In the “big data” era, with the fast development of various artificial intelligence (AI) systems for the more disparate tasks, there is an emerging challenge in semiconductor technology that urges researchers to develop a new form of computer that can proactively analyze and learn from data, solve unknown issues using what it has learned, and work with the human brain’s energy efficiency.
Recent AI methods, such as deep learning, have enjoyed considerable success in various machine learning tasks because of their powerful learning ability. They have been broadly applied in many signal processing areas including computer vision, natural language processing, data mining, and time series prediction. To train such AI-based solutions, many days of computation on graphics processing unit (GPU) clusters are commonly required. Given the current boom of deep learning-based applications, these solutions will soon hit a power-performance wall with limits set in the cloud for energy usage and plateauing in the Complementary Metal Oxide Semiconductor (CMOS) scaling. Furthermore, there is growing interest in edge computing and smart cognitive assistants (ICAs), where AI must be available on energy-constrained mobile platforms, autonomous drones, and IoT sensor nodes, thus no longer requiring reliance on cloud-based services but also ensuring user data privacy. This opened to the need AI-enabled complex and efficient embedded architectures.
This special issue aims to provide a forum for researchers and practitioners in academia and industry to present their latest research findings and engineering experiences in the configuration, implementation, optimization, and validation of AI/deep learning-based complex embedded architectures that can help to efficiently tackle real-world signal processing problems.
Papers are invited in theory, modeling, algorithms, implementations and applications of applying AI/deep learning for various signal processing tasks to establish the latest efforts of the research in this area. Topics of interest include, but not limited to:
• Smart AI/deep learning sensors and chips
• Deep learning on complex embedded architectures
• Deep learning/machine learning frameworks for complex embedded architectures
• AI-systems on chip for the Internet of Things (IoT), Industry 4.0, smart transportation and autonomous robots
• Programmable and reconfigurable chip for complexity-adapting AI solutions
• Efficient memory and communication methods for high-throughput AI approaches
• Embedded systems for large-scale smart healthcare.
• Hardware/software co-design synthesis reconfigurable hardware.
• Intelligent embedded system protocols for high-performance computing platforms.
• Intelligent Embedded-aware protocols for data quality and integrity.
• Intelligent methods timing analysis scheduling design.
• Real-time networking and system on chip control.
• Real-time embedded systems for Signal Processing – design implementation and performance evaluation.
• Security dependability and fault tolerance of real-time and distributed embedded systems.
Submission of manuscripts: 05 JAN 2021
Notification to Authors: 10 APR 2021
Final versions due: 25 AUG 2021
Prof. Dr. B.Nagaraj M.E., Ph.D., MIEEE
Dean – Innovation Centre
Rathinam Group of Institutions
Coimbatore, Tamilnadu, India
Dr. Niki Martinel
Assistant Professor of Computer Vision and Machine Learning
Department of Mathematics, Computer Science and Physics
University of Udine, Italy
Prof. Dr. Danilo Pelusi,
University of Teramo, Italy
Dept. of Communication Engineering
Prof. Valentina E. Balas
Professor-Automation and Applied Informatics,
Aurel Vlaicu University of Arad, Romania.