can greatly benefit from these algorithms in order to help the medical professional elaborate on [...] Read more.
The very good results achieved with recent algorithms for image classification based on deep learning have enabled new applications in many domains. The medical field is one that can greatly benefit from these algorithms in order to help the medical professional elaborate on his/her diagnostic. In particular, portable devices for medical image classification are useful in scenarios where a full analysis system is not an option or is difficult to obtain. Algorithms based on deep learning models are computationally demanding; therefore, it is difficult to run them in low-cost devices with a low energy consumption and high efficiency. In this paper, a low-cost system is proposed to classify skin cancer images. Two approaches were followed to achieve a fast and accurate system. At the algorithmic level, a cascade inference technique was considered, where two models were used for inference. At the architectural level, the deep learning processing unit from Vitis-AI was considered in order to design very efficient accelerators in FPGA. The dual model was trained and implemented for skin cancer detection in a ZYNQ UltraScale+ MPSoC ZCU104 evaluation kit with a ZU7EV device. The core was integrated in a full system-on-chip solution and tested with the HAM10000 dataset. It achieves a performance of 13.5 FPS with an accuracy of 87%, with only 33k LUTs, 80 DSPs, 70 BRAMs and 1 URAM. Full article
(This article belongs to the Special Issue Deep Neural Networks on Reconfigurable Embedded Systems)
►▼ Show Figures

Figure 1

12 pages, 2773 KiB  
Article
Real-Time Nanoscopic Rider Safety System for Smart and Green Mobility Based upon Varied Infrastructure Parameters
by Faheem Ahmed Malik, Laurent Dala and Krishna Busawon
Future Internet 2022, 14(1), 9; https://doi.org/10.3390/fi14010009 - 25 Dec 2021
Viewed by 3116
Abstract
To create a safe bicycle infrastructure system, this article develops an intelligent embedded learning system using a combination of deep neural networks. The learning system is used as a case study in the Northumbria region in England’s northeast. It is made up of [...] Read more.
To create a safe bicycle infrastructure system, this article develops an intelligent embedded learning system using a combination of deep neural networks. The learning system is used as a case study in the Northumbria region in England’s northeast. It is made up of three components: (a) input data unit, (b) knowledge processing unit, and (c) output unit. It is demonstrated that various infrastructure characteristics influence bikers’ safe interactions, which is used to estimate the riskiest age and gender rider groups. Two accurate prediction models are built, with a male accuracy of 88 per cent and a female accuracy of 95 per cent. The findings concluded that different infrastructures pose varying levels of risk to users of different ages and genders. Certain aspects of the infrastructure are hazardous to all bikers. However, the cyclist’s characteristics determine the level of risk that any infrastructure feature presents. Following validation, the built learning system is interoperable under various scenarios, including current heterogeneous and future semi-autonomous and autonomous transportation systems. The results contribute towards understanding the risk variation of various infrastructure types. The study’s findings will help to improve safety and lead to the construction of a sustainable integrated cycling transportation system. Full article
(This article belongs to the Special Issue Deep Neural Networks on Reconfigurable Embedded Systems)
►▼ Show Figures

Figure 1

20 pages, 1339 KiB  
Article
Configurable Hardware Core for IoT Object Detection
by Pedro R. Miranda, Daniel Pestana, João D. Lopes, Rui Policarpo Duarte, Mário P. Véstias, Horácio C. Neto and José T. de Sousa
Future Internet 2021, 13(11), 280; https://doi.org/10.3390/fi13110280 - 30 Oct 2021
Cited by 6 | Viewed by 2871
Abstract
Object detection is an important task for many applications, like transportation, security, and medical applications. Many of these applications are needed on edge devices to make local decisions. Therefore, it is necessary to provide low-cost, fast solutions for object detection. This work proposes [...] Read more.
Object detection is an important task for many applications, like transportation, security, and medical applications. Many of these applications are needed on edge devices to make local decisions. Therefore, it is necessary to provide low-cost, fast solutions for object detection. This work proposes a configurable hardware core on a field-programmable gate array (FPGA) for object detection. The configurability of the core allows its deployment on target devices with diverse hardware resources. The object detection accelerator is based on YOLO, for its good accuracy at moderate computational complexity. The solution was applied to the design of a core to accelerate the Tiny-YOLOv3, based on a CNN developed for constrained environments. However, it can be applied to other YOLO versions. The core was integrated into a full system-on-chip solution and tested with the COCO dataset. It achieved a performance from 7 to 14 FPS in a low-cost ZYNQ7020 FPGA, depending on the quantization, with an accuracy reduction from 2.1 to 1.4 points of mAP50. Full article
(This article belongs to the Special Issue Deep Neural Networks on Reconfigurable Embedded Systems)
►▼ Show Figures

Figure 1

18 pages, 3081 KiB  
Article
Improving Human Activity Monitoring by Imputation of Missing Sensory Data: Experimental Study
by Ivan Miguel Pires, Faisal Hussain, Nuno M. Garcia and Eftim Zdravevski
Future Internet 2020, 12(9), 155; https://doi.org/10.3390/fi12090155 - 17 Sep 2020
Cited by 21 | Viewed by 2875
Abstract
The automatic recognition of human activities with sensors available in off-the-shelf mobile devices has been the subject of different research studies in recent years. It may be useful for the monitoring of elderly people to present warning situations, monitoring the activity of sports [...] Read more.
The automatic recognition of human activities with sensors available in off-the-shelf mobile devices has been the subject of different research studies in recent years. It may be useful for the monitoring of elderly people to present warning situations, monitoring the activity of sports people, and other possibilities. However, the acquisition of the data from different sensors may fail for different reasons, and the human activities are recognized with better accuracy if the different datasets are fulfilled. This paper focused on two stages of a system for the recognition of human activities: data imputation and data classification. Regarding the data imputation, a methodology for extrapolating the missing samples of a dataset to better recognize the human activities was proposed. The K-Nearest Neighbors (KNN) imputation technique was used to extrapolate the missing samples in dataset captures. Regarding the data classification, the accuracy of the previously implemented method, i.e., Deep Neural Networks (DNN) with normalized and non-normalized data, was improved in relation to the previous results without data imputation. Full article
(This article belongs to the Special Issue Deep Neural Networks on Reconfigurable Embedded Systems)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop