Uploaded January 2022 | Updated September 2026, 20 hours ago
ArtIAMAS Seminar Series: Embedded System Design Optimization at the Network Edge
Shuvra S. Bhattacharyya
Professor
Electrical and Computer Engineering
Maryland Energy Innovation Institute
UMIACS
University of Maryland
Sophisticated sensor processing at the network edge opens up many new applications for extraction and exploitation of knowledge from diverse sensing modalities. However, these applications must typically satisfy stringent constraints on real-time performance and energy efficiency, and they involve complex trade-offs among processing that is performed at the edge, processing that is offloaded to more powerful resources (in the fog or cloud), and the communication required for such offloading. In this talk, I will discuss models and methods to explore the opportunities and address the challenges associated with pushing complex sensor processing tasks to the edge. Core themes of the presentation will include (1) model-based design methodologies, particularly those based on dataflow models of computation, for design and implementation of complex embedded hardware/software systems, and (2) design optimization techniques for efficiently utilizing multicore embedded processing platforms under stringent constraints on performance and energy consumption.
For more information on the Maryland Robotics Center see:
https://robotics.umd.edu
ArtIAMAS Seminar Series: Embedded System Design Optimization at the Network Edge
Shuvra S. Bhattacharyya
Professor
Electrical and Computer Engineering
Maryland Energy Innovation Institute
UMIACS
University of Maryland
Sophisticated sensor processing at the network edge opens up many new applications for extraction and exploitation of knowledge from diverse sensing modalities. However, these applications must typically satisfy stringent constraints on real-time performance and energy efficiency, and they involve complex trade-offs among processing that is performed at the edge, processing that is offloaded to more powerful resources (in the fog or cloud), and the communication required for such offloading. In this talk, I will discuss models and methods to explore the opportunities and address the challenges associated with pushing complex sensor processing tasks to the edge. Core themes of the presentation will include (1) model-based design methodologies, particularly those based on dataflow models of computation, for design and implementation of complex embedded hardware/software systems, and (2) design optimization techniques for efficiently utilizing multicore embedded processing platforms under stringent constraints on performance and energy consumption.
For more information on the Maryland Robotics Center see:
https://robotics.umd.edu
