Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
2.9
Journals
Electronics
Special Issues
Advances in Embedded Deep Learning Systems
share announcement

Advances in Embedded Deep Learning Systems

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (20 April 2024) | Viewed by 4816

Special Issue Editors

Dr. Irida Shallari

E-Mail Website
Guest Editor
STC Research Centre, Mid-Sweden University, Holmgatan 10, 85170 Sundsvall, Sweden
Interests: embedded deep learning systems; smart camera; intelligence partitioning
Prof. Dr. Mattias O'Nils

E-Mail Website
Guest Editor
STC Research Centre, Mid-Sweden University, Holmgatan 10, 85170 Sundsvall, Sweden
Interests: anomaly detection; 3D object detection; smart camera; deep learning systems; intelligence partitioning

Special Issue Information

Dear Colleagues,

The rapid evolution of Artificial Intelligence and Deep Learning-based methods has become the driving factor behind the current technological evolution. Novel models are continuously introduced and refined to provide high accuracy, while enabling an ever-growing range of applications. From an end-user perspective, the need is to have these sophisticated networks on low-cost and small form factor off-the-shelf devices to enable their use in a variety of scenarios, from industrial IoT to consumer electronics. At a time when DL algorithms are changing rapidly, the need is to develop generalized optimization methods that investigate how we can compress these computationally demanding DL algorithms to fit in embedded devices both from computational and energy perspectives. By placing these systems in the context of cyber-physical systems we can rely on approaches such as offloading strategies and tailored accelerators to satisfy constraints imposed by embedded platforms, while consideration of the inherent effects on privacy and security is also required.

The purpose of this Special Issue is to invite contributors to present their novel achievements on topics of interest that may include, but are not limited to:

  • Edge-based deep learning applications for IoT and Industry 4.0
  • Software-level accelerators for DL models in IoT applications
  • Hardware-level accelerators for DL models in IoT applications
  • Energy efficiency in DL embedded systems
  • DL-driven cyber–physical systems
  • Offloading strategies for efficient and high-performance DL
  • Real-time embedded DL applications
  • Security and privacy in DL-based smart sensor node

Dr. Irida Shallari
Prof. Dr. Mattias O'Nils
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. Electronics 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.

Keywords

  • deep learning
  • edge computing
  • pruning
  • quantization
  • energy efficiency
  • cyber-physical systems
  • Industry 4.0

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

Jump to: Review

0 pages, 17000 KiB  
Article
A Hybrid-Model-Based CNC Machining Trajectory Error Prediction and Compensation Method
by Wuwei He, Lipeng Zhang, Yi Hu, Zheng Zhou, Yusong Qiao and Dong Yu
Electronics 2024, 13(6), 1143; https://doi.org/10.3390/electronics13061143 - 20 Mar 2024
Viewed by 541
Abstract
Intelligent manufacturing is the main direction of Industry 4.0, pointing towards the future development of manufacturing. The core component of intelligent manufacturing is the computer numerical control (CNC) system. Predicting and compensating for machining trajectory errors by controlling the CNC system’s accuracy is [...] Read more.
Intelligent manufacturing is the main direction of Industry 4.0, pointing towards the future development of manufacturing. The core component of intelligent manufacturing is the computer numerical control (CNC) system. Predicting and compensating for machining trajectory errors by controlling the CNC system’s accuracy is of great significance in enhancing the efficiency, quality, and flexibility of intelligent manufacturing. Traditional machining trajectory error prediction and compensation methods make it challenging to consider the uncertainties that occur during the machining process, and they cannot meet the requirements of intelligent manufacturing with respect to the complexity and accuracy of process parameter optimization. In this paper, we propose a hybrid-model-based machining trajectory error prediction and compensation method to address these issues. Firstly, a digital twin framework for the CNC system, based on a hybrid model, was constructed. The machining trajectory error prediction and compensation mechanisms were then analyzed, and an artificial intelligence (AI) algorithm was used to predict the machining trajectory error. This error was then compensated for via the adaptive compensation method. Finally, the feasibility and effectiveness of the method were verified through specific experiments, and a realization case for this digital-twin-driven machining trajectory error prediction and compensation method was provided. Full article
(This article belongs to the Special Issue Advances in Embedded Deep Learning Systems)
►▼ Show Figures

Figure 1

21 pages, 4868 KiB  
Article
Optimizing Long Short-Term Memory Network for Air Pollution Prediction Using a Novel Binary Chimp Optimization Algorithm
by Sahba Baniasadi, Reza Salehi, Sepehr Soltani, Diego Martín, Parmida Pourmand and Ehsan Ghafourian
Electronics 2023, 12(18), 3985; https://doi.org/10.3390/electronics12183985 - 21 Sep 2023
Cited by 1 | Viewed by 1038
Abstract
Elevated levels of fine particulate matter (PM2.5) in the atmosphere present substantial risks to human health and welfare. The accurate assessment of PM2.5 concentrations plays a pivotal role in facilitating prompt responses by pertinent regulatory bodies to mitigate air pollution. [...] Read more.
Elevated levels of fine particulate matter (PM2.5) in the atmosphere present substantial risks to human health and welfare. The accurate assessment of PM2.5 concentrations plays a pivotal role in facilitating prompt responses by pertinent regulatory bodies to mitigate air pollution. Additionally, it furnishes indispensable information for epidemiological studies concentrating on PM2.5 exposure. In recent years, predictive models based on deep learning (DL) have offered promise in improving the accuracy and efficiency of air quality forecasts when compared to other approaches. Long short-term memory (LSTM) networks have proven to be effective in time series forecasting tasks, including air pollution prediction. However, optimizing LSTM models for enhanced accuracy and efficiency remains an ongoing research area. In this paper, we propose a novel approach that integrates the novel binary chimp optimization algorithm (BChOA) with LSTM networks to optimize air pollution prediction models. The proposed BChOA, inspired by the social behavior of chimpanzees, provides a powerful optimization technique to fine-tune the LSTM architecture and optimize its parameters. The evaluation of the results is performed using cross-validation methods such as the coefficient of determination (R2), accuracy, the root mean square error (RMSE), and receiver operating characteristic (ROC) curve. Additionally, the performance of the BChOA-LSTM model is compared against eight DL architectures. Experimental evaluations using real-world air pollution data demonstrate the superior performance of the proposed BChOA-based LSTM model compared to traditional LSTM models and other optimization algorithms. The BChOA-LSTM model achieved the highest accuracy of 96.41% on the validation datasets, making it the most successful approach. The results show that the BChOA-LSTM architecture performs better than the other architectures in terms of the  R2 convergence curve, RMSE, and accuracy. Full article
(This article belongs to the Special Issue Advances in Embedded Deep Learning Systems)
►▼ Show Figures

Figure 1

19 pages, 2279 KiB  
Article
Enhancing QoS with LSTM-Based Prediction for Congestion-Aware Aggregation Scheduling in Edge Federated Learning
by Prohim Tam, Seungwoo Kang, Seyha Ros and Seokhoon Kim
Electronics 2023, 12(17), 3615; https://doi.org/10.3390/electronics12173615 - 27 Aug 2023
Cited by 1 | Viewed by 893
Abstract
The advancement of the sensing capabilities of end devices drives a variety of data-intensive insights, yielding valuable information for modelling intelligent industrial applications. To apply intelligent models in 5G and beyond, edge intelligence integrates edge computing systems and deep learning solutions, which enables [...] Read more.
The advancement of the sensing capabilities of end devices drives a variety of data-intensive insights, yielding valuable information for modelling intelligent industrial applications. To apply intelligent models in 5G and beyond, edge intelligence integrates edge computing systems and deep learning solutions, which enables distributed model training and inference. Edge federated learning (EFL) offers collaborative edge intelligence learning with distributed aggregation capabilities, promoting resource efficiency, participant inclusivity, and privacy preservation. However, the quality of service (QoS) faces challenges due to congestion problems that arise from the diverse models and data in practical architectures. In this paper, we develop a modified long short-term memory (LSTM)-based congestion-aware EFL (MLSTM-CEFL) approach that aims to enhance QoS in the final model convergence between end devices, edge aggregators, and the global server. Given the diversity of service types, MLSTM-CEFL proactively detects the congestion rates, adequately schedules the edge aggregations, and effectively prioritizes high mission-critical serving resources. The proposed system is formulated to handle time series analysis from local/edge model parameter loading, weighing the configuration of resource pooling properties at specific congestion intervals. The MLSTM-CEFL policy orchestrates the establishment of long-term paths for participant-aggregator scheduling and follows the expected QoS metrics after final averaging in multiple industrial application classes. Full article
(This article belongs to the Special Issue Advances in Embedded Deep Learning Systems)
►▼ Show Figures

Figure 1

Review

Jump to: Research

33 pages, 3792 KiB  
Review
Intelligent Materials and Nanomaterials Improving Physical Properties and Control Oriented on Electronic Implementations
by Alessandro Massaro
Electronics 2023, 12(18), 3772; https://doi.org/10.3390/electronics12183772 - 06 Sep 2023
Cited by 4 | Viewed by 1732
Abstract
The review highlights possible research topics matching the experimental physics of matter with advances in electronics to improve the intelligent design and control of innovative smart materials. Specifically, following the European research guidelines of Key Enabling Technologies (KETs), I propose different topics suitable [...] Read more.
The review highlights possible research topics matching the experimental physics of matter with advances in electronics to improve the intelligent design and control of innovative smart materials. Specifically, following the European research guidelines of Key Enabling Technologies (KETs), I propose different topics suitable for project proposals and research, including advances in nanomaterials, nanocomposite materials, nanotechnology, and artificial intelligence (AI), with a focus on electronics implementation. The paper provides a new research framework addressing the study of AI driving electronic systems and design procedures to determine the physical properties of versatile materials and to control dynamically the material’s “self-reaction” when applying external stimuli. The proposed research framework allows one to ideate new circuital solutions to be integrated in intelligent embedded systems formed of materials, algorithms and circuits. The challenge of the review is to bring together different research concepts and topics regarding innovative materials to provide a research direction for possible AI applications. The discussed research topics are classified as Technology Readiness Levels (TRL) 1 and 2. Full article
(This article belongs to the Special Issue Advances in Embedded Deep Learning 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