Low-Power Data Processing on the Edge: Solutions for Artificial Intelligence Hardware Acceleration

Dear Colleagues,

This Special Issue aims to provide a comprehensive overview of the latest advancements and developments in the field of low-power data processing on edge devices, with a particular focus on hardware acceleration techniques for artificial intelligence (AI) and machine learning (ML) applications. Edge AI hardware acceleration is becoming increasingly vital in various fields, including space, industrial automation, automotive, and many more. The technology enables the faster and more efficient processing of data at the edge of the network, thus reducing the need for large amounts of data to be transferred to the cloud for processing. This allows for real-time decision-making in applications such as autonomous vehicles, predictive maintenance, and robotic automation. As the Internet of Things (IoT) continues to grow, edge AI hardware acceleration is becoming an essential component of many systems, enabling them to perform complex tasks with greater speed and accuracy. With the ability to process data at the edge, the technology is enabling new levels of innovation and efficiency in a wide range of industries.

The primary focus of this Special Issue is to present state-of-the-art research and developments related to low-power data processing and hardware acceleration techniques for AI and ML applications on edge devices. The convergence of big data and cognitive computing has resulted in a tremendous increase in the demand for efficient, low-power edge devices that can process and analyze data in real-time. This Issue will emphasize various aspects of edge computing, including energy efficiency, performance optimization, and the development of novel hardware architectures and systems.

The scope of this Special Issue encompasses a wide range of topics related to low-power data processing on the edge, including but not limited to:

• Energy-efficient architectures and systems for AI and ML applications;
• Hardware acceleration techniques for AI and ML on edge devices;
• Techniques for optimizing the performance of AI/ML algorithms in low-power settings;
• Novel memory and storage solutions for edge computing;
• Advanced software‒hardware co-design approaches for edge AI;
• Emerging technologies for low-power AI hardware;
• Security, privacy, and reliability concerns in low-power edge computing;
• Benchmarking and evaluation of low-power AI hardware and systems;
• Real-world applications and case studies of low-power AI on the edge.

The ultimate purpose of this Special Issue is to:

• Foster collaboration and knowledge exchange among researchers and practitioners working on low-power data processing and edge AI;
• Provide a platform for showcasing the latest breakthroughs and innovative solutions in the field;
• Identify and discuss the challenges and opportunities associated with low-power AI hardware acceleration;
• Offer insights and directions for future research and development in this burgeoning area of study.

This Special Issue will usefully supplement the existing literature on low-power data processing and edge AI in several ways; by offering a more comprehensive and up-to-date understanding of the state of the art in the field, this Issue will serve as a valuable resource for researchers, engineers, and practitioners seeking to stay abreast of the latest developments and trends.

Through the inclusion of real-world applications and case studies, this Special Issue will provide practical insights and examples that can inform and inspire future research, development, and deployment of low-power AI solutions on the edge.

By addressing security, privacy, and reliability concerns in low-power edge computing, this Issue will contribute to the ongoing conversation on ensuring the safe, secure, and responsible use of AI and ML technologies in edge devices.

Dr. Pietro Nannipieri
Dr. Marc Reichenbach
Dr. Lucana Santos
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. Big Data and Cognitive Computing 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 1800 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.

• low power
• data processing
• edge devices
• hardware acceleration
• artificial intelligence (AI)
• machine learning (ML)
• energy efficiency
• performance optimization
• hardware architectures
• memory and storage solutions
• software‒hardware co-design
• security
• privacy
• reliability
• benchmarking
• real-world applications
• case studies