Embedded AI

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Circuit and Signal Processing".

Deadline for manuscript submissions: 31 October 2024 | Viewed by 1884

Special Issue Editors


E-Mail Website
Guest Editor
Department of Electrical and Computer Engineering, Oakland University, Rochester, MI 48309, USA
Interests: embedded artificial intelligence; TinyML; high-speed embedded systems; anomaly detection in embedded systems; cyber-physical security; embedded networks; nanoimaging; biosensors

E-Mail Website
Guest Editor
Department of Computer Science, University of Georgia, Athens, GA 30602, USA
Interests: supercomputing; data Science; deep learning (AI); imaging science; other compute-intensive problems

Special Issue Information

Dear Colleagues,

A significant body of work has focused on artificial intelligence in embedded systems with the growth of the Internet of Things for applications in smart devices, security, robotics, and autonomous vehicles. These advancements have called for methods of implementing AI in hardware where compute and memory resources are scarce, parallel and pipelined architectures for AI in ASICs and FPGAs, massively parallel algorithms executed by GPUs, and techniques for taking advantage of powerful embedded cores and AI engines. There have been rapid advancements in generative intelligence, deep learning, federated learning, neural architecture search, meta-learning, transformer networks, and more. These have taken advantage of powerful cloud computing clusters with high-capacity memory and storage to transform the capabilities of AI. However, delivering on the promise of AI in embedded systems to meet the demands of requirements including high speed, high throughput, low power, low cost, and high availability with security through adaptations, architectures, and implementation techniques in a variety of embedded targets is challenging, and thus it is the subject of much research.

This Special Issue aims to present the latest research results and developments in the field of embedded AI. All researchers in this field are invited to submit their original work in research and review formats.

Topics of interest include, but are not limited to:

  • Algorithms for embedded AI;
  • TinyML;
  • Digital hardware for FPGAs or ASICS;
  • Analog circuits for AI;
  • Massively parallel AI for GPUs;
  • AI engines;
  • Reservoir computing for AI.

Dr. Darrin M. Hanna
Dr. Hamid Arabnia
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

  • embedded systems
  • artificial intelligence
  • IoT
  • machine learning
  • intelligent robotics
  • autonomous systems
  • FPGA
  • GPU

Published Papers (2 papers)

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

Research

22 pages, 1587 KiB  
Article
Reinforcement Learning-Based Event-Triggered Active-Battery-Cell-Balancing Control for Electric Vehicle Range Extension
by David Flessner, Jun Chen and Guojiang Xiong
Electronics 2024, 13(5), 990; https://doi.org/10.3390/electronics13050990 - 5 Mar 2024
Viewed by 744
Abstract
Optimal control techniques such as model predictive control (MPC) have been widely studied and successfully applied across a diverse field of applications. However, the large computational requirements for these methods result in a significant challenge for embedded applications. While event-triggered MPC (eMPC) is [...] Read more.
Optimal control techniques such as model predictive control (MPC) have been widely studied and successfully applied across a diverse field of applications. However, the large computational requirements for these methods result in a significant challenge for embedded applications. While event-triggered MPC (eMPC) is one solution that could address this issue by taking advantage of the prediction horizon, one obstacle that arises with this approach is that the event-trigger policy is complex to design to fulfill both throughput and control performance requirements. To address this challenge, this paper proposes to design the event trigger by training a deep Q-network reinforcement learning agent (RLeMPC) to learn the optimal event-trigger policy. This control technique was applied to an active-cell-balancing controller for the range extension of an electric vehicle battery. Simulation results with MPC, eMPC, and RLeMPC control policies are presented along with a discussion of the challenges of implementing RLeMPC. Full article
(This article belongs to the Special Issue Embedded AI)
Show Figures

Figure 1

14 pages, 1073 KiB  
Article
Hardware–Software Co-Design of an Audio Feature Extraction Pipeline for Machine Learning Applications
by Jure Vreča, Ratko Pilipović and Anton Biasizzo
Electronics 2024, 13(5), 875; https://doi.org/10.3390/electronics13050875 - 24 Feb 2024
Viewed by 715
Abstract
Keyword spotting is an important part of modern speech recognition pipelines. Typical contemporary keyword-spotting systems are based on Mel-Frequency Cepstral Coefficient (MFCC) audio features, which are relatively complex to compute. Considering the always-on nature of many keyword-spotting systems, it is prudent to optimize [...] Read more.
Keyword spotting is an important part of modern speech recognition pipelines. Typical contemporary keyword-spotting systems are based on Mel-Frequency Cepstral Coefficient (MFCC) audio features, which are relatively complex to compute. Considering the always-on nature of many keyword-spotting systems, it is prudent to optimize this part of the detection pipeline. We explore the simplifications of the MFCC audio features and derive a simplified version that can be more easily used in embedded applications. Additionally, we implement a hardware generator that generates an appropriate hardware pipeline for the simplified audio feature extraction. Using Chisel4ml framework, we integrate hardware generators into Python-based Keras framework, which facilitates the training process of the machine learning models using our simplified audio features. Full article
(This article belongs to the Special Issue Embedded AI)
Show Figures

Figure 1

Back to TopTop