Intelligent Edge Computing in Pervasive Environments
Permanent URI for this collectionhttps://hdl.handle.net/10125/107577
Browse
Recent Submissions
Item type: Item , Exploring Spiking Neural Networks (SNN) for Low Size, Weight, and Power (SWaP) Benefits(2024-01-03) Bihl, Trevor; Farr, Patrick; Di Caterina, Gaetano; Vicente-Sola, Alex; Manna, Davide; Kirkland, Paul; Liu, Jundong; Combs, KaraSize, Weight, and Power (SWaP) concerns are growing as artificial intelligence (AI) use spreads in edge applications. AI algorithms, such as artificial neural networks (ANNs), have revolutionized many fields, e.g. computer vision (CV), but at a large computational/power burden. Biological intelligence is notably more computationally efficient. Neuromorphic edge processors and spiking neural networks (SNNs) aim to follow biology closer with spike-based operations resulting in sparsity and lower-SWaP operations than traditional ANNs with SNNs only “firing/spiking” when needed. Understanding the trade space of SWaP when embracing neuromorphic computing has not been studied heavily. To addresses this, we present a repeatable and scalable apples-to-apples comparison of traditional ANNs and SNNs for edge processing with demonstration on both classical and neuromorphic edge hardware. Results show that SNNs combined with neuromorphic hardware can provide comparable accuracy for CV to ANNs at 1/10th the power.Item type: Item , Software as a Device in Edge Computing(2024-01-03) Juric, Radmila; Suh, Sang; Ronchieri, Elisabetta; Tanik, Murat; Carbone, John; Mcclenaghan, KarolineThe paper explores possibilities of defining a generic conceptual model for creating software as a device. This research was triggered by initiatives from the healthcare sector to start decoupling software, defined by device manufacturers, from their hardware and addresses problems in regulating medical devices and their accompanying software. The idea of creating situations where software plays the role of a device, might have long term benefits regarding (a) sustainability of mobile and wireless computing, particularly at the computing edge (b) proliferation of new gadgets/devices coupled with proprietary software which often deliver similar if not identical services and (c) rising heterogeneities of hardware and software which may be difficult to manage. For illustration this paper uses the example of Software as a Medical Device (SaMD). It gives a very clear picture of why it is urgent to change the way devices are manufactured and coupled with proprietary software when delivering services.Item type: Item , Introduction to the Minitrack on Intelligent Edge Computing in Pervasive Environments(2024-01-03) Juric, Radmila; Sanfilippo, Filippo; Ronchieri, Elisabetta